Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- checkpoint-99000/README.md +202 -0
- checkpoint-99000/adapter_config.json +39 -0
- checkpoint-99000/adapter_model.safetensors +3 -0
- checkpoint-99000/chat_template.jinja +93 -0
- checkpoint-99000/optimizer.pt +3 -0
- checkpoint-99000/rng_state.pth +3 -0
- checkpoint-99000/scheduler.pt +3 -0
- checkpoint-99000/special_tokens_map.json +17 -0
- checkpoint-99000/tokenizer.json +3 -0
- checkpoint-99000/tokenizer_config.json +2063 -0
- checkpoint-99000/trainer_state.json +1763 -0
- checkpoint-99000/training_args.bin +3 -0
.gitattributes
CHANGED
@@ -239,3 +239,4 @@ checkpoint-97000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
239 |
checkpoint-97500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
240 |
checkpoint-98000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
241 |
checkpoint-98500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
239 |
checkpoint-97500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
240 |
checkpoint-98000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
241 |
checkpoint-98500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
242 |
+
checkpoint-99000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-99000/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: meta-llama/Llama-3.2-1B-Instruct
|
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 0.15.2
|
checkpoint-99000/adapter_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Llama-3.2-1B-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": 128,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0.05,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": null,
|
22 |
+
"peft_type": "LORA",
|
23 |
+
"r": 64,
|
24 |
+
"rank_pattern": {},
|
25 |
+
"revision": null,
|
26 |
+
"target_modules": [
|
27 |
+
"v_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"o_proj",
|
30 |
+
"down_proj",
|
31 |
+
"q_proj",
|
32 |
+
"up_proj",
|
33 |
+
"k_proj"
|
34 |
+
],
|
35 |
+
"task_type": "CAUSAL_LM",
|
36 |
+
"trainable_token_indices": null,
|
37 |
+
"use_dora": false,
|
38 |
+
"use_rslora": false
|
39 |
+
}
|
checkpoint-99000/adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c4076b4eb36a40c9cc9416082e94c30e6b76523d31a813930a69b9f9f7a5022
|
3 |
+
size 180385008
|
checkpoint-99000/chat_template.jinja
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{{- bos_token }}
|
2 |
+
{%- if custom_tools is defined %}
|
3 |
+
{%- set tools = custom_tools %}
|
4 |
+
{%- endif %}
|
5 |
+
{%- if not tools_in_user_message is defined %}
|
6 |
+
{%- set tools_in_user_message = true %}
|
7 |
+
{%- endif %}
|
8 |
+
{%- if not date_string is defined %}
|
9 |
+
{%- if strftime_now is defined %}
|
10 |
+
{%- set date_string = strftime_now("%d %b %Y") %}
|
11 |
+
{%- else %}
|
12 |
+
{%- set date_string = "26 Jul 2024" %}
|
13 |
+
{%- endif %}
|
14 |
+
{%- endif %}
|
15 |
+
{%- if not tools is defined %}
|
16 |
+
{%- set tools = none %}
|
17 |
+
{%- endif %}
|
18 |
+
|
19 |
+
{#- This block extracts the system message, so we can slot it into the right place. #}
|
20 |
+
{%- if messages[0]['role'] == 'system' %}
|
21 |
+
{%- set system_message = messages[0]['content']|trim %}
|
22 |
+
{%- set messages = messages[1:] %}
|
23 |
+
{%- else %}
|
24 |
+
{%- set system_message = "" %}
|
25 |
+
{%- endif %}
|
26 |
+
|
27 |
+
{#- System message #}
|
28 |
+
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
29 |
+
{%- if tools is not none %}
|
30 |
+
{{- "Environment: ipython\n" }}
|
31 |
+
{%- endif %}
|
32 |
+
{{- "Cutting Knowledge Date: December 2023\n" }}
|
33 |
+
{{- "Today Date: " + date_string + "\n\n" }}
|
34 |
+
{%- if tools is not none and not tools_in_user_message %}
|
35 |
+
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
36 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
37 |
+
{{- "Do not use variables.\n\n" }}
|
38 |
+
{%- for t in tools %}
|
39 |
+
{{- t | tojson(indent=4) }}
|
40 |
+
{{- "\n\n" }}
|
41 |
+
{%- endfor %}
|
42 |
+
{%- endif %}
|
43 |
+
{{- system_message }}
|
44 |
+
{{- "<|eot_id|>" }}
|
45 |
+
|
46 |
+
{#- Custom tools are passed in a user message with some extra guidance #}
|
47 |
+
{%- if tools_in_user_message and not tools is none %}
|
48 |
+
{#- Extract the first user message so we can plug it in here #}
|
49 |
+
{%- if messages | length != 0 %}
|
50 |
+
{%- set first_user_message = messages[0]['content']|trim %}
|
51 |
+
{%- set messages = messages[1:] %}
|
52 |
+
{%- else %}
|
53 |
+
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
54 |
+
{%- endif %}
|
55 |
+
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
56 |
+
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
57 |
+
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
58 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
59 |
+
{{- "Do not use variables.\n\n" }}
|
60 |
+
{%- for t in tools %}
|
61 |
+
{{- t | tojson(indent=4) }}
|
62 |
+
{{- "\n\n" }}
|
63 |
+
{%- endfor %}
|
64 |
+
{{- first_user_message + "<|eot_id|>"}}
|
65 |
+
{%- endif %}
|
66 |
+
|
67 |
+
{%- for message in messages %}
|
68 |
+
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
69 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
70 |
+
{%- elif 'tool_calls' in message %}
|
71 |
+
{%- if not message.tool_calls|length == 1 %}
|
72 |
+
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
73 |
+
{%- endif %}
|
74 |
+
{%- set tool_call = message.tool_calls[0].function %}
|
75 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
76 |
+
{{- '{"name": "' + tool_call.name + '", ' }}
|
77 |
+
{{- '"parameters": ' }}
|
78 |
+
{{- tool_call.arguments | tojson }}
|
79 |
+
{{- "}" }}
|
80 |
+
{{- "<|eot_id|>" }}
|
81 |
+
{%- elif message.role == "tool" or message.role == "ipython" %}
|
82 |
+
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
83 |
+
{%- if message.content is mapping or message.content is iterable %}
|
84 |
+
{{- message.content | tojson }}
|
85 |
+
{%- else %}
|
86 |
+
{{- message.content }}
|
87 |
+
{%- endif %}
|
88 |
+
{{- "<|eot_id|>" }}
|
89 |
+
{%- endif %}
|
90 |
+
{%- endfor %}
|
91 |
+
{%- if add_generation_prompt %}
|
92 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
93 |
+
{%- endif %}
|
checkpoint-99000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03e418b3d947d4424de1f8bc2b22aaedfb13efb0e674155b2d0aeaed573a13f3
|
3 |
+
size 92432402
|
checkpoint-99000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ddfb3e9a25e57c2eb8b50db1c578ff2bdfa0f6aa66cc66dda2dfaefb6cf50fb
|
3 |
+
size 14244
|
checkpoint-99000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0b4c98851b5440f9e1c937ea9c04dafe25fe087e4539c638efe60b20eacdaa2
|
3 |
+
size 1064
|
checkpoint-99000/special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|eot_id|>"
|
17 |
+
}
|
checkpoint-99000/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90883524dbec2e8c465564ac46b4e5298235668a5cf8523690f06f45f51646fe
|
3 |
+
size 17210197
|
checkpoint-99000/tokenizer_config.json
ADDED
@@ -0,0 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"128000": {
|
4 |
+
"content": "<|begin_of_text|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"128002": {
|
20 |
+
"content": "<|reserved_special_token_0|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"128003": {
|
28 |
+
"content": "<|reserved_special_token_1|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128004": {
|
36 |
+
"content": "<|finetune_right_pad_id|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_2|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"128006": {
|
52 |
+
"content": "<|start_header_id|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"128007": {
|
60 |
+
"content": "<|end_header_id|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"128008": {
|
68 |
+
"content": "<|eom_id|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"128009": {
|
76 |
+
"content": "<|eot_id|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"128010": {
|
84 |
+
"content": "<|python_tag|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_3|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_4|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_5|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_6|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_7|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_8|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_9|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_10|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_11|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_12|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_13|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_14|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_15|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_16|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_17|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_18|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_19|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_20|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_21|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_22|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_23|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_24|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_25|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_26|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_27|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_28|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_29|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_30|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_31|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_32|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_33|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_34|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_35|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_36|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_37|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_38|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_39|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_40|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_41|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_42|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_43|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_44|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_45|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_46|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_47|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_48|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_49|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_50|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_51|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_52|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_53|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_54|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_55|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_56|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_57|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_58|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_59|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_60|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_61|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_62|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_63|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_64|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_65|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_66|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_67|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_68|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_69|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_70|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_71|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_72|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_73|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_74|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_75|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_76|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_77|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_78|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_79|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_80|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_81|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_82|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_83|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_84|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_85|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_86|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_87|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_88|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_89|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_90|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_91|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_92|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_93|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_94|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_95|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_96|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_97|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_98|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_99|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_100|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_101|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_102|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_103|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_104|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_105|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_106|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_107|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_108|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_109|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_110|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_111|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_112|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_113|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_114|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_115|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_116|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_117|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_118|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_119|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_120|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_121|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_122|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_123|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_124|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_125|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_126|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_127|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_128|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_129|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_130|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_131|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_132|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_133|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_134|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_135|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_136|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_137|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_138|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_139|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_140|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_141|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_142|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_143|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_144|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_145|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_146|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_147|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_148|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_149|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_150|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_151|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_152|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_153|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_154|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_155|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_156|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_157|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_158|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_159|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_160|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_161|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_162|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_163|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_164|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_165|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_166|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_167|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_168|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_169|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_170|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_171|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_172|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_173|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_174|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_175|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_176|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_177|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_178|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_179|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_180|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_181|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_182|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_183|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_184|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_185|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_186|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_187|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_188|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_189|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_190|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_191|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_192|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_193|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_194|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_195|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_196|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_197|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_198|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_199|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_200|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_201|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_202|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_203|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_204|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_205|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_206|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_207|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_208|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_209|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_210|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_211|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_212|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_213|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_214|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_215|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_216|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_217|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_218|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_219|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_220|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_221|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_222|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_223|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_224|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_225|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_226|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_227|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_228|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_229|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_230|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_231|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_232|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_233|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_234|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_235|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_236|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_237|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_238|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_239|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_240|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_241|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_242|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_243|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_244|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_245|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_246|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_247|>",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": false,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": true
|
2050 |
+
}
|
2051 |
+
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"clean_up_tokenization_spaces": true,
|
2054 |
+
"eos_token": "<|eot_id|>",
|
2055 |
+
"extra_special_tokens": {},
|
2056 |
+
"model_input_names": [
|
2057 |
+
"input_ids",
|
2058 |
+
"attention_mask"
|
2059 |
+
],
|
2060 |
+
"model_max_length": 131072,
|
2061 |
+
"pad_token": "<|eot_id|>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
2063 |
+
}
|
checkpoint-99000/trainer_state.json
ADDED
@@ -0,0 +1,1763 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": null,
|
3 |
+
"best_metric": null,
|
4 |
+
"best_model_checkpoint": null,
|
5 |
+
"epoch": 0.22670596236681026,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 99000,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 0.0009159836863305464,
|
14 |
+
"grad_norm": 3.5712358951568604,
|
15 |
+
"learning_rate": 0.0001596,
|
16 |
+
"loss": 1.5506,
|
17 |
+
"step": 400
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.0018319673726610928,
|
21 |
+
"grad_norm": 2.6055777072906494,
|
22 |
+
"learning_rate": 0.0001999999420964769,
|
23 |
+
"loss": 1.4925,
|
24 |
+
"step": 800
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.0027479510589916395,
|
28 |
+
"grad_norm": 2.598275899887085,
|
29 |
+
"learning_rate": 0.00019999968354149158,
|
30 |
+
"loss": 1.4543,
|
31 |
+
"step": 1200
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.0036639347453221857,
|
35 |
+
"grad_norm": 3.6462411880493164,
|
36 |
+
"learning_rate": 0.00019999921772856336,
|
37 |
+
"loss": 1.4282,
|
38 |
+
"step": 1600
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.004579918431652732,
|
42 |
+
"grad_norm": 3.534177780151367,
|
43 |
+
"learning_rate": 0.00019999854465865773,
|
44 |
+
"loss": 1.3997,
|
45 |
+
"step": 2000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.005495902117983279,
|
49 |
+
"grad_norm": 4.041103363037109,
|
50 |
+
"learning_rate": 0.00019999766433316963,
|
51 |
+
"loss": 1.4071,
|
52 |
+
"step": 2400
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.006411885804313826,
|
56 |
+
"grad_norm": 2.65792179107666,
|
57 |
+
"learning_rate": 0.0001999965767539236,
|
58 |
+
"loss": 1.3747,
|
59 |
+
"step": 2800
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.007327869490644371,
|
63 |
+
"grad_norm": 2.7183997631073,
|
64 |
+
"learning_rate": 0.0001999952819231738,
|
65 |
+
"loss": 1.3796,
|
66 |
+
"step": 3200
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.008243853176974918,
|
70 |
+
"grad_norm": 4.0687174797058105,
|
71 |
+
"learning_rate": 0.00019999377984360382,
|
72 |
+
"loss": 1.387,
|
73 |
+
"step": 3600
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.009159836863305465,
|
77 |
+
"grad_norm": 2.770643472671509,
|
78 |
+
"learning_rate": 0.00019999207051832687,
|
79 |
+
"loss": 1.3559,
|
80 |
+
"step": 4000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.010075820549636011,
|
84 |
+
"grad_norm": 2.8189332485198975,
|
85 |
+
"learning_rate": 0.00019999015395088566,
|
86 |
+
"loss": 1.3373,
|
87 |
+
"step": 4400
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.010991804235966558,
|
91 |
+
"grad_norm": 3.2458949089050293,
|
92 |
+
"learning_rate": 0.0001999880301452525,
|
93 |
+
"loss": 1.3498,
|
94 |
+
"step": 4800
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.011907787922297105,
|
98 |
+
"grad_norm": 2.921995162963867,
|
99 |
+
"learning_rate": 0.0001999856991058291,
|
100 |
+
"loss": 1.3519,
|
101 |
+
"step": 5200
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.012823771608627651,
|
105 |
+
"grad_norm": 2.910311460494995,
|
106 |
+
"learning_rate": 0.00019998316083744678,
|
107 |
+
"loss": 1.3468,
|
108 |
+
"step": 5600
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.013739755294958196,
|
112 |
+
"grad_norm": 2.994410753250122,
|
113 |
+
"learning_rate": 0.00019998041534536625,
|
114 |
+
"loss": 1.3274,
|
115 |
+
"step": 6000
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.014655738981288743,
|
119 |
+
"grad_norm": 2.5082335472106934,
|
120 |
+
"learning_rate": 0.00019997746263527785,
|
121 |
+
"loss": 1.3324,
|
122 |
+
"step": 6400
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.01557172266761929,
|
126 |
+
"grad_norm": 2.9452273845672607,
|
127 |
+
"learning_rate": 0.0001999743027133013,
|
128 |
+
"loss": 1.3379,
|
129 |
+
"step": 6800
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.016487706353949836,
|
133 |
+
"grad_norm": 2.3184399604797363,
|
134 |
+
"learning_rate": 0.0001999709355859858,
|
135 |
+
"loss": 1.324,
|
136 |
+
"step": 7200
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.017403690040280383,
|
140 |
+
"grad_norm": 2.8244330883026123,
|
141 |
+
"learning_rate": 0.00019996736126031,
|
142 |
+
"loss": 1.3279,
|
143 |
+
"step": 7600
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.01831967372661093,
|
147 |
+
"grad_norm": 2.5758519172668457,
|
148 |
+
"learning_rate": 0.00019996357974368204,
|
149 |
+
"loss": 1.312,
|
150 |
+
"step": 8000
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.019235657412941476,
|
154 |
+
"grad_norm": 2.689647674560547,
|
155 |
+
"learning_rate": 0.00019995959104393945,
|
156 |
+
"loss": 1.313,
|
157 |
+
"step": 8400
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.020151641099272023,
|
161 |
+
"grad_norm": 2.9180686473846436,
|
162 |
+
"learning_rate": 0.00019995539516934904,
|
163 |
+
"loss": 1.313,
|
164 |
+
"step": 8800
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.02106762478560257,
|
168 |
+
"grad_norm": 2.66694974899292,
|
169 |
+
"learning_rate": 0.00019995099212860725,
|
170 |
+
"loss": 1.3179,
|
171 |
+
"step": 9200
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.021983608471933116,
|
175 |
+
"grad_norm": 2.296940803527832,
|
176 |
+
"learning_rate": 0.0001999463819308397,
|
177 |
+
"loss": 1.3188,
|
178 |
+
"step": 9600
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.022899592158263662,
|
182 |
+
"grad_norm": 3.979454278945923,
|
183 |
+
"learning_rate": 0.00019994156458560147,
|
184 |
+
"loss": 1.3347,
|
185 |
+
"step": 10000
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.02381557584459421,
|
189 |
+
"grad_norm": 2.359060764312744,
|
190 |
+
"learning_rate": 0.00019993654010287687,
|
191 |
+
"loss": 1.3452,
|
192 |
+
"step": 10400
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.024731559530924756,
|
196 |
+
"grad_norm": 2.784097194671631,
|
197 |
+
"learning_rate": 0.00019993130849307956,
|
198 |
+
"loss": 1.3668,
|
199 |
+
"step": 10800
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.025647543217255302,
|
203 |
+
"grad_norm": 2.0763189792633057,
|
204 |
+
"learning_rate": 0.0001999258697670525,
|
205 |
+
"loss": 1.3175,
|
206 |
+
"step": 11200
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.026563526903585846,
|
210 |
+
"grad_norm": 2.903045415878296,
|
211 |
+
"learning_rate": 0.000199920223936068,
|
212 |
+
"loss": 1.3224,
|
213 |
+
"step": 11600
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.027479510589916392,
|
217 |
+
"grad_norm": 2.770756244659424,
|
218 |
+
"learning_rate": 0.00019991437101182747,
|
219 |
+
"loss": 1.3096,
|
220 |
+
"step": 12000
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.02839549427624694,
|
224 |
+
"grad_norm": 3.1364219188690186,
|
225 |
+
"learning_rate": 0.0001999083110064616,
|
226 |
+
"loss": 1.3298,
|
227 |
+
"step": 12400
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.029311477962577485,
|
231 |
+
"grad_norm": 3.2954201698303223,
|
232 |
+
"learning_rate": 0.00019990204393253026,
|
233 |
+
"loss": 1.3198,
|
234 |
+
"step": 12800
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.030227461648908032,
|
238 |
+
"grad_norm": 5.423952579498291,
|
239 |
+
"learning_rate": 0.00019989556980302254,
|
240 |
+
"loss": 1.3087,
|
241 |
+
"step": 13200
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.03114344533523858,
|
245 |
+
"grad_norm": 2.3389499187469482,
|
246 |
+
"learning_rate": 0.00019988888863135658,
|
247 |
+
"loss": 1.3093,
|
248 |
+
"step": 13600
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.03205942902156913,
|
252 |
+
"grad_norm": 2.3693130016326904,
|
253 |
+
"learning_rate": 0.00019988200043137973,
|
254 |
+
"loss": 1.306,
|
255 |
+
"step": 14000
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.03297541270789967,
|
259 |
+
"grad_norm": 2.584962844848633,
|
260 |
+
"learning_rate": 0.00019987490521736833,
|
261 |
+
"loss": 1.295,
|
262 |
+
"step": 14400
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.03389139639423022,
|
266 |
+
"grad_norm": 3.4960484504699707,
|
267 |
+
"learning_rate": 0.0001998676030040279,
|
268 |
+
"loss": 1.3255,
|
269 |
+
"step": 14800
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.034807380080560765,
|
273 |
+
"grad_norm": 5.452722072601318,
|
274 |
+
"learning_rate": 0.0001998600938064928,
|
275 |
+
"loss": 1.2998,
|
276 |
+
"step": 15200
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.03572336376689131,
|
280 |
+
"grad_norm": 2.527163028717041,
|
281 |
+
"learning_rate": 0.00019985237764032657,
|
282 |
+
"loss": 1.2932,
|
283 |
+
"step": 15600
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.03663934745322186,
|
287 |
+
"grad_norm": 3.5106911659240723,
|
288 |
+
"learning_rate": 0.0001998444545215216,
|
289 |
+
"loss": 1.3189,
|
290 |
+
"step": 16000
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.0375553311395524,
|
294 |
+
"grad_norm": 2.078429698944092,
|
295 |
+
"learning_rate": 0.0001998363244664992,
|
296 |
+
"loss": 1.3213,
|
297 |
+
"step": 16400
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.03847131482588295,
|
301 |
+
"grad_norm": 3.225316047668457,
|
302 |
+
"learning_rate": 0.00019982798749210965,
|
303 |
+
"loss": 1.2817,
|
304 |
+
"step": 16800
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.039387298512213495,
|
308 |
+
"grad_norm": 3.7959091663360596,
|
309 |
+
"learning_rate": 0.00019981944361563203,
|
310 |
+
"loss": 1.3254,
|
311 |
+
"step": 17200
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.040303282198544045,
|
315 |
+
"grad_norm": 2.8166396617889404,
|
316 |
+
"learning_rate": 0.00019981069285477429,
|
317 |
+
"loss": 1.2932,
|
318 |
+
"step": 17600
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.04121926588487459,
|
322 |
+
"grad_norm": 3.156550645828247,
|
323 |
+
"learning_rate": 0.0001998017352276731,
|
324 |
+
"loss": 1.33,
|
325 |
+
"step": 18000
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.04213524957120514,
|
329 |
+
"grad_norm": 2.330085277557373,
|
330 |
+
"learning_rate": 0.0001997925707528939,
|
331 |
+
"loss": 1.3186,
|
332 |
+
"step": 18400
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.04305123325753568,
|
336 |
+
"grad_norm": 3.9666330814361572,
|
337 |
+
"learning_rate": 0.0001997831994494309,
|
338 |
+
"loss": 1.314,
|
339 |
+
"step": 18800
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.04396721694386623,
|
343 |
+
"grad_norm": 3.022580146789551,
|
344 |
+
"learning_rate": 0.00019977362133670692,
|
345 |
+
"loss": 1.3444,
|
346 |
+
"step": 19200
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.044883200630196775,
|
350 |
+
"grad_norm": 4.415026664733887,
|
351 |
+
"learning_rate": 0.0001997638364345734,
|
352 |
+
"loss": 1.3019,
|
353 |
+
"step": 19600
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.045799184316527325,
|
357 |
+
"grad_norm": 2.2941715717315674,
|
358 |
+
"learning_rate": 0.00019975384476331035,
|
359 |
+
"loss": 1.3267,
|
360 |
+
"step": 20000
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.04671516800285787,
|
364 |
+
"grad_norm": 2.7769296169281006,
|
365 |
+
"learning_rate": 0.0001997436463436265,
|
366 |
+
"loss": 1.2882,
|
367 |
+
"step": 20400
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.04763115168918842,
|
371 |
+
"grad_norm": 2.3512470722198486,
|
372 |
+
"learning_rate": 0.00019973324119665882,
|
373 |
+
"loss": 1.3305,
|
374 |
+
"step": 20800
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.04854713537551896,
|
378 |
+
"grad_norm": 3.1230602264404297,
|
379 |
+
"learning_rate": 0.00019972262934397293,
|
380 |
+
"loss": 1.3018,
|
381 |
+
"step": 21200
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.04946311906184951,
|
385 |
+
"grad_norm": 3.0036442279815674,
|
386 |
+
"learning_rate": 0.00019971181080756279,
|
387 |
+
"loss": 1.2998,
|
388 |
+
"step": 21600
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.050379102748180055,
|
392 |
+
"grad_norm": 11.243963241577148,
|
393 |
+
"learning_rate": 0.00019970078560985078,
|
394 |
+
"loss": 1.3189,
|
395 |
+
"step": 22000
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.051295086434510605,
|
399 |
+
"grad_norm": 2.546957015991211,
|
400 |
+
"learning_rate": 0.0001996895537736875,
|
401 |
+
"loss": 1.3066,
|
402 |
+
"step": 22400
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.05221107012084115,
|
406 |
+
"grad_norm": 2.777229070663452,
|
407 |
+
"learning_rate": 0.00019967811532235196,
|
408 |
+
"loss": 1.2995,
|
409 |
+
"step": 22800
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.05312705380717169,
|
413 |
+
"grad_norm": 2.9132065773010254,
|
414 |
+
"learning_rate": 0.00019966647027955134,
|
415 |
+
"loss": 1.3097,
|
416 |
+
"step": 23200
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.05404303749350224,
|
420 |
+
"grad_norm": 3.6997904777526855,
|
421 |
+
"learning_rate": 0.00019965461866942093,
|
422 |
+
"loss": 1.2968,
|
423 |
+
"step": 23600
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.054959021179832784,
|
427 |
+
"grad_norm": 3.026538133621216,
|
428 |
+
"learning_rate": 0.0001996425605165243,
|
429 |
+
"loss": 1.3492,
|
430 |
+
"step": 24000
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.055875004866163334,
|
434 |
+
"grad_norm": 3.052229881286621,
|
435 |
+
"learning_rate": 0.00019963029584585293,
|
436 |
+
"loss": 1.2992,
|
437 |
+
"step": 24400
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.05679098855249388,
|
441 |
+
"grad_norm": 2.065054178237915,
|
442 |
+
"learning_rate": 0.00019961782468282645,
|
443 |
+
"loss": 1.3266,
|
444 |
+
"step": 24800
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.05770697223882443,
|
448 |
+
"grad_norm": 3.4963061809539795,
|
449 |
+
"learning_rate": 0.0001996051470532924,
|
450 |
+
"loss": 1.3034,
|
451 |
+
"step": 25200
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.05862295592515497,
|
455 |
+
"grad_norm": 2.485971689224243,
|
456 |
+
"learning_rate": 0.00019959226298352621,
|
457 |
+
"loss": 1.3158,
|
458 |
+
"step": 25600
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.05953893961148552,
|
462 |
+
"grad_norm": 2.431988000869751,
|
463 |
+
"learning_rate": 0.0001995791725002313,
|
464 |
+
"loss": 1.2833,
|
465 |
+
"step": 26000
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.060454923297816064,
|
469 |
+
"grad_norm": 2.6740353107452393,
|
470 |
+
"learning_rate": 0.00019956587563053883,
|
471 |
+
"loss": 1.2865,
|
472 |
+
"step": 26400
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.061370906984146614,
|
476 |
+
"grad_norm": 4.834751129150391,
|
477 |
+
"learning_rate": 0.00019955237240200762,
|
478 |
+
"loss": 1.2959,
|
479 |
+
"step": 26800
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.06228689067047716,
|
483 |
+
"grad_norm": 5.183393955230713,
|
484 |
+
"learning_rate": 0.00019953866284262432,
|
485 |
+
"loss": 1.3262,
|
486 |
+
"step": 27200
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.0632028743568077,
|
490 |
+
"grad_norm": 5.2344489097595215,
|
491 |
+
"learning_rate": 0.00019952474698080322,
|
492 |
+
"loss": 1.3133,
|
493 |
+
"step": 27600
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.06411885804313826,
|
497 |
+
"grad_norm": 3.3201353549957275,
|
498 |
+
"learning_rate": 0.00019951062484538604,
|
499 |
+
"loss": 1.3156,
|
500 |
+
"step": 28000
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.0650348417294688,
|
504 |
+
"grad_norm": 3.141674041748047,
|
505 |
+
"learning_rate": 0.00019949629646564217,
|
506 |
+
"loss": 1.3074,
|
507 |
+
"step": 28400
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.06595082541579934,
|
511 |
+
"grad_norm": 3.8046987056732178,
|
512 |
+
"learning_rate": 0.00019948176187126846,
|
513 |
+
"loss": 1.273,
|
514 |
+
"step": 28800
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.06686680910212989,
|
518 |
+
"grad_norm": 2.2140769958496094,
|
519 |
+
"learning_rate": 0.000199467021092389,
|
520 |
+
"loss": 1.307,
|
521 |
+
"step": 29200
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.06778279278846044,
|
525 |
+
"grad_norm": 2.583613872528076,
|
526 |
+
"learning_rate": 0.0001994520741595554,
|
527 |
+
"loss": 1.2793,
|
528 |
+
"step": 29600
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.06869877647479099,
|
532 |
+
"grad_norm": 3.466653347015381,
|
533 |
+
"learning_rate": 0.00019943692110374646,
|
534 |
+
"loss": 1.2848,
|
535 |
+
"step": 30000
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.06961476016112153,
|
539 |
+
"grad_norm": 2.8881075382232666,
|
540 |
+
"learning_rate": 0.00019942156195636819,
|
541 |
+
"loss": 1.3187,
|
542 |
+
"step": 30400
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.07053074384745207,
|
546 |
+
"grad_norm": 2.6795177459716797,
|
547 |
+
"learning_rate": 0.00019940599674925368,
|
548 |
+
"loss": 1.3043,
|
549 |
+
"step": 30800
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.07144672753378262,
|
553 |
+
"grad_norm": 2.6429250240325928,
|
554 |
+
"learning_rate": 0.00019939022551466323,
|
555 |
+
"loss": 1.2888,
|
556 |
+
"step": 31200
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.07236271122011317,
|
560 |
+
"grad_norm": 2.6998791694641113,
|
561 |
+
"learning_rate": 0.00019937424828528406,
|
562 |
+
"loss": 1.2778,
|
563 |
+
"step": 31600
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.07327869490644372,
|
567 |
+
"grad_norm": 2.7572948932647705,
|
568 |
+
"learning_rate": 0.00019935806509423034,
|
569 |
+
"loss": 1.3302,
|
570 |
+
"step": 32000
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.07419467859277426,
|
574 |
+
"grad_norm": 5.08123779296875,
|
575 |
+
"learning_rate": 0.00019934167597504315,
|
576 |
+
"loss": 1.3033,
|
577 |
+
"step": 32400
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.0751106622791048,
|
581 |
+
"grad_norm": 3.8141486644744873,
|
582 |
+
"learning_rate": 0.00019932508096169032,
|
583 |
+
"loss": 1.3028,
|
584 |
+
"step": 32800
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.07602664596543536,
|
588 |
+
"grad_norm": 4.578782558441162,
|
589 |
+
"learning_rate": 0.00019930828008856645,
|
590 |
+
"loss": 1.3011,
|
591 |
+
"step": 33200
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.0769426296517659,
|
595 |
+
"grad_norm": 4.768449306488037,
|
596 |
+
"learning_rate": 0.0001992912733904928,
|
597 |
+
"loss": 1.3303,
|
598 |
+
"step": 33600
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.07785861333809645,
|
602 |
+
"grad_norm": 3.1697211265563965,
|
603 |
+
"learning_rate": 0.0001992740609027172,
|
604 |
+
"loss": 1.2926,
|
605 |
+
"step": 34000
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.07877459702442699,
|
609 |
+
"grad_norm": 2.7294230461120605,
|
610 |
+
"learning_rate": 0.00019925664266091407,
|
611 |
+
"loss": 1.3147,
|
612 |
+
"step": 34400
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.07969058071075755,
|
616 |
+
"grad_norm": 2.3929479122161865,
|
617 |
+
"learning_rate": 0.0001992390187011841,
|
618 |
+
"loss": 1.3007,
|
619 |
+
"step": 34800
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.08060656439708809,
|
623 |
+
"grad_norm": 3.5411980152130127,
|
624 |
+
"learning_rate": 0.0001992211890600546,
|
625 |
+
"loss": 1.2973,
|
626 |
+
"step": 35200
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.08152254808341863,
|
630 |
+
"grad_norm": 2.940880537033081,
|
631 |
+
"learning_rate": 0.00019920315377447895,
|
632 |
+
"loss": 1.3072,
|
633 |
+
"step": 35600
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.08243853176974918,
|
637 |
+
"grad_norm": 2.7717535495758057,
|
638 |
+
"learning_rate": 0.00019918491288183684,
|
639 |
+
"loss": 1.2908,
|
640 |
+
"step": 36000
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.08335451545607973,
|
644 |
+
"grad_norm": 3.153017520904541,
|
645 |
+
"learning_rate": 0.00019916646641993406,
|
646 |
+
"loss": 1.3313,
|
647 |
+
"step": 36400
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.08427049914241028,
|
651 |
+
"grad_norm": 3.065833568572998,
|
652 |
+
"learning_rate": 0.00019914781442700253,
|
653 |
+
"loss": 1.3237,
|
654 |
+
"step": 36800
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.08518648282874082,
|
658 |
+
"grad_norm": 2.692406177520752,
|
659 |
+
"learning_rate": 0.00019912895694170014,
|
660 |
+
"loss": 1.3175,
|
661 |
+
"step": 37200
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.08610246651507136,
|
665 |
+
"grad_norm": 2.9629924297332764,
|
666 |
+
"learning_rate": 0.00019910989400311058,
|
667 |
+
"loss": 1.3247,
|
668 |
+
"step": 37600
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.0870184502014019,
|
672 |
+
"grad_norm": 3.1538310050964355,
|
673 |
+
"learning_rate": 0.00019909062565074345,
|
674 |
+
"loss": 1.2894,
|
675 |
+
"step": 38000
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.08793443388773246,
|
679 |
+
"grad_norm": 2.88925838470459,
|
680 |
+
"learning_rate": 0.00019907115192453412,
|
681 |
+
"loss": 1.2974,
|
682 |
+
"step": 38400
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.088850417574063,
|
686 |
+
"grad_norm": 3.396505832672119,
|
687 |
+
"learning_rate": 0.00019905147286484348,
|
688 |
+
"loss": 1.3409,
|
689 |
+
"step": 38800
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.08976640126039355,
|
693 |
+
"grad_norm": 5.7697978019714355,
|
694 |
+
"learning_rate": 0.0001990315885124581,
|
695 |
+
"loss": 1.3222,
|
696 |
+
"step": 39200
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.09068238494672409,
|
700 |
+
"grad_norm": 2.9619033336639404,
|
701 |
+
"learning_rate": 0.00019901149890859006,
|
702 |
+
"loss": 1.2918,
|
703 |
+
"step": 39600
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.09159836863305465,
|
707 |
+
"grad_norm": 2.1384809017181396,
|
708 |
+
"learning_rate": 0.00019899120409487675,
|
709 |
+
"loss": 1.2941,
|
710 |
+
"step": 40000
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.09251435231938519,
|
714 |
+
"grad_norm": 2.692207098007202,
|
715 |
+
"learning_rate": 0.0001989707041133809,
|
716 |
+
"loss": 1.3278,
|
717 |
+
"step": 40400
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.09343033600571574,
|
721 |
+
"grad_norm": 2.231248140335083,
|
722 |
+
"learning_rate": 0.00019894999900659053,
|
723 |
+
"loss": 1.2966,
|
724 |
+
"step": 40800
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.09434631969204628,
|
728 |
+
"grad_norm": 4.9003801345825195,
|
729 |
+
"learning_rate": 0.00019892908881741873,
|
730 |
+
"loss": 1.3301,
|
731 |
+
"step": 41200
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 0.09526230337837684,
|
735 |
+
"grad_norm": 2.9206295013427734,
|
736 |
+
"learning_rate": 0.00019890797358920365,
|
737 |
+
"loss": 1.3225,
|
738 |
+
"step": 41600
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.09617828706470738,
|
742 |
+
"grad_norm": 3.754241704940796,
|
743 |
+
"learning_rate": 0.0001988866533657084,
|
744 |
+
"loss": 1.3073,
|
745 |
+
"step": 42000
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.09709427075103792,
|
749 |
+
"grad_norm": 2.3221588134765625,
|
750 |
+
"learning_rate": 0.00019886512819112108,
|
751 |
+
"loss": 1.3078,
|
752 |
+
"step": 42400
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.09801025443736847,
|
756 |
+
"grad_norm": 3.1331708431243896,
|
757 |
+
"learning_rate": 0.00019884339811005432,
|
758 |
+
"loss": 1.3036,
|
759 |
+
"step": 42800
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.09892623812369902,
|
763 |
+
"grad_norm": 8.973402976989746,
|
764 |
+
"learning_rate": 0.0001988214631675457,
|
765 |
+
"loss": 1.3162,
|
766 |
+
"step": 43200
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.09984222181002957,
|
770 |
+
"grad_norm": 2.487173557281494,
|
771 |
+
"learning_rate": 0.00019879932340905723,
|
772 |
+
"loss": 1.3379,
|
773 |
+
"step": 43600
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.10075820549636011,
|
777 |
+
"grad_norm": 2.4204483032226562,
|
778 |
+
"learning_rate": 0.00019877697888047544,
|
779 |
+
"loss": 1.2983,
|
780 |
+
"step": 44000
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.10167418918269065,
|
784 |
+
"grad_norm": 2.4077422618865967,
|
785 |
+
"learning_rate": 0.00019875442962811131,
|
786 |
+
"loss": 1.2975,
|
787 |
+
"step": 44400
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.10259017286902121,
|
791 |
+
"grad_norm": 3.7924795150756836,
|
792 |
+
"learning_rate": 0.0001987316756987001,
|
793 |
+
"loss": 1.3049,
|
794 |
+
"step": 44800
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.10350615655535175,
|
798 |
+
"grad_norm": 2.4726195335388184,
|
799 |
+
"learning_rate": 0.00019870871713940133,
|
800 |
+
"loss": 1.3108,
|
801 |
+
"step": 45200
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.1044221402416823,
|
805 |
+
"grad_norm": 2.7203783988952637,
|
806 |
+
"learning_rate": 0.0001986855539977985,
|
807 |
+
"loss": 1.3079,
|
808 |
+
"step": 45600
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.10533812392801284,
|
812 |
+
"grad_norm": 3.3892195224761963,
|
813 |
+
"learning_rate": 0.00019866218632189926,
|
814 |
+
"loss": 1.2998,
|
815 |
+
"step": 46000
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 0.10625410761434338,
|
819 |
+
"grad_norm": 7.186534881591797,
|
820 |
+
"learning_rate": 0.0001986386141601351,
|
821 |
+
"loss": 1.3204,
|
822 |
+
"step": 46400
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.10717009130067394,
|
826 |
+
"grad_norm": 2.1294145584106445,
|
827 |
+
"learning_rate": 0.00019861483756136145,
|
828 |
+
"loss": 1.3159,
|
829 |
+
"step": 46800
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.10808607498700448,
|
833 |
+
"grad_norm": 2.179487943649292,
|
834 |
+
"learning_rate": 0.00019859085657485725,
|
835 |
+
"loss": 1.3221,
|
836 |
+
"step": 47200
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.10900205867333503,
|
840 |
+
"grad_norm": 2.950897216796875,
|
841 |
+
"learning_rate": 0.0001985666712503252,
|
842 |
+
"loss": 1.3029,
|
843 |
+
"step": 47600
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.10991804235966557,
|
847 |
+
"grad_norm": 3.8391480445861816,
|
848 |
+
"learning_rate": 0.00019854228163789143,
|
849 |
+
"loss": 1.3144,
|
850 |
+
"step": 48000
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 0.11083402604599613,
|
854 |
+
"grad_norm": 3.4370920658111572,
|
855 |
+
"learning_rate": 0.00019851768778810555,
|
856 |
+
"loss": 1.3077,
|
857 |
+
"step": 48400
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 0.11175000973232667,
|
861 |
+
"grad_norm": 3.353703260421753,
|
862 |
+
"learning_rate": 0.00019849288975194043,
|
863 |
+
"loss": 1.3034,
|
864 |
+
"step": 48800
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.11266599341865721,
|
868 |
+
"grad_norm": 3.25929856300354,
|
869 |
+
"learning_rate": 0.00019846788758079212,
|
870 |
+
"loss": 1.2789,
|
871 |
+
"step": 49200
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.11358197710498776,
|
875 |
+
"grad_norm": 2.8102946281433105,
|
876 |
+
"learning_rate": 0.00019844268132647975,
|
877 |
+
"loss": 1.3224,
|
878 |
+
"step": 49600
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.11449796079131831,
|
882 |
+
"grad_norm": 3.392300605773926,
|
883 |
+
"learning_rate": 0.00019841727104124543,
|
884 |
+
"loss": 1.3119,
|
885 |
+
"step": 50000
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.11541394447764886,
|
889 |
+
"grad_norm": 2.5362913608551025,
|
890 |
+
"learning_rate": 0.00019839165677775422,
|
891 |
+
"loss": 1.3027,
|
892 |
+
"step": 50400
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.1163299281639794,
|
896 |
+
"grad_norm": 1.9659497737884521,
|
897 |
+
"learning_rate": 0.00019836583858909388,
|
898 |
+
"loss": 1.2823,
|
899 |
+
"step": 50800
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 0.11724591185030994,
|
903 |
+
"grad_norm": 2.3742833137512207,
|
904 |
+
"learning_rate": 0.00019833981652877478,
|
905 |
+
"loss": 1.3226,
|
906 |
+
"step": 51200
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.1181618955366405,
|
910 |
+
"grad_norm": 2.898440361022949,
|
911 |
+
"learning_rate": 0.00019831359065072991,
|
912 |
+
"loss": 1.3127,
|
913 |
+
"step": 51600
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.11907787922297104,
|
917 |
+
"grad_norm": 3.8529317378997803,
|
918 |
+
"learning_rate": 0.00019828716100931467,
|
919 |
+
"loss": 1.3176,
|
920 |
+
"step": 52000
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.11999386290930159,
|
924 |
+
"grad_norm": 2.7400405406951904,
|
925 |
+
"learning_rate": 0.00019826052765930673,
|
926 |
+
"loss": 1.3108,
|
927 |
+
"step": 52400
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.12090984659563213,
|
931 |
+
"grad_norm": 3.10595965385437,
|
932 |
+
"learning_rate": 0.000198233690655906,
|
933 |
+
"loss": 1.3142,
|
934 |
+
"step": 52800
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.12182583028196267,
|
938 |
+
"grad_norm": 2.706665515899658,
|
939 |
+
"learning_rate": 0.00019820665005473452,
|
940 |
+
"loss": 1.3015,
|
941 |
+
"step": 53200
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.12274181396829323,
|
945 |
+
"grad_norm": 2.9297852516174316,
|
946 |
+
"learning_rate": 0.00019817940591183622,
|
947 |
+
"loss": 1.316,
|
948 |
+
"step": 53600
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.12365779765462377,
|
952 |
+
"grad_norm": 3.5302863121032715,
|
953 |
+
"learning_rate": 0.00019815195828367692,
|
954 |
+
"loss": 1.3253,
|
955 |
+
"step": 54000
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 0.12457378134095431,
|
959 |
+
"grad_norm": 2.3251285552978516,
|
960 |
+
"learning_rate": 0.0001981243072271442,
|
961 |
+
"loss": 1.3374,
|
962 |
+
"step": 54400
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.12548976502728487,
|
966 |
+
"grad_norm": 2.586763620376587,
|
967 |
+
"learning_rate": 0.0001980964527995473,
|
968 |
+
"loss": 1.3103,
|
969 |
+
"step": 54800
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.1264057487136154,
|
973 |
+
"grad_norm": 3.486201286315918,
|
974 |
+
"learning_rate": 0.00019806839505861684,
|
975 |
+
"loss": 1.3404,
|
976 |
+
"step": 55200
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.12732173239994596,
|
980 |
+
"grad_norm": 2.812666893005371,
|
981 |
+
"learning_rate": 0.00019804013406250496,
|
982 |
+
"loss": 1.2929,
|
983 |
+
"step": 55600
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.12823771608627652,
|
987 |
+
"grad_norm": 3.6000659465789795,
|
988 |
+
"learning_rate": 0.00019801166986978502,
|
989 |
+
"loss": 1.3145,
|
990 |
+
"step": 56000
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.12915369977260704,
|
994 |
+
"grad_norm": 2.623760938644409,
|
995 |
+
"learning_rate": 0.00019798300253945142,
|
996 |
+
"loss": 1.2905,
|
997 |
+
"step": 56400
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 0.1300696834589376,
|
1001 |
+
"grad_norm": 2.5378899574279785,
|
1002 |
+
"learning_rate": 0.00019795413213091973,
|
1003 |
+
"loss": 1.3345,
|
1004 |
+
"step": 56800
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.13098566714526813,
|
1008 |
+
"grad_norm": 3.966965913772583,
|
1009 |
+
"learning_rate": 0.00019792505870402634,
|
1010 |
+
"loss": 1.2805,
|
1011 |
+
"step": 57200
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.1319016508315987,
|
1015 |
+
"grad_norm": 3.2356481552124023,
|
1016 |
+
"learning_rate": 0.00019789578231902842,
|
1017 |
+
"loss": 1.2846,
|
1018 |
+
"step": 57600
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.13281763451792925,
|
1022 |
+
"grad_norm": 3.4602396488189697,
|
1023 |
+
"learning_rate": 0.00019786630303660383,
|
1024 |
+
"loss": 1.308,
|
1025 |
+
"step": 58000
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 0.13373361820425977,
|
1029 |
+
"grad_norm": 4.348870754241943,
|
1030 |
+
"learning_rate": 0.00019783662091785086,
|
1031 |
+
"loss": 1.2911,
|
1032 |
+
"step": 58400
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 0.13464960189059033,
|
1036 |
+
"grad_norm": 3.970092296600342,
|
1037 |
+
"learning_rate": 0.0001978067360242883,
|
1038 |
+
"loss": 1.3088,
|
1039 |
+
"step": 58800
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 0.1355655855769209,
|
1043 |
+
"grad_norm": 3.6399309635162354,
|
1044 |
+
"learning_rate": 0.00019777664841785515,
|
1045 |
+
"loss": 1.3451,
|
1046 |
+
"step": 59200
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.13648156926325142,
|
1050 |
+
"grad_norm": 2.8347928524017334,
|
1051 |
+
"learning_rate": 0.00019774635816091057,
|
1052 |
+
"loss": 1.3221,
|
1053 |
+
"step": 59600
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.13739755294958197,
|
1057 |
+
"grad_norm": 2.156590461730957,
|
1058 |
+
"learning_rate": 0.0001977158653162337,
|
1059 |
+
"loss": 1.3071,
|
1060 |
+
"step": 60000
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.1383135366359125,
|
1064 |
+
"grad_norm": 3.543612241744995,
|
1065 |
+
"learning_rate": 0.0001976851699470236,
|
1066 |
+
"loss": 1.3316,
|
1067 |
+
"step": 60400
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 0.13922952032224306,
|
1071 |
+
"grad_norm": 2.555818796157837,
|
1072 |
+
"learning_rate": 0.00019765427211689902,
|
1073 |
+
"loss": 1.3102,
|
1074 |
+
"step": 60800
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.14014550400857362,
|
1078 |
+
"grad_norm": 2.2213761806488037,
|
1079 |
+
"learning_rate": 0.00019762317188989843,
|
1080 |
+
"loss": 1.3198,
|
1081 |
+
"step": 61200
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 0.14106148769490415,
|
1085 |
+
"grad_norm": 2.6470835208892822,
|
1086 |
+
"learning_rate": 0.0001975918693304797,
|
1087 |
+
"loss": 1.279,
|
1088 |
+
"step": 61600
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.1419774713812347,
|
1092 |
+
"grad_norm": 2.345820903778076,
|
1093 |
+
"learning_rate": 0.00019756036450352009,
|
1094 |
+
"loss": 1.3239,
|
1095 |
+
"step": 62000
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.14289345506756523,
|
1099 |
+
"grad_norm": 2.149404287338257,
|
1100 |
+
"learning_rate": 0.00019752865747431605,
|
1101 |
+
"loss": 1.3445,
|
1102 |
+
"step": 62400
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 0.1438094387538958,
|
1106 |
+
"grad_norm": 2.8613338470458984,
|
1107 |
+
"learning_rate": 0.0001974967483085831,
|
1108 |
+
"loss": 1.371,
|
1109 |
+
"step": 62800
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 0.14472542244022635,
|
1113 |
+
"grad_norm": 2.959139585494995,
|
1114 |
+
"learning_rate": 0.00019746463707245575,
|
1115 |
+
"loss": 1.3083,
|
1116 |
+
"step": 63200
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 0.14564140612655688,
|
1120 |
+
"grad_norm": 2.392615795135498,
|
1121 |
+
"learning_rate": 0.00019743232383248732,
|
1122 |
+
"loss": 1.3123,
|
1123 |
+
"step": 63600
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 0.14655738981288743,
|
1127 |
+
"grad_norm": 3.202287435531616,
|
1128 |
+
"learning_rate": 0.00019739980865564972,
|
1129 |
+
"loss": 1.3188,
|
1130 |
+
"step": 64000
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.147473373499218,
|
1134 |
+
"grad_norm": 2.6809701919555664,
|
1135 |
+
"learning_rate": 0.00019736709160933353,
|
1136 |
+
"loss": 1.3307,
|
1137 |
+
"step": 64400
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.14838935718554852,
|
1141 |
+
"grad_norm": 2.6796672344207764,
|
1142 |
+
"learning_rate": 0.0001973341727613476,
|
1143 |
+
"loss": 1.3257,
|
1144 |
+
"step": 64800
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 0.14930534087187908,
|
1148 |
+
"grad_norm": 2.986403465270996,
|
1149 |
+
"learning_rate": 0.00019730105217991906,
|
1150 |
+
"loss": 1.3302,
|
1151 |
+
"step": 65200
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 0.1502213245582096,
|
1155 |
+
"grad_norm": 4.021244525909424,
|
1156 |
+
"learning_rate": 0.00019726772993369318,
|
1157 |
+
"loss": 1.3299,
|
1158 |
+
"step": 65600
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 0.15113730824454016,
|
1162 |
+
"grad_norm": 2.3918700218200684,
|
1163 |
+
"learning_rate": 0.00019723420609173319,
|
1164 |
+
"loss": 1.3285,
|
1165 |
+
"step": 66000
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 0.15205329193087072,
|
1169 |
+
"grad_norm": 2.162391185760498,
|
1170 |
+
"learning_rate": 0.0001972004807235201,
|
1171 |
+
"loss": 1.3017,
|
1172 |
+
"step": 66400
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.15296927561720125,
|
1176 |
+
"grad_norm": 3.2081525325775146,
|
1177 |
+
"learning_rate": 0.00019716655389895267,
|
1178 |
+
"loss": 1.3482,
|
1179 |
+
"step": 66800
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.1538852593035318,
|
1183 |
+
"grad_norm": 3.2288455963134766,
|
1184 |
+
"learning_rate": 0.00019713242568834716,
|
1185 |
+
"loss": 1.3169,
|
1186 |
+
"step": 67200
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 0.15480124298986236,
|
1190 |
+
"grad_norm": 4.8006792068481445,
|
1191 |
+
"learning_rate": 0.00019709809616243716,
|
1192 |
+
"loss": 1.3135,
|
1193 |
+
"step": 67600
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 0.1557172266761929,
|
1197 |
+
"grad_norm": 2.4130496978759766,
|
1198 |
+
"learning_rate": 0.00019706356539237366,
|
1199 |
+
"loss": 1.3152,
|
1200 |
+
"step": 68000
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.15663321036252345,
|
1204 |
+
"grad_norm": 3.030592441558838,
|
1205 |
+
"learning_rate": 0.00019702883344972463,
|
1206 |
+
"loss": 1.2712,
|
1207 |
+
"step": 68400
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 0.15754919404885398,
|
1211 |
+
"grad_norm": 2.5594406127929688,
|
1212 |
+
"learning_rate": 0.00019699390040647493,
|
1213 |
+
"loss": 1.3191,
|
1214 |
+
"step": 68800
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.15846517773518454,
|
1218 |
+
"grad_norm": 2.589397668838501,
|
1219 |
+
"learning_rate": 0.0001969587663350264,
|
1220 |
+
"loss": 1.3356,
|
1221 |
+
"step": 69200
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.1593811614215151,
|
1225 |
+
"grad_norm": 3.142416000366211,
|
1226 |
+
"learning_rate": 0.00019692343130819733,
|
1227 |
+
"loss": 1.2929,
|
1228 |
+
"step": 69600
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 0.16029714510784562,
|
1232 |
+
"grad_norm": 2.8887860774993896,
|
1233 |
+
"learning_rate": 0.00019688789539922265,
|
1234 |
+
"loss": 1.2715,
|
1235 |
+
"step": 70000
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 0.16121312879417618,
|
1239 |
+
"grad_norm": 2.9049878120422363,
|
1240 |
+
"learning_rate": 0.0001968521586817536,
|
1241 |
+
"loss": 1.3102,
|
1242 |
+
"step": 70400
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 0.1621291124805067,
|
1246 |
+
"grad_norm": 5.651445388793945,
|
1247 |
+
"learning_rate": 0.00019681622122985756,
|
1248 |
+
"loss": 1.3383,
|
1249 |
+
"step": 70800
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 0.16304509616683727,
|
1253 |
+
"grad_norm": 2.6682519912719727,
|
1254 |
+
"learning_rate": 0.00019678008311801803,
|
1255 |
+
"loss": 1.3298,
|
1256 |
+
"step": 71200
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.16396107985316782,
|
1260 |
+
"grad_norm": 2.235239267349243,
|
1261 |
+
"learning_rate": 0.0001967437444211343,
|
1262 |
+
"loss": 1.3179,
|
1263 |
+
"step": 71600
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.16487706353949835,
|
1267 |
+
"grad_norm": 2.893455982208252,
|
1268 |
+
"learning_rate": 0.00019670720521452152,
|
1269 |
+
"loss": 1.3156,
|
1270 |
+
"step": 72000
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 0.1657930472258289,
|
1274 |
+
"grad_norm": 2.421581268310547,
|
1275 |
+
"learning_rate": 0.00019667046557391026,
|
1276 |
+
"loss": 1.3122,
|
1277 |
+
"step": 72400
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 0.16670903091215947,
|
1281 |
+
"grad_norm": 2.4242067337036133,
|
1282 |
+
"learning_rate": 0.00019663352557544665,
|
1283 |
+
"loss": 1.3144,
|
1284 |
+
"step": 72800
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.16762501459849,
|
1288 |
+
"grad_norm": 2.6495418548583984,
|
1289 |
+
"learning_rate": 0.00019659638529569197,
|
1290 |
+
"loss": 1.3041,
|
1291 |
+
"step": 73200
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 0.16854099828482055,
|
1295 |
+
"grad_norm": 2.511672019958496,
|
1296 |
+
"learning_rate": 0.0001965590448116227,
|
1297 |
+
"loss": 1.3138,
|
1298 |
+
"step": 73600
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 0.16945698197115108,
|
1302 |
+
"grad_norm": 1.9795838594436646,
|
1303 |
+
"learning_rate": 0.0001965215042006301,
|
1304 |
+
"loss": 1.3126,
|
1305 |
+
"step": 74000
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.17037296565748164,
|
1309 |
+
"grad_norm": 2.0971930027008057,
|
1310 |
+
"learning_rate": 0.0001964837635405204,
|
1311 |
+
"loss": 1.3481,
|
1312 |
+
"step": 74400
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 0.1712889493438122,
|
1316 |
+
"grad_norm": 2.5095582008361816,
|
1317 |
+
"learning_rate": 0.00019644582290951436,
|
1318 |
+
"loss": 1.3169,
|
1319 |
+
"step": 74800
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 0.17220493303014273,
|
1323 |
+
"grad_norm": 2.5341243743896484,
|
1324 |
+
"learning_rate": 0.00019640768238624715,
|
1325 |
+
"loss": 1.3021,
|
1326 |
+
"step": 75200
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 0.17312091671647328,
|
1330 |
+
"grad_norm": 4.831284999847412,
|
1331 |
+
"learning_rate": 0.00019636934204976831,
|
1332 |
+
"loss": 1.3097,
|
1333 |
+
"step": 75600
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 0.1740369004028038,
|
1337 |
+
"grad_norm": 2.303138494491577,
|
1338 |
+
"learning_rate": 0.0001963308019795415,
|
1339 |
+
"loss": 1.3239,
|
1340 |
+
"step": 76000
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 0.17495288408913437,
|
1344 |
+
"grad_norm": 4.299285888671875,
|
1345 |
+
"learning_rate": 0.00019629206225544433,
|
1346 |
+
"loss": 1.3131,
|
1347 |
+
"step": 76400
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.17586886777546493,
|
1351 |
+
"grad_norm": 3.942025661468506,
|
1352 |
+
"learning_rate": 0.00019625312295776817,
|
1353 |
+
"loss": 1.3413,
|
1354 |
+
"step": 76800
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.17678485146179546,
|
1358 |
+
"grad_norm": 3.2219340801239014,
|
1359 |
+
"learning_rate": 0.0001962139841672181,
|
1360 |
+
"loss": 1.3132,
|
1361 |
+
"step": 77200
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 0.177700835148126,
|
1365 |
+
"grad_norm": 2.0211946964263916,
|
1366 |
+
"learning_rate": 0.0001961746459649126,
|
1367 |
+
"loss": 1.2732,
|
1368 |
+
"step": 77600
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 0.17861681883445657,
|
1372 |
+
"grad_norm": 3.735818862915039,
|
1373 |
+
"learning_rate": 0.00019613510843238352,
|
1374 |
+
"loss": 1.3029,
|
1375 |
+
"step": 78000
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 0.1795328025207871,
|
1379 |
+
"grad_norm": 2.5477070808410645,
|
1380 |
+
"learning_rate": 0.00019609537165157575,
|
1381 |
+
"loss": 1.3028,
|
1382 |
+
"step": 78400
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 0.18044878620711766,
|
1386 |
+
"grad_norm": 2.3577768802642822,
|
1387 |
+
"learning_rate": 0.00019605543570484725,
|
1388 |
+
"loss": 1.3296,
|
1389 |
+
"step": 78800
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.18136476989344819,
|
1393 |
+
"grad_norm": 2.8222320079803467,
|
1394 |
+
"learning_rate": 0.0001960153006749686,
|
1395 |
+
"loss": 1.3247,
|
1396 |
+
"step": 79200
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 0.18228075357977874,
|
1400 |
+
"grad_norm": 3.6256015300750732,
|
1401 |
+
"learning_rate": 0.0001959749666451232,
|
1402 |
+
"loss": 1.3482,
|
1403 |
+
"step": 79600
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 0.1831967372661093,
|
1407 |
+
"grad_norm": 3.6244571208953857,
|
1408 |
+
"learning_rate": 0.00019593443369890671,
|
1409 |
+
"loss": 1.2999,
|
1410 |
+
"step": 80000
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.18411272095243983,
|
1414 |
+
"grad_norm": 2.577220916748047,
|
1415 |
+
"learning_rate": 0.00019589370192032724,
|
1416 |
+
"loss": 1.2971,
|
1417 |
+
"step": 80400
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 0.18502870463877039,
|
1421 |
+
"grad_norm": 2.6459338665008545,
|
1422 |
+
"learning_rate": 0.00019585277139380484,
|
1423 |
+
"loss": 1.3178,
|
1424 |
+
"step": 80800
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 0.18594468832510094,
|
1428 |
+
"grad_norm": 2.8962595462799072,
|
1429 |
+
"learning_rate": 0.00019581164220417157,
|
1430 |
+
"loss": 1.2918,
|
1431 |
+
"step": 81200
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 0.18686067201143147,
|
1435 |
+
"grad_norm": 2.5094783306121826,
|
1436 |
+
"learning_rate": 0.00019577031443667118,
|
1437 |
+
"loss": 1.3126,
|
1438 |
+
"step": 81600
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 0.18777665569776203,
|
1442 |
+
"grad_norm": 4.931221008300781,
|
1443 |
+
"learning_rate": 0.00019572878817695905,
|
1444 |
+
"loss": 1.3178,
|
1445 |
+
"step": 82000
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 0.18869263938409256,
|
1449 |
+
"grad_norm": 2.7248241901397705,
|
1450 |
+
"learning_rate": 0.00019568706351110192,
|
1451 |
+
"loss": 1.3037,
|
1452 |
+
"step": 82400
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 0.18960862307042312,
|
1456 |
+
"grad_norm": 2.4585657119750977,
|
1457 |
+
"learning_rate": 0.00019564514052557776,
|
1458 |
+
"loss": 1.266,
|
1459 |
+
"step": 82800
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 0.19052460675675367,
|
1463 |
+
"grad_norm": 4.284319877624512,
|
1464 |
+
"learning_rate": 0.00019560301930727554,
|
1465 |
+
"loss": 1.3234,
|
1466 |
+
"step": 83200
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 0.1914405904430842,
|
1470 |
+
"grad_norm": 3.2392733097076416,
|
1471 |
+
"learning_rate": 0.00019556069994349512,
|
1472 |
+
"loss": 1.2925,
|
1473 |
+
"step": 83600
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 0.19235657412941476,
|
1477 |
+
"grad_norm": 3.9642889499664307,
|
1478 |
+
"learning_rate": 0.000195518182521947,
|
1479 |
+
"loss": 1.325,
|
1480 |
+
"step": 84000
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 0.1932725578157453,
|
1484 |
+
"grad_norm": 3.1390507221221924,
|
1485 |
+
"learning_rate": 0.00019547546713075223,
|
1486 |
+
"loss": 1.3283,
|
1487 |
+
"step": 84400
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 0.19418854150207585,
|
1491 |
+
"grad_norm": 2.6130847930908203,
|
1492 |
+
"learning_rate": 0.0001954325538584421,
|
1493 |
+
"loss": 1.315,
|
1494 |
+
"step": 84800
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 0.1951045251884064,
|
1498 |
+
"grad_norm": 2.1440110206604004,
|
1499 |
+
"learning_rate": 0.00019538944279395804,
|
1500 |
+
"loss": 1.2824,
|
1501 |
+
"step": 85200
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 0.19602050887473693,
|
1505 |
+
"grad_norm": 4.09576416015625,
|
1506 |
+
"learning_rate": 0.0001953461340266515,
|
1507 |
+
"loss": 1.2979,
|
1508 |
+
"step": 85600
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 0.1969364925610675,
|
1512 |
+
"grad_norm": 3.521430015563965,
|
1513 |
+
"learning_rate": 0.0001953026276462836,
|
1514 |
+
"loss": 1.2959,
|
1515 |
+
"step": 86000
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 0.19785247624739805,
|
1519 |
+
"grad_norm": 2.449007987976074,
|
1520 |
+
"learning_rate": 0.000195258923743025,
|
1521 |
+
"loss": 1.2622,
|
1522 |
+
"step": 86400
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 0.19876845993372858,
|
1526 |
+
"grad_norm": 2.7827935218811035,
|
1527 |
+
"learning_rate": 0.00019521502240745585,
|
1528 |
+
"loss": 1.3096,
|
1529 |
+
"step": 86800
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 0.19968444362005913,
|
1533 |
+
"grad_norm": 2.0877015590667725,
|
1534 |
+
"learning_rate": 0.00019517092373056544,
|
1535 |
+
"loss": 1.2967,
|
1536 |
+
"step": 87200
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 0.20060042730638966,
|
1540 |
+
"grad_norm": 3.6653809547424316,
|
1541 |
+
"learning_rate": 0.00019512662780375207,
|
1542 |
+
"loss": 1.2924,
|
1543 |
+
"step": 87600
|
1544 |
+
},
|
1545 |
+
{
|
1546 |
+
"epoch": 0.20151641099272022,
|
1547 |
+
"grad_norm": 2.5417637825012207,
|
1548 |
+
"learning_rate": 0.00019508213471882286,
|
1549 |
+
"loss": 1.3262,
|
1550 |
+
"step": 88000
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 0.20243239467905078,
|
1554 |
+
"grad_norm": 2.624288320541382,
|
1555 |
+
"learning_rate": 0.00019503744456799354,
|
1556 |
+
"loss": 1.3025,
|
1557 |
+
"step": 88400
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 0.2033483783653813,
|
1561 |
+
"grad_norm": 2.456366777420044,
|
1562 |
+
"learning_rate": 0.00019499255744388826,
|
1563 |
+
"loss": 1.3399,
|
1564 |
+
"step": 88800
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 0.20426436205171186,
|
1568 |
+
"grad_norm": 4.339550018310547,
|
1569 |
+
"learning_rate": 0.00019494747343953953,
|
1570 |
+
"loss": 1.3008,
|
1571 |
+
"step": 89200
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 0.20518034573804242,
|
1575 |
+
"grad_norm": 5.688206195831299,
|
1576 |
+
"learning_rate": 0.00019490219264838775,
|
1577 |
+
"loss": 1.31,
|
1578 |
+
"step": 89600
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 0.20609632942437295,
|
1582 |
+
"grad_norm": 2.1266727447509766,
|
1583 |
+
"learning_rate": 0.0001948567151642813,
|
1584 |
+
"loss": 1.3074,
|
1585 |
+
"step": 90000
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 0.2070123131107035,
|
1589 |
+
"grad_norm": 2.642869710922241,
|
1590 |
+
"learning_rate": 0.00019481104108147611,
|
1591 |
+
"loss": 1.3326,
|
1592 |
+
"step": 90400
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 0.20792829679703403,
|
1596 |
+
"grad_norm": 2.08663010597229,
|
1597 |
+
"learning_rate": 0.00019476517049463573,
|
1598 |
+
"loss": 1.3104,
|
1599 |
+
"step": 90800
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.2088442804833646,
|
1603 |
+
"grad_norm": 2.1731367111206055,
|
1604 |
+
"learning_rate": 0.00019471910349883083,
|
1605 |
+
"loss": 1.2756,
|
1606 |
+
"step": 91200
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"epoch": 0.20976026416969515,
|
1610 |
+
"grad_norm": 4.205643177032471,
|
1611 |
+
"learning_rate": 0.00019467284018953923,
|
1612 |
+
"loss": 1.3519,
|
1613 |
+
"step": 91600
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 0.21067624785602568,
|
1617 |
+
"grad_norm": 3.688913345336914,
|
1618 |
+
"learning_rate": 0.00019462638066264568,
|
1619 |
+
"loss": 1.3051,
|
1620 |
+
"step": 92000
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 0.21159223154235623,
|
1624 |
+
"grad_norm": 2.8318068981170654,
|
1625 |
+
"learning_rate": 0.00019457972501444145,
|
1626 |
+
"loss": 1.2898,
|
1627 |
+
"step": 92400
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 0.21250821522868676,
|
1631 |
+
"grad_norm": 2.134383201599121,
|
1632 |
+
"learning_rate": 0.00019453287334162447,
|
1633 |
+
"loss": 1.3033,
|
1634 |
+
"step": 92800
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 0.21342419891501732,
|
1638 |
+
"grad_norm": 2.209117889404297,
|
1639 |
+
"learning_rate": 0.0001944858257412988,
|
1640 |
+
"loss": 1.3375,
|
1641 |
+
"step": 93200
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 0.21434018260134788,
|
1645 |
+
"grad_norm": 2.902921438217163,
|
1646 |
+
"learning_rate": 0.00019443858231097462,
|
1647 |
+
"loss": 1.3301,
|
1648 |
+
"step": 93600
|
1649 |
+
},
|
1650 |
+
{
|
1651 |
+
"epoch": 0.2152561662876784,
|
1652 |
+
"grad_norm": 2.680903911590576,
|
1653 |
+
"learning_rate": 0.0001943911431485681,
|
1654 |
+
"loss": 1.3035,
|
1655 |
+
"step": 94000
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 0.21617214997400896,
|
1659 |
+
"grad_norm": 2.6961417198181152,
|
1660 |
+
"learning_rate": 0.00019434350835240087,
|
1661 |
+
"loss": 1.325,
|
1662 |
+
"step": 94400
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 0.21708813366033952,
|
1666 |
+
"grad_norm": 2.705254316329956,
|
1667 |
+
"learning_rate": 0.00019429567802120023,
|
1668 |
+
"loss": 1.3125,
|
1669 |
+
"step": 94800
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 0.21800411734667005,
|
1673 |
+
"grad_norm": 2.9032137393951416,
|
1674 |
+
"learning_rate": 0.0001942476522540986,
|
1675 |
+
"loss": 1.3146,
|
1676 |
+
"step": 95200
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 0.2189201010330006,
|
1680 |
+
"grad_norm": 2.815955877304077,
|
1681 |
+
"learning_rate": 0.00019419943115063352,
|
1682 |
+
"loss": 1.2994,
|
1683 |
+
"step": 95600
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 0.21983608471933114,
|
1687 |
+
"grad_norm": 2.9431276321411133,
|
1688 |
+
"learning_rate": 0.0001941510148107474,
|
1689 |
+
"loss": 1.3166,
|
1690 |
+
"step": 96000
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 0.2207520684056617,
|
1694 |
+
"grad_norm": 2.2290589809417725,
|
1695 |
+
"learning_rate": 0.0001941024033347872,
|
1696 |
+
"loss": 1.3363,
|
1697 |
+
"step": 96400
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 0.22166805209199225,
|
1701 |
+
"grad_norm": 6.320208549499512,
|
1702 |
+
"learning_rate": 0.0001940535968235045,
|
1703 |
+
"loss": 1.3342,
|
1704 |
+
"step": 96800
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 0.22258403577832278,
|
1708 |
+
"grad_norm": 2.5221080780029297,
|
1709 |
+
"learning_rate": 0.0001940045953780549,
|
1710 |
+
"loss": 1.3139,
|
1711 |
+
"step": 97200
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 0.22350001946465334,
|
1715 |
+
"grad_norm": 1.954762578010559,
|
1716 |
+
"learning_rate": 0.00019395539909999814,
|
1717 |
+
"loss": 1.3196,
|
1718 |
+
"step": 97600
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 0.2244160031509839,
|
1722 |
+
"grad_norm": 6.8120436668396,
|
1723 |
+
"learning_rate": 0.00019390600809129772,
|
1724 |
+
"loss": 1.3372,
|
1725 |
+
"step": 98000
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 0.22533198683731442,
|
1729 |
+
"grad_norm": 3.1833598613739014,
|
1730 |
+
"learning_rate": 0.00019385642245432077,
|
1731 |
+
"loss": 1.3251,
|
1732 |
+
"step": 98400
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 0.22624797052364498,
|
1736 |
+
"grad_norm": 2.615337610244751,
|
1737 |
+
"learning_rate": 0.00019380664229183775,
|
1738 |
+
"loss": 1.3092,
|
1739 |
+
"step": 98800
|
1740 |
+
}
|
1741 |
+
],
|
1742 |
+
"logging_steps": 400,
|
1743 |
+
"max_steps": 873378,
|
1744 |
+
"num_input_tokens_seen": 0,
|
1745 |
+
"num_train_epochs": 2,
|
1746 |
+
"save_steps": 50,
|
1747 |
+
"stateful_callbacks": {
|
1748 |
+
"TrainerControl": {
|
1749 |
+
"args": {
|
1750 |
+
"should_epoch_stop": false,
|
1751 |
+
"should_evaluate": false,
|
1752 |
+
"should_log": false,
|
1753 |
+
"should_save": true,
|
1754 |
+
"should_training_stop": false
|
1755 |
+
},
|
1756 |
+
"attributes": {}
|
1757 |
+
}
|
1758 |
+
},
|
1759 |
+
"total_flos": 1.23869495033856e+18,
|
1760 |
+
"train_batch_size": 2,
|
1761 |
+
"trial_name": null,
|
1762 |
+
"trial_params": null
|
1763 |
+
}
|
checkpoint-99000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d41cf245f1cbaed3057de22d80908b9da1fb1f2b5972cc6b8230f38f3f7323c2
|
3 |
+
size 5304
|