sohamgovande commited on
Commit
955923d
·
verified ·
1 Parent(s): e80ddac

Training in progress, step 57

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
adapter_config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-VL-7B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 16,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 8,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "layers.15.mlp.gate_proj",
28
+ "layers.17.mlp.up_proj",
29
+ "layers.25.mlp.up_proj",
30
+ "layers.4.mlp.down_proj",
31
+ "layers.20.mlp.gate_proj",
32
+ "k_proj",
33
+ "q_proj",
34
+ "layers.12.mlp.gate_proj",
35
+ "layers.26.mlp.gate_proj",
36
+ "layers.9.mlp.gate_proj",
37
+ "layers.4.mlp.up_proj",
38
+ "layers.27.mlp.down_proj",
39
+ "layers.13.mlp.down_proj",
40
+ "layers.20.mlp.down_proj",
41
+ "layers.9.mlp.down_proj",
42
+ "layers.15.mlp.up_proj",
43
+ "layers.18.mlp.up_proj",
44
+ "layers.19.mlp.down_proj",
45
+ "layers.6.mlp.down_proj",
46
+ "layers.5.mlp.down_proj",
47
+ "layers.2.mlp.gate_proj",
48
+ "layers.19.mlp.up_proj",
49
+ "layers.5.mlp.up_proj",
50
+ "layers.0.mlp.down_proj",
51
+ "layers.1.mlp.up_proj",
52
+ "layers.16.mlp.up_proj",
53
+ "layers.18.mlp.down_proj",
54
+ "layers.17.mlp.gate_proj",
55
+ "layers.0.mlp.up_proj",
56
+ "layers.3.mlp.up_proj",
57
+ "layers.21.mlp.down_proj",
58
+ "layers.15.mlp.down_proj",
59
+ "layers.14.mlp.gate_proj",
60
+ "layers.2.mlp.up_proj",
61
+ "layers.3.mlp.gate_proj",
62
+ "layers.20.mlp.up_proj",
63
+ "layers.2.mlp.down_proj",
64
+ "layers.10.mlp.up_proj",
65
+ "layers.16.mlp.down_proj",
66
+ "layers.9.mlp.up_proj",
67
+ "layers.22.mlp.gate_proj",
68
+ "layers.6.mlp.gate_proj",
69
+ "layers.6.mlp.up_proj",
70
+ "layers.8.mlp.down_proj",
71
+ "layers.21.mlp.up_proj",
72
+ "layers.27.mlp.up_proj",
73
+ "layers.17.mlp.down_proj",
74
+ "layers.25.mlp.down_proj",
75
+ "layers.24.mlp.down_proj",
76
+ "v_proj",
77
+ "layers.13.mlp.up_proj",
78
+ "layers.14.mlp.down_proj",
79
+ "layers.18.mlp.gate_proj",
80
+ "layers.7.mlp.gate_proj",
81
+ "layers.4.mlp.gate_proj",
82
+ "layers.13.mlp.gate_proj",
83
+ "layers.11.mlp.up_proj",
84
+ "layers.12.mlp.down_proj",
85
+ "layers.11.mlp.gate_proj",
86
+ "layers.27.mlp.gate_proj",
87
+ "layers.16.mlp.gate_proj",
88
+ "layers.23.mlp.down_proj",
89
+ "layers.1.mlp.gate_proj",
90
+ "layers.7.mlp.down_proj",
91
+ "layers.10.mlp.gate_proj",
92
+ "layers.22.mlp.down_proj",
93
+ "layers.25.mlp.gate_proj",
94
+ "layers.5.mlp.gate_proj",
95
+ "layers.21.mlp.gate_proj",
96
+ "layers.12.mlp.up_proj",
97
+ "o_proj",
98
+ "layers.1.mlp.down_proj",
99
+ "layers.11.mlp.down_proj",
100
+ "layers.26.mlp.down_proj",
101
+ "layers.3.mlp.down_proj",
102
+ "layers.8.mlp.gate_proj",
103
+ "layers.19.mlp.gate_proj",
104
+ "layers.23.mlp.gate_proj",
105
+ "layers.22.mlp.up_proj",
106
+ "layers.24.mlp.gate_proj",
107
+ "layers.14.mlp.up_proj",
108
+ "layers.7.mlp.up_proj",
109
+ "layers.0.mlp.gate_proj",
110
+ "layers.10.mlp.down_proj",
111
+ "layers.26.mlp.up_proj",
112
+ "layers.8.mlp.up_proj",
113
+ "layers.23.mlp.up_proj",
114
+ "layers.24.mlp.up_proj"
115
+ ],
116
+ "task_type": "CAUSAL_LM",
117
+ "trainable_token_indices": null,
118
+ "use_dora": false,
119
+ "use_rslora": false
120
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:730c94f88587dbf10defddf7d8fcd7df397a5fed511d1b9f403e5b81c9f431cc
3
+ size 80792096
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "padding_side": "right",
206
+ "processor_class": "Qwen2_5_VLProcessor",
207
+ "split_special_tokens": false,
208
+ "tokenizer_class": "Qwen2Tokenizer",
209
+ "unk_token": null
210
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 57, "loss": 0.6931, "accuracy": 0.0, "lr": 0.0, "epoch": 0.050314465408805034, "percentage": 1.75, "elapsed_time": "0:00:04", "remaining_time": "0:04:08"}
2
+ {"current_steps": 2, "total_steps": 57, "loss": 0.6931, "accuracy": 0.0, "lr": 8.333333333333333e-07, "epoch": 0.10062893081761007, "percentage": 3.51, "elapsed_time": "0:00:08", "remaining_time": "0:03:41"}
3
+ {"current_steps": 3, "total_steps": 57, "loss": 0.6751, "accuracy": 0.75, "lr": 1.6666666666666667e-06, "epoch": 0.1509433962264151, "percentage": 5.26, "elapsed_time": "0:00:11", "remaining_time": "0:03:29"}
4
+ {"current_steps": 4, "total_steps": 57, "loss": 0.6662, "accuracy": 0.625, "lr": 2.5e-06, "epoch": 0.20125786163522014, "percentage": 7.02, "elapsed_time": "0:00:15", "remaining_time": "0:03:23"}
5
+ {"current_steps": 5, "total_steps": 57, "loss": 0.6674, "accuracy": 0.75, "lr": 3.3333333333333333e-06, "epoch": 0.25157232704402516, "percentage": 8.77, "elapsed_time": "0:00:18", "remaining_time": "0:03:17"}
6
+ {"current_steps": 6, "total_steps": 57, "loss": 0.699, "accuracy": 0.625, "lr": 4.166666666666667e-06, "epoch": 0.3018867924528302, "percentage": 10.53, "elapsed_time": "0:00:22", "remaining_time": "0:03:14"}
7
+ {"current_steps": 7, "total_steps": 57, "loss": 0.7046, "accuracy": 0.25, "lr": 5e-06, "epoch": 0.3522012578616352, "percentage": 12.28, "elapsed_time": "0:00:26", "remaining_time": "0:03:11"}
8
+ {"current_steps": 8, "total_steps": 57, "loss": 0.701, "accuracy": 0.375, "lr": 4.995258321842611e-06, "epoch": 0.4025157232704403, "percentage": 14.04, "elapsed_time": "0:00:30", "remaining_time": "0:03:06"}
9
+ {"current_steps": 9, "total_steps": 57, "loss": 0.6906, "accuracy": 0.75, "lr": 4.98105127417984e-06, "epoch": 0.4528301886792453, "percentage": 15.79, "elapsed_time": "0:00:34", "remaining_time": "0:03:02"}
10
+ {"current_steps": 10, "total_steps": 57, "loss": 0.7101, "accuracy": 0.5, "lr": 4.957432749209755e-06, "epoch": 0.5031446540880503, "percentage": 17.54, "elapsed_time": "0:00:37", "remaining_time": "0:02:55"}
11
+ {"current_steps": 11, "total_steps": 57, "loss": 0.6873, "accuracy": 0.5, "lr": 4.9244923400875245e-06, "epoch": 0.5534591194968553, "percentage": 19.3, "elapsed_time": "0:00:40", "remaining_time": "0:02:49"}
12
+ {"current_steps": 12, "total_steps": 57, "loss": 0.6699, "accuracy": 0.625, "lr": 4.882355001067892e-06, "epoch": 0.6037735849056604, "percentage": 21.05, "elapsed_time": "0:00:44", "remaining_time": "0:02:45"}
13
+ {"current_steps": 13, "total_steps": 57, "loss": 0.6849, "accuracy": 0.5, "lr": 4.83118057351089e-06, "epoch": 0.6540880503144654, "percentage": 22.81, "elapsed_time": "0:00:47", "remaining_time": "0:02:41"}
14
+ {"current_steps": 14, "total_steps": 57, "loss": 0.7072, "accuracy": 0.375, "lr": 4.771163179548809e-06, "epoch": 0.7044025157232704, "percentage": 24.56, "elapsed_time": "0:00:51", "remaining_time": "0:02:38"}
15
+ {"current_steps": 15, "total_steps": 57, "loss": 0.7184, "accuracy": 0.25, "lr": 4.702530485714462e-06, "epoch": 0.7547169811320755, "percentage": 26.32, "elapsed_time": "0:00:55", "remaining_time": "0:02:34"}
16
+ {"current_steps": 16, "total_steps": 57, "loss": 0.7213, "accuracy": 0.25, "lr": 4.625542839324036e-06, "epoch": 0.8050314465408805, "percentage": 28.07, "elapsed_time": "0:00:58", "remaining_time": "0:02:30"}
17
+ {"current_steps": 17, "total_steps": 57, "loss": 0.6863, "accuracy": 0.625, "lr": 4.540492280890555e-06, "epoch": 0.8553459119496856, "percentage": 29.82, "elapsed_time": "0:01:02", "remaining_time": "0:02:27"}
18
+ {"current_steps": 18, "total_steps": 57, "loss": 0.6752, "accuracy": 0.75, "lr": 4.447701436314176e-06, "epoch": 0.9056603773584906, "percentage": 31.58, "elapsed_time": "0:01:05", "remaining_time": "0:02:22"}
19
+ {"current_steps": 19, "total_steps": 57, "loss": 0.7061, "accuracy": 0.375, "lr": 4.3475222930516484e-06, "epoch": 0.9559748427672956, "percentage": 33.33, "elapsed_time": "0:01:09", "remaining_time": "0:02:19"}
20
+ {"current_steps": 20, "total_steps": 57, "loss": 0.6147, "accuracy": 0.4285714626312256, "lr": 4.240334864907317e-06, "epoch": 1.0, "percentage": 35.09, "elapsed_time": "0:01:12", "remaining_time": "0:02:14"}
21
+ {"current_steps": 21, "total_steps": 57, "loss": 0.6785, "accuracy": 0.625, "lr": 4.126545750510605e-06, "epoch": 1.050314465408805, "percentage": 36.84, "elapsed_time": "0:01:16", "remaining_time": "0:02:10"}
22
+ {"current_steps": 22, "total_steps": 57, "loss": 0.6693, "accuracy": 0.75, "lr": 4.006586590948141e-06, "epoch": 1.10062893081761, "percentage": 38.6, "elapsed_time": "0:01:19", "remaining_time": "0:02:07"}
23
+ {"current_steps": 23, "total_steps": 57, "loss": 0.6842, "accuracy": 0.375, "lr": 3.880912432401265e-06, "epoch": 1.150943396226415, "percentage": 40.35, "elapsed_time": "0:01:23", "remaining_time": "0:02:03"}
24
+ {"current_steps": 24, "total_steps": 57, "loss": 0.6886, "accuracy": 0.5, "lr": 3.7500000000000005e-06, "epoch": 1.20125786163522, "percentage": 42.11, "elapsed_time": "0:01:27", "remaining_time": "0:01:59"}
25
+ {"current_steps": 25, "total_steps": 57, "loss": 0.713, "accuracy": 0.25, "lr": 3.6143458894413463e-06, "epoch": 1.251572327044025, "percentage": 43.86, "elapsed_time": "0:01:30", "remaining_time": "0:01:56"}
26
+ {"current_steps": 26, "total_steps": 57, "loss": 0.686, "accuracy": 0.625, "lr": 3.4744646832316985e-06, "epoch": 1.3018867924528301, "percentage": 45.61, "elapsed_time": "0:01:35", "remaining_time": "0:01:53"}
27
+ {"current_steps": 27, "total_steps": 57, "loss": 0.7063, "accuracy": 0.375, "lr": 3.3308869986991493e-06, "epoch": 1.3522012578616351, "percentage": 47.37, "elapsed_time": "0:01:38", "remaining_time": "0:01:49"}
28
+ {"current_steps": 28, "total_steps": 57, "loss": 0.6937, "accuracy": 0.375, "lr": 3.184157475180208e-06, "epoch": 1.4025157232704402, "percentage": 49.12, "elapsed_time": "0:01:42", "remaining_time": "0:01:46"}
29
+ {"current_steps": 29, "total_steps": 57, "loss": 0.6864, "accuracy": 0.375, "lr": 3.0348327080162438e-06, "epoch": 1.4528301886792452, "percentage": 50.88, "elapsed_time": "0:01:46", "remaining_time": "0:01:42"}
30
+ {"current_steps": 30, "total_steps": 57, "loss": 0.6785, "accuracy": 0.625, "lr": 2.883479137196714e-06, "epoch": 1.5031446540880502, "percentage": 52.63, "elapsed_time": "0:01:49", "remaining_time": "0:01:38"}
31
+ {"current_steps": 31, "total_steps": 57, "loss": 0.684, "accuracy": 0.5, "lr": 2.730670898658255e-06, "epoch": 1.5534591194968552, "percentage": 54.39, "elapsed_time": "0:01:53", "remaining_time": "0:01:35"}
32
+ {"current_steps": 32, "total_steps": 57, "loss": 0.6863, "accuracy": 0.5, "lr": 2.576987646390426e-06, "epoch": 1.6037735849056602, "percentage": 56.14, "elapsed_time": "0:01:56", "remaining_time": "0:01:31"}
33
+ {"current_steps": 33, "total_steps": 57, "loss": 0.7014, "accuracy": 0.375, "lr": 2.4230123536095746e-06, "epoch": 1.6540880503144653, "percentage": 57.89, "elapsed_time": "0:02:00", "remaining_time": "0:01:27"}
34
+ {"current_steps": 34, "total_steps": 57, "loss": 0.7397, "accuracy": 0.25, "lr": 2.269329101341745e-06, "epoch": 1.7044025157232703, "percentage": 59.65, "elapsed_time": "0:02:03", "remaining_time": "0:01:23"}
35
+ {"current_steps": 35, "total_steps": 57, "loss": 0.7225, "accuracy": 0.25, "lr": 2.1165208628032863e-06, "epoch": 1.7547169811320755, "percentage": 61.4, "elapsed_time": "0:02:07", "remaining_time": "0:01:20"}
36
+ {"current_steps": 36, "total_steps": 57, "loss": 0.6884, "accuracy": 0.75, "lr": 1.965167291983757e-06, "epoch": 1.8050314465408805, "percentage": 63.16, "elapsed_time": "0:02:11", "remaining_time": "0:01:16"}
37
+ {"current_steps": 37, "total_steps": 57, "loss": 0.6894, "accuracy": 0.625, "lr": 1.8158425248197931e-06, "epoch": 1.8553459119496856, "percentage": 64.91, "elapsed_time": "0:02:14", "remaining_time": "0:01:12"}
38
+ {"current_steps": 38, "total_steps": 57, "loss": 0.7, "accuracy": 0.375, "lr": 1.6691130013008514e-06, "epoch": 1.9056603773584906, "percentage": 66.67, "elapsed_time": "0:02:17", "remaining_time": "0:01:08"}
39
+ {"current_steps": 39, "total_steps": 57, "loss": 0.6984, "accuracy": 0.375, "lr": 1.5255353167683017e-06, "epoch": 1.9559748427672956, "percentage": 68.42, "elapsed_time": "0:02:21", "remaining_time": "0:01:05"}
40
+ {"current_steps": 40, "total_steps": 57, "loss": 0.5913, "accuracy": 0.7142857313156128, "lr": 1.3856541105586545e-06, "epoch": 2.0, "percentage": 70.18, "elapsed_time": "0:02:24", "remaining_time": "0:01:01"}
41
+ {"current_steps": 41, "total_steps": 57, "loss": 0.6709, "accuracy": 0.625, "lr": 1.2500000000000007e-06, "epoch": 2.050314465408805, "percentage": 71.93, "elapsed_time": "0:02:28", "remaining_time": "0:00:57"}
42
+ {"current_steps": 42, "total_steps": 57, "loss": 0.7154, "accuracy": 0.375, "lr": 1.1190875675987355e-06, "epoch": 2.10062893081761, "percentage": 73.68, "elapsed_time": "0:02:31", "remaining_time": "0:00:54"}
43
+ {"current_steps": 43, "total_steps": 57, "loss": 0.7073, "accuracy": 0.5, "lr": 9.934134090518593e-07, "epoch": 2.150943396226415, "percentage": 75.44, "elapsed_time": "0:02:35", "remaining_time": "0:00:50"}
44
+ {"current_steps": 44, "total_steps": 57, "loss": 0.6837, "accuracy": 0.75, "lr": 8.734542494893955e-07, "epoch": 2.20125786163522, "percentage": 77.19, "elapsed_time": "0:02:39", "remaining_time": "0:00:47"}
45
+ {"current_steps": 45, "total_steps": 57, "loss": 0.6766, "accuracy": 0.875, "lr": 7.596651350926837e-07, "epoch": 2.251572327044025, "percentage": 78.95, "elapsed_time": "0:02:42", "remaining_time": "0:00:43"}
46
+ {"current_steps": 46, "total_steps": 57, "loss": 0.7142, "accuracy": 0.375, "lr": 6.524777069483526e-07, "epoch": 2.30188679245283, "percentage": 80.7, "elapsed_time": "0:02:46", "remaining_time": "0:00:39"}
47
+ {"current_steps": 47, "total_steps": 57, "loss": 0.7144, "accuracy": 0.5, "lr": 5.522985636858238e-07, "epoch": 2.352201257861635, "percentage": 82.46, "elapsed_time": "0:02:49", "remaining_time": "0:00:36"}
48
+ {"current_steps": 48, "total_steps": 57, "loss": 0.6922, "accuracy": 0.625, "lr": 4.5950771910944603e-07, "epoch": 2.40251572327044, "percentage": 84.21, "elapsed_time": "0:02:53", "remaining_time": "0:00:32"}
49
+ {"current_steps": 49, "total_steps": 57, "loss": 0.6911, "accuracy": 0.5, "lr": 3.7445716067596506e-07, "epoch": 2.452830188679245, "percentage": 85.96, "elapsed_time": "0:02:57", "remaining_time": "0:00:28"}
50
+ {"current_steps": 50, "total_steps": 57, "loss": 0.7054, "accuracy": 0.5, "lr": 2.9746951428553884e-07, "epoch": 2.50314465408805, "percentage": 87.72, "elapsed_time": "0:03:01", "remaining_time": "0:00:25"}
51
+ {"current_steps": 51, "total_steps": 57, "loss": 0.6727, "accuracy": 0.5, "lr": 2.2883682045119066e-07, "epoch": 2.5534591194968552, "percentage": 89.47, "elapsed_time": "0:03:04", "remaining_time": "0:00:21"}
52
+ {"current_steps": 52, "total_steps": 57, "loss": 0.6728, "accuracy": 0.625, "lr": 1.6881942648911077e-07, "epoch": 2.6037735849056602, "percentage": 91.23, "elapsed_time": "0:03:08", "remaining_time": "0:00:18"}
53
+ {"current_steps": 53, "total_steps": 57, "loss": 0.6823, "accuracy": 0.5, "lr": 1.1764499893210879e-07, "epoch": 2.6540880503144653, "percentage": 92.98, "elapsed_time": "0:03:11", "remaining_time": "0:00:14"}
54
+ {"current_steps": 54, "total_steps": 57, "loss": 0.674, "accuracy": 0.625, "lr": 7.550765991247655e-08, "epoch": 2.7044025157232703, "percentage": 94.74, "elapsed_time": "0:03:15", "remaining_time": "0:00:10"}
55
+ {"current_steps": 55, "total_steps": 57, "loss": 0.7088, "accuracy": 0.375, "lr": 4.256725079024554e-08, "epoch": 2.7547169811320753, "percentage": 96.49, "elapsed_time": "0:03:19", "remaining_time": "0:00:07"}
56
+ {"current_steps": 56, "total_steps": 57, "loss": 0.6993, "accuracy": 0.625, "lr": 1.8948725820160663e-08, "epoch": 2.8050314465408803, "percentage": 98.25, "elapsed_time": "0:03:22", "remaining_time": "0:00:03"}
57
+ {"current_steps": 57, "total_steps": 57, "loss": 0.7055, "accuracy": 0.25, "lr": 4.74167815738974e-09, "epoch": 2.8553459119496853, "percentage": 100.0, "elapsed_time": "0:03:26", "remaining_time": "0:00:00"}
58
+ {"current_steps": 57, "total_steps": 57, "epoch": 2.8553459119496853, "percentage": 100.0, "elapsed_time": "0:03:27", "remaining_time": "0:00:00"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e06ca6a7637f82f71dafdab216326cb8fb0b3247e8f3b394dad4f68e61a42a3a
3
+ size 5752
vocab.json ADDED
The diff for this file is too large to render. See raw diff