Hugging Face's logo

zhangjingyu111
/
tabx

Safetensors
multi_modality
Model card Files
xet
Community
zhangjingyu111 commited on
Commit
da490b6
·
1 Parent(s): d7c1618

commit from

Browse files
Files changed (26) hide show
  1. checkpoint-10380/README.md +202 -0
  2. checkpoint-10380/adapter_config.json +32 -0
  3. checkpoint-10380/adapter_model.safetensors +3 -0
  4. checkpoint-10380/optimizer.pt +3 -0
  5. checkpoint-10380/rng_state.pth +3 -0
  6. checkpoint-10380/scheduler.pt +3 -0
  7. checkpoint-10380/trainer_state.json +1482 -0
  8. checkpoint-10380/training_args.bin +3 -0
  9. checkpoint-20760/README.md +202 -0
  10. checkpoint-20760/adapter_config.json +32 -0
  11. checkpoint-20760/adapter_model.safetensors +3 -0
  12. checkpoint-20760/optimizer.pt +3 -0
  13. checkpoint-20760/rng_state.pth +3 -0
  14. checkpoint-20760/scheduler.pt +3 -0
  15. checkpoint-20760/trainer_state.json +2938 -0
  16. checkpoint-20760/training_args.bin +3 -0
  17. config.json +64 -0
  18. model-00001-of-00003.safetensors +3 -0
  19. model-00002-of-00003.safetensors +3 -0
  20. model-00003-of-00003.safetensors +3 -0
  21. model.safetensors.index.json +943 -0
  22. preprocessor_config.json +23 -0
  23. processor_config.json +12 -0
  24. special_tokens_map.json +34 -0
  25. tokenizer.json +0 -0
  26. tokenizer_config.json +0 -0
checkpoint-10380/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ./result/tabx
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.14.0
checkpoint-10380/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./result/tabx",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 16,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 8,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "q_proj",
27
+ "v_proj"
28
+ ],
29
+ "task_type": "CAUSAL_LM",
30
+ "use_dora": false,
31
+ "use_rslora": false
32
+ }
checkpoint-10380/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b39f62a195898c82e36ac706e0917b586a9cc14ca7a6fd2c121974ae11133a
3
+ size 15746352
checkpoint-10380/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d44c86719057b767a74bd597c07255cfdedbbf550e731bf9b527cadad82e19b
3
+ size 31560890
checkpoint-10380/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20be6224296eba67cae319fbfc44b3a9f8c89b0ecb6363efd62e65ac05e3fe8e
3
+ size 14244
checkpoint-10380/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d45f8518e4ad4d29824a72b70f92e0557358f67242127b152a6ce336226dc865
3
+ size 1000
checkpoint-10380/trainer_state.json ADDED
@@ -0,0 +1,1482 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9999277508850517,
5
+ "eval_steps": 500,
6
+ "global_step": 10380,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004816607663222792,
13
+ "grad_norm": 0.006126338616013527,
14
+ "learning_rate": 1.204238921001927e-07,
15
+ "loss": 0.9708,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.009633215326445585,
20
+ "grad_norm": 0.005320949479937553,
21
+ "learning_rate": 2.408477842003854e-07,
22
+ "loss": 0.9695,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.014449822989668376,
27
+ "grad_norm": 0.007401228882372379,
28
+ "learning_rate": 3.612716763005781e-07,
29
+ "loss": 0.9666,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.01926643065289117,
34
+ "grad_norm": 0.007720685563981533,
35
+ "learning_rate": 4.816955684007708e-07,
36
+ "loss": 0.9658,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.024083038316113962,
41
+ "grad_norm": 0.0045981802977621555,
42
+ "learning_rate": 6.021194605009634e-07,
43
+ "loss": 0.9782,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.028899645979336752,
48
+ "grad_norm": 0.0035435317549854517,
49
+ "learning_rate": 7.225433526011562e-07,
50
+ "loss": 0.9763,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.03371625364255954,
55
+ "grad_norm": 0.00575470644980669,
56
+ "learning_rate": 8.429672447013489e-07,
57
+ "loss": 0.9679,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.03853286130578234,
62
+ "grad_norm": 0.00474235974252224,
63
+ "learning_rate": 9.633911368015416e-07,
64
+ "loss": 0.9723,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.04334946896900513,
69
+ "grad_norm": 0.005123383365571499,
70
+ "learning_rate": 1.0838150289017341e-06,
71
+ "loss": 0.9689,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.048166076632227925,
76
+ "grad_norm": 0.004203244112432003,
77
+ "learning_rate": 1.2042389210019269e-06,
78
+ "loss": 0.9715,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.052982684295450715,
83
+ "grad_norm": 0.004875039681792259,
84
+ "learning_rate": 1.3246628131021197e-06,
85
+ "loss": 0.9722,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.057799291958673504,
90
+ "grad_norm": 0.004557117819786072,
91
+ "learning_rate": 1.4450867052023124e-06,
92
+ "loss": 0.9703,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.0626158996218963,
97
+ "grad_norm": 0.005739388056099415,
98
+ "learning_rate": 1.565510597302505e-06,
99
+ "loss": 0.9736,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.06743250728511908,
104
+ "grad_norm": 0.006271078251302242,
105
+ "learning_rate": 1.6859344894026978e-06,
106
+ "loss": 0.9665,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.07224911494834188,
111
+ "grad_norm": 0.005068830214440823,
112
+ "learning_rate": 1.8063583815028903e-06,
113
+ "loss": 0.9706,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.07706572261156468,
118
+ "grad_norm": 0.00502425990998745,
119
+ "learning_rate": 1.926782273603083e-06,
120
+ "loss": 0.973,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.08188233027478747,
125
+ "grad_norm": 0.0058668977580964565,
126
+ "learning_rate": 2.0472061657032757e-06,
127
+ "loss": 0.9671,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.08669893793801026,
132
+ "grad_norm": 0.006117091979831457,
133
+ "learning_rate": 2.1676300578034682e-06,
134
+ "loss": 0.9742,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.09151554560123305,
139
+ "grad_norm": 0.00683088693767786,
140
+ "learning_rate": 2.288053949903661e-06,
141
+ "loss": 0.9759,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.09633215326445585,
146
+ "grad_norm": 0.006263008341193199,
147
+ "learning_rate": 2.4084778420038538e-06,
148
+ "loss": 0.9734,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.10114876092767863,
153
+ "grad_norm": 0.008486876264214516,
154
+ "learning_rate": 2.5289017341040468e-06,
155
+ "loss": 0.9711,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.10596536859090143,
160
+ "grad_norm": 0.009161265566945076,
161
+ "learning_rate": 2.6493256262042393e-06,
162
+ "loss": 0.9681,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.11078197625412423,
167
+ "grad_norm": 0.011058177798986435,
168
+ "learning_rate": 2.769749518304432e-06,
169
+ "loss": 0.9746,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.11559858391734701,
174
+ "grad_norm": 0.007972915656864643,
175
+ "learning_rate": 2.890173410404625e-06,
176
+ "loss": 0.9764,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.1204151915805698,
181
+ "grad_norm": 0.012226037681102753,
182
+ "learning_rate": 3.0105973025048174e-06,
183
+ "loss": 0.9772,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.1252317992437926,
188
+ "grad_norm": 0.00945008173584938,
189
+ "learning_rate": 3.13102119460501e-06,
190
+ "loss": 0.9646,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.13004840690701538,
195
+ "grad_norm": 0.009660482406616211,
196
+ "learning_rate": 3.2514450867052026e-06,
197
+ "loss": 0.9687,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.13486501457023817,
202
+ "grad_norm": 0.011101615615189075,
203
+ "learning_rate": 3.3718689788053955e-06,
204
+ "loss": 0.9706,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.13968162223346098,
209
+ "grad_norm": 0.010446416214108467,
210
+ "learning_rate": 3.492292870905588e-06,
211
+ "loss": 0.973,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.14449822989668376,
216
+ "grad_norm": 0.008989120833575726,
217
+ "learning_rate": 3.6127167630057807e-06,
218
+ "loss": 0.9749,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.14931483755990657,
223
+ "grad_norm": 0.013530201278626919,
224
+ "learning_rate": 3.7331406551059736e-06,
225
+ "loss": 0.9676,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 0.15413144522312935,
230
+ "grad_norm": 0.01546582579612732,
231
+ "learning_rate": 3.853564547206166e-06,
232
+ "loss": 0.9696,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 0.15894805288635214,
237
+ "grad_norm": 0.011816772632300854,
238
+ "learning_rate": 3.973988439306359e-06,
239
+ "loss": 0.97,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 0.16376466054957495,
244
+ "grad_norm": 0.017899101600050926,
245
+ "learning_rate": 4.094412331406551e-06,
246
+ "loss": 0.9739,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 0.16858126821279773,
251
+ "grad_norm": 0.010724999010562897,
252
+ "learning_rate": 4.214836223506744e-06,
253
+ "loss": 0.9754,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 0.1733978758760205,
258
+ "grad_norm": 0.009775185026228428,
259
+ "learning_rate": 4.3352601156069365e-06,
260
+ "loss": 0.9719,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 0.17821448353924332,
265
+ "grad_norm": 0.013262300752103329,
266
+ "learning_rate": 4.45568400770713e-06,
267
+ "loss": 0.9671,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 0.1830310912024661,
272
+ "grad_norm": 0.016223512589931488,
273
+ "learning_rate": 4.576107899807322e-06,
274
+ "loss": 0.9718,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 0.1878476988656889,
279
+ "grad_norm": 0.014330854639410973,
280
+ "learning_rate": 4.696531791907515e-06,
281
+ "loss": 0.9691,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 0.1926643065289117,
286
+ "grad_norm": 0.013619545847177505,
287
+ "learning_rate": 4.8169556840077075e-06,
288
+ "loss": 0.97,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 0.19748091419213448,
293
+ "grad_norm": 0.01791592873632908,
294
+ "learning_rate": 4.9373795761079e-06,
295
+ "loss": 0.97,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 0.20229752185535727,
300
+ "grad_norm": 0.01708158478140831,
301
+ "learning_rate": 5.0578034682080935e-06,
302
+ "loss": 0.9673,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 0.20711412951858008,
307
+ "grad_norm": 0.01698676496744156,
308
+ "learning_rate": 5.178227360308285e-06,
309
+ "loss": 0.9704,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 0.21193073718180286,
314
+ "grad_norm": 0.019560791552066803,
315
+ "learning_rate": 5.298651252408479e-06,
316
+ "loss": 0.9672,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 0.21674734484502564,
321
+ "grad_norm": 0.013388896360993385,
322
+ "learning_rate": 5.419075144508671e-06,
323
+ "loss": 0.9666,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 0.22156395250824845,
328
+ "grad_norm": 0.014111978933215141,
329
+ "learning_rate": 5.539499036608864e-06,
330
+ "loss": 0.9681,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 0.22638056017147123,
335
+ "grad_norm": 0.014271333813667297,
336
+ "learning_rate": 5.659922928709056e-06,
337
+ "loss": 0.9686,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 0.23119716783469402,
342
+ "grad_norm": 0.015145047567784786,
343
+ "learning_rate": 5.78034682080925e-06,
344
+ "loss": 0.9761,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 0.23601377549791683,
349
+ "grad_norm": 0.01296105608344078,
350
+ "learning_rate": 5.9007707129094414e-06,
351
+ "loss": 0.9707,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 0.2408303831611396,
356
+ "grad_norm": 0.020001647993922234,
357
+ "learning_rate": 6.021194605009635e-06,
358
+ "loss": 0.971,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 0.2456469908243624,
363
+ "grad_norm": 0.016972048208117485,
364
+ "learning_rate": 6.1416184971098266e-06,
365
+ "loss": 0.9687,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 0.2504635984875852,
370
+ "grad_norm": 0.014618949964642525,
371
+ "learning_rate": 6.26204238921002e-06,
372
+ "loss": 0.9754,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 0.255280206150808,
377
+ "grad_norm": 0.01802586205303669,
378
+ "learning_rate": 6.3824662813102125e-06,
379
+ "loss": 0.9774,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 0.26009681381403077,
384
+ "grad_norm": 0.014718293212354183,
385
+ "learning_rate": 6.502890173410405e-06,
386
+ "loss": 0.9657,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 0.26491342147725355,
391
+ "grad_norm": 0.015037412755191326,
392
+ "learning_rate": 6.623314065510598e-06,
393
+ "loss": 0.9739,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 0.26973002914047634,
398
+ "grad_norm": 0.01608668453991413,
399
+ "learning_rate": 6.743737957610791e-06,
400
+ "loss": 0.9722,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 0.2745466368036992,
405
+ "grad_norm": 0.018442656844854355,
406
+ "learning_rate": 6.864161849710983e-06,
407
+ "loss": 0.9772,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 0.27936324446692196,
412
+ "grad_norm": 0.01769097149372101,
413
+ "learning_rate": 6.984585741811176e-06,
414
+ "loss": 0.9733,
415
+ "step": 2900
416
+ },
417
+ {
418
+ "epoch": 0.28417985213014474,
419
+ "grad_norm": 0.019516944885253906,
420
+ "learning_rate": 7.105009633911368e-06,
421
+ "loss": 0.9723,
422
+ "step": 2950
423
+ },
424
+ {
425
+ "epoch": 0.2889964597933675,
426
+ "grad_norm": 0.01777079701423645,
427
+ "learning_rate": 7.225433526011561e-06,
428
+ "loss": 0.9688,
429
+ "step": 3000
430
+ },
431
+ {
432
+ "epoch": 0.2938130674565903,
433
+ "grad_norm": 0.016445022076368332,
434
+ "learning_rate": 7.345857418111754e-06,
435
+ "loss": 0.9646,
436
+ "step": 3050
437
+ },
438
+ {
439
+ "epoch": 0.29862967511981314,
440
+ "grad_norm": 0.018231108784675598,
441
+ "learning_rate": 7.466281310211947e-06,
442
+ "loss": 0.9713,
443
+ "step": 3100
444
+ },
445
+ {
446
+ "epoch": 0.3034462827830359,
447
+ "grad_norm": 0.018171431496739388,
448
+ "learning_rate": 7.586705202312139e-06,
449
+ "loss": 0.9727,
450
+ "step": 3150
451
+ },
452
+ {
453
+ "epoch": 0.3082628904462587,
454
+ "grad_norm": 0.021160680800676346,
455
+ "learning_rate": 7.707129094412332e-06,
456
+ "loss": 0.9678,
457
+ "step": 3200
458
+ },
459
+ {
460
+ "epoch": 0.3130794981094815,
461
+ "grad_norm": 0.016429034993052483,
462
+ "learning_rate": 7.827552986512524e-06,
463
+ "loss": 0.9747,
464
+ "step": 3250
465
+ },
466
+ {
467
+ "epoch": 0.3178961057727043,
468
+ "grad_norm": 0.01525623258203268,
469
+ "learning_rate": 7.947976878612718e-06,
470
+ "loss": 0.9772,
471
+ "step": 3300
472
+ },
473
+ {
474
+ "epoch": 0.32271271343592706,
475
+ "grad_norm": 0.01664959080517292,
476
+ "learning_rate": 8.06840077071291e-06,
477
+ "loss": 0.9698,
478
+ "step": 3350
479
+ },
480
+ {
481
+ "epoch": 0.3275293210991499,
482
+ "grad_norm": 0.01823030784726143,
483
+ "learning_rate": 8.188824662813103e-06,
484
+ "loss": 0.9692,
485
+ "step": 3400
486
+ },
487
+ {
488
+ "epoch": 0.3323459287623727,
489
+ "grad_norm": 0.016893787309527397,
490
+ "learning_rate": 8.309248554913294e-06,
491
+ "loss": 0.9746,
492
+ "step": 3450
493
+ },
494
+ {
495
+ "epoch": 0.33716253642559546,
496
+ "grad_norm": 0.017619503661990166,
497
+ "learning_rate": 8.429672447013488e-06,
498
+ "loss": 0.9716,
499
+ "step": 3500
500
+ },
501
+ {
502
+ "epoch": 0.34197914408881824,
503
+ "grad_norm": 0.017689380794763565,
504
+ "learning_rate": 8.550096339113681e-06,
505
+ "loss": 0.9705,
506
+ "step": 3550
507
+ },
508
+ {
509
+ "epoch": 0.346795751752041,
510
+ "grad_norm": 0.021607734262943268,
511
+ "learning_rate": 8.670520231213873e-06,
512
+ "loss": 0.9706,
513
+ "step": 3600
514
+ },
515
+ {
516
+ "epoch": 0.3516123594152638,
517
+ "grad_norm": 0.014947572723031044,
518
+ "learning_rate": 8.790944123314066e-06,
519
+ "loss": 0.9712,
520
+ "step": 3650
521
+ },
522
+ {
523
+ "epoch": 0.35642896707848665,
524
+ "grad_norm": 0.020626170560717583,
525
+ "learning_rate": 8.91136801541426e-06,
526
+ "loss": 0.9675,
527
+ "step": 3700
528
+ },
529
+ {
530
+ "epoch": 0.36124557474170943,
531
+ "grad_norm": 0.022836238145828247,
532
+ "learning_rate": 9.031791907514451e-06,
533
+ "loss": 0.9715,
534
+ "step": 3750
535
+ },
536
+ {
537
+ "epoch": 0.3660621824049322,
538
+ "grad_norm": 0.018653474748134613,
539
+ "learning_rate": 9.152215799614645e-06,
540
+ "loss": 0.9675,
541
+ "step": 3800
542
+ },
543
+ {
544
+ "epoch": 0.370878790068155,
545
+ "grad_norm": 0.02013775333762169,
546
+ "learning_rate": 9.272639691714837e-06,
547
+ "loss": 0.9668,
548
+ "step": 3850
549
+ },
550
+ {
551
+ "epoch": 0.3756953977313778,
552
+ "grad_norm": 0.017947306856513023,
553
+ "learning_rate": 9.39306358381503e-06,
554
+ "loss": 0.9774,
555
+ "step": 3900
556
+ },
557
+ {
558
+ "epoch": 0.38051200539460056,
559
+ "grad_norm": 0.01862495392560959,
560
+ "learning_rate": 9.513487475915222e-06,
561
+ "loss": 0.9731,
562
+ "step": 3950
563
+ },
564
+ {
565
+ "epoch": 0.3853286130578234,
566
+ "grad_norm": 0.019523387774825096,
567
+ "learning_rate": 9.633911368015415e-06,
568
+ "loss": 0.9684,
569
+ "step": 4000
570
+ },
571
+ {
572
+ "epoch": 0.3901452207210462,
573
+ "grad_norm": 0.02111661061644554,
574
+ "learning_rate": 9.754335260115609e-06,
575
+ "loss": 0.9652,
576
+ "step": 4050
577
+ },
578
+ {
579
+ "epoch": 0.39496182838426896,
580
+ "grad_norm": 0.02122378721833229,
581
+ "learning_rate": 9.8747591522158e-06,
582
+ "loss": 0.9679,
583
+ "step": 4100
584
+ },
585
+ {
586
+ "epoch": 0.39977843604749175,
587
+ "grad_norm": 0.020203029736876488,
588
+ "learning_rate": 9.995183044315994e-06,
589
+ "loss": 0.975,
590
+ "step": 4150
591
+ },
592
+ {
593
+ "epoch": 0.40459504371071453,
594
+ "grad_norm": 0.018844136968255043,
595
+ "learning_rate": 1.0115606936416187e-05,
596
+ "loss": 0.9725,
597
+ "step": 4200
598
+ },
599
+ {
600
+ "epoch": 0.4094116513739373,
601
+ "grad_norm": 0.021215271204710007,
602
+ "learning_rate": 1.0236030828516379e-05,
603
+ "loss": 0.965,
604
+ "step": 4250
605
+ },
606
+ {
607
+ "epoch": 0.41422825903716015,
608
+ "grad_norm": 0.016644105315208435,
609
+ "learning_rate": 1.035645472061657e-05,
610
+ "loss": 0.9732,
611
+ "step": 4300
612
+ },
613
+ {
614
+ "epoch": 0.41904486670038293,
615
+ "grad_norm": 0.021778760477900505,
616
+ "learning_rate": 1.0476878612716764e-05,
617
+ "loss": 0.9695,
618
+ "step": 4350
619
+ },
620
+ {
621
+ "epoch": 0.4238614743636057,
622
+ "grad_norm": 0.02292022295296192,
623
+ "learning_rate": 1.0597302504816957e-05,
624
+ "loss": 0.9723,
625
+ "step": 4400
626
+ },
627
+ {
628
+ "epoch": 0.4286780820268285,
629
+ "grad_norm": 0.025219304487109184,
630
+ "learning_rate": 1.0717726396917149e-05,
631
+ "loss": 0.9705,
632
+ "step": 4450
633
+ },
634
+ {
635
+ "epoch": 0.4334946896900513,
636
+ "grad_norm": 0.016190696507692337,
637
+ "learning_rate": 1.0838150289017342e-05,
638
+ "loss": 0.9696,
639
+ "step": 4500
640
+ },
641
+ {
642
+ "epoch": 0.43831129735327407,
643
+ "grad_norm": 0.022926099598407745,
644
+ "learning_rate": 1.0958574181117534e-05,
645
+ "loss": 0.9814,
646
+ "step": 4550
647
+ },
648
+ {
649
+ "epoch": 0.4431279050164969,
650
+ "grad_norm": 0.022171182557940483,
651
+ "learning_rate": 1.1078998073217728e-05,
652
+ "loss": 0.9714,
653
+ "step": 4600
654
+ },
655
+ {
656
+ "epoch": 0.4479445126797197,
657
+ "grad_norm": 0.020946532487869263,
658
+ "learning_rate": 1.1199421965317921e-05,
659
+ "loss": 0.9708,
660
+ "step": 4650
661
+ },
662
+ {
663
+ "epoch": 0.45276112034294247,
664
+ "grad_norm": 0.024337617680430412,
665
+ "learning_rate": 1.1319845857418113e-05,
666
+ "loss": 0.9693,
667
+ "step": 4700
668
+ },
669
+ {
670
+ "epoch": 0.45757772800616525,
671
+ "grad_norm": 0.016778983175754547,
672
+ "learning_rate": 1.1440269749518304e-05,
673
+ "loss": 0.9761,
674
+ "step": 4750
675
+ },
676
+ {
677
+ "epoch": 0.46239433566938803,
678
+ "grad_norm": 0.019471049308776855,
679
+ "learning_rate": 1.15606936416185e-05,
680
+ "loss": 0.9692,
681
+ "step": 4800
682
+ },
683
+ {
684
+ "epoch": 0.4672109433326108,
685
+ "grad_norm": 0.019639885053038597,
686
+ "learning_rate": 1.1681117533718691e-05,
687
+ "loss": 0.97,
688
+ "step": 4850
689
+ },
690
+ {
691
+ "epoch": 0.47202755099583366,
692
+ "grad_norm": 0.020082898437976837,
693
+ "learning_rate": 1.1801541425818883e-05,
694
+ "loss": 0.9689,
695
+ "step": 4900
696
+ },
697
+ {
698
+ "epoch": 0.47684415865905644,
699
+ "grad_norm": 0.024678485468029976,
700
+ "learning_rate": 1.1921965317919075e-05,
701
+ "loss": 0.9656,
702
+ "step": 4950
703
+ },
704
+ {
705
+ "epoch": 0.4816607663222792,
706
+ "grad_norm": 0.024683095514774323,
707
+ "learning_rate": 1.204238921001927e-05,
708
+ "loss": 0.9642,
709
+ "step": 5000
710
+ },
711
+ {
712
+ "epoch": 0.486477373985502,
713
+ "grad_norm": 0.01706753671169281,
714
+ "learning_rate": 1.2162813102119461e-05,
715
+ "loss": 0.9712,
716
+ "step": 5050
717
+ },
718
+ {
719
+ "epoch": 0.4912939816487248,
720
+ "grad_norm": 0.018906202167272568,
721
+ "learning_rate": 1.2283236994219653e-05,
722
+ "loss": 0.9698,
723
+ "step": 5100
724
+ },
725
+ {
726
+ "epoch": 0.49611058931194757,
727
+ "grad_norm": 0.02169940434396267,
728
+ "learning_rate": 1.2403660886319847e-05,
729
+ "loss": 0.9812,
730
+ "step": 5150
731
+ },
732
+ {
733
+ "epoch": 0.5009271969751704,
734
+ "grad_norm": 0.019748864695429802,
735
+ "learning_rate": 1.252408477842004e-05,
736
+ "loss": 0.9697,
737
+ "step": 5200
738
+ },
739
+ {
740
+ "epoch": 0.5057438046383932,
741
+ "grad_norm": 0.025600366294384003,
742
+ "learning_rate": 1.2644508670520232e-05,
743
+ "loss": 0.9756,
744
+ "step": 5250
745
+ },
746
+ {
747
+ "epoch": 0.510560412301616,
748
+ "grad_norm": 0.02122749388217926,
749
+ "learning_rate": 1.2764932562620425e-05,
750
+ "loss": 0.9754,
751
+ "step": 5300
752
+ },
753
+ {
754
+ "epoch": 0.5153770199648388,
755
+ "grad_norm": 0.019833318889141083,
756
+ "learning_rate": 1.2885356454720617e-05,
757
+ "loss": 0.9662,
758
+ "step": 5350
759
+ },
760
+ {
761
+ "epoch": 0.5201936276280615,
762
+ "grad_norm": 0.023730387911200523,
763
+ "learning_rate": 1.300578034682081e-05,
764
+ "loss": 0.969,
765
+ "step": 5400
766
+ },
767
+ {
768
+ "epoch": 0.5250102352912843,
769
+ "grad_norm": 0.019496504217386246,
770
+ "learning_rate": 1.3126204238921004e-05,
771
+ "loss": 0.9707,
772
+ "step": 5450
773
+ },
774
+ {
775
+ "epoch": 0.5298268429545071,
776
+ "grad_norm": 0.02589583210647106,
777
+ "learning_rate": 1.3246628131021195e-05,
778
+ "loss": 0.9701,
779
+ "step": 5500
780
+ },
781
+ {
782
+ "epoch": 0.5346434506177299,
783
+ "grad_norm": 0.022606389597058296,
784
+ "learning_rate": 1.3367052023121387e-05,
785
+ "loss": 0.9726,
786
+ "step": 5550
787
+ },
788
+ {
789
+ "epoch": 0.5394600582809527,
790
+ "grad_norm": 0.02263002097606659,
791
+ "learning_rate": 1.3487475915221582e-05,
792
+ "loss": 0.9794,
793
+ "step": 5600
794
+ },
795
+ {
796
+ "epoch": 0.5442766659441756,
797
+ "grad_norm": 0.02536887302994728,
798
+ "learning_rate": 1.3607899807321774e-05,
799
+ "loss": 0.9669,
800
+ "step": 5650
801
+ },
802
+ {
803
+ "epoch": 0.5490932736073983,
804
+ "grad_norm": 0.0196990929543972,
805
+ "learning_rate": 1.3728323699421966e-05,
806
+ "loss": 0.9703,
807
+ "step": 5700
808
+ },
809
+ {
810
+ "epoch": 0.5539098812706211,
811
+ "grad_norm": 0.02041424624621868,
812
+ "learning_rate": 1.3848747591522157e-05,
813
+ "loss": 0.9667,
814
+ "step": 5750
815
+ },
816
+ {
817
+ "epoch": 0.5587264889338439,
818
+ "grad_norm": 0.019019950181245804,
819
+ "learning_rate": 1.3969171483622352e-05,
820
+ "loss": 0.9703,
821
+ "step": 5800
822
+ },
823
+ {
824
+ "epoch": 0.5635430965970667,
825
+ "grad_norm": 0.02298571914434433,
826
+ "learning_rate": 1.4089595375722544e-05,
827
+ "loss": 0.9688,
828
+ "step": 5850
829
+ },
830
+ {
831
+ "epoch": 0.5683597042602895,
832
+ "grad_norm": 0.025440840050578117,
833
+ "learning_rate": 1.4210019267822736e-05,
834
+ "loss": 0.9704,
835
+ "step": 5900
836
+ },
837
+ {
838
+ "epoch": 0.5731763119235123,
839
+ "grad_norm": 0.019567478448152542,
840
+ "learning_rate": 1.433044315992293e-05,
841
+ "loss": 0.978,
842
+ "step": 5950
843
+ },
844
+ {
845
+ "epoch": 0.577992919586735,
846
+ "grad_norm": 0.021922102198004723,
847
+ "learning_rate": 1.4450867052023123e-05,
848
+ "loss": 0.972,
849
+ "step": 6000
850
+ },
851
+ {
852
+ "epoch": 0.5828095272499578,
853
+ "grad_norm": 0.023248879238963127,
854
+ "learning_rate": 1.4571290944123316e-05,
855
+ "loss": 0.9751,
856
+ "step": 6050
857
+ },
858
+ {
859
+ "epoch": 0.5876261349131806,
860
+ "grad_norm": 0.025605713948607445,
861
+ "learning_rate": 1.4691714836223508e-05,
862
+ "loss": 0.9706,
863
+ "step": 6100
864
+ },
865
+ {
866
+ "epoch": 0.5924427425764034,
867
+ "grad_norm": 0.022256705909967422,
868
+ "learning_rate": 1.4812138728323701e-05,
869
+ "loss": 0.9711,
870
+ "step": 6150
871
+ },
872
+ {
873
+ "epoch": 0.5972593502396263,
874
+ "grad_norm": 0.019437307491898537,
875
+ "learning_rate": 1.4932562620423895e-05,
876
+ "loss": 0.9777,
877
+ "step": 6200
878
+ },
879
+ {
880
+ "epoch": 0.6020759579028491,
881
+ "grad_norm": 0.02306896448135376,
882
+ "learning_rate": 1.5052986512524086e-05,
883
+ "loss": 0.9743,
884
+ "step": 6250
885
+ },
886
+ {
887
+ "epoch": 0.6068925655660719,
888
+ "grad_norm": 0.025738820433616638,
889
+ "learning_rate": 1.5173410404624278e-05,
890
+ "loss": 0.97,
891
+ "step": 6300
892
+ },
893
+ {
894
+ "epoch": 0.6117091732292946,
895
+ "grad_norm": 0.019557103514671326,
896
+ "learning_rate": 1.5293834296724473e-05,
897
+ "loss": 0.97,
898
+ "step": 6350
899
+ },
900
+ {
901
+ "epoch": 0.6165257808925174,
902
+ "grad_norm": 0.025096602737903595,
903
+ "learning_rate": 1.5414258188824665e-05,
904
+ "loss": 0.9658,
905
+ "step": 6400
906
+ },
907
+ {
908
+ "epoch": 0.6213423885557402,
909
+ "grad_norm": 0.028057411313056946,
910
+ "learning_rate": 1.5534682080924857e-05,
911
+ "loss": 0.9709,
912
+ "step": 6450
913
+ },
914
+ {
915
+ "epoch": 0.626158996218963,
916
+ "grad_norm": 0.03152346611022949,
917
+ "learning_rate": 1.5655105973025048e-05,
918
+ "loss": 0.9751,
919
+ "step": 6500
920
+ },
921
+ {
922
+ "epoch": 0.6309756038821858,
923
+ "grad_norm": 0.017900671809911728,
924
+ "learning_rate": 1.5775529865125243e-05,
925
+ "loss": 0.9702,
926
+ "step": 6550
927
+ },
928
+ {
929
+ "epoch": 0.6357922115454085,
930
+ "grad_norm": 0.022004351019859314,
931
+ "learning_rate": 1.5895953757225435e-05,
932
+ "loss": 0.9681,
933
+ "step": 6600
934
+ },
935
+ {
936
+ "epoch": 0.6406088192086313,
937
+ "grad_norm": 0.021472521126270294,
938
+ "learning_rate": 1.6016377649325627e-05,
939
+ "loss": 0.9709,
940
+ "step": 6650
941
+ },
942
+ {
943
+ "epoch": 0.6454254268718541,
944
+ "grad_norm": 0.01908615604043007,
945
+ "learning_rate": 1.613680154142582e-05,
946
+ "loss": 0.9716,
947
+ "step": 6700
948
+ },
949
+ {
950
+ "epoch": 0.6502420345350769,
951
+ "grad_norm": 0.02205970697104931,
952
+ "learning_rate": 1.6257225433526014e-05,
953
+ "loss": 0.9774,
954
+ "step": 6750
955
+ },
956
+ {
957
+ "epoch": 0.6550586421982998,
958
+ "grad_norm": 0.02467629499733448,
959
+ "learning_rate": 1.6377649325626205e-05,
960
+ "loss": 0.9682,
961
+ "step": 6800
962
+ },
963
+ {
964
+ "epoch": 0.6598752498615226,
965
+ "grad_norm": 0.01893242448568344,
966
+ "learning_rate": 1.6498073217726397e-05,
967
+ "loss": 0.9761,
968
+ "step": 6850
969
+ },
970
+ {
971
+ "epoch": 0.6646918575247454,
972
+ "grad_norm": 0.02502221241593361,
973
+ "learning_rate": 1.661849710982659e-05,
974
+ "loss": 0.9726,
975
+ "step": 6900
976
+ },
977
+ {
978
+ "epoch": 0.6695084651879681,
979
+ "grad_norm": 0.02121950313448906,
980
+ "learning_rate": 1.6738921001926784e-05,
981
+ "loss": 0.9671,
982
+ "step": 6950
983
+ },
984
+ {
985
+ "epoch": 0.6743250728511909,
986
+ "grad_norm": 0.019996950402855873,
987
+ "learning_rate": 1.6859344894026976e-05,
988
+ "loss": 0.9734,
989
+ "step": 7000
990
+ },
991
+ {
992
+ "epoch": 0.6791416805144137,
993
+ "grad_norm": 0.023754192516207695,
994
+ "learning_rate": 1.6979768786127167e-05,
995
+ "loss": 0.9657,
996
+ "step": 7050
997
+ },
998
+ {
999
+ "epoch": 0.6839582881776365,
1000
+ "grad_norm": 0.019974833354353905,
1001
+ "learning_rate": 1.7100192678227362e-05,
1002
+ "loss": 0.9699,
1003
+ "step": 7100
1004
+ },
1005
+ {
1006
+ "epoch": 0.6887748958408593,
1007
+ "grad_norm": 0.019718438386917114,
1008
+ "learning_rate": 1.7220616570327554e-05,
1009
+ "loss": 0.9774,
1010
+ "step": 7150
1011
+ },
1012
+ {
1013
+ "epoch": 0.693591503504082,
1014
+ "grad_norm": 0.02473635785281658,
1015
+ "learning_rate": 1.7341040462427746e-05,
1016
+ "loss": 0.9705,
1017
+ "step": 7200
1018
+ },
1019
+ {
1020
+ "epoch": 0.6984081111673048,
1021
+ "grad_norm": 0.0264342799782753,
1022
+ "learning_rate": 1.746146435452794e-05,
1023
+ "loss": 0.9729,
1024
+ "step": 7250
1025
+ },
1026
+ {
1027
+ "epoch": 0.7032247188305276,
1028
+ "grad_norm": 0.021187305450439453,
1029
+ "learning_rate": 1.7581888246628133e-05,
1030
+ "loss": 0.9687,
1031
+ "step": 7300
1032
+ },
1033
+ {
1034
+ "epoch": 0.7080413264937504,
1035
+ "grad_norm": 0.01752212457358837,
1036
+ "learning_rate": 1.7702312138728324e-05,
1037
+ "loss": 0.9675,
1038
+ "step": 7350
1039
+ },
1040
+ {
1041
+ "epoch": 0.7128579341569733,
1042
+ "grad_norm": 0.02413749136030674,
1043
+ "learning_rate": 1.782273603082852e-05,
1044
+ "loss": 0.9681,
1045
+ "step": 7400
1046
+ },
1047
+ {
1048
+ "epoch": 0.7176745418201961,
1049
+ "grad_norm": 0.023940233513712883,
1050
+ "learning_rate": 1.794315992292871e-05,
1051
+ "loss": 0.9721,
1052
+ "step": 7450
1053
+ },
1054
+ {
1055
+ "epoch": 0.7224911494834189,
1056
+ "grad_norm": 0.024347305297851562,
1057
+ "learning_rate": 1.8063583815028903e-05,
1058
+ "loss": 0.9655,
1059
+ "step": 7500
1060
+ },
1061
+ {
1062
+ "epoch": 0.7273077571466416,
1063
+ "grad_norm": 0.023215830326080322,
1064
+ "learning_rate": 1.8184007707129098e-05,
1065
+ "loss": 0.9708,
1066
+ "step": 7550
1067
+ },
1068
+ {
1069
+ "epoch": 0.7321243648098644,
1070
+ "grad_norm": 0.019564125686883926,
1071
+ "learning_rate": 1.830443159922929e-05,
1072
+ "loss": 0.9658,
1073
+ "step": 7600
1074
+ },
1075
+ {
1076
+ "epoch": 0.7369409724730872,
1077
+ "grad_norm": 0.02049618400633335,
1078
+ "learning_rate": 1.842485549132948e-05,
1079
+ "loss": 0.9662,
1080
+ "step": 7650
1081
+ },
1082
+ {
1083
+ "epoch": 0.74175758013631,
1084
+ "grad_norm": 0.031806960701942444,
1085
+ "learning_rate": 1.8545279383429673e-05,
1086
+ "loss": 0.9668,
1087
+ "step": 7700
1088
+ },
1089
+ {
1090
+ "epoch": 0.7465741877995328,
1091
+ "grad_norm": 0.02331661805510521,
1092
+ "learning_rate": 1.8665703275529868e-05,
1093
+ "loss": 0.972,
1094
+ "step": 7750
1095
+ },
1096
+ {
1097
+ "epoch": 0.7513907954627556,
1098
+ "grad_norm": 0.020196113735437393,
1099
+ "learning_rate": 1.878612716763006e-05,
1100
+ "loss": 0.9765,
1101
+ "step": 7800
1102
+ },
1103
+ {
1104
+ "epoch": 0.7562074031259783,
1105
+ "grad_norm": 0.028458353132009506,
1106
+ "learning_rate": 1.890655105973025e-05,
1107
+ "loss": 0.9658,
1108
+ "step": 7850
1109
+ },
1110
+ {
1111
+ "epoch": 0.7610240107892011,
1112
+ "grad_norm": 0.025394223630428314,
1113
+ "learning_rate": 1.9026974951830443e-05,
1114
+ "loss": 0.9747,
1115
+ "step": 7900
1116
+ },
1117
+ {
1118
+ "epoch": 0.7658406184524239,
1119
+ "grad_norm": 0.02368360199034214,
1120
+ "learning_rate": 1.914739884393064e-05,
1121
+ "loss": 0.9815,
1122
+ "step": 7950
1123
+ },
1124
+ {
1125
+ "epoch": 0.7706572261156468,
1126
+ "grad_norm": 0.021498555317521095,
1127
+ "learning_rate": 1.926782273603083e-05,
1128
+ "loss": 0.9709,
1129
+ "step": 8000
1130
+ },
1131
+ {
1132
+ "epoch": 0.7754738337788696,
1133
+ "grad_norm": 0.027243509888648987,
1134
+ "learning_rate": 1.9388246628131022e-05,
1135
+ "loss": 0.9745,
1136
+ "step": 8050
1137
+ },
1138
+ {
1139
+ "epoch": 0.7802904414420924,
1140
+ "grad_norm": 0.019903521984815598,
1141
+ "learning_rate": 1.9508670520231217e-05,
1142
+ "loss": 0.9694,
1143
+ "step": 8100
1144
+ },
1145
+ {
1146
+ "epoch": 0.7851070491053151,
1147
+ "grad_norm": 0.02099510096013546,
1148
+ "learning_rate": 1.962909441233141e-05,
1149
+ "loss": 0.9709,
1150
+ "step": 8150
1151
+ },
1152
+ {
1153
+ "epoch": 0.7899236567685379,
1154
+ "grad_norm": 0.025477971881628036,
1155
+ "learning_rate": 1.97495183044316e-05,
1156
+ "loss": 0.9693,
1157
+ "step": 8200
1158
+ },
1159
+ {
1160
+ "epoch": 0.7947402644317607,
1161
+ "grad_norm": 0.018335288390517235,
1162
+ "learning_rate": 1.9869942196531792e-05,
1163
+ "loss": 0.9682,
1164
+ "step": 8250
1165
+ },
1166
+ {
1167
+ "epoch": 0.7995568720949835,
1168
+ "grad_norm": 0.021306857466697693,
1169
+ "learning_rate": 1.9990366088631987e-05,
1170
+ "loss": 0.9646,
1171
+ "step": 8300
1172
+ },
1173
+ {
1174
+ "epoch": 0.8043734797582063,
1175
+ "grad_norm": 0.015945710241794586,
1176
+ "learning_rate": 1.9999981307496558e-05,
1177
+ "loss": 0.9738,
1178
+ "step": 8350
1179
+ },
1180
+ {
1181
+ "epoch": 0.8091900874214291,
1182
+ "grad_norm": 0.022564787417650223,
1183
+ "learning_rate": 1.9999918586988815e-05,
1184
+ "loss": 0.9702,
1185
+ "step": 8400
1186
+ },
1187
+ {
1188
+ "epoch": 0.8140066950846518,
1189
+ "grad_norm": 0.02257794328033924,
1190
+ "learning_rate": 1.9999811697411585e-05,
1191
+ "loss": 0.9634,
1192
+ "step": 8450
1193
+ },
1194
+ {
1195
+ "epoch": 0.8188233027478746,
1196
+ "grad_norm": 0.017230728641152382,
1197
+ "learning_rate": 1.9999660639236997e-05,
1198
+ "loss": 0.9757,
1199
+ "step": 8500
1200
+ },
1201
+ {
1202
+ "epoch": 0.8236399104110974,
1203
+ "grad_norm": 0.02081149071455002,
1204
+ "learning_rate": 1.999946541313226e-05,
1205
+ "loss": 0.9674,
1206
+ "step": 8550
1207
+ },
1208
+ {
1209
+ "epoch": 0.8284565180743203,
1210
+ "grad_norm": 0.019852489233016968,
1211
+ "learning_rate": 1.9999226019959675e-05,
1212
+ "loss": 0.9753,
1213
+ "step": 8600
1214
+ },
1215
+ {
1216
+ "epoch": 0.8332731257375431,
1217
+ "grad_norm": 0.022209197282791138,
1218
+ "learning_rate": 1.9998942460776637e-05,
1219
+ "loss": 0.967,
1220
+ "step": 8650
1221
+ },
1222
+ {
1223
+ "epoch": 0.8380897334007659,
1224
+ "grad_norm": 0.01641988568007946,
1225
+ "learning_rate": 1.99986147368356e-05,
1226
+ "loss": 0.9691,
1227
+ "step": 8700
1228
+ },
1229
+ {
1230
+ "epoch": 0.8429063410639887,
1231
+ "grad_norm": 0.022373568266630173,
1232
+ "learning_rate": 1.999824284958411e-05,
1233
+ "loss": 0.9714,
1234
+ "step": 8750
1235
+ },
1236
+ {
1237
+ "epoch": 0.8477229487272114,
1238
+ "grad_norm": 0.01713249646127224,
1239
+ "learning_rate": 1.9997826800664773e-05,
1240
+ "loss": 0.9675,
1241
+ "step": 8800
1242
+ },
1243
+ {
1244
+ "epoch": 0.8525395563904342,
1245
+ "grad_norm": 0.022914381697773933,
1246
+ "learning_rate": 1.9997366591915246e-05,
1247
+ "loss": 0.9723,
1248
+ "step": 8850
1249
+ },
1250
+ {
1251
+ "epoch": 0.857356164053657,
1252
+ "grad_norm": 0.018057918176054955,
1253
+ "learning_rate": 1.9996862225368248e-05,
1254
+ "loss": 0.9728,
1255
+ "step": 8900
1256
+ },
1257
+ {
1258
+ "epoch": 0.8621727717168798,
1259
+ "grad_norm": 0.022914033383131027,
1260
+ "learning_rate": 1.9996313703251536e-05,
1261
+ "loss": 0.9693,
1262
+ "step": 8950
1263
+ },
1264
+ {
1265
+ "epoch": 0.8669893793801026,
1266
+ "grad_norm": 0.028229426592588425,
1267
+ "learning_rate": 1.9995721027987903e-05,
1268
+ "loss": 0.9695,
1269
+ "step": 9000
1270
+ },
1271
+ {
1272
+ "epoch": 0.8718059870433253,
1273
+ "grad_norm": 0.022879110649228096,
1274
+ "learning_rate": 1.999508420219516e-05,
1275
+ "loss": 0.9739,
1276
+ "step": 9050
1277
+ },
1278
+ {
1279
+ "epoch": 0.8766225947065481,
1280
+ "grad_norm": 0.016597425565123558,
1281
+ "learning_rate": 1.9994403228686134e-05,
1282
+ "loss": 0.9693,
1283
+ "step": 9100
1284
+ },
1285
+ {
1286
+ "epoch": 0.881439202369771,
1287
+ "grad_norm": 0.020313039422035217,
1288
+ "learning_rate": 1.9993678110468642e-05,
1289
+ "loss": 0.9781,
1290
+ "step": 9150
1291
+ },
1292
+ {
1293
+ "epoch": 0.8862558100329938,
1294
+ "grad_norm": 0.023865938186645508,
1295
+ "learning_rate": 1.999290885074549e-05,
1296
+ "loss": 0.9676,
1297
+ "step": 9200
1298
+ },
1299
+ {
1300
+ "epoch": 0.8910724176962166,
1301
+ "grad_norm": 0.02183787152171135,
1302
+ "learning_rate": 1.9992095452914454e-05,
1303
+ "loss": 0.9794,
1304
+ "step": 9250
1305
+ },
1306
+ {
1307
+ "epoch": 0.8958890253594394,
1308
+ "grad_norm": 0.029220541939139366,
1309
+ "learning_rate": 1.9991237920568272e-05,
1310
+ "loss": 0.9728,
1311
+ "step": 9300
1312
+ },
1313
+ {
1314
+ "epoch": 0.9007056330226622,
1315
+ "grad_norm": 0.02130264975130558,
1316
+ "learning_rate": 1.9990336257494607e-05,
1317
+ "loss": 0.9743,
1318
+ "step": 9350
1319
+ },
1320
+ {
1321
+ "epoch": 0.9055222406858849,
1322
+ "grad_norm": 0.02516760677099228,
1323
+ "learning_rate": 1.9989390467676057e-05,
1324
+ "loss": 0.9726,
1325
+ "step": 9400
1326
+ },
1327
+ {
1328
+ "epoch": 0.9103388483491077,
1329
+ "grad_norm": 0.024124667048454285,
1330
+ "learning_rate": 1.998840055529012e-05,
1331
+ "loss": 0.9687,
1332
+ "step": 9450
1333
+ },
1334
+ {
1335
+ "epoch": 0.9151554560123305,
1336
+ "grad_norm": 0.020920995622873306,
1337
+ "learning_rate": 1.9987366524709187e-05,
1338
+ "loss": 0.9826,
1339
+ "step": 9500
1340
+ },
1341
+ {
1342
+ "epoch": 0.9199720636755533,
1343
+ "grad_norm": 0.016224917024374008,
1344
+ "learning_rate": 1.9986288380500508e-05,
1345
+ "loss": 0.9695,
1346
+ "step": 9550
1347
+ },
1348
+ {
1349
+ "epoch": 0.9247886713387761,
1350
+ "grad_norm": 0.023870129138231277,
1351
+ "learning_rate": 1.9985166127426186e-05,
1352
+ "loss": 0.968,
1353
+ "step": 9600
1354
+ },
1355
+ {
1356
+ "epoch": 0.9296052790019989,
1357
+ "grad_norm": 0.018101558089256287,
1358
+ "learning_rate": 1.998399977044315e-05,
1359
+ "loss": 0.968,
1360
+ "step": 9650
1361
+ },
1362
+ {
1363
+ "epoch": 0.9344218866652216,
1364
+ "grad_norm": 0.021635858342051506,
1365
+ "learning_rate": 1.9982789314703126e-05,
1366
+ "loss": 0.967,
1367
+ "step": 9700
1368
+ },
1369
+ {
1370
+ "epoch": 0.9392384943284445,
1371
+ "grad_norm": 0.02077612280845642,
1372
+ "learning_rate": 1.9981534765552638e-05,
1373
+ "loss": 0.9729,
1374
+ "step": 9750
1375
+ },
1376
+ {
1377
+ "epoch": 0.9440551019916673,
1378
+ "grad_norm": 0.018736233934760094,
1379
+ "learning_rate": 1.9980236128532948e-05,
1380
+ "loss": 0.9637,
1381
+ "step": 9800
1382
+ },
1383
+ {
1384
+ "epoch": 0.9488717096548901,
1385
+ "grad_norm": 0.019599338993430138,
1386
+ "learning_rate": 1.9978893409380063e-05,
1387
+ "loss": 0.972,
1388
+ "step": 9850
1389
+ },
1390
+ {
1391
+ "epoch": 0.9536883173181129,
1392
+ "grad_norm": 0.024034442380070686,
1393
+ "learning_rate": 1.9977506614024706e-05,
1394
+ "loss": 0.9711,
1395
+ "step": 9900
1396
+ },
1397
+ {
1398
+ "epoch": 0.9585049249813357,
1399
+ "grad_norm": 0.023441381752490997,
1400
+ "learning_rate": 1.9976075748592264e-05,
1401
+ "loss": 0.9668,
1402
+ "step": 9950
1403
+ },
1404
+ {
1405
+ "epoch": 0.9633215326445584,
1406
+ "grad_norm": 0.03189970180392265,
1407
+ "learning_rate": 1.997460081940279e-05,
1408
+ "loss": 0.9695,
1409
+ "step": 10000
1410
+ },
1411
+ {
1412
+ "epoch": 0.9681381403077812,
1413
+ "grad_norm": 0.022853758186101913,
1414
+ "learning_rate": 1.9973081832970962e-05,
1415
+ "loss": 0.9718,
1416
+ "step": 10050
1417
+ },
1418
+ {
1419
+ "epoch": 0.972954747971004,
1420
+ "grad_norm": 0.020372973755002022,
1421
+ "learning_rate": 1.9971550488396247e-05,
1422
+ "loss": 0.9749,
1423
+ "step": 10100
1424
+ },
1425
+ {
1426
+ "epoch": 0.9777713556342268,
1427
+ "grad_norm": 0.02032754011452198,
1428
+ "learning_rate": 1.996994428860578e-05,
1429
+ "loss": 0.9709,
1430
+ "step": 10150
1431
+ },
1432
+ {
1433
+ "epoch": 0.9825879632974496,
1434
+ "grad_norm": 0.01894865557551384,
1435
+ "learning_rate": 1.996829405214059e-05,
1436
+ "loss": 0.9709,
1437
+ "step": 10200
1438
+ },
1439
+ {
1440
+ "epoch": 0.9874045709606724,
1441
+ "grad_norm": 0.023153427988290787,
1442
+ "learning_rate": 1.9966599786289677e-05,
1443
+ "loss": 0.9652,
1444
+ "step": 10250
1445
+ },
1446
+ {
1447
+ "epoch": 0.9922211786238951,
1448
+ "grad_norm": 0.016725238412618637,
1449
+ "learning_rate": 1.9964861498536514e-05,
1450
+ "loss": 0.9671,
1451
+ "step": 10300
1452
+ },
1453
+ {
1454
+ "epoch": 0.997037786287118,
1455
+ "grad_norm": 0.01910654455423355,
1456
+ "learning_rate": 1.9963079196559025e-05,
1457
+ "loss": 0.9654,
1458
+ "step": 10350
1459
+ }
1460
+ ],
1461
+ "logging_steps": 50,
1462
+ "max_steps": 20760,
1463
+ "num_input_tokens_seen": 0,
1464
+ "num_train_epochs": 2,
1465
+ "save_steps": 500,
1466
+ "stateful_callbacks": {
1467
+ "TrainerControl": {
1468
+ "args": {
1469
+ "should_epoch_stop": false,
1470
+ "should_evaluate": false,
1471
+ "should_log": false,
1472
+ "should_save": true,
1473
+ "should_training_stop": false
1474
+ },
1475
+ "attributes": {}
1476
+ }
1477
+ },
1478
+ "total_flos": 2.516209204815695e+18,
1479
+ "train_batch_size": 2,
1480
+ "trial_name": null,
1481
+ "trial_params": null
1482
+ }
checkpoint-10380/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf4af21635e2a3d5153e5b199fe36a29ba0574d6cbf377a6c2c41dc1a46333f
3
+ size 5304
checkpoint-20760/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ./result/tabx
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.14.0
checkpoint-20760/adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "./result/tabx",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 16,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 8,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "q_proj",
27
+ "v_proj"
28
+ ],
29
+ "task_type": "CAUSAL_LM",
30
+ "use_dora": false,
31
+ "use_rslora": false
32
+ }
checkpoint-20760/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08cd0f0f5a59d518581465f26a1c45663c27eebcfe895ab0ac879ab3de4e80df
3
+ size 15746352
checkpoint-20760/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f4908c5b123e03bcfecadf208eb488abcb87364e3b559ada45160e112931f85
3
+ size 31560890
checkpoint-20760/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaf0f15ec7f8c675cad3cb86a2ce987fdceae103ec4a68a1cbc5e6f87ad52b99
3
+ size 14244
checkpoint-20760/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceb51089b5d0bb0fdc3c9852c56f29e5bd8b9a9529b9585225d4a6383c29fb2d
3
+ size 1000
checkpoint-20760/trainer_state.json ADDED
@@ -0,0 +1,2938 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9999277508850517,
5
+ "eval_steps": 500,
6
+ "global_step": 20760,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.004816607663222792,
13
+ "grad_norm": 0.006126338616013527,
14
+ "learning_rate": 1.204238921001927e-07,
15
+ "loss": 0.9708,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.009633215326445585,
20
+ "grad_norm": 0.005320949479937553,
21
+ "learning_rate": 2.408477842003854e-07,
22
+ "loss": 0.9695,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.014449822989668376,
27
+ "grad_norm": 0.007401228882372379,
28
+ "learning_rate": 3.612716763005781e-07,
29
+ "loss": 0.9666,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.01926643065289117,
34
+ "grad_norm": 0.007720685563981533,
35
+ "learning_rate": 4.816955684007708e-07,
36
+ "loss": 0.9658,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.024083038316113962,
41
+ "grad_norm": 0.0045981802977621555,
42
+ "learning_rate": 6.021194605009634e-07,
43
+ "loss": 0.9782,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.028899645979336752,
48
+ "grad_norm": 0.0035435317549854517,
49
+ "learning_rate": 7.225433526011562e-07,
50
+ "loss": 0.9763,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.03371625364255954,
55
+ "grad_norm": 0.00575470644980669,
56
+ "learning_rate": 8.429672447013489e-07,
57
+ "loss": 0.9679,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.03853286130578234,
62
+ "grad_norm": 0.00474235974252224,
63
+ "learning_rate": 9.633911368015416e-07,
64
+ "loss": 0.9723,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.04334946896900513,
69
+ "grad_norm": 0.005123383365571499,
70
+ "learning_rate": 1.0838150289017341e-06,
71
+ "loss": 0.9689,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.048166076632227925,
76
+ "grad_norm": 0.004203244112432003,
77
+ "learning_rate": 1.2042389210019269e-06,
78
+ "loss": 0.9715,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.052982684295450715,
83
+ "grad_norm": 0.004875039681792259,
84
+ "learning_rate": 1.3246628131021197e-06,
85
+ "loss": 0.9722,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.057799291958673504,
90
+ "grad_norm": 0.004557117819786072,
91
+ "learning_rate": 1.4450867052023124e-06,
92
+ "loss": 0.9703,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.0626158996218963,
97
+ "grad_norm": 0.005739388056099415,
98
+ "learning_rate": 1.565510597302505e-06,
99
+ "loss": 0.9736,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.06743250728511908,
104
+ "grad_norm": 0.006271078251302242,
105
+ "learning_rate": 1.6859344894026978e-06,
106
+ "loss": 0.9665,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.07224911494834188,
111
+ "grad_norm": 0.005068830214440823,
112
+ "learning_rate": 1.8063583815028903e-06,
113
+ "loss": 0.9706,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.07706572261156468,
118
+ "grad_norm": 0.00502425990998745,
119
+ "learning_rate": 1.926782273603083e-06,
120
+ "loss": 0.973,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.08188233027478747,
125
+ "grad_norm": 0.0058668977580964565,
126
+ "learning_rate": 2.0472061657032757e-06,
127
+ "loss": 0.9671,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.08669893793801026,
132
+ "grad_norm": 0.006117091979831457,
133
+ "learning_rate": 2.1676300578034682e-06,
134
+ "loss": 0.9742,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.09151554560123305,
139
+ "grad_norm": 0.00683088693767786,
140
+ "learning_rate": 2.288053949903661e-06,
141
+ "loss": 0.9759,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.09633215326445585,
146
+ "grad_norm": 0.006263008341193199,
147
+ "learning_rate": 2.4084778420038538e-06,
148
+ "loss": 0.9734,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.10114876092767863,
153
+ "grad_norm": 0.008486876264214516,
154
+ "learning_rate": 2.5289017341040468e-06,
155
+ "loss": 0.9711,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.10596536859090143,
160
+ "grad_norm": 0.009161265566945076,
161
+ "learning_rate": 2.6493256262042393e-06,
162
+ "loss": 0.9681,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.11078197625412423,
167
+ "grad_norm": 0.011058177798986435,
168
+ "learning_rate": 2.769749518304432e-06,
169
+ "loss": 0.9746,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.11559858391734701,
174
+ "grad_norm": 0.007972915656864643,
175
+ "learning_rate": 2.890173410404625e-06,
176
+ "loss": 0.9764,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.1204151915805698,
181
+ "grad_norm": 0.012226037681102753,
182
+ "learning_rate": 3.0105973025048174e-06,
183
+ "loss": 0.9772,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.1252317992437926,
188
+ "grad_norm": 0.00945008173584938,
189
+ "learning_rate": 3.13102119460501e-06,
190
+ "loss": 0.9646,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.13004840690701538,
195
+ "grad_norm": 0.009660482406616211,
196
+ "learning_rate": 3.2514450867052026e-06,
197
+ "loss": 0.9687,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.13486501457023817,
202
+ "grad_norm": 0.011101615615189075,
203
+ "learning_rate": 3.3718689788053955e-06,
204
+ "loss": 0.9706,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.13968162223346098,
209
+ "grad_norm": 0.010446416214108467,
210
+ "learning_rate": 3.492292870905588e-06,
211
+ "loss": 0.973,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.14449822989668376,
216
+ "grad_norm": 0.008989120833575726,
217
+ "learning_rate": 3.6127167630057807e-06,
218
+ "loss": 0.9749,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.14931483755990657,
223
+ "grad_norm": 0.013530201278626919,
224
+ "learning_rate": 3.7331406551059736e-06,
225
+ "loss": 0.9676,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 0.15413144522312935,
230
+ "grad_norm": 0.01546582579612732,
231
+ "learning_rate": 3.853564547206166e-06,
232
+ "loss": 0.9696,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 0.15894805288635214,
237
+ "grad_norm": 0.011816772632300854,
238
+ "learning_rate": 3.973988439306359e-06,
239
+ "loss": 0.97,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 0.16376466054957495,
244
+ "grad_norm": 0.017899101600050926,
245
+ "learning_rate": 4.094412331406551e-06,
246
+ "loss": 0.9739,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 0.16858126821279773,
251
+ "grad_norm": 0.010724999010562897,
252
+ "learning_rate": 4.214836223506744e-06,
253
+ "loss": 0.9754,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 0.1733978758760205,
258
+ "grad_norm": 0.009775185026228428,
259
+ "learning_rate": 4.3352601156069365e-06,
260
+ "loss": 0.9719,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 0.17821448353924332,
265
+ "grad_norm": 0.013262300752103329,
266
+ "learning_rate": 4.45568400770713e-06,
267
+ "loss": 0.9671,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 0.1830310912024661,
272
+ "grad_norm": 0.016223512589931488,
273
+ "learning_rate": 4.576107899807322e-06,
274
+ "loss": 0.9718,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 0.1878476988656889,
279
+ "grad_norm": 0.014330854639410973,
280
+ "learning_rate": 4.696531791907515e-06,
281
+ "loss": 0.9691,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 0.1926643065289117,
286
+ "grad_norm": 0.013619545847177505,
287
+ "learning_rate": 4.8169556840077075e-06,
288
+ "loss": 0.97,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 0.19748091419213448,
293
+ "grad_norm": 0.01791592873632908,
294
+ "learning_rate": 4.9373795761079e-06,
295
+ "loss": 0.97,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 0.20229752185535727,
300
+ "grad_norm": 0.01708158478140831,
301
+ "learning_rate": 5.0578034682080935e-06,
302
+ "loss": 0.9673,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 0.20711412951858008,
307
+ "grad_norm": 0.01698676496744156,
308
+ "learning_rate": 5.178227360308285e-06,
309
+ "loss": 0.9704,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 0.21193073718180286,
314
+ "grad_norm": 0.019560791552066803,
315
+ "learning_rate": 5.298651252408479e-06,
316
+ "loss": 0.9672,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 0.21674734484502564,
321
+ "grad_norm": 0.013388896360993385,
322
+ "learning_rate": 5.419075144508671e-06,
323
+ "loss": 0.9666,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 0.22156395250824845,
328
+ "grad_norm": 0.014111978933215141,
329
+ "learning_rate": 5.539499036608864e-06,
330
+ "loss": 0.9681,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 0.22638056017147123,
335
+ "grad_norm": 0.014271333813667297,
336
+ "learning_rate": 5.659922928709056e-06,
337
+ "loss": 0.9686,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 0.23119716783469402,
342
+ "grad_norm": 0.015145047567784786,
343
+ "learning_rate": 5.78034682080925e-06,
344
+ "loss": 0.9761,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 0.23601377549791683,
349
+ "grad_norm": 0.01296105608344078,
350
+ "learning_rate": 5.9007707129094414e-06,
351
+ "loss": 0.9707,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 0.2408303831611396,
356
+ "grad_norm": 0.020001647993922234,
357
+ "learning_rate": 6.021194605009635e-06,
358
+ "loss": 0.971,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 0.2456469908243624,
363
+ "grad_norm": 0.016972048208117485,
364
+ "learning_rate": 6.1416184971098266e-06,
365
+ "loss": 0.9687,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 0.2504635984875852,
370
+ "grad_norm": 0.014618949964642525,
371
+ "learning_rate": 6.26204238921002e-06,
372
+ "loss": 0.9754,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 0.255280206150808,
377
+ "grad_norm": 0.01802586205303669,
378
+ "learning_rate": 6.3824662813102125e-06,
379
+ "loss": 0.9774,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 0.26009681381403077,
384
+ "grad_norm": 0.014718293212354183,
385
+ "learning_rate": 6.502890173410405e-06,
386
+ "loss": 0.9657,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 0.26491342147725355,
391
+ "grad_norm": 0.015037412755191326,
392
+ "learning_rate": 6.623314065510598e-06,
393
+ "loss": 0.9739,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 0.26973002914047634,
398
+ "grad_norm": 0.01608668453991413,
399
+ "learning_rate": 6.743737957610791e-06,
400
+ "loss": 0.9722,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 0.2745466368036992,
405
+ "grad_norm": 0.018442656844854355,
406
+ "learning_rate": 6.864161849710983e-06,
407
+ "loss": 0.9772,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 0.27936324446692196,
412
+ "grad_norm": 0.01769097149372101,
413
+ "learning_rate": 6.984585741811176e-06,
414
+ "loss": 0.9733,
415
+ "step": 2900
416
+ },
417
+ {
418
+ "epoch": 0.28417985213014474,
419
+ "grad_norm": 0.019516944885253906,
420
+ "learning_rate": 7.105009633911368e-06,
421
+ "loss": 0.9723,
422
+ "step": 2950
423
+ },
424
+ {
425
+ "epoch": 0.2889964597933675,
426
+ "grad_norm": 0.01777079701423645,
427
+ "learning_rate": 7.225433526011561e-06,
428
+ "loss": 0.9688,
429
+ "step": 3000
430
+ },
431
+ {
432
+ "epoch": 0.2938130674565903,
433
+ "grad_norm": 0.016445022076368332,
434
+ "learning_rate": 7.345857418111754e-06,
435
+ "loss": 0.9646,
436
+ "step": 3050
437
+ },
438
+ {
439
+ "epoch": 0.29862967511981314,
440
+ "grad_norm": 0.018231108784675598,
441
+ "learning_rate": 7.466281310211947e-06,
442
+ "loss": 0.9713,
443
+ "step": 3100
444
+ },
445
+ {
446
+ "epoch": 0.3034462827830359,
447
+ "grad_norm": 0.018171431496739388,
448
+ "learning_rate": 7.586705202312139e-06,
449
+ "loss": 0.9727,
450
+ "step": 3150
451
+ },
452
+ {
453
+ "epoch": 0.3082628904462587,
454
+ "grad_norm": 0.021160680800676346,
455
+ "learning_rate": 7.707129094412332e-06,
456
+ "loss": 0.9678,
457
+ "step": 3200
458
+ },
459
+ {
460
+ "epoch": 0.3130794981094815,
461
+ "grad_norm": 0.016429034993052483,
462
+ "learning_rate": 7.827552986512524e-06,
463
+ "loss": 0.9747,
464
+ "step": 3250
465
+ },
466
+ {
467
+ "epoch": 0.3178961057727043,
468
+ "grad_norm": 0.01525623258203268,
469
+ "learning_rate": 7.947976878612718e-06,
470
+ "loss": 0.9772,
471
+ "step": 3300
472
+ },
473
+ {
474
+ "epoch": 0.32271271343592706,
475
+ "grad_norm": 0.01664959080517292,
476
+ "learning_rate": 8.06840077071291e-06,
477
+ "loss": 0.9698,
478
+ "step": 3350
479
+ },
480
+ {
481
+ "epoch": 0.3275293210991499,
482
+ "grad_norm": 0.01823030784726143,
483
+ "learning_rate": 8.188824662813103e-06,
484
+ "loss": 0.9692,
485
+ "step": 3400
486
+ },
487
+ {
488
+ "epoch": 0.3323459287623727,
489
+ "grad_norm": 0.016893787309527397,
490
+ "learning_rate": 8.309248554913294e-06,
491
+ "loss": 0.9746,
492
+ "step": 3450
493
+ },
494
+ {
495
+ "epoch": 0.33716253642559546,
496
+ "grad_norm": 0.017619503661990166,
497
+ "learning_rate": 8.429672447013488e-06,
498
+ "loss": 0.9716,
499
+ "step": 3500
500
+ },
501
+ {
502
+ "epoch": 0.34197914408881824,
503
+ "grad_norm": 0.017689380794763565,
504
+ "learning_rate": 8.550096339113681e-06,
505
+ "loss": 0.9705,
506
+ "step": 3550
507
+ },
508
+ {
509
+ "epoch": 0.346795751752041,
510
+ "grad_norm": 0.021607734262943268,
511
+ "learning_rate": 8.670520231213873e-06,
512
+ "loss": 0.9706,
513
+ "step": 3600
514
+ },
515
+ {
516
+ "epoch": 0.3516123594152638,
517
+ "grad_norm": 0.014947572723031044,
518
+ "learning_rate": 8.790944123314066e-06,
519
+ "loss": 0.9712,
520
+ "step": 3650
521
+ },
522
+ {
523
+ "epoch": 0.35642896707848665,
524
+ "grad_norm": 0.020626170560717583,
525
+ "learning_rate": 8.91136801541426e-06,
526
+ "loss": 0.9675,
527
+ "step": 3700
528
+ },
529
+ {
530
+ "epoch": 0.36124557474170943,
531
+ "grad_norm": 0.022836238145828247,
532
+ "learning_rate": 9.031791907514451e-06,
533
+ "loss": 0.9715,
534
+ "step": 3750
535
+ },
536
+ {
537
+ "epoch": 0.3660621824049322,
538
+ "grad_norm": 0.018653474748134613,
539
+ "learning_rate": 9.152215799614645e-06,
540
+ "loss": 0.9675,
541
+ "step": 3800
542
+ },
543
+ {
544
+ "epoch": 0.370878790068155,
545
+ "grad_norm": 0.02013775333762169,
546
+ "learning_rate": 9.272639691714837e-06,
547
+ "loss": 0.9668,
548
+ "step": 3850
549
+ },
550
+ {
551
+ "epoch": 0.3756953977313778,
552
+ "grad_norm": 0.017947306856513023,
553
+ "learning_rate": 9.39306358381503e-06,
554
+ "loss": 0.9774,
555
+ "step": 3900
556
+ },
557
+ {
558
+ "epoch": 0.38051200539460056,
559
+ "grad_norm": 0.01862495392560959,
560
+ "learning_rate": 9.513487475915222e-06,
561
+ "loss": 0.9731,
562
+ "step": 3950
563
+ },
564
+ {
565
+ "epoch": 0.3853286130578234,
566
+ "grad_norm": 0.019523387774825096,
567
+ "learning_rate": 9.633911368015415e-06,
568
+ "loss": 0.9684,
569
+ "step": 4000
570
+ },
571
+ {
572
+ "epoch": 0.3901452207210462,
573
+ "grad_norm": 0.02111661061644554,
574
+ "learning_rate": 9.754335260115609e-06,
575
+ "loss": 0.9652,
576
+ "step": 4050
577
+ },
578
+ {
579
+ "epoch": 0.39496182838426896,
580
+ "grad_norm": 0.02122378721833229,
581
+ "learning_rate": 9.8747591522158e-06,
582
+ "loss": 0.9679,
583
+ "step": 4100
584
+ },
585
+ {
586
+ "epoch": 0.39977843604749175,
587
+ "grad_norm": 0.020203029736876488,
588
+ "learning_rate": 9.995183044315994e-06,
589
+ "loss": 0.975,
590
+ "step": 4150
591
+ },
592
+ {
593
+ "epoch": 0.40459504371071453,
594
+ "grad_norm": 0.018844136968255043,
595
+ "learning_rate": 1.0115606936416187e-05,
596
+ "loss": 0.9725,
597
+ "step": 4200
598
+ },
599
+ {
600
+ "epoch": 0.4094116513739373,
601
+ "grad_norm": 0.021215271204710007,
602
+ "learning_rate": 1.0236030828516379e-05,
603
+ "loss": 0.965,
604
+ "step": 4250
605
+ },
606
+ {
607
+ "epoch": 0.41422825903716015,
608
+ "grad_norm": 0.016644105315208435,
609
+ "learning_rate": 1.035645472061657e-05,
610
+ "loss": 0.9732,
611
+ "step": 4300
612
+ },
613
+ {
614
+ "epoch": 0.41904486670038293,
615
+ "grad_norm": 0.021778760477900505,
616
+ "learning_rate": 1.0476878612716764e-05,
617
+ "loss": 0.9695,
618
+ "step": 4350
619
+ },
620
+ {
621
+ "epoch": 0.4238614743636057,
622
+ "grad_norm": 0.02292022295296192,
623
+ "learning_rate": 1.0597302504816957e-05,
624
+ "loss": 0.9723,
625
+ "step": 4400
626
+ },
627
+ {
628
+ "epoch": 0.4286780820268285,
629
+ "grad_norm": 0.025219304487109184,
630
+ "learning_rate": 1.0717726396917149e-05,
631
+ "loss": 0.9705,
632
+ "step": 4450
633
+ },
634
+ {
635
+ "epoch": 0.4334946896900513,
636
+ "grad_norm": 0.016190696507692337,
637
+ "learning_rate": 1.0838150289017342e-05,
638
+ "loss": 0.9696,
639
+ "step": 4500
640
+ },
641
+ {
642
+ "epoch": 0.43831129735327407,
643
+ "grad_norm": 0.022926099598407745,
644
+ "learning_rate": 1.0958574181117534e-05,
645
+ "loss": 0.9814,
646
+ "step": 4550
647
+ },
648
+ {
649
+ "epoch": 0.4431279050164969,
650
+ "grad_norm": 0.022171182557940483,
651
+ "learning_rate": 1.1078998073217728e-05,
652
+ "loss": 0.9714,
653
+ "step": 4600
654
+ },
655
+ {
656
+ "epoch": 0.4479445126797197,
657
+ "grad_norm": 0.020946532487869263,
658
+ "learning_rate": 1.1199421965317921e-05,
659
+ "loss": 0.9708,
660
+ "step": 4650
661
+ },
662
+ {
663
+ "epoch": 0.45276112034294247,
664
+ "grad_norm": 0.024337617680430412,
665
+ "learning_rate": 1.1319845857418113e-05,
666
+ "loss": 0.9693,
667
+ "step": 4700
668
+ },
669
+ {
670
+ "epoch": 0.45757772800616525,
671
+ "grad_norm": 0.016778983175754547,
672
+ "learning_rate": 1.1440269749518304e-05,
673
+ "loss": 0.9761,
674
+ "step": 4750
675
+ },
676
+ {
677
+ "epoch": 0.46239433566938803,
678
+ "grad_norm": 0.019471049308776855,
679
+ "learning_rate": 1.15606936416185e-05,
680
+ "loss": 0.9692,
681
+ "step": 4800
682
+ },
683
+ {
684
+ "epoch": 0.4672109433326108,
685
+ "grad_norm": 0.019639885053038597,
686
+ "learning_rate": 1.1681117533718691e-05,
687
+ "loss": 0.97,
688
+ "step": 4850
689
+ },
690
+ {
691
+ "epoch": 0.47202755099583366,
692
+ "grad_norm": 0.020082898437976837,
693
+ "learning_rate": 1.1801541425818883e-05,
694
+ "loss": 0.9689,
695
+ "step": 4900
696
+ },
697
+ {
698
+ "epoch": 0.47684415865905644,
699
+ "grad_norm": 0.024678485468029976,
700
+ "learning_rate": 1.1921965317919075e-05,
701
+ "loss": 0.9656,
702
+ "step": 4950
703
+ },
704
+ {
705
+ "epoch": 0.4816607663222792,
706
+ "grad_norm": 0.024683095514774323,
707
+ "learning_rate": 1.204238921001927e-05,
708
+ "loss": 0.9642,
709
+ "step": 5000
710
+ },
711
+ {
712
+ "epoch": 0.486477373985502,
713
+ "grad_norm": 0.01706753671169281,
714
+ "learning_rate": 1.2162813102119461e-05,
715
+ "loss": 0.9712,
716
+ "step": 5050
717
+ },
718
+ {
719
+ "epoch": 0.4912939816487248,
720
+ "grad_norm": 0.018906202167272568,
721
+ "learning_rate": 1.2283236994219653e-05,
722
+ "loss": 0.9698,
723
+ "step": 5100
724
+ },
725
+ {
726
+ "epoch": 0.49611058931194757,
727
+ "grad_norm": 0.02169940434396267,
728
+ "learning_rate": 1.2403660886319847e-05,
729
+ "loss": 0.9812,
730
+ "step": 5150
731
+ },
732
+ {
733
+ "epoch": 0.5009271969751704,
734
+ "grad_norm": 0.019748864695429802,
735
+ "learning_rate": 1.252408477842004e-05,
736
+ "loss": 0.9697,
737
+ "step": 5200
738
+ },
739
+ {
740
+ "epoch": 0.5057438046383932,
741
+ "grad_norm": 0.025600366294384003,
742
+ "learning_rate": 1.2644508670520232e-05,
743
+ "loss": 0.9756,
744
+ "step": 5250
745
+ },
746
+ {
747
+ "epoch": 0.510560412301616,
748
+ "grad_norm": 0.02122749388217926,
749
+ "learning_rate": 1.2764932562620425e-05,
750
+ "loss": 0.9754,
751
+ "step": 5300
752
+ },
753
+ {
754
+ "epoch": 0.5153770199648388,
755
+ "grad_norm": 0.019833318889141083,
756
+ "learning_rate": 1.2885356454720617e-05,
757
+ "loss": 0.9662,
758
+ "step": 5350
759
+ },
760
+ {
761
+ "epoch": 0.5201936276280615,
762
+ "grad_norm": 0.023730387911200523,
763
+ "learning_rate": 1.300578034682081e-05,
764
+ "loss": 0.969,
765
+ "step": 5400
766
+ },
767
+ {
768
+ "epoch": 0.5250102352912843,
769
+ "grad_norm": 0.019496504217386246,
770
+ "learning_rate": 1.3126204238921004e-05,
771
+ "loss": 0.9707,
772
+ "step": 5450
773
+ },
774
+ {
775
+ "epoch": 0.5298268429545071,
776
+ "grad_norm": 0.02589583210647106,
777
+ "learning_rate": 1.3246628131021195e-05,
778
+ "loss": 0.9701,
779
+ "step": 5500
780
+ },
781
+ {
782
+ "epoch": 0.5346434506177299,
783
+ "grad_norm": 0.022606389597058296,
784
+ "learning_rate": 1.3367052023121387e-05,
785
+ "loss": 0.9726,
786
+ "step": 5550
787
+ },
788
+ {
789
+ "epoch": 0.5394600582809527,
790
+ "grad_norm": 0.02263002097606659,
791
+ "learning_rate": 1.3487475915221582e-05,
792
+ "loss": 0.9794,
793
+ "step": 5600
794
+ },
795
+ {
796
+ "epoch": 0.5442766659441756,
797
+ "grad_norm": 0.02536887302994728,
798
+ "learning_rate": 1.3607899807321774e-05,
799
+ "loss": 0.9669,
800
+ "step": 5650
801
+ },
802
+ {
803
+ "epoch": 0.5490932736073983,
804
+ "grad_norm": 0.0196990929543972,
805
+ "learning_rate": 1.3728323699421966e-05,
806
+ "loss": 0.9703,
807
+ "step": 5700
808
+ },
809
+ {
810
+ "epoch": 0.5539098812706211,
811
+ "grad_norm": 0.02041424624621868,
812
+ "learning_rate": 1.3848747591522157e-05,
813
+ "loss": 0.9667,
814
+ "step": 5750
815
+ },
816
+ {
817
+ "epoch": 0.5587264889338439,
818
+ "grad_norm": 0.019019950181245804,
819
+ "learning_rate": 1.3969171483622352e-05,
820
+ "loss": 0.9703,
821
+ "step": 5800
822
+ },
823
+ {
824
+ "epoch": 0.5635430965970667,
825
+ "grad_norm": 0.02298571914434433,
826
+ "learning_rate": 1.4089595375722544e-05,
827
+ "loss": 0.9688,
828
+ "step": 5850
829
+ },
830
+ {
831
+ "epoch": 0.5683597042602895,
832
+ "grad_norm": 0.025440840050578117,
833
+ "learning_rate": 1.4210019267822736e-05,
834
+ "loss": 0.9704,
835
+ "step": 5900
836
+ },
837
+ {
838
+ "epoch": 0.5731763119235123,
839
+ "grad_norm": 0.019567478448152542,
840
+ "learning_rate": 1.433044315992293e-05,
841
+ "loss": 0.978,
842
+ "step": 5950
843
+ },
844
+ {
845
+ "epoch": 0.577992919586735,
846
+ "grad_norm": 0.021922102198004723,
847
+ "learning_rate": 1.4450867052023123e-05,
848
+ "loss": 0.972,
849
+ "step": 6000
850
+ },
851
+ {
852
+ "epoch": 0.5828095272499578,
853
+ "grad_norm": 0.023248879238963127,
854
+ "learning_rate": 1.4571290944123316e-05,
855
+ "loss": 0.9751,
856
+ "step": 6050
857
+ },
858
+ {
859
+ "epoch": 0.5876261349131806,
860
+ "grad_norm": 0.025605713948607445,
861
+ "learning_rate": 1.4691714836223508e-05,
862
+ "loss": 0.9706,
863
+ "step": 6100
864
+ },
865
+ {
866
+ "epoch": 0.5924427425764034,
867
+ "grad_norm": 0.022256705909967422,
868
+ "learning_rate": 1.4812138728323701e-05,
869
+ "loss": 0.9711,
870
+ "step": 6150
871
+ },
872
+ {
873
+ "epoch": 0.5972593502396263,
874
+ "grad_norm": 0.019437307491898537,
875
+ "learning_rate": 1.4932562620423895e-05,
876
+ "loss": 0.9777,
877
+ "step": 6200
878
+ },
879
+ {
880
+ "epoch": 0.6020759579028491,
881
+ "grad_norm": 0.02306896448135376,
882
+ "learning_rate": 1.5052986512524086e-05,
883
+ "loss": 0.9743,
884
+ "step": 6250
885
+ },
886
+ {
887
+ "epoch": 0.6068925655660719,
888
+ "grad_norm": 0.025738820433616638,
889
+ "learning_rate": 1.5173410404624278e-05,
890
+ "loss": 0.97,
891
+ "step": 6300
892
+ },
893
+ {
894
+ "epoch": 0.6117091732292946,
895
+ "grad_norm": 0.019557103514671326,
896
+ "learning_rate": 1.5293834296724473e-05,
897
+ "loss": 0.97,
898
+ "step": 6350
899
+ },
900
+ {
901
+ "epoch": 0.6165257808925174,
902
+ "grad_norm": 0.025096602737903595,
903
+ "learning_rate": 1.5414258188824665e-05,
904
+ "loss": 0.9658,
905
+ "step": 6400
906
+ },
907
+ {
908
+ "epoch": 0.6213423885557402,
909
+ "grad_norm": 0.028057411313056946,
910
+ "learning_rate": 1.5534682080924857e-05,
911
+ "loss": 0.9709,
912
+ "step": 6450
913
+ },
914
+ {
915
+ "epoch": 0.626158996218963,
916
+ "grad_norm": 0.03152346611022949,
917
+ "learning_rate": 1.5655105973025048e-05,
918
+ "loss": 0.9751,
919
+ "step": 6500
920
+ },
921
+ {
922
+ "epoch": 0.6309756038821858,
923
+ "grad_norm": 0.017900671809911728,
924
+ "learning_rate": 1.5775529865125243e-05,
925
+ "loss": 0.9702,
926
+ "step": 6550
927
+ },
928
+ {
929
+ "epoch": 0.6357922115454085,
930
+ "grad_norm": 0.022004351019859314,
931
+ "learning_rate": 1.5895953757225435e-05,
932
+ "loss": 0.9681,
933
+ "step": 6600
934
+ },
935
+ {
936
+ "epoch": 0.6406088192086313,
937
+ "grad_norm": 0.021472521126270294,
938
+ "learning_rate": 1.6016377649325627e-05,
939
+ "loss": 0.9709,
940
+ "step": 6650
941
+ },
942
+ {
943
+ "epoch": 0.6454254268718541,
944
+ "grad_norm": 0.01908615604043007,
945
+ "learning_rate": 1.613680154142582e-05,
946
+ "loss": 0.9716,
947
+ "step": 6700
948
+ },
949
+ {
950
+ "epoch": 0.6502420345350769,
951
+ "grad_norm": 0.02205970697104931,
952
+ "learning_rate": 1.6257225433526014e-05,
953
+ "loss": 0.9774,
954
+ "step": 6750
955
+ },
956
+ {
957
+ "epoch": 0.6550586421982998,
958
+ "grad_norm": 0.02467629499733448,
959
+ "learning_rate": 1.6377649325626205e-05,
960
+ "loss": 0.9682,
961
+ "step": 6800
962
+ },
963
+ {
964
+ "epoch": 0.6598752498615226,
965
+ "grad_norm": 0.01893242448568344,
966
+ "learning_rate": 1.6498073217726397e-05,
967
+ "loss": 0.9761,
968
+ "step": 6850
969
+ },
970
+ {
971
+ "epoch": 0.6646918575247454,
972
+ "grad_norm": 0.02502221241593361,
973
+ "learning_rate": 1.661849710982659e-05,
974
+ "loss": 0.9726,
975
+ "step": 6900
976
+ },
977
+ {
978
+ "epoch": 0.6695084651879681,
979
+ "grad_norm": 0.02121950313448906,
980
+ "learning_rate": 1.6738921001926784e-05,
981
+ "loss": 0.9671,
982
+ "step": 6950
983
+ },
984
+ {
985
+ "epoch": 0.6743250728511909,
986
+ "grad_norm": 0.019996950402855873,
987
+ "learning_rate": 1.6859344894026976e-05,
988
+ "loss": 0.9734,
989
+ "step": 7000
990
+ },
991
+ {
992
+ "epoch": 0.6791416805144137,
993
+ "grad_norm": 0.023754192516207695,
994
+ "learning_rate": 1.6979768786127167e-05,
995
+ "loss": 0.9657,
996
+ "step": 7050
997
+ },
998
+ {
999
+ "epoch": 0.6839582881776365,
1000
+ "grad_norm": 0.019974833354353905,
1001
+ "learning_rate": 1.7100192678227362e-05,
1002
+ "loss": 0.9699,
1003
+ "step": 7100
1004
+ },
1005
+ {
1006
+ "epoch": 0.6887748958408593,
1007
+ "grad_norm": 0.019718438386917114,
1008
+ "learning_rate": 1.7220616570327554e-05,
1009
+ "loss": 0.9774,
1010
+ "step": 7150
1011
+ },
1012
+ {
1013
+ "epoch": 0.693591503504082,
1014
+ "grad_norm": 0.02473635785281658,
1015
+ "learning_rate": 1.7341040462427746e-05,
1016
+ "loss": 0.9705,
1017
+ "step": 7200
1018
+ },
1019
+ {
1020
+ "epoch": 0.6984081111673048,
1021
+ "grad_norm": 0.0264342799782753,
1022
+ "learning_rate": 1.746146435452794e-05,
1023
+ "loss": 0.9729,
1024
+ "step": 7250
1025
+ },
1026
+ {
1027
+ "epoch": 0.7032247188305276,
1028
+ "grad_norm": 0.021187305450439453,
1029
+ "learning_rate": 1.7581888246628133e-05,
1030
+ "loss": 0.9687,
1031
+ "step": 7300
1032
+ },
1033
+ {
1034
+ "epoch": 0.7080413264937504,
1035
+ "grad_norm": 0.01752212457358837,
1036
+ "learning_rate": 1.7702312138728324e-05,
1037
+ "loss": 0.9675,
1038
+ "step": 7350
1039
+ },
1040
+ {
1041
+ "epoch": 0.7128579341569733,
1042
+ "grad_norm": 0.02413749136030674,
1043
+ "learning_rate": 1.782273603082852e-05,
1044
+ "loss": 0.9681,
1045
+ "step": 7400
1046
+ },
1047
+ {
1048
+ "epoch": 0.7176745418201961,
1049
+ "grad_norm": 0.023940233513712883,
1050
+ "learning_rate": 1.794315992292871e-05,
1051
+ "loss": 0.9721,
1052
+ "step": 7450
1053
+ },
1054
+ {
1055
+ "epoch": 0.7224911494834189,
1056
+ "grad_norm": 0.024347305297851562,
1057
+ "learning_rate": 1.8063583815028903e-05,
1058
+ "loss": 0.9655,
1059
+ "step": 7500
1060
+ },
1061
+ {
1062
+ "epoch": 0.7273077571466416,
1063
+ "grad_norm": 0.023215830326080322,
1064
+ "learning_rate": 1.8184007707129098e-05,
1065
+ "loss": 0.9708,
1066
+ "step": 7550
1067
+ },
1068
+ {
1069
+ "epoch": 0.7321243648098644,
1070
+ "grad_norm": 0.019564125686883926,
1071
+ "learning_rate": 1.830443159922929e-05,
1072
+ "loss": 0.9658,
1073
+ "step": 7600
1074
+ },
1075
+ {
1076
+ "epoch": 0.7369409724730872,
1077
+ "grad_norm": 0.02049618400633335,
1078
+ "learning_rate": 1.842485549132948e-05,
1079
+ "loss": 0.9662,
1080
+ "step": 7650
1081
+ },
1082
+ {
1083
+ "epoch": 0.74175758013631,
1084
+ "grad_norm": 0.031806960701942444,
1085
+ "learning_rate": 1.8545279383429673e-05,
1086
+ "loss": 0.9668,
1087
+ "step": 7700
1088
+ },
1089
+ {
1090
+ "epoch": 0.7465741877995328,
1091
+ "grad_norm": 0.02331661805510521,
1092
+ "learning_rate": 1.8665703275529868e-05,
1093
+ "loss": 0.972,
1094
+ "step": 7750
1095
+ },
1096
+ {
1097
+ "epoch": 0.7513907954627556,
1098
+ "grad_norm": 0.020196113735437393,
1099
+ "learning_rate": 1.878612716763006e-05,
1100
+ "loss": 0.9765,
1101
+ "step": 7800
1102
+ },
1103
+ {
1104
+ "epoch": 0.7562074031259783,
1105
+ "grad_norm": 0.028458353132009506,
1106
+ "learning_rate": 1.890655105973025e-05,
1107
+ "loss": 0.9658,
1108
+ "step": 7850
1109
+ },
1110
+ {
1111
+ "epoch": 0.7610240107892011,
1112
+ "grad_norm": 0.025394223630428314,
1113
+ "learning_rate": 1.9026974951830443e-05,
1114
+ "loss": 0.9747,
1115
+ "step": 7900
1116
+ },
1117
+ {
1118
+ "epoch": 0.7658406184524239,
1119
+ "grad_norm": 0.02368360199034214,
1120
+ "learning_rate": 1.914739884393064e-05,
1121
+ "loss": 0.9815,
1122
+ "step": 7950
1123
+ },
1124
+ {
1125
+ "epoch": 0.7706572261156468,
1126
+ "grad_norm": 0.021498555317521095,
1127
+ "learning_rate": 1.926782273603083e-05,
1128
+ "loss": 0.9709,
1129
+ "step": 8000
1130
+ },
1131
+ {
1132
+ "epoch": 0.7754738337788696,
1133
+ "grad_norm": 0.027243509888648987,
1134
+ "learning_rate": 1.9388246628131022e-05,
1135
+ "loss": 0.9745,
1136
+ "step": 8050
1137
+ },
1138
+ {
1139
+ "epoch": 0.7802904414420924,
1140
+ "grad_norm": 0.019903521984815598,
1141
+ "learning_rate": 1.9508670520231217e-05,
1142
+ "loss": 0.9694,
1143
+ "step": 8100
1144
+ },
1145
+ {
1146
+ "epoch": 0.7851070491053151,
1147
+ "grad_norm": 0.02099510096013546,
1148
+ "learning_rate": 1.962909441233141e-05,
1149
+ "loss": 0.9709,
1150
+ "step": 8150
1151
+ },
1152
+ {
1153
+ "epoch": 0.7899236567685379,
1154
+ "grad_norm": 0.025477971881628036,
1155
+ "learning_rate": 1.97495183044316e-05,
1156
+ "loss": 0.9693,
1157
+ "step": 8200
1158
+ },
1159
+ {
1160
+ "epoch": 0.7947402644317607,
1161
+ "grad_norm": 0.018335288390517235,
1162
+ "learning_rate": 1.9869942196531792e-05,
1163
+ "loss": 0.9682,
1164
+ "step": 8250
1165
+ },
1166
+ {
1167
+ "epoch": 0.7995568720949835,
1168
+ "grad_norm": 0.021306857466697693,
1169
+ "learning_rate": 1.9990366088631987e-05,
1170
+ "loss": 0.9646,
1171
+ "step": 8300
1172
+ },
1173
+ {
1174
+ "epoch": 0.8043734797582063,
1175
+ "grad_norm": 0.015945710241794586,
1176
+ "learning_rate": 1.9999981307496558e-05,
1177
+ "loss": 0.9738,
1178
+ "step": 8350
1179
+ },
1180
+ {
1181
+ "epoch": 0.8091900874214291,
1182
+ "grad_norm": 0.022564787417650223,
1183
+ "learning_rate": 1.9999918586988815e-05,
1184
+ "loss": 0.9702,
1185
+ "step": 8400
1186
+ },
1187
+ {
1188
+ "epoch": 0.8140066950846518,
1189
+ "grad_norm": 0.02257794328033924,
1190
+ "learning_rate": 1.9999811697411585e-05,
1191
+ "loss": 0.9634,
1192
+ "step": 8450
1193
+ },
1194
+ {
1195
+ "epoch": 0.8188233027478746,
1196
+ "grad_norm": 0.017230728641152382,
1197
+ "learning_rate": 1.9999660639236997e-05,
1198
+ "loss": 0.9757,
1199
+ "step": 8500
1200
+ },
1201
+ {
1202
+ "epoch": 0.8236399104110974,
1203
+ "grad_norm": 0.02081149071455002,
1204
+ "learning_rate": 1.999946541313226e-05,
1205
+ "loss": 0.9674,
1206
+ "step": 8550
1207
+ },
1208
+ {
1209
+ "epoch": 0.8284565180743203,
1210
+ "grad_norm": 0.019852489233016968,
1211
+ "learning_rate": 1.9999226019959675e-05,
1212
+ "loss": 0.9753,
1213
+ "step": 8600
1214
+ },
1215
+ {
1216
+ "epoch": 0.8332731257375431,
1217
+ "grad_norm": 0.022209197282791138,
1218
+ "learning_rate": 1.9998942460776637e-05,
1219
+ "loss": 0.967,
1220
+ "step": 8650
1221
+ },
1222
+ {
1223
+ "epoch": 0.8380897334007659,
1224
+ "grad_norm": 0.01641988568007946,
1225
+ "learning_rate": 1.99986147368356e-05,
1226
+ "loss": 0.9691,
1227
+ "step": 8700
1228
+ },
1229
+ {
1230
+ "epoch": 0.8429063410639887,
1231
+ "grad_norm": 0.022373568266630173,
1232
+ "learning_rate": 1.999824284958411e-05,
1233
+ "loss": 0.9714,
1234
+ "step": 8750
1235
+ },
1236
+ {
1237
+ "epoch": 0.8477229487272114,
1238
+ "grad_norm": 0.01713249646127224,
1239
+ "learning_rate": 1.9997826800664773e-05,
1240
+ "loss": 0.9675,
1241
+ "step": 8800
1242
+ },
1243
+ {
1244
+ "epoch": 0.8525395563904342,
1245
+ "grad_norm": 0.022914381697773933,
1246
+ "learning_rate": 1.9997366591915246e-05,
1247
+ "loss": 0.9723,
1248
+ "step": 8850
1249
+ },
1250
+ {
1251
+ "epoch": 0.857356164053657,
1252
+ "grad_norm": 0.018057918176054955,
1253
+ "learning_rate": 1.9996862225368248e-05,
1254
+ "loss": 0.9728,
1255
+ "step": 8900
1256
+ },
1257
+ {
1258
+ "epoch": 0.8621727717168798,
1259
+ "grad_norm": 0.022914033383131027,
1260
+ "learning_rate": 1.9996313703251536e-05,
1261
+ "loss": 0.9693,
1262
+ "step": 8950
1263
+ },
1264
+ {
1265
+ "epoch": 0.8669893793801026,
1266
+ "grad_norm": 0.028229426592588425,
1267
+ "learning_rate": 1.9995721027987903e-05,
1268
+ "loss": 0.9695,
1269
+ "step": 9000
1270
+ },
1271
+ {
1272
+ "epoch": 0.8718059870433253,
1273
+ "grad_norm": 0.022879110649228096,
1274
+ "learning_rate": 1.999508420219516e-05,
1275
+ "loss": 0.9739,
1276
+ "step": 9050
1277
+ },
1278
+ {
1279
+ "epoch": 0.8766225947065481,
1280
+ "grad_norm": 0.016597425565123558,
1281
+ "learning_rate": 1.9994403228686134e-05,
1282
+ "loss": 0.9693,
1283
+ "step": 9100
1284
+ },
1285
+ {
1286
+ "epoch": 0.881439202369771,
1287
+ "grad_norm": 0.020313039422035217,
1288
+ "learning_rate": 1.9993678110468642e-05,
1289
+ "loss": 0.9781,
1290
+ "step": 9150
1291
+ },
1292
+ {
1293
+ "epoch": 0.8862558100329938,
1294
+ "grad_norm": 0.023865938186645508,
1295
+ "learning_rate": 1.999290885074549e-05,
1296
+ "loss": 0.9676,
1297
+ "step": 9200
1298
+ },
1299
+ {
1300
+ "epoch": 0.8910724176962166,
1301
+ "grad_norm": 0.02183787152171135,
1302
+ "learning_rate": 1.9992095452914454e-05,
1303
+ "loss": 0.9794,
1304
+ "step": 9250
1305
+ },
1306
+ {
1307
+ "epoch": 0.8958890253594394,
1308
+ "grad_norm": 0.029220541939139366,
1309
+ "learning_rate": 1.9991237920568272e-05,
1310
+ "loss": 0.9728,
1311
+ "step": 9300
1312
+ },
1313
+ {
1314
+ "epoch": 0.9007056330226622,
1315
+ "grad_norm": 0.02130264975130558,
1316
+ "learning_rate": 1.9990336257494607e-05,
1317
+ "loss": 0.9743,
1318
+ "step": 9350
1319
+ },
1320
+ {
1321
+ "epoch": 0.9055222406858849,
1322
+ "grad_norm": 0.02516760677099228,
1323
+ "learning_rate": 1.9989390467676057e-05,
1324
+ "loss": 0.9726,
1325
+ "step": 9400
1326
+ },
1327
+ {
1328
+ "epoch": 0.9103388483491077,
1329
+ "grad_norm": 0.024124667048454285,
1330
+ "learning_rate": 1.998840055529012e-05,
1331
+ "loss": 0.9687,
1332
+ "step": 9450
1333
+ },
1334
+ {
1335
+ "epoch": 0.9151554560123305,
1336
+ "grad_norm": 0.020920995622873306,
1337
+ "learning_rate": 1.9987366524709187e-05,
1338
+ "loss": 0.9826,
1339
+ "step": 9500
1340
+ },
1341
+ {
1342
+ "epoch": 0.9199720636755533,
1343
+ "grad_norm": 0.016224917024374008,
1344
+ "learning_rate": 1.9986288380500508e-05,
1345
+ "loss": 0.9695,
1346
+ "step": 9550
1347
+ },
1348
+ {
1349
+ "epoch": 0.9247886713387761,
1350
+ "grad_norm": 0.023870129138231277,
1351
+ "learning_rate": 1.9985166127426186e-05,
1352
+ "loss": 0.968,
1353
+ "step": 9600
1354
+ },
1355
+ {
1356
+ "epoch": 0.9296052790019989,
1357
+ "grad_norm": 0.018101558089256287,
1358
+ "learning_rate": 1.998399977044315e-05,
1359
+ "loss": 0.968,
1360
+ "step": 9650
1361
+ },
1362
+ {
1363
+ "epoch": 0.9344218866652216,
1364
+ "grad_norm": 0.021635858342051506,
1365
+ "learning_rate": 1.9982789314703126e-05,
1366
+ "loss": 0.967,
1367
+ "step": 9700
1368
+ },
1369
+ {
1370
+ "epoch": 0.9392384943284445,
1371
+ "grad_norm": 0.02077612280845642,
1372
+ "learning_rate": 1.9981534765552638e-05,
1373
+ "loss": 0.9729,
1374
+ "step": 9750
1375
+ },
1376
+ {
1377
+ "epoch": 0.9440551019916673,
1378
+ "grad_norm": 0.018736233934760094,
1379
+ "learning_rate": 1.9980236128532948e-05,
1380
+ "loss": 0.9637,
1381
+ "step": 9800
1382
+ },
1383
+ {
1384
+ "epoch": 0.9488717096548901,
1385
+ "grad_norm": 0.019599338993430138,
1386
+ "learning_rate": 1.9978893409380063e-05,
1387
+ "loss": 0.972,
1388
+ "step": 9850
1389
+ },
1390
+ {
1391
+ "epoch": 0.9536883173181129,
1392
+ "grad_norm": 0.024034442380070686,
1393
+ "learning_rate": 1.9977506614024706e-05,
1394
+ "loss": 0.9711,
1395
+ "step": 9900
1396
+ },
1397
+ {
1398
+ "epoch": 0.9585049249813357,
1399
+ "grad_norm": 0.023441381752490997,
1400
+ "learning_rate": 1.9976075748592264e-05,
1401
+ "loss": 0.9668,
1402
+ "step": 9950
1403
+ },
1404
+ {
1405
+ "epoch": 0.9633215326445584,
1406
+ "grad_norm": 0.03189970180392265,
1407
+ "learning_rate": 1.997460081940279e-05,
1408
+ "loss": 0.9695,
1409
+ "step": 10000
1410
+ },
1411
+ {
1412
+ "epoch": 0.9681381403077812,
1413
+ "grad_norm": 0.022853758186101913,
1414
+ "learning_rate": 1.9973081832970962e-05,
1415
+ "loss": 0.9718,
1416
+ "step": 10050
1417
+ },
1418
+ {
1419
+ "epoch": 0.972954747971004,
1420
+ "grad_norm": 0.020372973755002022,
1421
+ "learning_rate": 1.9971550488396247e-05,
1422
+ "loss": 0.9749,
1423
+ "step": 10100
1424
+ },
1425
+ {
1426
+ "epoch": 0.9777713556342268,
1427
+ "grad_norm": 0.02032754011452198,
1428
+ "learning_rate": 1.996994428860578e-05,
1429
+ "loss": 0.9709,
1430
+ "step": 10150
1431
+ },
1432
+ {
1433
+ "epoch": 0.9825879632974496,
1434
+ "grad_norm": 0.01894865557551384,
1435
+ "learning_rate": 1.996829405214059e-05,
1436
+ "loss": 0.9709,
1437
+ "step": 10200
1438
+ },
1439
+ {
1440
+ "epoch": 0.9874045709606724,
1441
+ "grad_norm": 0.023153427988290787,
1442
+ "learning_rate": 1.9966599786289677e-05,
1443
+ "loss": 0.9652,
1444
+ "step": 10250
1445
+ },
1446
+ {
1447
+ "epoch": 0.9922211786238951,
1448
+ "grad_norm": 0.016725238412618637,
1449
+ "learning_rate": 1.9964861498536514e-05,
1450
+ "loss": 0.9671,
1451
+ "step": 10300
1452
+ },
1453
+ {
1454
+ "epoch": 0.997037786287118,
1455
+ "grad_norm": 0.01910654455423355,
1456
+ "learning_rate": 1.9963079196559025e-05,
1457
+ "loss": 0.9654,
1458
+ "step": 10350
1459
+ },
1460
+ {
1461
+ "epoch": 1.0019266430652891,
1462
+ "grad_norm": 0.016868438571691513,
1463
+ "learning_rate": 1.9961252888229533e-05,
1464
+ "loss": 0.9826,
1465
+ "step": 10400
1466
+ },
1467
+ {
1468
+ "epoch": 1.006743250728512,
1469
+ "grad_norm": 0.024409230798482895,
1470
+ "learning_rate": 1.9959382581614738e-05,
1471
+ "loss": 0.9717,
1472
+ "step": 10450
1473
+ },
1474
+ {
1475
+ "epoch": 1.0115598583917347,
1476
+ "grad_norm": 0.02388002723455429,
1477
+ "learning_rate": 1.9957468284975676e-05,
1478
+ "loss": 0.9704,
1479
+ "step": 10500
1480
+ },
1481
+ {
1482
+ "epoch": 1.0163764660549575,
1483
+ "grad_norm": 0.02049044892191887,
1484
+ "learning_rate": 1.9955510006767688e-05,
1485
+ "loss": 0.9661,
1486
+ "step": 10550
1487
+ },
1488
+ {
1489
+ "epoch": 1.0211930737181802,
1490
+ "grad_norm": 0.02806607447564602,
1491
+ "learning_rate": 1.9953507755640373e-05,
1492
+ "loss": 0.965,
1493
+ "step": 10600
1494
+ },
1495
+ {
1496
+ "epoch": 1.026009681381403,
1497
+ "grad_norm": 0.02697833627462387,
1498
+ "learning_rate": 1.9951461540437568e-05,
1499
+ "loss": 0.9719,
1500
+ "step": 10650
1501
+ },
1502
+ {
1503
+ "epoch": 1.0308262890446258,
1504
+ "grad_norm": 0.024413883686065674,
1505
+ "learning_rate": 1.9949371370197277e-05,
1506
+ "loss": 0.968,
1507
+ "step": 10700
1508
+ },
1509
+ {
1510
+ "epoch": 1.0356428967078486,
1511
+ "grad_norm": 0.026219476014375687,
1512
+ "learning_rate": 1.9947237254151676e-05,
1513
+ "loss": 0.9703,
1514
+ "step": 10750
1515
+ },
1516
+ {
1517
+ "epoch": 1.0404595043710714,
1518
+ "grad_norm": 0.021840987727046013,
1519
+ "learning_rate": 1.9945059201727023e-05,
1520
+ "loss": 0.972,
1521
+ "step": 10800
1522
+ },
1523
+ {
1524
+ "epoch": 1.0452761120342942,
1525
+ "grad_norm": 0.024745196104049683,
1526
+ "learning_rate": 1.9942837222543656e-05,
1527
+ "loss": 0.977,
1528
+ "step": 10850
1529
+ },
1530
+ {
1531
+ "epoch": 1.050092719697517,
1532
+ "grad_norm": 0.029609955847263336,
1533
+ "learning_rate": 1.994057132641593e-05,
1534
+ "loss": 0.9679,
1535
+ "step": 10900
1536
+ },
1537
+ {
1538
+ "epoch": 1.0549093273607397,
1539
+ "grad_norm": 0.026458898559212685,
1540
+ "learning_rate": 1.9938261523352176e-05,
1541
+ "loss": 0.972,
1542
+ "step": 10950
1543
+ },
1544
+ {
1545
+ "epoch": 1.0597259350239627,
1546
+ "grad_norm": 0.023683995008468628,
1547
+ "learning_rate": 1.993590782355467e-05,
1548
+ "loss": 0.9669,
1549
+ "step": 11000
1550
+ },
1551
+ {
1552
+ "epoch": 1.0645425426871855,
1553
+ "grad_norm": 0.026212599128484726,
1554
+ "learning_rate": 1.9933510237419563e-05,
1555
+ "loss": 0.9705,
1556
+ "step": 11050
1557
+ },
1558
+ {
1559
+ "epoch": 1.0693591503504083,
1560
+ "grad_norm": 0.025770004838705063,
1561
+ "learning_rate": 1.9931068775536853e-05,
1562
+ "loss": 0.9748,
1563
+ "step": 11100
1564
+ },
1565
+ {
1566
+ "epoch": 1.074175758013631,
1567
+ "grad_norm": 0.028559479862451553,
1568
+ "learning_rate": 1.9928583448690345e-05,
1569
+ "loss": 0.9708,
1570
+ "step": 11150
1571
+ },
1572
+ {
1573
+ "epoch": 1.0789923656768539,
1574
+ "grad_norm": 0.023568179458379745,
1575
+ "learning_rate": 1.992605426785758e-05,
1576
+ "loss": 0.9618,
1577
+ "step": 11200
1578
+ },
1579
+ {
1580
+ "epoch": 1.0838089733400766,
1581
+ "grad_norm": 0.02477218583226204,
1582
+ "learning_rate": 1.9923481244209812e-05,
1583
+ "loss": 0.9685,
1584
+ "step": 11250
1585
+ },
1586
+ {
1587
+ "epoch": 1.0886255810032994,
1588
+ "grad_norm": 0.02419090084731579,
1589
+ "learning_rate": 1.9920864389111932e-05,
1590
+ "loss": 0.9679,
1591
+ "step": 11300
1592
+ },
1593
+ {
1594
+ "epoch": 1.0934421886665222,
1595
+ "grad_norm": 0.02636454440653324,
1596
+ "learning_rate": 1.9918203714122443e-05,
1597
+ "loss": 0.9699,
1598
+ "step": 11350
1599
+ },
1600
+ {
1601
+ "epoch": 1.098258796329745,
1602
+ "grad_norm": 0.029870351776480675,
1603
+ "learning_rate": 1.99154992309934e-05,
1604
+ "loss": 0.9708,
1605
+ "step": 11400
1606
+ },
1607
+ {
1608
+ "epoch": 1.1030754039929678,
1609
+ "grad_norm": 0.024796070531010628,
1610
+ "learning_rate": 1.9912750951670343e-05,
1611
+ "loss": 0.9692,
1612
+ "step": 11450
1613
+ },
1614
+ {
1615
+ "epoch": 1.1078920116561906,
1616
+ "grad_norm": 0.023329641669988632,
1617
+ "learning_rate": 1.9909958888292264e-05,
1618
+ "loss": 0.9712,
1619
+ "step": 11500
1620
+ },
1621
+ {
1622
+ "epoch": 1.1127086193194133,
1623
+ "grad_norm": 0.017567068338394165,
1624
+ "learning_rate": 1.9907123053191552e-05,
1625
+ "loss": 0.9666,
1626
+ "step": 11550
1627
+ },
1628
+ {
1629
+ "epoch": 1.1175252269826361,
1630
+ "grad_norm": 0.027991535142064095,
1631
+ "learning_rate": 1.990424345889393e-05,
1632
+ "loss": 0.9641,
1633
+ "step": 11600
1634
+ },
1635
+ {
1636
+ "epoch": 1.122341834645859,
1637
+ "grad_norm": 0.02564748004078865,
1638
+ "learning_rate": 1.9901320118118396e-05,
1639
+ "loss": 0.9743,
1640
+ "step": 11650
1641
+ },
1642
+ {
1643
+ "epoch": 1.1271584423090817,
1644
+ "grad_norm": 0.02555004321038723,
1645
+ "learning_rate": 1.9898353043777184e-05,
1646
+ "loss": 0.9721,
1647
+ "step": 11700
1648
+ },
1649
+ {
1650
+ "epoch": 1.1319750499723045,
1651
+ "grad_norm": 0.02131088450551033,
1652
+ "learning_rate": 1.989534224897569e-05,
1653
+ "loss": 0.9758,
1654
+ "step": 11750
1655
+ },
1656
+ {
1657
+ "epoch": 1.1367916576355273,
1658
+ "grad_norm": 0.026900706812739372,
1659
+ "learning_rate": 1.9892287747012424e-05,
1660
+ "loss": 0.9724,
1661
+ "step": 11800
1662
+ },
1663
+ {
1664
+ "epoch": 1.14160826529875,
1665
+ "grad_norm": 0.029474128037691116,
1666
+ "learning_rate": 1.9889189551378946e-05,
1667
+ "loss": 0.9713,
1668
+ "step": 11850
1669
+ },
1670
+ {
1671
+ "epoch": 1.1464248729619728,
1672
+ "grad_norm": 0.024047445505857468,
1673
+ "learning_rate": 1.9886047675759806e-05,
1674
+ "loss": 0.9717,
1675
+ "step": 11900
1676
+ },
1677
+ {
1678
+ "epoch": 1.1512414806251956,
1679
+ "grad_norm": 0.03356277942657471,
1680
+ "learning_rate": 1.9882862134032496e-05,
1681
+ "loss": 0.9677,
1682
+ "step": 11950
1683
+ },
1684
+ {
1685
+ "epoch": 1.1560580882884184,
1686
+ "grad_norm": 0.021987082436680794,
1687
+ "learning_rate": 1.9879632940267367e-05,
1688
+ "loss": 0.9694,
1689
+ "step": 12000
1690
+ },
1691
+ {
1692
+ "epoch": 1.1608746959516412,
1693
+ "grad_norm": 0.02819712460041046,
1694
+ "learning_rate": 1.9876360108727587e-05,
1695
+ "loss": 0.9698,
1696
+ "step": 12050
1697
+ },
1698
+ {
1699
+ "epoch": 1.1656913036148642,
1700
+ "grad_norm": 0.025663986802101135,
1701
+ "learning_rate": 1.987304365386906e-05,
1702
+ "loss": 0.9644,
1703
+ "step": 12100
1704
+ },
1705
+ {
1706
+ "epoch": 1.170507911278087,
1707
+ "grad_norm": 0.027840405702590942,
1708
+ "learning_rate": 1.986975121888025e-05,
1709
+ "loss": 0.9697,
1710
+ "step": 12150
1711
+ },
1712
+ {
1713
+ "epoch": 1.1753245189413097,
1714
+ "grad_norm": 0.027610784396529198,
1715
+ "learning_rate": 1.986634843325252e-05,
1716
+ "loss": 0.9714,
1717
+ "step": 12200
1718
+ },
1719
+ {
1720
+ "epoch": 1.1801411266045325,
1721
+ "grad_norm": 0.0255660992115736,
1722
+ "learning_rate": 1.9862902068527047e-05,
1723
+ "loss": 0.9686,
1724
+ "step": 12250
1725
+ },
1726
+ {
1727
+ "epoch": 1.1849577342677553,
1728
+ "grad_norm": 0.02563071809709072,
1729
+ "learning_rate": 1.9859412139926226e-05,
1730
+ "loss": 0.9772,
1731
+ "step": 12300
1732
+ },
1733
+ {
1734
+ "epoch": 1.189774341930978,
1735
+ "grad_norm": 0.02713589556515217,
1736
+ "learning_rate": 1.985587866286487e-05,
1737
+ "loss": 0.9657,
1738
+ "step": 12350
1739
+ },
1740
+ {
1741
+ "epoch": 1.1945909495942009,
1742
+ "grad_norm": 0.022765563800930977,
1743
+ "learning_rate": 1.9852301652950153e-05,
1744
+ "loss": 0.9735,
1745
+ "step": 12400
1746
+ },
1747
+ {
1748
+ "epoch": 1.1994075572574237,
1749
+ "grad_norm": 0.02689959481358528,
1750
+ "learning_rate": 1.9848681125981514e-05,
1751
+ "loss": 0.9649,
1752
+ "step": 12450
1753
+ },
1754
+ {
1755
+ "epoch": 1.2042241649206464,
1756
+ "grad_norm": 0.028635011985898018,
1757
+ "learning_rate": 1.984501709795062e-05,
1758
+ "loss": 0.9735,
1759
+ "step": 12500
1760
+ },
1761
+ {
1762
+ "epoch": 1.2090407725838692,
1763
+ "grad_norm": 0.02618209645152092,
1764
+ "learning_rate": 1.984130958504127e-05,
1765
+ "loss": 0.9681,
1766
+ "step": 12550
1767
+ },
1768
+ {
1769
+ "epoch": 1.213857380247092,
1770
+ "grad_norm": 0.03409925475716591,
1771
+ "learning_rate": 1.9837558603629342e-05,
1772
+ "loss": 0.9673,
1773
+ "step": 12600
1774
+ },
1775
+ {
1776
+ "epoch": 1.2186739879103148,
1777
+ "grad_norm": 0.024016890674829483,
1778
+ "learning_rate": 1.98337641702827e-05,
1779
+ "loss": 0.9714,
1780
+ "step": 12650
1781
+ },
1782
+ {
1783
+ "epoch": 1.2234905955735376,
1784
+ "grad_norm": 0.02566283568739891,
1785
+ "learning_rate": 1.9829926301761148e-05,
1786
+ "loss": 0.9637,
1787
+ "step": 12700
1788
+ },
1789
+ {
1790
+ "epoch": 1.2283072032367603,
1791
+ "grad_norm": 0.030937056988477707,
1792
+ "learning_rate": 1.9826045015016325e-05,
1793
+ "loss": 0.9638,
1794
+ "step": 12750
1795
+ },
1796
+ {
1797
+ "epoch": 1.2331238108999831,
1798
+ "grad_norm": 0.024775423109531403,
1799
+ "learning_rate": 1.9822120327191656e-05,
1800
+ "loss": 0.9745,
1801
+ "step": 12800
1802
+ },
1803
+ {
1804
+ "epoch": 1.237940418563206,
1805
+ "grad_norm": 0.029670532792806625,
1806
+ "learning_rate": 1.981815225562226e-05,
1807
+ "loss": 0.973,
1808
+ "step": 12850
1809
+ },
1810
+ {
1811
+ "epoch": 1.2427570262264287,
1812
+ "grad_norm": 0.03619584068655968,
1813
+ "learning_rate": 1.9814140817834885e-05,
1814
+ "loss": 0.9683,
1815
+ "step": 12900
1816
+ },
1817
+ {
1818
+ "epoch": 1.2475736338896515,
1819
+ "grad_norm": 0.02621552161872387,
1820
+ "learning_rate": 1.9810086031547824e-05,
1821
+ "loss": 0.9757,
1822
+ "step": 12950
1823
+ },
1824
+ {
1825
+ "epoch": 1.2523902415528743,
1826
+ "grad_norm": 0.029616640880703926,
1827
+ "learning_rate": 1.9805987914670836e-05,
1828
+ "loss": 0.9745,
1829
+ "step": 13000
1830
+ },
1831
+ {
1832
+ "epoch": 1.257206849216097,
1833
+ "grad_norm": 0.03276960924267769,
1834
+ "learning_rate": 1.9801846485305067e-05,
1835
+ "loss": 0.9687,
1836
+ "step": 13050
1837
+ },
1838
+ {
1839
+ "epoch": 1.2620234568793198,
1840
+ "grad_norm": 0.02453836239874363,
1841
+ "learning_rate": 1.9797661761742976e-05,
1842
+ "loss": 0.9741,
1843
+ "step": 13100
1844
+ },
1845
+ {
1846
+ "epoch": 1.2668400645425426,
1847
+ "grad_norm": 0.028019757941365242,
1848
+ "learning_rate": 1.9793433762468247e-05,
1849
+ "loss": 0.9687,
1850
+ "step": 13150
1851
+ },
1852
+ {
1853
+ "epoch": 1.2716566722057654,
1854
+ "grad_norm": 0.03742435574531555,
1855
+ "learning_rate": 1.978916250615571e-05,
1856
+ "loss": 0.9729,
1857
+ "step": 13200
1858
+ },
1859
+ {
1860
+ "epoch": 1.2764732798689882,
1861
+ "grad_norm": 0.030632615089416504,
1862
+ "learning_rate": 1.9784848011671266e-05,
1863
+ "loss": 0.9694,
1864
+ "step": 13250
1865
+ },
1866
+ {
1867
+ "epoch": 1.281289887532211,
1868
+ "grad_norm": 0.029843851923942566,
1869
+ "learning_rate": 1.9780490298071783e-05,
1870
+ "loss": 0.9681,
1871
+ "step": 13300
1872
+ },
1873
+ {
1874
+ "epoch": 1.2861064951954337,
1875
+ "grad_norm": 0.030314400792121887,
1876
+ "learning_rate": 1.9776089384605042e-05,
1877
+ "loss": 0.9685,
1878
+ "step": 13350
1879
+ },
1880
+ {
1881
+ "epoch": 1.2909231028586565,
1882
+ "grad_norm": 0.03156287223100662,
1883
+ "learning_rate": 1.9771645290709617e-05,
1884
+ "loss": 0.9706,
1885
+ "step": 13400
1886
+ },
1887
+ {
1888
+ "epoch": 1.2957397105218793,
1889
+ "grad_norm": 0.023538535460829735,
1890
+ "learning_rate": 1.9767158036014826e-05,
1891
+ "loss": 0.9758,
1892
+ "step": 13450
1893
+ },
1894
+ {
1895
+ "epoch": 1.3005563181851023,
1896
+ "grad_norm": 0.024605972692370415,
1897
+ "learning_rate": 1.9762627640340608e-05,
1898
+ "loss": 0.9701,
1899
+ "step": 13500
1900
+ },
1901
+ {
1902
+ "epoch": 1.305372925848325,
1903
+ "grad_norm": 0.030106617137789726,
1904
+ "learning_rate": 1.975805412369747e-05,
1905
+ "loss": 0.9636,
1906
+ "step": 13550
1907
+ },
1908
+ {
1909
+ "epoch": 1.3101895335115479,
1910
+ "grad_norm": 0.026056772097945213,
1911
+ "learning_rate": 1.975343750628637e-05,
1912
+ "loss": 0.9737,
1913
+ "step": 13600
1914
+ },
1915
+ {
1916
+ "epoch": 1.3150061411747707,
1917
+ "grad_norm": 0.028378983959555626,
1918
+ "learning_rate": 1.9748777808498644e-05,
1919
+ "loss": 0.9746,
1920
+ "step": 13650
1921
+ },
1922
+ {
1923
+ "epoch": 1.3198227488379934,
1924
+ "grad_norm": 0.034412529319524765,
1925
+ "learning_rate": 1.974407505091591e-05,
1926
+ "loss": 0.9743,
1927
+ "step": 13700
1928
+ },
1929
+ {
1930
+ "epoch": 1.3246393565012162,
1931
+ "grad_norm": 0.031644053757190704,
1932
+ "learning_rate": 1.973932925430998e-05,
1933
+ "loss": 0.9732,
1934
+ "step": 13750
1935
+ },
1936
+ {
1937
+ "epoch": 1.329455964164439,
1938
+ "grad_norm": 0.02847512625157833,
1939
+ "learning_rate": 1.973454043964277e-05,
1940
+ "loss": 0.9652,
1941
+ "step": 13800
1942
+ },
1943
+ {
1944
+ "epoch": 1.3342725718276618,
1945
+ "grad_norm": 0.0374007448554039,
1946
+ "learning_rate": 1.9729708628066196e-05,
1947
+ "loss": 0.9692,
1948
+ "step": 13850
1949
+ },
1950
+ {
1951
+ "epoch": 1.3390891794908846,
1952
+ "grad_norm": 0.025235909968614578,
1953
+ "learning_rate": 1.9724833840922097e-05,
1954
+ "loss": 0.9685,
1955
+ "step": 13900
1956
+ },
1957
+ {
1958
+ "epoch": 1.3439057871541074,
1959
+ "grad_norm": 0.025667540729045868,
1960
+ "learning_rate": 1.9719916099742132e-05,
1961
+ "loss": 0.9723,
1962
+ "step": 13950
1963
+ },
1964
+ {
1965
+ "epoch": 1.3487223948173301,
1966
+ "grad_norm": 0.023921718820929527,
1967
+ "learning_rate": 1.9714955426247678e-05,
1968
+ "loss": 0.9662,
1969
+ "step": 14000
1970
+ },
1971
+ {
1972
+ "epoch": 1.353539002480553,
1973
+ "grad_norm": 0.02556893602013588,
1974
+ "learning_rate": 1.9709951842349748e-05,
1975
+ "loss": 0.9741,
1976
+ "step": 14050
1977
+ },
1978
+ {
1979
+ "epoch": 1.3583556101437757,
1980
+ "grad_norm": 0.026045670732855797,
1981
+ "learning_rate": 1.9704905370148887e-05,
1982
+ "loss": 0.9624,
1983
+ "step": 14100
1984
+ },
1985
+ {
1986
+ "epoch": 1.3631722178069985,
1987
+ "grad_norm": 0.023858319967985153,
1988
+ "learning_rate": 1.9699816031935074e-05,
1989
+ "loss": 0.9674,
1990
+ "step": 14150
1991
+ },
1992
+ {
1993
+ "epoch": 1.3679888254702213,
1994
+ "grad_norm": 0.0322500616312027,
1995
+ "learning_rate": 1.9694786913542897e-05,
1996
+ "loss": 0.977,
1997
+ "step": 14200
1998
+ },
1999
+ {
2000
+ "epoch": 1.372805433133444,
2001
+ "grad_norm": 0.03224671259522438,
2002
+ "learning_rate": 1.9689612767124294e-05,
2003
+ "loss": 0.9689,
2004
+ "step": 14250
2005
+ },
2006
+ {
2007
+ "epoch": 1.3776220407966668,
2008
+ "grad_norm": 0.03843426704406738,
2009
+ "learning_rate": 1.9684395822239297e-05,
2010
+ "loss": 0.9752,
2011
+ "step": 14300
2012
+ },
2013
+ {
2014
+ "epoch": 1.3824386484598896,
2015
+ "grad_norm": 0.026064148172736168,
2016
+ "learning_rate": 1.9679136101930848e-05,
2017
+ "loss": 0.9778,
2018
+ "step": 14350
2019
+ },
2020
+ {
2021
+ "epoch": 1.3872552561231126,
2022
+ "grad_norm": 0.025711484253406525,
2023
+ "learning_rate": 1.9673833629430832e-05,
2024
+ "loss": 0.9689,
2025
+ "step": 14400
2026
+ },
2027
+ {
2028
+ "epoch": 1.3920718637863354,
2029
+ "grad_norm": 0.0261895302683115,
2030
+ "learning_rate": 1.9668488428159973e-05,
2031
+ "loss": 0.9644,
2032
+ "step": 14450
2033
+ },
2034
+ {
2035
+ "epoch": 1.3968884714495582,
2036
+ "grad_norm": 0.03175192326307297,
2037
+ "learning_rate": 1.9663100521727716e-05,
2038
+ "loss": 0.9691,
2039
+ "step": 14500
2040
+ },
2041
+ {
2042
+ "epoch": 1.401705079112781,
2043
+ "grad_norm": 0.03027217462658882,
2044
+ "learning_rate": 1.9657669933932136e-05,
2045
+ "loss": 0.971,
2046
+ "step": 14550
2047
+ },
2048
+ {
2049
+ "epoch": 1.4065216867760038,
2050
+ "grad_norm": 0.024579547345638275,
2051
+ "learning_rate": 1.9652196688759827e-05,
2052
+ "loss": 0.9703,
2053
+ "step": 14600
2054
+ },
2055
+ {
2056
+ "epoch": 1.4113382944392265,
2057
+ "grad_norm": 0.028914442285895348,
2058
+ "learning_rate": 1.9646680810385804e-05,
2059
+ "loss": 0.9674,
2060
+ "step": 14650
2061
+ },
2062
+ {
2063
+ "epoch": 1.4161549021024493,
2064
+ "grad_norm": 0.03456846624612808,
2065
+ "learning_rate": 1.964112232317339e-05,
2066
+ "loss": 0.9781,
2067
+ "step": 14700
2068
+ },
2069
+ {
2070
+ "epoch": 1.420971509765672,
2071
+ "grad_norm": 0.028025124222040176,
2072
+ "learning_rate": 1.9635521251674098e-05,
2073
+ "loss": 0.9707,
2074
+ "step": 14750
2075
+ },
2076
+ {
2077
+ "epoch": 1.4257881174288949,
2078
+ "grad_norm": 0.05355874449014664,
2079
+ "learning_rate": 1.9629877620627546e-05,
2080
+ "loss": 0.9692,
2081
+ "step": 14800
2082
+ },
2083
+ {
2084
+ "epoch": 1.4306047250921177,
2085
+ "grad_norm": 0.03182777762413025,
2086
+ "learning_rate": 1.9624191454961325e-05,
2087
+ "loss": 0.9711,
2088
+ "step": 14850
2089
+ },
2090
+ {
2091
+ "epoch": 1.4354213327553405,
2092
+ "grad_norm": 0.05597613751888275,
2093
+ "learning_rate": 1.961846277979091e-05,
2094
+ "loss": 0.9683,
2095
+ "step": 14900
2096
+ },
2097
+ {
2098
+ "epoch": 1.4402379404185632,
2099
+ "grad_norm": 0.030285140499472618,
2100
+ "learning_rate": 1.961269162041953e-05,
2101
+ "loss": 0.9732,
2102
+ "step": 14950
2103
+ },
2104
+ {
2105
+ "epoch": 1.445054548081786,
2106
+ "grad_norm": 0.03114873729646206,
2107
+ "learning_rate": 1.960687800233807e-05,
2108
+ "loss": 0.9725,
2109
+ "step": 15000
2110
+ },
2111
+ {
2112
+ "epoch": 1.4498711557450088,
2113
+ "grad_norm": 0.03588712215423584,
2114
+ "learning_rate": 1.9601021951224944e-05,
2115
+ "loss": 0.9719,
2116
+ "step": 15050
2117
+ },
2118
+ {
2119
+ "epoch": 1.4546877634082316,
2120
+ "grad_norm": 0.030071932822465897,
2121
+ "learning_rate": 1.9595123492945993e-05,
2122
+ "loss": 0.969,
2123
+ "step": 15100
2124
+ },
2125
+ {
2126
+ "epoch": 1.4595043710714544,
2127
+ "grad_norm": 0.027533281594514847,
2128
+ "learning_rate": 1.958918265355438e-05,
2129
+ "loss": 0.9661,
2130
+ "step": 15150
2131
+ },
2132
+ {
2133
+ "epoch": 1.4643209787346771,
2134
+ "grad_norm": 0.0330142118036747,
2135
+ "learning_rate": 1.9583199459290446e-05,
2136
+ "loss": 0.965,
2137
+ "step": 15200
2138
+ },
2139
+ {
2140
+ "epoch": 1.4691375863979,
2141
+ "grad_norm": 0.022118212655186653,
2142
+ "learning_rate": 1.957717393658162e-05,
2143
+ "loss": 0.9664,
2144
+ "step": 15250
2145
+ },
2146
+ {
2147
+ "epoch": 1.4739541940611227,
2148
+ "grad_norm": 0.032654423266649246,
2149
+ "learning_rate": 1.957110611204229e-05,
2150
+ "loss": 0.9715,
2151
+ "step": 15300
2152
+ },
2153
+ {
2154
+ "epoch": 1.4787708017243455,
2155
+ "grad_norm": 0.02691168710589409,
2156
+ "learning_rate": 1.9564996012473694e-05,
2157
+ "loss": 0.9706,
2158
+ "step": 15350
2159
+ },
2160
+ {
2161
+ "epoch": 1.4835874093875683,
2162
+ "grad_norm": 0.03887908160686493,
2163
+ "learning_rate": 1.9558843664863795e-05,
2164
+ "loss": 0.9662,
2165
+ "step": 15400
2166
+ },
2167
+ {
2168
+ "epoch": 1.488404017050791,
2169
+ "grad_norm": 0.0344851128757,
2170
+ "learning_rate": 1.9552649096387153e-05,
2171
+ "loss": 0.9761,
2172
+ "step": 15450
2173
+ },
2174
+ {
2175
+ "epoch": 1.4932206247140138,
2176
+ "grad_norm": 0.03265225887298584,
2177
+ "learning_rate": 1.9546412334404832e-05,
2178
+ "loss": 0.9681,
2179
+ "step": 15500
2180
+ },
2181
+ {
2182
+ "epoch": 1.4980372323772366,
2183
+ "grad_norm": 0.029123323038220406,
2184
+ "learning_rate": 1.9540133406464247e-05,
2185
+ "loss": 0.9651,
2186
+ "step": 15550
2187
+ },
2188
+ {
2189
+ "epoch": 1.5028538400404594,
2190
+ "grad_norm": 0.02822013758122921,
2191
+ "learning_rate": 1.953381234029907e-05,
2192
+ "loss": 0.9673,
2193
+ "step": 15600
2194
+ },
2195
+ {
2196
+ "epoch": 1.5076704477036822,
2197
+ "grad_norm": 0.02857852540910244,
2198
+ "learning_rate": 1.9527449163829084e-05,
2199
+ "loss": 0.9684,
2200
+ "step": 15650
2201
+ },
2202
+ {
2203
+ "epoch": 1.512487055366905,
2204
+ "grad_norm": 0.027361080050468445,
2205
+ "learning_rate": 1.952104390516008e-05,
2206
+ "loss": 0.9711,
2207
+ "step": 15700
2208
+ },
2209
+ {
2210
+ "epoch": 1.5173036630301278,
2211
+ "grad_norm": 0.03336118161678314,
2212
+ "learning_rate": 1.9514596592583718e-05,
2213
+ "loss": 0.9661,
2214
+ "step": 15750
2215
+ },
2216
+ {
2217
+ "epoch": 1.5221202706933505,
2218
+ "grad_norm": 0.033473215997219086,
2219
+ "learning_rate": 1.950810725457741e-05,
2220
+ "loss": 0.9759,
2221
+ "step": 15800
2222
+ },
2223
+ {
2224
+ "epoch": 1.5269368783565733,
2225
+ "grad_norm": 0.030235016718506813,
2226
+ "learning_rate": 1.9501575919804192e-05,
2227
+ "loss": 0.9744,
2228
+ "step": 15850
2229
+ },
2230
+ {
2231
+ "epoch": 1.531753486019796,
2232
+ "grad_norm": 0.035084497183561325,
2233
+ "learning_rate": 1.9495002617112594e-05,
2234
+ "loss": 0.9684,
2235
+ "step": 15900
2236
+ },
2237
+ {
2238
+ "epoch": 1.536570093683019,
2239
+ "grad_norm": 0.036444876343011856,
2240
+ "learning_rate": 1.9488387375536525e-05,
2241
+ "loss": 0.9733,
2242
+ "step": 15950
2243
+ },
2244
+ {
2245
+ "epoch": 1.541386701346242,
2246
+ "grad_norm": 0.03955389931797981,
2247
+ "learning_rate": 1.9481730224295123e-05,
2248
+ "loss": 0.9702,
2249
+ "step": 16000
2250
+ },
2251
+ {
2252
+ "epoch": 1.5462033090094647,
2253
+ "grad_norm": 0.03296295925974846,
2254
+ "learning_rate": 1.9475031192792648e-05,
2255
+ "loss": 0.9719,
2256
+ "step": 16050
2257
+ },
2258
+ {
2259
+ "epoch": 1.5510199166726875,
2260
+ "grad_norm": 0.0423264279961586,
2261
+ "learning_rate": 1.946829031061834e-05,
2262
+ "loss": 0.9738,
2263
+ "step": 16100
2264
+ },
2265
+ {
2266
+ "epoch": 1.5558365243359102,
2267
+ "grad_norm": 0.028733521699905396,
2268
+ "learning_rate": 1.9461507607546286e-05,
2269
+ "loss": 0.9709,
2270
+ "step": 16150
2271
+ },
2272
+ {
2273
+ "epoch": 1.560653131999133,
2274
+ "grad_norm": 0.024974407628178596,
2275
+ "learning_rate": 1.9454683113535306e-05,
2276
+ "loss": 0.9722,
2277
+ "step": 16200
2278
+ },
2279
+ {
2280
+ "epoch": 1.5654697396623558,
2281
+ "grad_norm": 0.035207174718379974,
2282
+ "learning_rate": 1.9447816858728793e-05,
2283
+ "loss": 0.9691,
2284
+ "step": 16250
2285
+ },
2286
+ {
2287
+ "epoch": 1.5702863473255786,
2288
+ "grad_norm": 0.029747210443019867,
2289
+ "learning_rate": 1.9441047441921626e-05,
2290
+ "loss": 0.9738,
2291
+ "step": 16300
2292
+ },
2293
+ {
2294
+ "epoch": 1.5751029549888014,
2295
+ "grad_norm": 0.024529732763767242,
2296
+ "learning_rate": 1.9434098590390843e-05,
2297
+ "loss": 0.975,
2298
+ "step": 16350
2299
+ },
2300
+ {
2301
+ "epoch": 1.5799195626520242,
2302
+ "grad_norm": 0.03319941461086273,
2303
+ "learning_rate": 1.9427108068985197e-05,
2304
+ "loss": 0.9789,
2305
+ "step": 16400
2306
+ },
2307
+ {
2308
+ "epoch": 1.584736170315247,
2309
+ "grad_norm": 0.03864700347185135,
2310
+ "learning_rate": 1.9420075908581416e-05,
2311
+ "loss": 0.9652,
2312
+ "step": 16450
2313
+ },
2314
+ {
2315
+ "epoch": 1.5895527779784697,
2316
+ "grad_norm": 0.03296511247754097,
2317
+ "learning_rate": 1.9413002140240153e-05,
2318
+ "loss": 0.9644,
2319
+ "step": 16500
2320
+ },
2321
+ {
2322
+ "epoch": 1.5943693856416925,
2323
+ "grad_norm": 0.031712450087070465,
2324
+ "learning_rate": 1.940588679520584e-05,
2325
+ "loss": 0.969,
2326
+ "step": 16550
2327
+ },
2328
+ {
2329
+ "epoch": 1.5991859933049155,
2330
+ "grad_norm": 0.028867822140455246,
2331
+ "learning_rate": 1.939872990490655e-05,
2332
+ "loss": 0.9658,
2333
+ "step": 16600
2334
+ },
2335
+ {
2336
+ "epoch": 1.6040026009681383,
2337
+ "grad_norm": 0.03712575510144234,
2338
+ "learning_rate": 1.9391531500953856e-05,
2339
+ "loss": 0.9723,
2340
+ "step": 16650
2341
+ },
2342
+ {
2343
+ "epoch": 1.608819208631361,
2344
+ "grad_norm": 0.03416059911251068,
2345
+ "learning_rate": 1.9384291615142705e-05,
2346
+ "loss": 0.9689,
2347
+ "step": 16700
2348
+ },
2349
+ {
2350
+ "epoch": 1.6136358162945839,
2351
+ "grad_norm": 0.028371134772896767,
2352
+ "learning_rate": 1.9377010279451248e-05,
2353
+ "loss": 0.9641,
2354
+ "step": 16750
2355
+ },
2356
+ {
2357
+ "epoch": 1.6184524239578066,
2358
+ "grad_norm": 0.02121553383767605,
2359
+ "learning_rate": 1.9369687526040738e-05,
2360
+ "loss": 0.973,
2361
+ "step": 16800
2362
+ },
2363
+ {
2364
+ "epoch": 1.6232690316210294,
2365
+ "grad_norm": 0.035169586539268494,
2366
+ "learning_rate": 1.9362323387255358e-05,
2367
+ "loss": 0.9699,
2368
+ "step": 16850
2369
+ },
2370
+ {
2371
+ "epoch": 1.6280856392842522,
2372
+ "grad_norm": 0.04021048918366432,
2373
+ "learning_rate": 1.9354917895622084e-05,
2374
+ "loss": 0.9658,
2375
+ "step": 16900
2376
+ },
2377
+ {
2378
+ "epoch": 1.632902246947475,
2379
+ "grad_norm": 0.030784184113144875,
2380
+ "learning_rate": 1.934747108385055e-05,
2381
+ "loss": 0.9712,
2382
+ "step": 16950
2383
+ },
2384
+ {
2385
+ "epoch": 1.6377188546106978,
2386
+ "grad_norm": 0.028953375294804573,
2387
+ "learning_rate": 1.9339982984832904e-05,
2388
+ "loss": 0.9745,
2389
+ "step": 17000
2390
+ },
2391
+ {
2392
+ "epoch": 1.6425354622739206,
2393
+ "grad_norm": 0.02870544232428074,
2394
+ "learning_rate": 1.933245363164365e-05,
2395
+ "loss": 0.9662,
2396
+ "step": 17050
2397
+ },
2398
+ {
2399
+ "epoch": 1.6473520699371433,
2400
+ "grad_norm": 0.03799861669540405,
2401
+ "learning_rate": 1.9324883057539506e-05,
2402
+ "loss": 0.9625,
2403
+ "step": 17100
2404
+ },
2405
+ {
2406
+ "epoch": 1.6521686776003661,
2407
+ "grad_norm": 0.03466878831386566,
2408
+ "learning_rate": 1.931727129595927e-05,
2409
+ "loss": 0.9705,
2410
+ "step": 17150
2411
+ },
2412
+ {
2413
+ "epoch": 1.656985285263589,
2414
+ "grad_norm": 0.026363851502537727,
2415
+ "learning_rate": 1.930961838052366e-05,
2416
+ "loss": 0.9743,
2417
+ "step": 17200
2418
+ },
2419
+ {
2420
+ "epoch": 1.6618018929268117,
2421
+ "grad_norm": 0.03705060854554176,
2422
+ "learning_rate": 1.9301924345035162e-05,
2423
+ "loss": 0.9737,
2424
+ "step": 17250
2425
+ },
2426
+ {
2427
+ "epoch": 1.6666185005900345,
2428
+ "grad_norm": 0.03183252364397049,
2429
+ "learning_rate": 1.9294189223477895e-05,
2430
+ "loss": 0.9645,
2431
+ "step": 17300
2432
+ },
2433
+ {
2434
+ "epoch": 1.6714351082532573,
2435
+ "grad_norm": 0.030151918530464172,
2436
+ "learning_rate": 1.9286413050017446e-05,
2437
+ "loss": 0.9818,
2438
+ "step": 17350
2439
+ },
2440
+ {
2441
+ "epoch": 1.67625171591648,
2442
+ "grad_norm": 0.03267509490251541,
2443
+ "learning_rate": 1.9278595859000732e-05,
2444
+ "loss": 0.9684,
2445
+ "step": 17400
2446
+ },
2447
+ {
2448
+ "epoch": 1.6810683235797028,
2449
+ "grad_norm": 0.04097314551472664,
2450
+ "learning_rate": 1.9270737684955842e-05,
2451
+ "loss": 0.9747,
2452
+ "step": 17450
2453
+ },
2454
+ {
2455
+ "epoch": 1.6858849312429256,
2456
+ "grad_norm": 0.03502653166651726,
2457
+ "learning_rate": 1.9262838562591876e-05,
2458
+ "loss": 0.9684,
2459
+ "step": 17500
2460
+ },
2461
+ {
2462
+ "epoch": 1.6907015389061484,
2463
+ "grad_norm": 0.03247523680329323,
2464
+ "learning_rate": 1.9254898526798808e-05,
2465
+ "loss": 0.9849,
2466
+ "step": 17550
2467
+ },
2468
+ {
2469
+ "epoch": 1.6955181465693712,
2470
+ "grad_norm": 0.04047703742980957,
2471
+ "learning_rate": 1.9246917612647323e-05,
2472
+ "loss": 0.9644,
2473
+ "step": 17600
2474
+ },
2475
+ {
2476
+ "epoch": 1.700334754232594,
2477
+ "grad_norm": 0.029567096382379532,
2478
+ "learning_rate": 1.923889585538867e-05,
2479
+ "loss": 0.969,
2480
+ "step": 17650
2481
+ },
2482
+ {
2483
+ "epoch": 1.7051513618958167,
2484
+ "grad_norm": 0.027141790837049484,
2485
+ "learning_rate": 1.923083329045448e-05,
2486
+ "loss": 0.9689,
2487
+ "step": 17700
2488
+ },
2489
+ {
2490
+ "epoch": 1.7099679695590395,
2491
+ "grad_norm": 0.03246340900659561,
2492
+ "learning_rate": 1.9222729953456654e-05,
2493
+ "loss": 0.9736,
2494
+ "step": 17750
2495
+ },
2496
+ {
2497
+ "epoch": 1.7147845772222623,
2498
+ "grad_norm": 0.03585787117481232,
2499
+ "learning_rate": 1.921458588018716e-05,
2500
+ "loss": 0.9723,
2501
+ "step": 17800
2502
+ },
2503
+ {
2504
+ "epoch": 1.719601184885485,
2505
+ "grad_norm": 0.032114990055561066,
2506
+ "learning_rate": 1.920640110661791e-05,
2507
+ "loss": 0.967,
2508
+ "step": 17850
2509
+ },
2510
+ {
2511
+ "epoch": 1.7244177925487079,
2512
+ "grad_norm": 0.029773587360978127,
2513
+ "learning_rate": 1.9198175668900584e-05,
2514
+ "loss": 0.9743,
2515
+ "step": 17900
2516
+ },
2517
+ {
2518
+ "epoch": 1.7292344002119306,
2519
+ "grad_norm": 0.04874695837497711,
2520
+ "learning_rate": 1.9189909603366463e-05,
2521
+ "loss": 0.9672,
2522
+ "step": 17950
2523
+ },
2524
+ {
2525
+ "epoch": 1.7340510078751534,
2526
+ "grad_norm": 0.03545283526182175,
2527
+ "learning_rate": 1.9181769477220878e-05,
2528
+ "loss": 0.9682,
2529
+ "step": 18000
2530
+ },
2531
+ {
2532
+ "epoch": 1.7388676155383762,
2533
+ "grad_norm": 0.03573315218091011,
2534
+ "learning_rate": 1.9173423076496282e-05,
2535
+ "loss": 0.9683,
2536
+ "step": 18050
2537
+ },
2538
+ {
2539
+ "epoch": 1.743684223201599,
2540
+ "grad_norm": 0.03943735361099243,
2541
+ "learning_rate": 1.9165036157285686e-05,
2542
+ "loss": 0.9744,
2543
+ "step": 18100
2544
+ },
2545
+ {
2546
+ "epoch": 1.7485008308648218,
2547
+ "grad_norm": 0.036090608686208725,
2548
+ "learning_rate": 1.9156608756633628e-05,
2549
+ "loss": 0.9676,
2550
+ "step": 18150
2551
+ },
2552
+ {
2553
+ "epoch": 1.7533174385280446,
2554
+ "grad_norm": 0.02353888936340809,
2555
+ "learning_rate": 1.9148140911763456e-05,
2556
+ "loss": 0.9681,
2557
+ "step": 18200
2558
+ },
2559
+ {
2560
+ "epoch": 1.7581340461912673,
2561
+ "grad_norm": 0.03864511474967003,
2562
+ "learning_rate": 1.913963266007716e-05,
2563
+ "loss": 0.9727,
2564
+ "step": 18250
2565
+ },
2566
+ {
2567
+ "epoch": 1.7629506538544901,
2568
+ "grad_norm": 0.038263238966464996,
2569
+ "learning_rate": 1.91310840391552e-05,
2570
+ "loss": 0.9667,
2571
+ "step": 18300
2572
+ },
2573
+ {
2574
+ "epoch": 1.7677672615177131,
2575
+ "grad_norm": 0.03713950514793396,
2576
+ "learning_rate": 1.912249508675635e-05,
2577
+ "loss": 0.9718,
2578
+ "step": 18350
2579
+ },
2580
+ {
2581
+ "epoch": 1.772583869180936,
2582
+ "grad_norm": 0.03242368623614311,
2583
+ "learning_rate": 1.9113865840817515e-05,
2584
+ "loss": 0.9719,
2585
+ "step": 18400
2586
+ },
2587
+ {
2588
+ "epoch": 1.7774004768441587,
2589
+ "grad_norm": 0.027840277180075645,
2590
+ "learning_rate": 1.9105196339453587e-05,
2591
+ "loss": 0.9692,
2592
+ "step": 18450
2593
+ },
2594
+ {
2595
+ "epoch": 1.7822170845073815,
2596
+ "grad_norm": 0.03802412003278732,
2597
+ "learning_rate": 1.9096486620957256e-05,
2598
+ "loss": 0.9659,
2599
+ "step": 18500
2600
+ },
2601
+ {
2602
+ "epoch": 1.7870336921706043,
2603
+ "grad_norm": 0.02906882017850876,
2604
+ "learning_rate": 1.9087736723798858e-05,
2605
+ "loss": 0.975,
2606
+ "step": 18550
2607
+ },
2608
+ {
2609
+ "epoch": 1.791850299833827,
2610
+ "grad_norm": 0.044180627912282944,
2611
+ "learning_rate": 1.907894668662618e-05,
2612
+ "loss": 0.9642,
2613
+ "step": 18600
2614
+ },
2615
+ {
2616
+ "epoch": 1.7966669074970498,
2617
+ "grad_norm": 0.03528657183051109,
2618
+ "learning_rate": 1.9070116548264324e-05,
2619
+ "loss": 0.9611,
2620
+ "step": 18650
2621
+ },
2622
+ {
2623
+ "epoch": 1.8014835151602726,
2624
+ "grad_norm": 0.0406530499458313,
2625
+ "learning_rate": 1.9061246347715497e-05,
2626
+ "loss": 0.9736,
2627
+ "step": 18700
2628
+ },
2629
+ {
2630
+ "epoch": 1.8063001228234954,
2631
+ "grad_norm": 0.051499903202056885,
2632
+ "learning_rate": 1.9052336124158878e-05,
2633
+ "loss": 0.9684,
2634
+ "step": 18750
2635
+ },
2636
+ {
2637
+ "epoch": 1.8111167304867182,
2638
+ "grad_norm": 0.04132218286395073,
2639
+ "learning_rate": 1.9043385916950408e-05,
2640
+ "loss": 0.9712,
2641
+ "step": 18800
2642
+ },
2643
+ {
2644
+ "epoch": 1.815933338149941,
2645
+ "grad_norm": 0.04125228524208069,
2646
+ "learning_rate": 1.9034395765622644e-05,
2647
+ "loss": 0.9702,
2648
+ "step": 18850
2649
+ },
2650
+ {
2651
+ "epoch": 1.8207499458131637,
2652
+ "grad_norm": 0.039924681186676025,
2653
+ "learning_rate": 1.902536570988457e-05,
2654
+ "loss": 0.967,
2655
+ "step": 18900
2656
+ },
2657
+ {
2658
+ "epoch": 1.8255665534763867,
2659
+ "grad_norm": 0.03247521445155144,
2660
+ "learning_rate": 1.901629578962143e-05,
2661
+ "loss": 0.9733,
2662
+ "step": 18950
2663
+ },
2664
+ {
2665
+ "epoch": 1.8303831611396095,
2666
+ "grad_norm": 0.0357697531580925,
2667
+ "learning_rate": 1.900718604489454e-05,
2668
+ "loss": 0.973,
2669
+ "step": 19000
2670
+ },
2671
+ {
2672
+ "epoch": 1.8351997688028323,
2673
+ "grad_norm": 0.038057841360569,
2674
+ "learning_rate": 1.8998036515941126e-05,
2675
+ "loss": 0.968,
2676
+ "step": 19050
2677
+ },
2678
+ {
2679
+ "epoch": 1.840016376466055,
2680
+ "grad_norm": 0.04882153868675232,
2681
+ "learning_rate": 1.8988847243174132e-05,
2682
+ "loss": 0.9756,
2683
+ "step": 19100
2684
+ },
2685
+ {
2686
+ "epoch": 1.8448329841292779,
2687
+ "grad_norm": 0.04649386182427406,
2688
+ "learning_rate": 1.8979618267182055e-05,
2689
+ "loss": 0.9686,
2690
+ "step": 19150
2691
+ },
2692
+ {
2693
+ "epoch": 1.8496495917925007,
2694
+ "grad_norm": 0.03845987841486931,
2695
+ "learning_rate": 1.897034962872875e-05,
2696
+ "loss": 0.9759,
2697
+ "step": 19200
2698
+ },
2699
+ {
2700
+ "epoch": 1.8544661994557234,
2701
+ "grad_norm": 0.028005842119455338,
2702
+ "learning_rate": 1.8961041368753265e-05,
2703
+ "loss": 0.972,
2704
+ "step": 19250
2705
+ },
2706
+ {
2707
+ "epoch": 1.8592828071189462,
2708
+ "grad_norm": 0.04040095955133438,
2709
+ "learning_rate": 1.8951693528369657e-05,
2710
+ "loss": 0.9795,
2711
+ "step": 19300
2712
+ },
2713
+ {
2714
+ "epoch": 1.864099414782169,
2715
+ "grad_norm": 0.0448676161468029,
2716
+ "learning_rate": 1.8942306148866802e-05,
2717
+ "loss": 0.9744,
2718
+ "step": 19350
2719
+ },
2720
+ {
2721
+ "epoch": 1.8689160224453918,
2722
+ "grad_norm": 0.033535186201334,
2723
+ "learning_rate": 1.8932879271708216e-05,
2724
+ "loss": 0.9687,
2725
+ "step": 19400
2726
+ },
2727
+ {
2728
+ "epoch": 1.8737326301086146,
2729
+ "grad_norm": 0.04124687612056732,
2730
+ "learning_rate": 1.8923412938531877e-05,
2731
+ "loss": 0.975,
2732
+ "step": 19450
2733
+ },
2734
+ {
2735
+ "epoch": 1.8785492377718374,
2736
+ "grad_norm": 0.03508332371711731,
2737
+ "learning_rate": 1.8913907191150045e-05,
2738
+ "loss": 0.9701,
2739
+ "step": 19500
2740
+ },
2741
+ {
2742
+ "epoch": 1.8833658454350601,
2743
+ "grad_norm": 0.030656304210424423,
2744
+ "learning_rate": 1.8904362071549057e-05,
2745
+ "loss": 0.9719,
2746
+ "step": 19550
2747
+ },
2748
+ {
2749
+ "epoch": 1.888182453098283,
2750
+ "grad_norm": 0.04930535703897476,
2751
+ "learning_rate": 1.8894777621889162e-05,
2752
+ "loss": 0.9682,
2753
+ "step": 19600
2754
+ },
2755
+ {
2756
+ "epoch": 1.8929990607615057,
2757
+ "grad_norm": 0.047555629163980484,
2758
+ "learning_rate": 1.8885153884504328e-05,
2759
+ "loss": 0.9713,
2760
+ "step": 19650
2761
+ },
2762
+ {
2763
+ "epoch": 1.8978156684247285,
2764
+ "grad_norm": 0.037693556398153305,
2765
+ "learning_rate": 1.8875490901902056e-05,
2766
+ "loss": 0.9657,
2767
+ "step": 19700
2768
+ },
2769
+ {
2770
+ "epoch": 1.9026322760879513,
2771
+ "grad_norm": 0.0341501459479332,
2772
+ "learning_rate": 1.8865788716763185e-05,
2773
+ "loss": 0.9659,
2774
+ "step": 19750
2775
+ },
2776
+ {
2777
+ "epoch": 1.907448883751174,
2778
+ "grad_norm": 0.03856112062931061,
2779
+ "learning_rate": 1.8856047371941714e-05,
2780
+ "loss": 0.9741,
2781
+ "step": 19800
2782
+ },
2783
+ {
2784
+ "epoch": 1.9122654914143968,
2785
+ "grad_norm": 0.03828900679945946,
2786
+ "learning_rate": 1.8846266910464605e-05,
2787
+ "loss": 0.9684,
2788
+ "step": 19850
2789
+ },
2790
+ {
2791
+ "epoch": 1.9170820990776196,
2792
+ "grad_norm": 0.03888611122965813,
2793
+ "learning_rate": 1.8836447375531603e-05,
2794
+ "loss": 0.9655,
2795
+ "step": 19900
2796
+ },
2797
+ {
2798
+ "epoch": 1.9218987067408424,
2799
+ "grad_norm": 0.03091917186975479,
2800
+ "learning_rate": 1.882658881051503e-05,
2801
+ "loss": 0.972,
2802
+ "step": 19950
2803
+ },
2804
+ {
2805
+ "epoch": 1.9267153144040652,
2806
+ "grad_norm": 0.02642899379134178,
2807
+ "learning_rate": 1.8816691258959603e-05,
2808
+ "loss": 0.9623,
2809
+ "step": 20000
2810
+ },
2811
+ {
2812
+ "epoch": 1.931531922067288,
2813
+ "grad_norm": 0.05221928656101227,
2814
+ "learning_rate": 1.8806754764582244e-05,
2815
+ "loss": 0.9632,
2816
+ "step": 20050
2817
+ },
2818
+ {
2819
+ "epoch": 1.9363485297305107,
2820
+ "grad_norm": 0.029367584735155106,
2821
+ "learning_rate": 1.8796779371271883e-05,
2822
+ "loss": 0.9721,
2823
+ "step": 20100
2824
+ },
2825
+ {
2826
+ "epoch": 1.9411651373937335,
2827
+ "grad_norm": 0.0352255254983902,
2828
+ "learning_rate": 1.878676512308926e-05,
2829
+ "loss": 0.9727,
2830
+ "step": 20150
2831
+ },
2832
+ {
2833
+ "epoch": 1.9459817450569563,
2834
+ "grad_norm": 0.035805653780698776,
2835
+ "learning_rate": 1.877671206426674e-05,
2836
+ "loss": 0.9723,
2837
+ "step": 20200
2838
+ },
2839
+ {
2840
+ "epoch": 1.950798352720179,
2841
+ "grad_norm": 0.030969569459557533,
2842
+ "learning_rate": 1.876662023920811e-05,
2843
+ "loss": 0.9723,
2844
+ "step": 20250
2845
+ },
2846
+ {
2847
+ "epoch": 1.9556149603834019,
2848
+ "grad_norm": 0.03802033141255379,
2849
+ "learning_rate": 1.875648969248838e-05,
2850
+ "loss": 0.9739,
2851
+ "step": 20300
2852
+ },
2853
+ {
2854
+ "epoch": 1.9604315680466247,
2855
+ "grad_norm": 0.03381386026740074,
2856
+ "learning_rate": 1.8746320468853602e-05,
2857
+ "loss": 0.9754,
2858
+ "step": 20350
2859
+ },
2860
+ {
2861
+ "epoch": 1.9652481757098474,
2862
+ "grad_norm": 0.050473056733608246,
2863
+ "learning_rate": 1.873631714863555e-05,
2864
+ "loss": 0.9779,
2865
+ "step": 20400
2866
+ },
2867
+ {
2868
+ "epoch": 1.9700647833730702,
2869
+ "grad_norm": 0.028497766703367233,
2870
+ "learning_rate": 1.8726071477387204e-05,
2871
+ "loss": 0.968,
2872
+ "step": 20450
2873
+ },
2874
+ {
2875
+ "epoch": 1.974881391036293,
2876
+ "grad_norm": 0.03649654984474182,
2877
+ "learning_rate": 1.8715787263579322e-05,
2878
+ "loss": 0.9709,
2879
+ "step": 20500
2880
+ },
2881
+ {
2882
+ "epoch": 1.9796979986995158,
2883
+ "grad_norm": 0.03871350362896919,
2884
+ "learning_rate": 1.87054645526367e-05,
2885
+ "loss": 0.9688,
2886
+ "step": 20550
2887
+ },
2888
+ {
2889
+ "epoch": 1.9845146063627386,
2890
+ "grad_norm": 0.04097853973507881,
2891
+ "learning_rate": 1.8695103390154155e-05,
2892
+ "loss": 0.9715,
2893
+ "step": 20600
2894
+ },
2895
+ {
2896
+ "epoch": 1.9893312140259614,
2897
+ "grad_norm": 0.04054868221282959,
2898
+ "learning_rate": 1.8684703821896356e-05,
2899
+ "loss": 0.9669,
2900
+ "step": 20650
2901
+ },
2902
+ {
2903
+ "epoch": 1.9941478216891841,
2904
+ "grad_norm": 0.03923407196998596,
2905
+ "learning_rate": 1.8674265893797595e-05,
2906
+ "loss": 0.9654,
2907
+ "step": 20700
2908
+ },
2909
+ {
2910
+ "epoch": 1.9989644293524071,
2911
+ "grad_norm": 0.03828323259949684,
2912
+ "learning_rate": 1.866378965196161e-05,
2913
+ "loss": 0.9691,
2914
+ "step": 20750
2915
+ }
2916
+ ],
2917
+ "logging_steps": 50,
2918
+ "max_steps": 20760,
2919
+ "num_input_tokens_seen": 0,
2920
+ "num_train_epochs": 2,
2921
+ "save_steps": 500,
2922
+ "stateful_callbacks": {
2923
+ "TrainerControl": {
2924
+ "args": {
2925
+ "should_epoch_stop": false,
2926
+ "should_evaluate": false,
2927
+ "should_log": false,
2928
+ "should_save": true,
2929
+ "should_training_stop": true
2930
+ },
2931
+ "attributes": {}
2932
+ }
2933
+ },
2934
+ "total_flos": 5.032348559679028e+18,
2935
+ "train_batch_size": 2,
2936
+ "trial_name": null,
2937
+ "trial_params": null
2938
+ }
checkpoint-20760/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf4af21635e2a3d5153e5b199fe36a29ba0574d6cbf377a6c2c41dc1a46333f
3
+ size 5304
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./result/tabx",
3
+ "aligner_config": {
4
+ "cls": "MlpProjector",
5
+ "model_type": "aligner",
6
+ "params": {
7
+ "depth": 2,
8
+ "input_dim": 1024,
9
+ "n_embed": 4096,
10
+ "projector_type": "mlp_gelu"
11
+ }
12
+ },
13
+ "architectures": [
14
+ "EnhancedMultiModalModel"
15
+ ],
16
+ "gen_aligner_config": {
17
+ "cls": "MlpProjector",
18
+ "model_type": "gen_aligner",
19
+ "params": {
20
+ "depth": 2,
21
+ "input_dim": 8,
22
+ "n_embed": 4096,
23
+ "projector_type": "mlp_gelu"
24
+ }
25
+ },
26
+ "gen_head_config": {
27
+ "cls": "vision_head",
28
+ "model_type": "gen_head",
29
+ "params": {
30
+ "image_token_embed": 4096,
31
+ "image_token_size": 16384,
32
+ "n_embed": 4096
33
+ }
34
+ },
35
+ "gen_vision_config": {
36
+ "cls": "VQ-16",
37
+ "model_type": "gen_vision",
38
+ "params": {
39
+ "image_token_size": 16384,
40
+ "n_embed": 8
41
+ }
42
+ },
43
+ "language_config": {
44
+ "_attn_implementation_autoset": true,
45
+ "max_position_embeddings": 16384,
46
+ "model_type": "llama",
47
+ "num_hidden_layers": 30,
48
+ "torch_dtype": "bfloat16",
49
+ "vocab_size": 102400
50
+ },
51
+ "model_type": "multi_modality",
52
+ "torch_dtype": "float16",
53
+ "transformers_version": "4.48.1",
54
+ "vision_config": {
55
+ "cls": "CLIPVisionTower",
56
+ "model_type": "vision",
57
+ "params": {
58
+ "image_size": 384,
59
+ "model_name": "siglip_large_patch16_384",
60
+ "select_feature": "same",
61
+ "select_layer": -1
62
+ }
63
+ }
64
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e08cb25420cd273c585eb5074179228c7875e0c92e33d51115a84ece5ee20f8
3
+ size 4916850806
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0d7d7a27c4b41cb20b12e5a0c123eeb3c7c1ca5cd815a61b7f3a99d383939a1
3
+ size 4947392384
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf84efbe21b17d0d5a2e4c85b50b4e03471f67639103cb0ac9c43aa5d77f9782
3
+ size 4976742512
model.safetensors.index.json ADDED
@@ -0,0 +1,943 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14840868118
4
+ },
5
+ "weight_map": {
6
+ "aligner.layers.0.bias": "model-00001-of-00003.safetensors",
7
+ "aligner.layers.0.weight": "model-00001-of-00003.safetensors",
8
+ "aligner.layers.2.bias": "model-00001-of-00003.safetensors",
9
+ "aligner.layers.2.weight": "model-00001-of-00003.safetensors",
10
+ "gen_aligner.layers.0.bias": "model-00001-of-00003.safetensors",
11
+ "gen_aligner.layers.0.weight": "model-00001-of-00003.safetensors",
12
+ "gen_aligner.layers.2.bias": "model-00001-of-00003.safetensors",
13
+ "gen_aligner.layers.2.weight": "model-00001-of-00003.safetensors",
14
+ "gen_embed.weight": "model-00001-of-00003.safetensors",
15
+ "gen_head.output_mlp_projector.bias": "model-00001-of-00003.safetensors",
16
+ "gen_head.output_mlp_projector.weight": "model-00001-of-00003.safetensors",
17
+ "gen_head.vision_head.bias": "model-00001-of-00003.safetensors",
18
+ "gen_head.vision_head.weight": "model-00001-of-00003.safetensors",
19
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.k.bias": "model-00001-of-00003.safetensors",
20
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.k.weight": "model-00001-of-00003.safetensors",
21
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.norm.bias": "model-00001-of-00003.safetensors",
22
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.norm.weight": "model-00001-of-00003.safetensors",
23
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.proj_out.bias": "model-00001-of-00003.safetensors",
24
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.proj_out.weight": "model-00001-of-00003.safetensors",
25
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.q.bias": "model-00001-of-00003.safetensors",
26
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.q.weight": "model-00001-of-00003.safetensors",
27
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.v.bias": "model-00001-of-00003.safetensors",
28
+ "gen_vision_model.decoder.conv_blocks.0.attn.0.v.weight": "model-00001-of-00003.safetensors",
29
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.k.bias": "model-00001-of-00003.safetensors",
30
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.k.weight": "model-00001-of-00003.safetensors",
31
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.norm.bias": "model-00001-of-00003.safetensors",
32
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.norm.weight": "model-00001-of-00003.safetensors",
33
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.proj_out.bias": "model-00001-of-00003.safetensors",
34
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.proj_out.weight": "model-00001-of-00003.safetensors",
35
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.q.bias": "model-00001-of-00003.safetensors",
36
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.q.weight": "model-00001-of-00003.safetensors",
37
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.v.bias": "model-00001-of-00003.safetensors",
38
+ "gen_vision_model.decoder.conv_blocks.0.attn.1.v.weight": "model-00001-of-00003.safetensors",
39
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.k.bias": "model-00001-of-00003.safetensors",
40
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.k.weight": "model-00001-of-00003.safetensors",
41
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.norm.bias": "model-00001-of-00003.safetensors",
42
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.norm.weight": "model-00001-of-00003.safetensors",
43
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.proj_out.bias": "model-00001-of-00003.safetensors",
44
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.proj_out.weight": "model-00001-of-00003.safetensors",
45
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.q.bias": "model-00001-of-00003.safetensors",
46
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.q.weight": "model-00001-of-00003.safetensors",
47
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.v.bias": "model-00001-of-00003.safetensors",
48
+ "gen_vision_model.decoder.conv_blocks.0.attn.2.v.weight": "model-00001-of-00003.safetensors",
49
+ "gen_vision_model.decoder.conv_blocks.0.res.0.conv1.bias": "model-00001-of-00003.safetensors",
50
+ "gen_vision_model.decoder.conv_blocks.0.res.0.conv1.weight": "model-00001-of-00003.safetensors",
51
+ "gen_vision_model.decoder.conv_blocks.0.res.0.conv2.bias": "model-00001-of-00003.safetensors",
52
+ "gen_vision_model.decoder.conv_blocks.0.res.0.conv2.weight": "model-00001-of-00003.safetensors",
53
+ "gen_vision_model.decoder.conv_blocks.0.res.0.norm1.bias": "model-00001-of-00003.safetensors",
54
+ "gen_vision_model.decoder.conv_blocks.0.res.0.norm1.weight": "model-00001-of-00003.safetensors",
55
+ "gen_vision_model.decoder.conv_blocks.0.res.0.norm2.bias": "model-00001-of-00003.safetensors",
56
+ "gen_vision_model.decoder.conv_blocks.0.res.0.norm2.weight": "model-00001-of-00003.safetensors",
57
+ "gen_vision_model.decoder.conv_blocks.0.res.1.conv1.bias": "model-00001-of-00003.safetensors",
58
+ "gen_vision_model.decoder.conv_blocks.0.res.1.conv1.weight": "model-00001-of-00003.safetensors",
59
+ "gen_vision_model.decoder.conv_blocks.0.res.1.conv2.bias": "model-00001-of-00003.safetensors",
60
+ "gen_vision_model.decoder.conv_blocks.0.res.1.conv2.weight": "model-00001-of-00003.safetensors",
61
+ "gen_vision_model.decoder.conv_blocks.0.res.1.norm1.bias": "model-00001-of-00003.safetensors",
62
+ "gen_vision_model.decoder.conv_blocks.0.res.1.norm1.weight": "model-00001-of-00003.safetensors",
63
+ "gen_vision_model.decoder.conv_blocks.0.res.1.norm2.bias": "model-00001-of-00003.safetensors",
64
+ "gen_vision_model.decoder.conv_blocks.0.res.1.norm2.weight": "model-00001-of-00003.safetensors",
65
+ "gen_vision_model.decoder.conv_blocks.0.res.2.conv1.bias": "model-00001-of-00003.safetensors",
66
+ "gen_vision_model.decoder.conv_blocks.0.res.2.conv1.weight": "model-00001-of-00003.safetensors",
67
+ "gen_vision_model.decoder.conv_blocks.0.res.2.conv2.bias": "model-00001-of-00003.safetensors",
68
+ "gen_vision_model.decoder.conv_blocks.0.res.2.conv2.weight": "model-00001-of-00003.safetensors",
69
+ "gen_vision_model.decoder.conv_blocks.0.res.2.norm1.bias": "model-00001-of-00003.safetensors",
70
+ "gen_vision_model.decoder.conv_blocks.0.res.2.norm1.weight": "model-00001-of-00003.safetensors",
71
+ "gen_vision_model.decoder.conv_blocks.0.res.2.norm2.bias": "model-00001-of-00003.safetensors",
72
+ "gen_vision_model.decoder.conv_blocks.0.res.2.norm2.weight": "model-00001-of-00003.safetensors",
73
+ "gen_vision_model.decoder.conv_blocks.0.upsample.conv.bias": "model-00001-of-00003.safetensors",
74
+ "gen_vision_model.decoder.conv_blocks.0.upsample.conv.weight": "model-00001-of-00003.safetensors",
75
+ "gen_vision_model.decoder.conv_blocks.1.res.0.conv1.bias": "model-00001-of-00003.safetensors",
76
+ "gen_vision_model.decoder.conv_blocks.1.res.0.conv1.weight": "model-00001-of-00003.safetensors",
77
+ "gen_vision_model.decoder.conv_blocks.1.res.0.conv2.bias": "model-00001-of-00003.safetensors",
78
+ "gen_vision_model.decoder.conv_blocks.1.res.0.conv2.weight": "model-00001-of-00003.safetensors",
79
+ "gen_vision_model.decoder.conv_blocks.1.res.0.nin_shortcut.bias": "model-00001-of-00003.safetensors",
80
+ "gen_vision_model.decoder.conv_blocks.1.res.0.nin_shortcut.weight": "model-00001-of-00003.safetensors",
81
+ "gen_vision_model.decoder.conv_blocks.1.res.0.norm1.bias": "model-00001-of-00003.safetensors",
82
+ "gen_vision_model.decoder.conv_blocks.1.res.0.norm1.weight": "model-00001-of-00003.safetensors",
83
+ "gen_vision_model.decoder.conv_blocks.1.res.0.norm2.bias": "model-00001-of-00003.safetensors",
84
+ "gen_vision_model.decoder.conv_blocks.1.res.0.norm2.weight": "model-00001-of-00003.safetensors",
85
+ "gen_vision_model.decoder.conv_blocks.1.res.1.conv1.bias": "model-00001-of-00003.safetensors",
86
+ "gen_vision_model.decoder.conv_blocks.1.res.1.conv1.weight": "model-00001-of-00003.safetensors",
87
+ "gen_vision_model.decoder.conv_blocks.1.res.1.conv2.bias": "model-00001-of-00003.safetensors",
88
+ "gen_vision_model.decoder.conv_blocks.1.res.1.conv2.weight": "model-00001-of-00003.safetensors",
89
+ "gen_vision_model.decoder.conv_blocks.1.res.1.norm1.bias": "model-00001-of-00003.safetensors",
90
+ "gen_vision_model.decoder.conv_blocks.1.res.1.norm1.weight": "model-00001-of-00003.safetensors",
91
+ "gen_vision_model.decoder.conv_blocks.1.res.1.norm2.bias": "model-00001-of-00003.safetensors",
92
+ "gen_vision_model.decoder.conv_blocks.1.res.1.norm2.weight": "model-00001-of-00003.safetensors",
93
+ "gen_vision_model.decoder.conv_blocks.1.res.2.conv1.bias": "model-00001-of-00003.safetensors",
94
+ "gen_vision_model.decoder.conv_blocks.1.res.2.conv1.weight": "model-00001-of-00003.safetensors",
95
+ "gen_vision_model.decoder.conv_blocks.1.res.2.conv2.bias": "model-00001-of-00003.safetensors",
96
+ "gen_vision_model.decoder.conv_blocks.1.res.2.conv2.weight": "model-00001-of-00003.safetensors",
97
+ "gen_vision_model.decoder.conv_blocks.1.res.2.norm1.bias": "model-00001-of-00003.safetensors",
98
+ "gen_vision_model.decoder.conv_blocks.1.res.2.norm1.weight": "model-00001-of-00003.safetensors",
99
+ "gen_vision_model.decoder.conv_blocks.1.res.2.norm2.bias": "model-00001-of-00003.safetensors",
100
+ "gen_vision_model.decoder.conv_blocks.1.res.2.norm2.weight": "model-00001-of-00003.safetensors",
101
+ "gen_vision_model.decoder.conv_blocks.1.upsample.conv.bias": "model-00001-of-00003.safetensors",
102
+ "gen_vision_model.decoder.conv_blocks.1.upsample.conv.weight": "model-00001-of-00003.safetensors",
103
+ "gen_vision_model.decoder.conv_blocks.2.res.0.conv1.bias": "model-00001-of-00003.safetensors",
104
+ "gen_vision_model.decoder.conv_blocks.2.res.0.conv1.weight": "model-00001-of-00003.safetensors",
105
+ "gen_vision_model.decoder.conv_blocks.2.res.0.conv2.bias": "model-00001-of-00003.safetensors",
106
+ "gen_vision_model.decoder.conv_blocks.2.res.0.conv2.weight": "model-00001-of-00003.safetensors",
107
+ "gen_vision_model.decoder.conv_blocks.2.res.0.norm1.bias": "model-00001-of-00003.safetensors",
108
+ "gen_vision_model.decoder.conv_blocks.2.res.0.norm1.weight": "model-00001-of-00003.safetensors",
109
+ "gen_vision_model.decoder.conv_blocks.2.res.0.norm2.bias": "model-00001-of-00003.safetensors",
110
+ "gen_vision_model.decoder.conv_blocks.2.res.0.norm2.weight": "model-00001-of-00003.safetensors",
111
+ "gen_vision_model.decoder.conv_blocks.2.res.1.conv1.bias": "model-00001-of-00003.safetensors",
112
+ "gen_vision_model.decoder.conv_blocks.2.res.1.conv1.weight": "model-00001-of-00003.safetensors",
113
+ "gen_vision_model.decoder.conv_blocks.2.res.1.conv2.bias": "model-00001-of-00003.safetensors",
114
+ "gen_vision_model.decoder.conv_blocks.2.res.1.conv2.weight": "model-00001-of-00003.safetensors",
115
+ "gen_vision_model.decoder.conv_blocks.2.res.1.norm1.bias": "model-00001-of-00003.safetensors",
116
+ "gen_vision_model.decoder.conv_blocks.2.res.1.norm1.weight": "model-00001-of-00003.safetensors",
117
+ "gen_vision_model.decoder.conv_blocks.2.res.1.norm2.bias": "model-00001-of-00003.safetensors",
118
+ "gen_vision_model.decoder.conv_blocks.2.res.1.norm2.weight": "model-00001-of-00003.safetensors",
119
+ "gen_vision_model.decoder.conv_blocks.2.res.2.conv1.bias": "model-00001-of-00003.safetensors",
120
+ "gen_vision_model.decoder.conv_blocks.2.res.2.conv1.weight": "model-00001-of-00003.safetensors",
121
+ "gen_vision_model.decoder.conv_blocks.2.res.2.conv2.bias": "model-00001-of-00003.safetensors",
122
+ "gen_vision_model.decoder.conv_blocks.2.res.2.conv2.weight": "model-00001-of-00003.safetensors",
123
+ "gen_vision_model.decoder.conv_blocks.2.res.2.norm1.bias": "model-00001-of-00003.safetensors",
124
+ "gen_vision_model.decoder.conv_blocks.2.res.2.norm1.weight": "model-00001-of-00003.safetensors",
125
+ "gen_vision_model.decoder.conv_blocks.2.res.2.norm2.bias": "model-00001-of-00003.safetensors",
126
+ "gen_vision_model.decoder.conv_blocks.2.res.2.norm2.weight": "model-00001-of-00003.safetensors",
127
+ "gen_vision_model.decoder.conv_blocks.2.upsample.conv.bias": "model-00001-of-00003.safetensors",
128
+ "gen_vision_model.decoder.conv_blocks.2.upsample.conv.weight": "model-00001-of-00003.safetensors",
129
+ "gen_vision_model.decoder.conv_blocks.3.res.0.conv1.bias": "model-00001-of-00003.safetensors",
130
+ "gen_vision_model.decoder.conv_blocks.3.res.0.conv1.weight": "model-00001-of-00003.safetensors",
131
+ "gen_vision_model.decoder.conv_blocks.3.res.0.conv2.bias": "model-00001-of-00003.safetensors",
132
+ "gen_vision_model.decoder.conv_blocks.3.res.0.conv2.weight": "model-00001-of-00003.safetensors",
133
+ "gen_vision_model.decoder.conv_blocks.3.res.0.nin_shortcut.bias": "model-00001-of-00003.safetensors",
134
+ "gen_vision_model.decoder.conv_blocks.3.res.0.nin_shortcut.weight": "model-00001-of-00003.safetensors",
135
+ "gen_vision_model.decoder.conv_blocks.3.res.0.norm1.bias": "model-00001-of-00003.safetensors",
136
+ "gen_vision_model.decoder.conv_blocks.3.res.0.norm1.weight": "model-00001-of-00003.safetensors",
137
+ "gen_vision_model.decoder.conv_blocks.3.res.0.norm2.bias": "model-00001-of-00003.safetensors",
138
+ "gen_vision_model.decoder.conv_blocks.3.res.0.norm2.weight": "model-00001-of-00003.safetensors",
139
+ "gen_vision_model.decoder.conv_blocks.3.res.1.conv1.bias": "model-00001-of-00003.safetensors",
140
+ "gen_vision_model.decoder.conv_blocks.3.res.1.conv1.weight": "model-00001-of-00003.safetensors",
141
+ "gen_vision_model.decoder.conv_blocks.3.res.1.conv2.bias": "model-00001-of-00003.safetensors",
142
+ "gen_vision_model.decoder.conv_blocks.3.res.1.conv2.weight": "model-00001-of-00003.safetensors",
143
+ "gen_vision_model.decoder.conv_blocks.3.res.1.norm1.bias": "model-00001-of-00003.safetensors",
144
+ "gen_vision_model.decoder.conv_blocks.3.res.1.norm1.weight": "model-00001-of-00003.safetensors",
145
+ "gen_vision_model.decoder.conv_blocks.3.res.1.norm2.bias": "model-00001-of-00003.safetensors",
146
+ "gen_vision_model.decoder.conv_blocks.3.res.1.norm2.weight": "model-00001-of-00003.safetensors",
147
+ "gen_vision_model.decoder.conv_blocks.3.res.2.conv1.bias": "model-00001-of-00003.safetensors",
148
+ "gen_vision_model.decoder.conv_blocks.3.res.2.conv1.weight": "model-00001-of-00003.safetensors",
149
+ "gen_vision_model.decoder.conv_blocks.3.res.2.conv2.bias": "model-00001-of-00003.safetensors",
150
+ "gen_vision_model.decoder.conv_blocks.3.res.2.conv2.weight": "model-00001-of-00003.safetensors",
151
+ "gen_vision_model.decoder.conv_blocks.3.res.2.norm1.bias": "model-00001-of-00003.safetensors",
152
+ "gen_vision_model.decoder.conv_blocks.3.res.2.norm1.weight": "model-00001-of-00003.safetensors",
153
+ "gen_vision_model.decoder.conv_blocks.3.res.2.norm2.bias": "model-00001-of-00003.safetensors",
154
+ "gen_vision_model.decoder.conv_blocks.3.res.2.norm2.weight": "model-00001-of-00003.safetensors",
155
+ "gen_vision_model.decoder.conv_blocks.3.upsample.conv.bias": "model-00001-of-00003.safetensors",
156
+ "gen_vision_model.decoder.conv_blocks.3.upsample.conv.weight": "model-00001-of-00003.safetensors",
157
+ "gen_vision_model.decoder.conv_blocks.4.res.0.conv1.bias": "model-00001-of-00003.safetensors",
158
+ "gen_vision_model.decoder.conv_blocks.4.res.0.conv1.weight": "model-00001-of-00003.safetensors",
159
+ "gen_vision_model.decoder.conv_blocks.4.res.0.conv2.bias": "model-00001-of-00003.safetensors",
160
+ "gen_vision_model.decoder.conv_blocks.4.res.0.conv2.weight": "model-00001-of-00003.safetensors",
161
+ "gen_vision_model.decoder.conv_blocks.4.res.0.norm1.bias": "model-00001-of-00003.safetensors",
162
+ "gen_vision_model.decoder.conv_blocks.4.res.0.norm1.weight": "model-00001-of-00003.safetensors",
163
+ "gen_vision_model.decoder.conv_blocks.4.res.0.norm2.bias": "model-00001-of-00003.safetensors",
164
+ "gen_vision_model.decoder.conv_blocks.4.res.0.norm2.weight": "model-00001-of-00003.safetensors",
165
+ "gen_vision_model.decoder.conv_blocks.4.res.1.conv1.bias": "model-00001-of-00003.safetensors",
166
+ "gen_vision_model.decoder.conv_blocks.4.res.1.conv1.weight": "model-00001-of-00003.safetensors",
167
+ "gen_vision_model.decoder.conv_blocks.4.res.1.conv2.bias": "model-00001-of-00003.safetensors",
168
+ "gen_vision_model.decoder.conv_blocks.4.res.1.conv2.weight": "model-00001-of-00003.safetensors",
169
+ "gen_vision_model.decoder.conv_blocks.4.res.1.norm1.bias": "model-00001-of-00003.safetensors",
170
+ "gen_vision_model.decoder.conv_blocks.4.res.1.norm1.weight": "model-00001-of-00003.safetensors",
171
+ "gen_vision_model.decoder.conv_blocks.4.res.1.norm2.bias": "model-00001-of-00003.safetensors",
172
+ "gen_vision_model.decoder.conv_blocks.4.res.1.norm2.weight": "model-00001-of-00003.safetensors",
173
+ "gen_vision_model.decoder.conv_blocks.4.res.2.conv1.bias": "model-00001-of-00003.safetensors",
174
+ "gen_vision_model.decoder.conv_blocks.4.res.2.conv1.weight": "model-00001-of-00003.safetensors",
175
+ "gen_vision_model.decoder.conv_blocks.4.res.2.conv2.bias": "model-00001-of-00003.safetensors",
176
+ "gen_vision_model.decoder.conv_blocks.4.res.2.conv2.weight": "model-00001-of-00003.safetensors",
177
+ "gen_vision_model.decoder.conv_blocks.4.res.2.norm1.bias": "model-00001-of-00003.safetensors",
178
+ "gen_vision_model.decoder.conv_blocks.4.res.2.norm1.weight": "model-00001-of-00003.safetensors",
179
+ "gen_vision_model.decoder.conv_blocks.4.res.2.norm2.bias": "model-00001-of-00003.safetensors",
180
+ "gen_vision_model.decoder.conv_blocks.4.res.2.norm2.weight": "model-00001-of-00003.safetensors",
181
+ "gen_vision_model.decoder.conv_in.bias": "model-00001-of-00003.safetensors",
182
+ "gen_vision_model.decoder.conv_in.weight": "model-00001-of-00003.safetensors",
183
+ "gen_vision_model.decoder.conv_out.bias": "model-00001-of-00003.safetensors",
184
+ "gen_vision_model.decoder.conv_out.weight": "model-00001-of-00003.safetensors",
185
+ "gen_vision_model.decoder.mid.0.conv1.bias": "model-00001-of-00003.safetensors",
186
+ "gen_vision_model.decoder.mid.0.conv1.weight": "model-00001-of-00003.safetensors",
187
+ "gen_vision_model.decoder.mid.0.conv2.bias": "model-00001-of-00003.safetensors",
188
+ "gen_vision_model.decoder.mid.0.conv2.weight": "model-00001-of-00003.safetensors",
189
+ "gen_vision_model.decoder.mid.0.norm1.bias": "model-00001-of-00003.safetensors",
190
+ "gen_vision_model.decoder.mid.0.norm1.weight": "model-00001-of-00003.safetensors",
191
+ "gen_vision_model.decoder.mid.0.norm2.bias": "model-00001-of-00003.safetensors",
192
+ "gen_vision_model.decoder.mid.0.norm2.weight": "model-00001-of-00003.safetensors",
193
+ "gen_vision_model.decoder.mid.1.k.bias": "model-00001-of-00003.safetensors",
194
+ "gen_vision_model.decoder.mid.1.k.weight": "model-00001-of-00003.safetensors",
195
+ "gen_vision_model.decoder.mid.1.norm.bias": "model-00001-of-00003.safetensors",
196
+ "gen_vision_model.decoder.mid.1.norm.weight": "model-00001-of-00003.safetensors",
197
+ "gen_vision_model.decoder.mid.1.proj_out.bias": "model-00001-of-00003.safetensors",
198
+ "gen_vision_model.decoder.mid.1.proj_out.weight": "model-00001-of-00003.safetensors",
199
+ "gen_vision_model.decoder.mid.1.q.bias": "model-00001-of-00003.safetensors",
200
+ "gen_vision_model.decoder.mid.1.q.weight": "model-00001-of-00003.safetensors",
201
+ "gen_vision_model.decoder.mid.1.v.bias": "model-00001-of-00003.safetensors",
202
+ "gen_vision_model.decoder.mid.1.v.weight": "model-00001-of-00003.safetensors",
203
+ "gen_vision_model.decoder.mid.2.conv1.bias": "model-00001-of-00003.safetensors",
204
+ "gen_vision_model.decoder.mid.2.conv1.weight": "model-00001-of-00003.safetensors",
205
+ "gen_vision_model.decoder.mid.2.conv2.bias": "model-00001-of-00003.safetensors",
206
+ "gen_vision_model.decoder.mid.2.conv2.weight": "model-00001-of-00003.safetensors",
207
+ "gen_vision_model.decoder.mid.2.norm1.bias": "model-00001-of-00003.safetensors",
208
+ "gen_vision_model.decoder.mid.2.norm1.weight": "model-00001-of-00003.safetensors",
209
+ "gen_vision_model.decoder.mid.2.norm2.bias": "model-00001-of-00003.safetensors",
210
+ "gen_vision_model.decoder.mid.2.norm2.weight": "model-00001-of-00003.safetensors",
211
+ "gen_vision_model.decoder.norm_out.bias": "model-00001-of-00003.safetensors",
212
+ "gen_vision_model.decoder.norm_out.weight": "model-00001-of-00003.safetensors",
213
+ "gen_vision_model.encoder.conv_blocks.0.downsample.conv.bias": "model-00001-of-00003.safetensors",
214
+ "gen_vision_model.encoder.conv_blocks.0.downsample.conv.weight": "model-00001-of-00003.safetensors",
215
+ "gen_vision_model.encoder.conv_blocks.0.res.0.conv1.bias": "model-00001-of-00003.safetensors",
216
+ "gen_vision_model.encoder.conv_blocks.0.res.0.conv1.weight": "model-00001-of-00003.safetensors",
217
+ "gen_vision_model.encoder.conv_blocks.0.res.0.conv2.bias": "model-00001-of-00003.safetensors",
218
+ "gen_vision_model.encoder.conv_blocks.0.res.0.conv2.weight": "model-00001-of-00003.safetensors",
219
+ "gen_vision_model.encoder.conv_blocks.0.res.0.norm1.bias": "model-00001-of-00003.safetensors",
220
+ "gen_vision_model.encoder.conv_blocks.0.res.0.norm1.weight": "model-00001-of-00003.safetensors",
221
+ "gen_vision_model.encoder.conv_blocks.0.res.0.norm2.bias": "model-00001-of-00003.safetensors",
222
+ "gen_vision_model.encoder.conv_blocks.0.res.0.norm2.weight": "model-00001-of-00003.safetensors",
223
+ "gen_vision_model.encoder.conv_blocks.0.res.1.conv1.bias": "model-00001-of-00003.safetensors",
224
+ "gen_vision_model.encoder.conv_blocks.0.res.1.conv1.weight": "model-00001-of-00003.safetensors",
225
+ "gen_vision_model.encoder.conv_blocks.0.res.1.conv2.bias": "model-00001-of-00003.safetensors",
226
+ "gen_vision_model.encoder.conv_blocks.0.res.1.conv2.weight": "model-00001-of-00003.safetensors",
227
+ "gen_vision_model.encoder.conv_blocks.0.res.1.norm1.bias": "model-00001-of-00003.safetensors",
228
+ "gen_vision_model.encoder.conv_blocks.0.res.1.norm1.weight": "model-00001-of-00003.safetensors",
229
+ "gen_vision_model.encoder.conv_blocks.0.res.1.norm2.bias": "model-00001-of-00003.safetensors",
230
+ "gen_vision_model.encoder.conv_blocks.0.res.1.norm2.weight": "model-00001-of-00003.safetensors",
231
+ "gen_vision_model.encoder.conv_blocks.1.downsample.conv.bias": "model-00001-of-00003.safetensors",
232
+ "gen_vision_model.encoder.conv_blocks.1.downsample.conv.weight": "model-00001-of-00003.safetensors",
233
+ "gen_vision_model.encoder.conv_blocks.1.res.0.conv1.bias": "model-00001-of-00003.safetensors",
234
+ "gen_vision_model.encoder.conv_blocks.1.res.0.conv1.weight": "model-00001-of-00003.safetensors",
235
+ "gen_vision_model.encoder.conv_blocks.1.res.0.conv2.bias": "model-00001-of-00003.safetensors",
236
+ "gen_vision_model.encoder.conv_blocks.1.res.0.conv2.weight": "model-00001-of-00003.safetensors",
237
+ "gen_vision_model.encoder.conv_blocks.1.res.0.norm1.bias": "model-00001-of-00003.safetensors",
238
+ "gen_vision_model.encoder.conv_blocks.1.res.0.norm1.weight": "model-00001-of-00003.safetensors",
239
+ "gen_vision_model.encoder.conv_blocks.1.res.0.norm2.bias": "model-00001-of-00003.safetensors",
240
+ "gen_vision_model.encoder.conv_blocks.1.res.0.norm2.weight": "model-00001-of-00003.safetensors",
241
+ "gen_vision_model.encoder.conv_blocks.1.res.1.conv1.bias": "model-00001-of-00003.safetensors",
242
+ "gen_vision_model.encoder.conv_blocks.1.res.1.conv1.weight": "model-00001-of-00003.safetensors",
243
+ "gen_vision_model.encoder.conv_blocks.1.res.1.conv2.bias": "model-00001-of-00003.safetensors",
244
+ "gen_vision_model.encoder.conv_blocks.1.res.1.conv2.weight": "model-00001-of-00003.safetensors",
245
+ "gen_vision_model.encoder.conv_blocks.1.res.1.norm1.bias": "model-00001-of-00003.safetensors",
246
+ "gen_vision_model.encoder.conv_blocks.1.res.1.norm1.weight": "model-00001-of-00003.safetensors",
247
+ "gen_vision_model.encoder.conv_blocks.1.res.1.norm2.bias": "model-00001-of-00003.safetensors",
248
+ "gen_vision_model.encoder.conv_blocks.1.res.1.norm2.weight": "model-00001-of-00003.safetensors",
249
+ "gen_vision_model.encoder.conv_blocks.2.downsample.conv.bias": "model-00001-of-00003.safetensors",
250
+ "gen_vision_model.encoder.conv_blocks.2.downsample.conv.weight": "model-00001-of-00003.safetensors",
251
+ "gen_vision_model.encoder.conv_blocks.2.res.0.conv1.bias": "model-00001-of-00003.safetensors",
252
+ "gen_vision_model.encoder.conv_blocks.2.res.0.conv1.weight": "model-00001-of-00003.safetensors",
253
+ "gen_vision_model.encoder.conv_blocks.2.res.0.conv2.bias": "model-00001-of-00003.safetensors",
254
+ "gen_vision_model.encoder.conv_blocks.2.res.0.conv2.weight": "model-00001-of-00003.safetensors",
255
+ "gen_vision_model.encoder.conv_blocks.2.res.0.nin_shortcut.bias": "model-00001-of-00003.safetensors",
256
+ "gen_vision_model.encoder.conv_blocks.2.res.0.nin_shortcut.weight": "model-00001-of-00003.safetensors",
257
+ "gen_vision_model.encoder.conv_blocks.2.res.0.norm1.bias": "model-00001-of-00003.safetensors",
258
+ "gen_vision_model.encoder.conv_blocks.2.res.0.norm1.weight": "model-00001-of-00003.safetensors",
259
+ "gen_vision_model.encoder.conv_blocks.2.res.0.norm2.bias": "model-00001-of-00003.safetensors",
260
+ "gen_vision_model.encoder.conv_blocks.2.res.0.norm2.weight": "model-00001-of-00003.safetensors",
261
+ "gen_vision_model.encoder.conv_blocks.2.res.1.conv1.bias": "model-00001-of-00003.safetensors",
262
+ "gen_vision_model.encoder.conv_blocks.2.res.1.conv1.weight": "model-00001-of-00003.safetensors",
263
+ "gen_vision_model.encoder.conv_blocks.2.res.1.conv2.bias": "model-00001-of-00003.safetensors",
264
+ "gen_vision_model.encoder.conv_blocks.2.res.1.conv2.weight": "model-00001-of-00003.safetensors",
265
+ "gen_vision_model.encoder.conv_blocks.2.res.1.norm1.bias": "model-00001-of-00003.safetensors",
266
+ "gen_vision_model.encoder.conv_blocks.2.res.1.norm1.weight": "model-00001-of-00003.safetensors",
267
+ "gen_vision_model.encoder.conv_blocks.2.res.1.norm2.bias": "model-00001-of-00003.safetensors",
268
+ "gen_vision_model.encoder.conv_blocks.2.res.1.norm2.weight": "model-00001-of-00003.safetensors",
269
+ "gen_vision_model.encoder.conv_blocks.3.downsample.conv.bias": "model-00001-of-00003.safetensors",
270
+ "gen_vision_model.encoder.conv_blocks.3.downsample.conv.weight": "model-00001-of-00003.safetensors",
271
+ "gen_vision_model.encoder.conv_blocks.3.res.0.conv1.bias": "model-00001-of-00003.safetensors",
272
+ "gen_vision_model.encoder.conv_blocks.3.res.0.conv1.weight": "model-00001-of-00003.safetensors",
273
+ "gen_vision_model.encoder.conv_blocks.3.res.0.conv2.bias": "model-00001-of-00003.safetensors",
274
+ "gen_vision_model.encoder.conv_blocks.3.res.0.conv2.weight": "model-00001-of-00003.safetensors",
275
+ "gen_vision_model.encoder.conv_blocks.3.res.0.norm1.bias": "model-00001-of-00003.safetensors",
276
+ "gen_vision_model.encoder.conv_blocks.3.res.0.norm1.weight": "model-00001-of-00003.safetensors",
277
+ "gen_vision_model.encoder.conv_blocks.3.res.0.norm2.bias": "model-00001-of-00003.safetensors",
278
+ "gen_vision_model.encoder.conv_blocks.3.res.0.norm2.weight": "model-00001-of-00003.safetensors",
279
+ "gen_vision_model.encoder.conv_blocks.3.res.1.conv1.bias": "model-00001-of-00003.safetensors",
280
+ "gen_vision_model.encoder.conv_blocks.3.res.1.conv1.weight": "model-00001-of-00003.safetensors",
281
+ "gen_vision_model.encoder.conv_blocks.3.res.1.conv2.bias": "model-00001-of-00003.safetensors",
282
+ "gen_vision_model.encoder.conv_blocks.3.res.1.conv2.weight": "model-00001-of-00003.safetensors",
283
+ "gen_vision_model.encoder.conv_blocks.3.res.1.norm1.bias": "model-00001-of-00003.safetensors",
284
+ "gen_vision_model.encoder.conv_blocks.3.res.1.norm1.weight": "model-00001-of-00003.safetensors",
285
+ "gen_vision_model.encoder.conv_blocks.3.res.1.norm2.bias": "model-00001-of-00003.safetensors",
286
+ "gen_vision_model.encoder.conv_blocks.3.res.1.norm2.weight": "model-00001-of-00003.safetensors",
287
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.k.bias": "model-00001-of-00003.safetensors",
288
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.k.weight": "model-00001-of-00003.safetensors",
289
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.norm.bias": "model-00001-of-00003.safetensors",
290
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.norm.weight": "model-00001-of-00003.safetensors",
291
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.proj_out.bias": "model-00001-of-00003.safetensors",
292
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.proj_out.weight": "model-00001-of-00003.safetensors",
293
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.q.bias": "model-00001-of-00003.safetensors",
294
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.q.weight": "model-00001-of-00003.safetensors",
295
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.v.bias": "model-00001-of-00003.safetensors",
296
+ "gen_vision_model.encoder.conv_blocks.4.attn.0.v.weight": "model-00001-of-00003.safetensors",
297
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.k.bias": "model-00001-of-00003.safetensors",
298
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.k.weight": "model-00001-of-00003.safetensors",
299
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.norm.bias": "model-00001-of-00003.safetensors",
300
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.norm.weight": "model-00001-of-00003.safetensors",
301
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.proj_out.bias": "model-00001-of-00003.safetensors",
302
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.proj_out.weight": "model-00001-of-00003.safetensors",
303
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.q.bias": "model-00001-of-00003.safetensors",
304
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.q.weight": "model-00001-of-00003.safetensors",
305
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.v.bias": "model-00001-of-00003.safetensors",
306
+ "gen_vision_model.encoder.conv_blocks.4.attn.1.v.weight": "model-00001-of-00003.safetensors",
307
+ "gen_vision_model.encoder.conv_blocks.4.res.0.conv1.bias": "model-00001-of-00003.safetensors",
308
+ "gen_vision_model.encoder.conv_blocks.4.res.0.conv1.weight": "model-00001-of-00003.safetensors",
309
+ "gen_vision_model.encoder.conv_blocks.4.res.0.conv2.bias": "model-00001-of-00003.safetensors",
310
+ "gen_vision_model.encoder.conv_blocks.4.res.0.conv2.weight": "model-00001-of-00003.safetensors",
311
+ "gen_vision_model.encoder.conv_blocks.4.res.0.nin_shortcut.bias": "model-00001-of-00003.safetensors",
312
+ "gen_vision_model.encoder.conv_blocks.4.res.0.nin_shortcut.weight": "model-00001-of-00003.safetensors",
313
+ "gen_vision_model.encoder.conv_blocks.4.res.0.norm1.bias": "model-00001-of-00003.safetensors",
314
+ "gen_vision_model.encoder.conv_blocks.4.res.0.norm1.weight": "model-00001-of-00003.safetensors",
315
+ "gen_vision_model.encoder.conv_blocks.4.res.0.norm2.bias": "model-00001-of-00003.safetensors",
316
+ "gen_vision_model.encoder.conv_blocks.4.res.0.norm2.weight": "model-00001-of-00003.safetensors",
317
+ "gen_vision_model.encoder.conv_blocks.4.res.1.conv1.bias": "model-00001-of-00003.safetensors",
318
+ "gen_vision_model.encoder.conv_blocks.4.res.1.conv1.weight": "model-00001-of-00003.safetensors",
319
+ "gen_vision_model.encoder.conv_blocks.4.res.1.conv2.bias": "model-00001-of-00003.safetensors",
320
+ "gen_vision_model.encoder.conv_blocks.4.res.1.conv2.weight": "model-00001-of-00003.safetensors",
321
+ "gen_vision_model.encoder.conv_blocks.4.res.1.norm1.bias": "model-00001-of-00003.safetensors",
322
+ "gen_vision_model.encoder.conv_blocks.4.res.1.norm1.weight": "model-00001-of-00003.safetensors",
323
+ "gen_vision_model.encoder.conv_blocks.4.res.1.norm2.bias": "model-00001-of-00003.safetensors",
324
+ "gen_vision_model.encoder.conv_blocks.4.res.1.norm2.weight": "model-00001-of-00003.safetensors",
325
+ "gen_vision_model.encoder.conv_in.bias": "model-00001-of-00003.safetensors",
326
+ "gen_vision_model.encoder.conv_in.weight": "model-00001-of-00003.safetensors",
327
+ "gen_vision_model.encoder.conv_out.bias": "model-00001-of-00003.safetensors",
328
+ "gen_vision_model.encoder.conv_out.weight": "model-00001-of-00003.safetensors",
329
+ "gen_vision_model.encoder.mid.0.conv1.bias": "model-00001-of-00003.safetensors",
330
+ "gen_vision_model.encoder.mid.0.conv1.weight": "model-00001-of-00003.safetensors",
331
+ "gen_vision_model.encoder.mid.0.conv2.bias": "model-00001-of-00003.safetensors",
332
+ "gen_vision_model.encoder.mid.0.conv2.weight": "model-00001-of-00003.safetensors",
333
+ "gen_vision_model.encoder.mid.0.norm1.bias": "model-00001-of-00003.safetensors",
334
+ "gen_vision_model.encoder.mid.0.norm1.weight": "model-00001-of-00003.safetensors",
335
+ "gen_vision_model.encoder.mid.0.norm2.bias": "model-00001-of-00003.safetensors",
336
+ "gen_vision_model.encoder.mid.0.norm2.weight": "model-00001-of-00003.safetensors",
337
+ "gen_vision_model.encoder.mid.1.k.bias": "model-00001-of-00003.safetensors",
338
+ "gen_vision_model.encoder.mid.1.k.weight": "model-00001-of-00003.safetensors",
339
+ "gen_vision_model.encoder.mid.1.norm.bias": "model-00001-of-00003.safetensors",
340
+ "gen_vision_model.encoder.mid.1.norm.weight": "model-00001-of-00003.safetensors",
341
+ "gen_vision_model.encoder.mid.1.proj_out.bias": "model-00001-of-00003.safetensors",
342
+ "gen_vision_model.encoder.mid.1.proj_out.weight": "model-00001-of-00003.safetensors",
343
+ "gen_vision_model.encoder.mid.1.q.bias": "model-00001-of-00003.safetensors",
344
+ "gen_vision_model.encoder.mid.1.q.weight": "model-00001-of-00003.safetensors",
345
+ "gen_vision_model.encoder.mid.1.v.bias": "model-00001-of-00003.safetensors",
346
+ "gen_vision_model.encoder.mid.1.v.weight": "model-00001-of-00003.safetensors",
347
+ "gen_vision_model.encoder.mid.2.conv1.bias": "model-00001-of-00003.safetensors",
348
+ "gen_vision_model.encoder.mid.2.conv1.weight": "model-00001-of-00003.safetensors",
349
+ "gen_vision_model.encoder.mid.2.conv2.bias": "model-00001-of-00003.safetensors",
350
+ "gen_vision_model.encoder.mid.2.conv2.weight": "model-00001-of-00003.safetensors",
351
+ "gen_vision_model.encoder.mid.2.norm1.bias": "model-00001-of-00003.safetensors",
352
+ "gen_vision_model.encoder.mid.2.norm1.weight": "model-00001-of-00003.safetensors",
353
+ "gen_vision_model.encoder.mid.2.norm2.bias": "model-00001-of-00003.safetensors",
354
+ "gen_vision_model.encoder.mid.2.norm2.weight": "model-00001-of-00003.safetensors",
355
+ "gen_vision_model.encoder.norm_out.bias": "model-00001-of-00003.safetensors",
356
+ "gen_vision_model.encoder.norm_out.weight": "model-00001-of-00003.safetensors",
357
+ "gen_vision_model.post_quant_conv.bias": "model-00001-of-00003.safetensors",
358
+ "gen_vision_model.post_quant_conv.weight": "model-00001-of-00003.safetensors",
359
+ "gen_vision_model.quant_conv.bias": "model-00001-of-00003.safetensors",
360
+ "gen_vision_model.quant_conv.weight": "model-00001-of-00003.safetensors",
361
+ "gen_vision_model.quantize.codebook_used": "model-00001-of-00003.safetensors",
362
+ "gen_vision_model.quantize.embedding.weight": "model-00001-of-00003.safetensors",
363
+ "language_model.lm_head.weight": "model-00003-of-00003.safetensors",
364
+ "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
365
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
366
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
367
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
368
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
369
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
370
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
371
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
372
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
373
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
374
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
375
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
376
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
377
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
378
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
379
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
380
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
381
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
382
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
383
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
384
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
385
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
386
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
387
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
388
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
389
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
390
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
391
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
392
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
393
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
394
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
395
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
396
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
397
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
398
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
399
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
400
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
401
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
402
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
403
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
404
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
405
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
406
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
407
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
408
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
409
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
410
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
411
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
412
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
413
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
414
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
415
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
416
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
417
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
418
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
419
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
420
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
421
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
422
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
423
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
424
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
425
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
426
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
427
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
428
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
429
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
430
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
431
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
432
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
433
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
434
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
435
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
436
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
437
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
438
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
439
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
440
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
441
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
442
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
443
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
444
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
445
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
446
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
447
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
448
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
449
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
450
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
451
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
452
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
453
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
454
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
455
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
456
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
457
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
458
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
459
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
460
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
461
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
462
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
463
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
464
+ "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00003.safetensors",
465
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
466
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
467
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
468
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
469
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
470
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
471
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
472
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
473
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
474
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
475
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
476
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
477
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
478
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
479
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
480
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
481
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
482
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
483
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
484
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
485
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
486
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
487
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
488
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
489
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
490
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
491
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
492
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
493
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
494
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
495
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
496
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
497
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
498
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
499
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
500
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
501
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
502
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
503
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
504
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
505
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
506
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
507
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
508
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
509
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
510
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
511
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
512
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
513
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
514
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
515
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
516
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
517
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
518
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
519
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
520
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
521
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
522
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
523
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
524
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
525
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
526
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
527
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
528
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
529
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
530
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
531
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
532
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
533
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
534
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
535
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
536
+ "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
537
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
538
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
539
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
540
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
541
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
542
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
543
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
544
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
545
+ "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
546
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
547
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
548
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
549
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
550
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
551
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
552
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
553
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
554
+ "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
555
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
556
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
557
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
558
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
559
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
560
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
561
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
562
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
563
+ "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
564
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
565
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
566
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
567
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
568
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
569
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
570
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
571
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
572
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
573
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
574
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
575
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
576
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
577
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
578
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
579
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
580
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
581
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
582
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
583
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
584
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
585
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
586
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
587
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
588
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
589
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
590
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
591
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
592
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
593
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
594
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
595
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
596
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
597
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
598
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
599
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
600
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
601
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
602
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
603
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
604
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
605
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
606
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
607
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
608
+ "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
609
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
610
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
611
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
612
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
613
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
614
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
615
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
616
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
617
+ "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
618
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
619
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
620
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
621
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
622
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
623
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
624
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
625
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
626
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
627
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
628
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
629
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
630
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
631
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
632
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
633
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
634
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
635
+ "language_model.model.norm.weight": "model-00003-of-00003.safetensors",
636
+ "vision_model.vision_tower.attn_pool.kv.bias": "model-00001-of-00003.safetensors",
637
+ "vision_model.vision_tower.attn_pool.kv.weight": "model-00001-of-00003.safetensors",
638
+ "vision_model.vision_tower.attn_pool.latent": "model-00001-of-00003.safetensors",
639
+ "vision_model.vision_tower.attn_pool.mlp.fc1.bias": "model-00001-of-00003.safetensors",
640
+ "vision_model.vision_tower.attn_pool.mlp.fc1.weight": "model-00001-of-00003.safetensors",
641
+ "vision_model.vision_tower.attn_pool.mlp.fc2.bias": "model-00001-of-00003.safetensors",
642
+ "vision_model.vision_tower.attn_pool.mlp.fc2.weight": "model-00001-of-00003.safetensors",
643
+ "vision_model.vision_tower.attn_pool.norm.bias": "model-00001-of-00003.safetensors",
644
+ "vision_model.vision_tower.attn_pool.norm.weight": "model-00001-of-00003.safetensors",
645
+ "vision_model.vision_tower.attn_pool.proj.bias": "model-00001-of-00003.safetensors",
646
+ "vision_model.vision_tower.attn_pool.proj.weight": "model-00001-of-00003.safetensors",
647
+ "vision_model.vision_tower.attn_pool.q.bias": "model-00001-of-00003.safetensors",
648
+ "vision_model.vision_tower.attn_pool.q.weight": "model-00001-of-00003.safetensors",
649
+ "vision_model.vision_tower.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
650
+ "vision_model.vision_tower.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
651
+ "vision_model.vision_tower.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
652
+ "vision_model.vision_tower.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
653
+ "vision_model.vision_tower.blocks.0.mlp.fc1.bias": "model-00001-of-00003.safetensors",
654
+ "vision_model.vision_tower.blocks.0.mlp.fc1.weight": "model-00001-of-00003.safetensors",
655
+ "vision_model.vision_tower.blocks.0.mlp.fc2.bias": "model-00001-of-00003.safetensors",
656
+ "vision_model.vision_tower.blocks.0.mlp.fc2.weight": "model-00001-of-00003.safetensors",
657
+ "vision_model.vision_tower.blocks.0.norm1.bias": "model-00001-of-00003.safetensors",
658
+ "vision_model.vision_tower.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
659
+ "vision_model.vision_tower.blocks.0.norm2.bias": "model-00001-of-00003.safetensors",
660
+ "vision_model.vision_tower.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
661
+ "vision_model.vision_tower.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
662
+ "vision_model.vision_tower.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
663
+ "vision_model.vision_tower.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
664
+ "vision_model.vision_tower.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
665
+ "vision_model.vision_tower.blocks.1.mlp.fc1.bias": "model-00001-of-00003.safetensors",
666
+ "vision_model.vision_tower.blocks.1.mlp.fc1.weight": "model-00001-of-00003.safetensors",
667
+ "vision_model.vision_tower.blocks.1.mlp.fc2.bias": "model-00001-of-00003.safetensors",
668
+ "vision_model.vision_tower.blocks.1.mlp.fc2.weight": "model-00001-of-00003.safetensors",
669
+ "vision_model.vision_tower.blocks.1.norm1.bias": "model-00001-of-00003.safetensors",
670
+ "vision_model.vision_tower.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
671
+ "vision_model.vision_tower.blocks.1.norm2.bias": "model-00001-of-00003.safetensors",
672
+ "vision_model.vision_tower.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
673
+ "vision_model.vision_tower.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
674
+ "vision_model.vision_tower.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
675
+ "vision_model.vision_tower.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
676
+ "vision_model.vision_tower.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
677
+ "vision_model.vision_tower.blocks.10.mlp.fc1.bias": "model-00001-of-00003.safetensors",
678
+ "vision_model.vision_tower.blocks.10.mlp.fc1.weight": "model-00001-of-00003.safetensors",
679
+ "vision_model.vision_tower.blocks.10.mlp.fc2.bias": "model-00001-of-00003.safetensors",
680
+ "vision_model.vision_tower.blocks.10.mlp.fc2.weight": "model-00001-of-00003.safetensors",
681
+ "vision_model.vision_tower.blocks.10.norm1.bias": "model-00001-of-00003.safetensors",
682
+ "vision_model.vision_tower.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
683
+ "vision_model.vision_tower.blocks.10.norm2.bias": "model-00001-of-00003.safetensors",
684
+ "vision_model.vision_tower.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
685
+ "vision_model.vision_tower.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
686
+ "vision_model.vision_tower.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
687
+ "vision_model.vision_tower.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
688
+ "vision_model.vision_tower.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
689
+ "vision_model.vision_tower.blocks.11.mlp.fc1.bias": "model-00001-of-00003.safetensors",
690
+ "vision_model.vision_tower.blocks.11.mlp.fc1.weight": "model-00001-of-00003.safetensors",
691
+ "vision_model.vision_tower.blocks.11.mlp.fc2.bias": "model-00001-of-00003.safetensors",
692
+ "vision_model.vision_tower.blocks.11.mlp.fc2.weight": "model-00001-of-00003.safetensors",
693
+ "vision_model.vision_tower.blocks.11.norm1.bias": "model-00001-of-00003.safetensors",
694
+ "vision_model.vision_tower.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
695
+ "vision_model.vision_tower.blocks.11.norm2.bias": "model-00001-of-00003.safetensors",
696
+ "vision_model.vision_tower.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
697
+ "vision_model.vision_tower.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
698
+ "vision_model.vision_tower.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
699
+ "vision_model.vision_tower.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
700
+ "vision_model.vision_tower.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
701
+ "vision_model.vision_tower.blocks.12.mlp.fc1.bias": "model-00001-of-00003.safetensors",
702
+ "vision_model.vision_tower.blocks.12.mlp.fc1.weight": "model-00001-of-00003.safetensors",
703
+ "vision_model.vision_tower.blocks.12.mlp.fc2.bias": "model-00001-of-00003.safetensors",
704
+ "vision_model.vision_tower.blocks.12.mlp.fc2.weight": "model-00001-of-00003.safetensors",
705
+ "vision_model.vision_tower.blocks.12.norm1.bias": "model-00001-of-00003.safetensors",
706
+ "vision_model.vision_tower.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
707
+ "vision_model.vision_tower.blocks.12.norm2.bias": "model-00001-of-00003.safetensors",
708
+ "vision_model.vision_tower.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
709
+ "vision_model.vision_tower.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
710
+ "vision_model.vision_tower.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
711
+ "vision_model.vision_tower.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
712
+ "vision_model.vision_tower.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
713
+ "vision_model.vision_tower.blocks.13.mlp.fc1.bias": "model-00001-of-00003.safetensors",
714
+ "vision_model.vision_tower.blocks.13.mlp.fc1.weight": "model-00001-of-00003.safetensors",
715
+ "vision_model.vision_tower.blocks.13.mlp.fc2.bias": "model-00001-of-00003.safetensors",
716
+ "vision_model.vision_tower.blocks.13.mlp.fc2.weight": "model-00001-of-00003.safetensors",
717
+ "vision_model.vision_tower.blocks.13.norm1.bias": "model-00001-of-00003.safetensors",
718
+ "vision_model.vision_tower.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
719
+ "vision_model.vision_tower.blocks.13.norm2.bias": "model-00001-of-00003.safetensors",
720
+ "vision_model.vision_tower.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
721
+ "vision_model.vision_tower.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
722
+ "vision_model.vision_tower.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
723
+ "vision_model.vision_tower.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
724
+ "vision_model.vision_tower.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
725
+ "vision_model.vision_tower.blocks.14.mlp.fc1.bias": "model-00001-of-00003.safetensors",
726
+ "vision_model.vision_tower.blocks.14.mlp.fc1.weight": "model-00001-of-00003.safetensors",
727
+ "vision_model.vision_tower.blocks.14.mlp.fc2.bias": "model-00001-of-00003.safetensors",
728
+ "vision_model.vision_tower.blocks.14.mlp.fc2.weight": "model-00001-of-00003.safetensors",
729
+ "vision_model.vision_tower.blocks.14.norm1.bias": "model-00001-of-00003.safetensors",
730
+ "vision_model.vision_tower.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
731
+ "vision_model.vision_tower.blocks.14.norm2.bias": "model-00001-of-00003.safetensors",
732
+ "vision_model.vision_tower.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
733
+ "vision_model.vision_tower.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
734
+ "vision_model.vision_tower.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
735
+ "vision_model.vision_tower.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
736
+ "vision_model.vision_tower.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
737
+ "vision_model.vision_tower.blocks.15.mlp.fc1.bias": "model-00001-of-00003.safetensors",
738
+ "vision_model.vision_tower.blocks.15.mlp.fc1.weight": "model-00001-of-00003.safetensors",
739
+ "vision_model.vision_tower.blocks.15.mlp.fc2.bias": "model-00001-of-00003.safetensors",
740
+ "vision_model.vision_tower.blocks.15.mlp.fc2.weight": "model-00001-of-00003.safetensors",
741
+ "vision_model.vision_tower.blocks.15.norm1.bias": "model-00001-of-00003.safetensors",
742
+ "vision_model.vision_tower.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
743
+ "vision_model.vision_tower.blocks.15.norm2.bias": "model-00001-of-00003.safetensors",
744
+ "vision_model.vision_tower.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
745
+ "vision_model.vision_tower.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
746
+ "vision_model.vision_tower.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
747
+ "vision_model.vision_tower.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
748
+ "vision_model.vision_tower.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
749
+ "vision_model.vision_tower.blocks.16.mlp.fc1.bias": "model-00001-of-00003.safetensors",
750
+ "vision_model.vision_tower.blocks.16.mlp.fc1.weight": "model-00001-of-00003.safetensors",
751
+ "vision_model.vision_tower.blocks.16.mlp.fc2.bias": "model-00001-of-00003.safetensors",
752
+ "vision_model.vision_tower.blocks.16.mlp.fc2.weight": "model-00001-of-00003.safetensors",
753
+ "vision_model.vision_tower.blocks.16.norm1.bias": "model-00001-of-00003.safetensors",
754
+ "vision_model.vision_tower.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
755
+ "vision_model.vision_tower.blocks.16.norm2.bias": "model-00001-of-00003.safetensors",
756
+ "vision_model.vision_tower.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
757
+ "vision_model.vision_tower.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
758
+ "vision_model.vision_tower.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
759
+ "vision_model.vision_tower.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
760
+ "vision_model.vision_tower.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
761
+ "vision_model.vision_tower.blocks.17.mlp.fc1.bias": "model-00001-of-00003.safetensors",
762
+ "vision_model.vision_tower.blocks.17.mlp.fc1.weight": "model-00001-of-00003.safetensors",
763
+ "vision_model.vision_tower.blocks.17.mlp.fc2.bias": "model-00001-of-00003.safetensors",
764
+ "vision_model.vision_tower.blocks.17.mlp.fc2.weight": "model-00001-of-00003.safetensors",
765
+ "vision_model.vision_tower.blocks.17.norm1.bias": "model-00001-of-00003.safetensors",
766
+ "vision_model.vision_tower.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
767
+ "vision_model.vision_tower.blocks.17.norm2.bias": "model-00001-of-00003.safetensors",
768
+ "vision_model.vision_tower.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
769
+ "vision_model.vision_tower.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
770
+ "vision_model.vision_tower.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
771
+ "vision_model.vision_tower.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
772
+ "vision_model.vision_tower.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
773
+ "vision_model.vision_tower.blocks.18.mlp.fc1.bias": "model-00001-of-00003.safetensors",
774
+ "vision_model.vision_tower.blocks.18.mlp.fc1.weight": "model-00001-of-00003.safetensors",
775
+ "vision_model.vision_tower.blocks.18.mlp.fc2.bias": "model-00001-of-00003.safetensors",
776
+ "vision_model.vision_tower.blocks.18.mlp.fc2.weight": "model-00001-of-00003.safetensors",
777
+ "vision_model.vision_tower.blocks.18.norm1.bias": "model-00001-of-00003.safetensors",
778
+ "vision_model.vision_tower.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
779
+ "vision_model.vision_tower.blocks.18.norm2.bias": "model-00001-of-00003.safetensors",
780
+ "vision_model.vision_tower.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
781
+ "vision_model.vision_tower.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
782
+ "vision_model.vision_tower.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
783
+ "vision_model.vision_tower.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
784
+ "vision_model.vision_tower.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
785
+ "vision_model.vision_tower.blocks.19.mlp.fc1.bias": "model-00001-of-00003.safetensors",
786
+ "vision_model.vision_tower.blocks.19.mlp.fc1.weight": "model-00001-of-00003.safetensors",
787
+ "vision_model.vision_tower.blocks.19.mlp.fc2.bias": "model-00001-of-00003.safetensors",
788
+ "vision_model.vision_tower.blocks.19.mlp.fc2.weight": "model-00001-of-00003.safetensors",
789
+ "vision_model.vision_tower.blocks.19.norm1.bias": "model-00001-of-00003.safetensors",
790
+ "vision_model.vision_tower.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
791
+ "vision_model.vision_tower.blocks.19.norm2.bias": "model-00001-of-00003.safetensors",
792
+ "vision_model.vision_tower.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
793
+ "vision_model.vision_tower.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
794
+ "vision_model.vision_tower.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
795
+ "vision_model.vision_tower.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
796
+ "vision_model.vision_tower.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
797
+ "vision_model.vision_tower.blocks.2.mlp.fc1.bias": "model-00001-of-00003.safetensors",
798
+ "vision_model.vision_tower.blocks.2.mlp.fc1.weight": "model-00001-of-00003.safetensors",
799
+ "vision_model.vision_tower.blocks.2.mlp.fc2.bias": "model-00001-of-00003.safetensors",
800
+ "vision_model.vision_tower.blocks.2.mlp.fc2.weight": "model-00001-of-00003.safetensors",
801
+ "vision_model.vision_tower.blocks.2.norm1.bias": "model-00001-of-00003.safetensors",
802
+ "vision_model.vision_tower.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
803
+ "vision_model.vision_tower.blocks.2.norm2.bias": "model-00001-of-00003.safetensors",
804
+ "vision_model.vision_tower.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
805
+ "vision_model.vision_tower.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
806
+ "vision_model.vision_tower.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
807
+ "vision_model.vision_tower.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
808
+ "vision_model.vision_tower.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
809
+ "vision_model.vision_tower.blocks.20.mlp.fc1.bias": "model-00001-of-00003.safetensors",
810
+ "vision_model.vision_tower.blocks.20.mlp.fc1.weight": "model-00001-of-00003.safetensors",
811
+ "vision_model.vision_tower.blocks.20.mlp.fc2.bias": "model-00001-of-00003.safetensors",
812
+ "vision_model.vision_tower.blocks.20.mlp.fc2.weight": "model-00001-of-00003.safetensors",
813
+ "vision_model.vision_tower.blocks.20.norm1.bias": "model-00001-of-00003.safetensors",
814
+ "vision_model.vision_tower.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
815
+ "vision_model.vision_tower.blocks.20.norm2.bias": "model-00001-of-00003.safetensors",
816
+ "vision_model.vision_tower.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
817
+ "vision_model.vision_tower.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
818
+ "vision_model.vision_tower.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
819
+ "vision_model.vision_tower.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
820
+ "vision_model.vision_tower.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
821
+ "vision_model.vision_tower.blocks.21.mlp.fc1.bias": "model-00001-of-00003.safetensors",
822
+ "vision_model.vision_tower.blocks.21.mlp.fc1.weight": "model-00001-of-00003.safetensors",
823
+ "vision_model.vision_tower.blocks.21.mlp.fc2.bias": "model-00001-of-00003.safetensors",
824
+ "vision_model.vision_tower.blocks.21.mlp.fc2.weight": "model-00001-of-00003.safetensors",
825
+ "vision_model.vision_tower.blocks.21.norm1.bias": "model-00001-of-00003.safetensors",
826
+ "vision_model.vision_tower.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
827
+ "vision_model.vision_tower.blocks.21.norm2.bias": "model-00001-of-00003.safetensors",
828
+ "vision_model.vision_tower.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
829
+ "vision_model.vision_tower.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
830
+ "vision_model.vision_tower.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
831
+ "vision_model.vision_tower.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
832
+ "vision_model.vision_tower.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
833
+ "vision_model.vision_tower.blocks.22.mlp.fc1.bias": "model-00001-of-00003.safetensors",
834
+ "vision_model.vision_tower.blocks.22.mlp.fc1.weight": "model-00001-of-00003.safetensors",
835
+ "vision_model.vision_tower.blocks.22.mlp.fc2.bias": "model-00001-of-00003.safetensors",
836
+ "vision_model.vision_tower.blocks.22.mlp.fc2.weight": "model-00001-of-00003.safetensors",
837
+ "vision_model.vision_tower.blocks.22.norm1.bias": "model-00001-of-00003.safetensors",
838
+ "vision_model.vision_tower.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
839
+ "vision_model.vision_tower.blocks.22.norm2.bias": "model-00001-of-00003.safetensors",
840
+ "vision_model.vision_tower.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
841
+ "vision_model.vision_tower.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
842
+ "vision_model.vision_tower.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
843
+ "vision_model.vision_tower.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
844
+ "vision_model.vision_tower.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
845
+ "vision_model.vision_tower.blocks.23.mlp.fc1.bias": "model-00001-of-00003.safetensors",
846
+ "vision_model.vision_tower.blocks.23.mlp.fc1.weight": "model-00001-of-00003.safetensors",
847
+ "vision_model.vision_tower.blocks.23.mlp.fc2.bias": "model-00001-of-00003.safetensors",
848
+ "vision_model.vision_tower.blocks.23.mlp.fc2.weight": "model-00001-of-00003.safetensors",
849
+ "vision_model.vision_tower.blocks.23.norm1.bias": "model-00001-of-00003.safetensors",
850
+ "vision_model.vision_tower.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
851
+ "vision_model.vision_tower.blocks.23.norm2.bias": "model-00001-of-00003.safetensors",
852
+ "vision_model.vision_tower.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
853
+ "vision_model.vision_tower.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
854
+ "vision_model.vision_tower.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
855
+ "vision_model.vision_tower.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
856
+ "vision_model.vision_tower.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
857
+ "vision_model.vision_tower.blocks.3.mlp.fc1.bias": "model-00001-of-00003.safetensors",
858
+ "vision_model.vision_tower.blocks.3.mlp.fc1.weight": "model-00001-of-00003.safetensors",
859
+ "vision_model.vision_tower.blocks.3.mlp.fc2.bias": "model-00001-of-00003.safetensors",
860
+ "vision_model.vision_tower.blocks.3.mlp.fc2.weight": "model-00001-of-00003.safetensors",
861
+ "vision_model.vision_tower.blocks.3.norm1.bias": "model-00001-of-00003.safetensors",
862
+ "vision_model.vision_tower.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
863
+ "vision_model.vision_tower.blocks.3.norm2.bias": "model-00001-of-00003.safetensors",
864
+ "vision_model.vision_tower.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
865
+ "vision_model.vision_tower.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
866
+ "vision_model.vision_tower.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
867
+ "vision_model.vision_tower.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
868
+ "vision_model.vision_tower.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
869
+ "vision_model.vision_tower.blocks.4.mlp.fc1.bias": "model-00001-of-00003.safetensors",
870
+ "vision_model.vision_tower.blocks.4.mlp.fc1.weight": "model-00001-of-00003.safetensors",
871
+ "vision_model.vision_tower.blocks.4.mlp.fc2.bias": "model-00001-of-00003.safetensors",
872
+ "vision_model.vision_tower.blocks.4.mlp.fc2.weight": "model-00001-of-00003.safetensors",
873
+ "vision_model.vision_tower.blocks.4.norm1.bias": "model-00001-of-00003.safetensors",
874
+ "vision_model.vision_tower.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
875
+ "vision_model.vision_tower.blocks.4.norm2.bias": "model-00001-of-00003.safetensors",
876
+ "vision_model.vision_tower.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
877
+ "vision_model.vision_tower.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
878
+ "vision_model.vision_tower.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
879
+ "vision_model.vision_tower.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
880
+ "vision_model.vision_tower.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
881
+ "vision_model.vision_tower.blocks.5.mlp.fc1.bias": "model-00001-of-00003.safetensors",
882
+ "vision_model.vision_tower.blocks.5.mlp.fc1.weight": "model-00001-of-00003.safetensors",
883
+ "vision_model.vision_tower.blocks.5.mlp.fc2.bias": "model-00001-of-00003.safetensors",
884
+ "vision_model.vision_tower.blocks.5.mlp.fc2.weight": "model-00001-of-00003.safetensors",
885
+ "vision_model.vision_tower.blocks.5.norm1.bias": "model-00001-of-00003.safetensors",
886
+ "vision_model.vision_tower.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
887
+ "vision_model.vision_tower.blocks.5.norm2.bias": "model-00001-of-00003.safetensors",
888
+ "vision_model.vision_tower.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
889
+ "vision_model.vision_tower.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
890
+ "vision_model.vision_tower.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
891
+ "vision_model.vision_tower.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
892
+ "vision_model.vision_tower.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
893
+ "vision_model.vision_tower.blocks.6.mlp.fc1.bias": "model-00001-of-00003.safetensors",
894
+ "vision_model.vision_tower.blocks.6.mlp.fc1.weight": "model-00001-of-00003.safetensors",
895
+ "vision_model.vision_tower.blocks.6.mlp.fc2.bias": "model-00001-of-00003.safetensors",
896
+ "vision_model.vision_tower.blocks.6.mlp.fc2.weight": "model-00001-of-00003.safetensors",
897
+ "vision_model.vision_tower.blocks.6.norm1.bias": "model-00001-of-00003.safetensors",
898
+ "vision_model.vision_tower.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
899
+ "vision_model.vision_tower.blocks.6.norm2.bias": "model-00001-of-00003.safetensors",
900
+ "vision_model.vision_tower.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
901
+ "vision_model.vision_tower.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
902
+ "vision_model.vision_tower.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
903
+ "vision_model.vision_tower.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
904
+ "vision_model.vision_tower.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
905
+ "vision_model.vision_tower.blocks.7.mlp.fc1.bias": "model-00001-of-00003.safetensors",
906
+ "vision_model.vision_tower.blocks.7.mlp.fc1.weight": "model-00001-of-00003.safetensors",
907
+ "vision_model.vision_tower.blocks.7.mlp.fc2.bias": "model-00001-of-00003.safetensors",
908
+ "vision_model.vision_tower.blocks.7.mlp.fc2.weight": "model-00001-of-00003.safetensors",
909
+ "vision_model.vision_tower.blocks.7.norm1.bias": "model-00001-of-00003.safetensors",
910
+ "vision_model.vision_tower.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
911
+ "vision_model.vision_tower.blocks.7.norm2.bias": "model-00001-of-00003.safetensors",
912
+ "vision_model.vision_tower.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
913
+ "vision_model.vision_tower.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
914
+ "vision_model.vision_tower.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
915
+ "vision_model.vision_tower.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
916
+ "vision_model.vision_tower.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
917
+ "vision_model.vision_tower.blocks.8.mlp.fc1.bias": "model-00001-of-00003.safetensors",
918
+ "vision_model.vision_tower.blocks.8.mlp.fc1.weight": "model-00001-of-00003.safetensors",
919
+ "vision_model.vision_tower.blocks.8.mlp.fc2.bias": "model-00001-of-00003.safetensors",
920
+ "vision_model.vision_tower.blocks.8.mlp.fc2.weight": "model-00001-of-00003.safetensors",
921
+ "vision_model.vision_tower.blocks.8.norm1.bias": "model-00001-of-00003.safetensors",
922
+ "vision_model.vision_tower.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
923
+ "vision_model.vision_tower.blocks.8.norm2.bias": "model-00001-of-00003.safetensors",
924
+ "vision_model.vision_tower.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
925
+ "vision_model.vision_tower.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
926
+ "vision_model.vision_tower.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
927
+ "vision_model.vision_tower.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
928
+ "vision_model.vision_tower.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
929
+ "vision_model.vision_tower.blocks.9.mlp.fc1.bias": "model-00001-of-00003.safetensors",
930
+ "vision_model.vision_tower.blocks.9.mlp.fc1.weight": "model-00001-of-00003.safetensors",
931
+ "vision_model.vision_tower.blocks.9.mlp.fc2.bias": "model-00001-of-00003.safetensors",
932
+ "vision_model.vision_tower.blocks.9.mlp.fc2.weight": "model-00001-of-00003.safetensors",
933
+ "vision_model.vision_tower.blocks.9.norm1.bias": "model-00001-of-00003.safetensors",
934
+ "vision_model.vision_tower.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
935
+ "vision_model.vision_tower.blocks.9.norm2.bias": "model-00001-of-00003.safetensors",
936
+ "vision_model.vision_tower.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
937
+ "vision_model.vision_tower.norm.bias": "model-00001-of-00003.safetensors",
938
+ "vision_model.vision_tower.norm.weight": "model-00001-of-00003.safetensors",
939
+ "vision_model.vision_tower.patch_embed.proj.bias": "model-00001-of-00003.safetensors",
940
+ "vision_model.vision_tower.patch_embed.proj.weight": "model-00001-of-00003.safetensors",
941
+ "vision_model.vision_tower.pos_embed": "model-00001-of-00003.safetensors"
942
+ }
943
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "background_color": [
3
+ 127,
4
+ 127,
5
+ 127
6
+ ],
7
+ "do_normalize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "VLMImageProcessor",
14
+ "image_size": 384,
15
+ "image_std": [
16
+ 0.5,
17
+ 0.5,
18
+ 0.5
19
+ ],
20
+ "min_size": 14,
21
+ "processor_class": "VLChatProcessor",
22
+ "rescale_factor": 0.00392156862745098
23
+ }
processor_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_special_token": false,
3
+ "ignore_id": -100,
4
+ "image_end_tag": "<end_of_image>",
5
+ "image_start_tag": "<begin_of_image>",
6
+ "image_tag": "<image_placeholder>",
7
+ "mask_prompt": true,
8
+ "num_image_tokens": 576,
9
+ "pad_tag": "<\uff5c\u2581pad\u2581\uff5c>",
10
+ "processor_class": "VLChatProcessor",
11
+ "sft_format": "deepseek"
12
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<image_placeholder>",
4
+ "<patch_placeholder>",
5
+ "<|ref|>",
6
+ "<|/ref|>",
7
+ "<|det|>",
8
+ "<|/det|>",
9
+ "<|grounding|>",
10
+ "<|User|>",
11
+ "<|Assistant|>"
12
+ ],
13
+ "bos_token": {
14
+ "content": "<｜begin▁of▁sentence｜>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "<｜end▁of▁sentence｜>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "pad_token": {
28
+ "content": "<｜▁pad▁｜>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff