Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +207 -0
- adapter_config.json +41 -0
- adapter_model.safetensors +3 -0
- chat_template.jinja +1 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2063 -0
- trainer_state.json +2158 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: nvidia/Llama-3_3-Nemotron-Super-49B-v1
|
3 |
+
library_name: peft
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- base_model:adapter:nvidia/Llama-3_3-Nemotron-Super-49B-v1
|
7 |
+
- lora
|
8 |
+
- transformers
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Card for Model ID
|
12 |
+
|
13 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
14 |
+
|
15 |
+
|
16 |
+
|
17 |
+
## Model Details
|
18 |
+
|
19 |
+
### Model Description
|
20 |
+
|
21 |
+
<!-- Provide a longer summary of what this model is. -->
|
22 |
+
|
23 |
+
|
24 |
+
|
25 |
+
- **Developed by:** [More Information Needed]
|
26 |
+
- **Funded by [optional]:** [More Information Needed]
|
27 |
+
- **Shared by [optional]:** [More Information Needed]
|
28 |
+
- **Model type:** [More Information Needed]
|
29 |
+
- **Language(s) (NLP):** [More Information Needed]
|
30 |
+
- **License:** [More Information Needed]
|
31 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
32 |
+
|
33 |
+
### Model Sources [optional]
|
34 |
+
|
35 |
+
<!-- Provide the basic links for the model. -->
|
36 |
+
|
37 |
+
- **Repository:** [More Information Needed]
|
38 |
+
- **Paper [optional]:** [More Information Needed]
|
39 |
+
- **Demo [optional]:** [More Information Needed]
|
40 |
+
|
41 |
+
## Uses
|
42 |
+
|
43 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
44 |
+
|
45 |
+
### Direct Use
|
46 |
+
|
47 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
48 |
+
|
49 |
+
[More Information Needed]
|
50 |
+
|
51 |
+
### Downstream Use [optional]
|
52 |
+
|
53 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
54 |
+
|
55 |
+
[More Information Needed]
|
56 |
+
|
57 |
+
### Out-of-Scope Use
|
58 |
+
|
59 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
60 |
+
|
61 |
+
[More Information Needed]
|
62 |
+
|
63 |
+
## Bias, Risks, and Limitations
|
64 |
+
|
65 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
66 |
+
|
67 |
+
[More Information Needed]
|
68 |
+
|
69 |
+
### Recommendations
|
70 |
+
|
71 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
72 |
+
|
73 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
74 |
+
|
75 |
+
## How to Get Started with the Model
|
76 |
+
|
77 |
+
Use the code below to get started with the model.
|
78 |
+
|
79 |
+
[More Information Needed]
|
80 |
+
|
81 |
+
## Training Details
|
82 |
+
|
83 |
+
### Training Data
|
84 |
+
|
85 |
+
<!-- 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. -->
|
86 |
+
|
87 |
+
[More Information Needed]
|
88 |
+
|
89 |
+
### Training Procedure
|
90 |
+
|
91 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
92 |
+
|
93 |
+
#### Preprocessing [optional]
|
94 |
+
|
95 |
+
[More Information Needed]
|
96 |
+
|
97 |
+
|
98 |
+
#### Training Hyperparameters
|
99 |
+
|
100 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
101 |
+
|
102 |
+
#### Speeds, Sizes, Times [optional]
|
103 |
+
|
104 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
105 |
+
|
106 |
+
[More Information Needed]
|
107 |
+
|
108 |
+
## Evaluation
|
109 |
+
|
110 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
111 |
+
|
112 |
+
### Testing Data, Factors & Metrics
|
113 |
+
|
114 |
+
#### Testing Data
|
115 |
+
|
116 |
+
<!-- This should link to a Dataset Card if possible. -->
|
117 |
+
|
118 |
+
[More Information Needed]
|
119 |
+
|
120 |
+
#### Factors
|
121 |
+
|
122 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
123 |
+
|
124 |
+
[More Information Needed]
|
125 |
+
|
126 |
+
#### Metrics
|
127 |
+
|
128 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
129 |
+
|
130 |
+
[More Information Needed]
|
131 |
+
|
132 |
+
### Results
|
133 |
+
|
134 |
+
[More Information Needed]
|
135 |
+
|
136 |
+
#### Summary
|
137 |
+
|
138 |
+
|
139 |
+
|
140 |
+
## Model Examination [optional]
|
141 |
+
|
142 |
+
<!-- Relevant interpretability work for the model goes here -->
|
143 |
+
|
144 |
+
[More Information Needed]
|
145 |
+
|
146 |
+
## Environmental Impact
|
147 |
+
|
148 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
149 |
+
|
150 |
+
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).
|
151 |
+
|
152 |
+
- **Hardware Type:** [More Information Needed]
|
153 |
+
- **Hours used:** [More Information Needed]
|
154 |
+
- **Cloud Provider:** [More Information Needed]
|
155 |
+
- **Compute Region:** [More Information Needed]
|
156 |
+
- **Carbon Emitted:** [More Information Needed]
|
157 |
+
|
158 |
+
## Technical Specifications [optional]
|
159 |
+
|
160 |
+
### Model Architecture and Objective
|
161 |
+
|
162 |
+
[More Information Needed]
|
163 |
+
|
164 |
+
### Compute Infrastructure
|
165 |
+
|
166 |
+
[More Information Needed]
|
167 |
+
|
168 |
+
#### Hardware
|
169 |
+
|
170 |
+
[More Information Needed]
|
171 |
+
|
172 |
+
#### Software
|
173 |
+
|
174 |
+
[More Information Needed]
|
175 |
+
|
176 |
+
## Citation [optional]
|
177 |
+
|
178 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
179 |
+
|
180 |
+
**BibTeX:**
|
181 |
+
|
182 |
+
[More Information Needed]
|
183 |
+
|
184 |
+
**APA:**
|
185 |
+
|
186 |
+
[More Information Needed]
|
187 |
+
|
188 |
+
## Glossary [optional]
|
189 |
+
|
190 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
191 |
+
|
192 |
+
[More Information Needed]
|
193 |
+
|
194 |
+
## More Information [optional]
|
195 |
+
|
196 |
+
[More Information Needed]
|
197 |
+
|
198 |
+
## Model Card Authors [optional]
|
199 |
+
|
200 |
+
[More Information Needed]
|
201 |
+
|
202 |
+
## Model Card Contact
|
203 |
+
|
204 |
+
[More Information Needed]
|
205 |
+
### Framework versions
|
206 |
+
|
207 |
+
- PEFT 0.16.0
|
adapter_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "nvidia/Llama-3_3-Nemotron-Super-49B-v1",
|
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 |
+
"qalora_group_size": 16,
|
24 |
+
"r": 64,
|
25 |
+
"rank_pattern": {},
|
26 |
+
"revision": null,
|
27 |
+
"target_modules": [
|
28 |
+
"o_proj",
|
29 |
+
"gate_proj",
|
30 |
+
"q_proj",
|
31 |
+
"up_proj",
|
32 |
+
"k_proj",
|
33 |
+
"v_proj",
|
34 |
+
"down_proj"
|
35 |
+
],
|
36 |
+
"task_type": "CAUSAL_LM",
|
37 |
+
"trainable_token_indices": null,
|
38 |
+
"use_dora": false,
|
39 |
+
"use_qalora": false,
|
40 |
+
"use_rslora": false
|
41 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9773a2b163096ef686db10f125cb6c5442be4468da6ec65b5c41effdb3301a20
|
3 |
+
size 2407124984
|
chat_template.jinja
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{{- bos_token }}{%- if messages[0]['role'] == 'system' %}{%- set system_message = messages[0]['content']|trim %}{%- set messages = messages[1:] %}{%- else %}{%- set system_message = "" %}{%- endif %}{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}{{- system_message }}{{- "<|eot_id|>" }}{%- for message in messages %}{%- if message['role'] == 'assistant' and '</think>' in message['content'] %}{%- set content = message['content'].split('</think>')[-1].lstrip() %}{%- else %}{%- set content = message['content'] %}{%- endif %}{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + content | trim + '<|eot_id|>' }}{%- endfor %}{%- if add_generation_prompt %}{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{%- endif %}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdc08050c40d80abc6807b01161f0bba43072e72516f633f172a9fb27199af63
|
3 |
+
size 4814766483
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db61035136b236555c8504e792c62845ebda02ba222cfea40d6bf96a3f8b7e16
|
3 |
+
size 14917
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0542557bfea7b4e5a91714666547e6993ed1dacac5d10597fc4b847e70fc6834
|
3 |
+
size 14917
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e4f68aa5539ae9e9482237c94f5aa413280dbe2c1b409a7f57e2856674e9174
|
3 |
+
size 1465
|
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 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
3 |
+
size 17209920
|
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": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 3000,
|
3 |
+
"best_metric": 0.9846093654632568,
|
4 |
+
"best_model_checkpoint": "/workspace/runs_woodcoder_noed_doctok/checkpoint-3000",
|
5 |
+
"epoch": 0.5584512285927029,
|
6 |
+
"eval_steps": 1000,
|
7 |
+
"global_step": 3000,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 0.0018615040953090098,
|
14 |
+
"grad_norm": 0.7674914002418518,
|
15 |
+
"learning_rate": 9.98324646314222e-06,
|
16 |
+
"loss": 2.1657,
|
17 |
+
"step": 10
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.0037230081906180195,
|
21 |
+
"grad_norm": 0.45955613255500793,
|
22 |
+
"learning_rate": 9.96463142218913e-06,
|
23 |
+
"loss": 1.9308,
|
24 |
+
"step": 20
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.005584512285927029,
|
28 |
+
"grad_norm": 0.38521695137023926,
|
29 |
+
"learning_rate": 9.94601638123604e-06,
|
30 |
+
"loss": 1.7409,
|
31 |
+
"step": 30
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.007446016381236039,
|
35 |
+
"grad_norm": 0.36704158782958984,
|
36 |
+
"learning_rate": 9.927401340282949e-06,
|
37 |
+
"loss": 1.654,
|
38 |
+
"step": 40
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.009307520476545048,
|
42 |
+
"grad_norm": 0.33126699924468994,
|
43 |
+
"learning_rate": 9.908786299329859e-06,
|
44 |
+
"loss": 1.565,
|
45 |
+
"step": 50
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.011169024571854059,
|
49 |
+
"grad_norm": 0.33799418807029724,
|
50 |
+
"learning_rate": 9.89017125837677e-06,
|
51 |
+
"loss": 1.4881,
|
52 |
+
"step": 60
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.013030528667163067,
|
56 |
+
"grad_norm": 0.35992538928985596,
|
57 |
+
"learning_rate": 9.87155621742368e-06,
|
58 |
+
"loss": 1.4591,
|
59 |
+
"step": 70
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.014892032762472078,
|
63 |
+
"grad_norm": 0.37104639410972595,
|
64 |
+
"learning_rate": 9.852941176470589e-06,
|
65 |
+
"loss": 1.4483,
|
66 |
+
"step": 80
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.01675353685778109,
|
70 |
+
"grad_norm": 0.39575058221817017,
|
71 |
+
"learning_rate": 9.834326135517499e-06,
|
72 |
+
"loss": 1.3643,
|
73 |
+
"step": 90
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.018615040953090096,
|
77 |
+
"grad_norm": 0.4714430570602417,
|
78 |
+
"learning_rate": 9.815711094564408e-06,
|
79 |
+
"loss": 1.3396,
|
80 |
+
"step": 100
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.020476545048399106,
|
84 |
+
"grad_norm": 0.4331431984901428,
|
85 |
+
"learning_rate": 9.79709605361132e-06,
|
86 |
+
"loss": 1.3313,
|
87 |
+
"step": 110
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.022338049143708117,
|
91 |
+
"grad_norm": 0.48714113235473633,
|
92 |
+
"learning_rate": 9.778481012658229e-06,
|
93 |
+
"loss": 1.3349,
|
94 |
+
"step": 120
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.024199553239017124,
|
98 |
+
"grad_norm": 0.4605439603328705,
|
99 |
+
"learning_rate": 9.759865971705139e-06,
|
100 |
+
"loss": 1.2987,
|
101 |
+
"step": 130
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.026061057334326135,
|
105 |
+
"grad_norm": 0.5611202120780945,
|
106 |
+
"learning_rate": 9.741250930752048e-06,
|
107 |
+
"loss": 1.2958,
|
108 |
+
"step": 140
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.027922561429635145,
|
112 |
+
"grad_norm": 0.5166555643081665,
|
113 |
+
"learning_rate": 9.722635889798958e-06,
|
114 |
+
"loss": 1.2701,
|
115 |
+
"step": 150
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.029784065524944156,
|
119 |
+
"grad_norm": 0.4774516820907593,
|
120 |
+
"learning_rate": 9.704020848845869e-06,
|
121 |
+
"loss": 1.2691,
|
122 |
+
"step": 160
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.03164556962025317,
|
126 |
+
"grad_norm": 0.5399760007858276,
|
127 |
+
"learning_rate": 9.685405807892779e-06,
|
128 |
+
"loss": 1.2494,
|
129 |
+
"step": 170
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.03350707371556218,
|
133 |
+
"grad_norm": 0.5710811018943787,
|
134 |
+
"learning_rate": 9.666790766939688e-06,
|
135 |
+
"loss": 1.2264,
|
136 |
+
"step": 180
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.03536857781087118,
|
140 |
+
"grad_norm": 0.5183510780334473,
|
141 |
+
"learning_rate": 9.648175725986598e-06,
|
142 |
+
"loss": 1.24,
|
143 |
+
"step": 190
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.03723008190618019,
|
147 |
+
"grad_norm": 0.6085354089736938,
|
148 |
+
"learning_rate": 9.629560685033507e-06,
|
149 |
+
"loss": 1.218,
|
150 |
+
"step": 200
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.0390915860014892,
|
154 |
+
"grad_norm": 0.560085117816925,
|
155 |
+
"learning_rate": 9.610945644080419e-06,
|
156 |
+
"loss": 1.2043,
|
157 |
+
"step": 210
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.04095309009679821,
|
161 |
+
"grad_norm": 0.6347622275352478,
|
162 |
+
"learning_rate": 9.592330603127328e-06,
|
163 |
+
"loss": 1.1912,
|
164 |
+
"step": 220
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.04281459419210722,
|
168 |
+
"grad_norm": 0.5740385055541992,
|
169 |
+
"learning_rate": 9.573715562174238e-06,
|
170 |
+
"loss": 1.1808,
|
171 |
+
"step": 230
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.044676098287416234,
|
175 |
+
"grad_norm": 0.5910650491714478,
|
176 |
+
"learning_rate": 9.555100521221147e-06,
|
177 |
+
"loss": 1.1935,
|
178 |
+
"step": 240
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.046537602382725245,
|
182 |
+
"grad_norm": 0.6126322746276855,
|
183 |
+
"learning_rate": 9.536485480268057e-06,
|
184 |
+
"loss": 1.191,
|
185 |
+
"step": 250
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.04839910647803425,
|
189 |
+
"grad_norm": 0.6276088356971741,
|
190 |
+
"learning_rate": 9.517870439314967e-06,
|
191 |
+
"loss": 1.1956,
|
192 |
+
"step": 260
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.05026061057334326,
|
196 |
+
"grad_norm": 0.6804961562156677,
|
197 |
+
"learning_rate": 9.499255398361878e-06,
|
198 |
+
"loss": 1.1567,
|
199 |
+
"step": 270
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.05212211466865227,
|
203 |
+
"grad_norm": 0.672312319278717,
|
204 |
+
"learning_rate": 9.480640357408788e-06,
|
205 |
+
"loss": 1.1594,
|
206 |
+
"step": 280
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.05398361876396128,
|
210 |
+
"grad_norm": 0.6751535534858704,
|
211 |
+
"learning_rate": 9.462025316455697e-06,
|
212 |
+
"loss": 1.1567,
|
213 |
+
"step": 290
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.05584512285927029,
|
217 |
+
"grad_norm": 0.6339168548583984,
|
218 |
+
"learning_rate": 9.443410275502607e-06,
|
219 |
+
"loss": 1.1642,
|
220 |
+
"step": 300
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.0577066269545793,
|
224 |
+
"grad_norm": 0.7527929544448853,
|
225 |
+
"learning_rate": 9.424795234549516e-06,
|
226 |
+
"loss": 1.1347,
|
227 |
+
"step": 310
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.05956813104988831,
|
231 |
+
"grad_norm": 0.7240985631942749,
|
232 |
+
"learning_rate": 9.406180193596428e-06,
|
233 |
+
"loss": 1.1528,
|
234 |
+
"step": 320
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.06142963514519732,
|
238 |
+
"grad_norm": 0.649124801158905,
|
239 |
+
"learning_rate": 9.387565152643337e-06,
|
240 |
+
"loss": 1.1451,
|
241 |
+
"step": 330
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.06329113924050633,
|
245 |
+
"grad_norm": 0.6791466474533081,
|
246 |
+
"learning_rate": 9.368950111690247e-06,
|
247 |
+
"loss": 1.1612,
|
248 |
+
"step": 340
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.06515264333581534,
|
252 |
+
"grad_norm": 0.7401267290115356,
|
253 |
+
"learning_rate": 9.350335070737156e-06,
|
254 |
+
"loss": 1.1321,
|
255 |
+
"step": 350
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.06701414743112435,
|
259 |
+
"grad_norm": 0.6535454392433167,
|
260 |
+
"learning_rate": 9.331720029784066e-06,
|
261 |
+
"loss": 1.1513,
|
262 |
+
"step": 360
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.06887565152643335,
|
266 |
+
"grad_norm": 0.6639511585235596,
|
267 |
+
"learning_rate": 9.313104988830977e-06,
|
268 |
+
"loss": 1.1278,
|
269 |
+
"step": 370
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.07073715562174236,
|
273 |
+
"grad_norm": 0.6609712839126587,
|
274 |
+
"learning_rate": 9.294489947877887e-06,
|
275 |
+
"loss": 1.1171,
|
276 |
+
"step": 380
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.07259865971705137,
|
280 |
+
"grad_norm": 0.7166458368301392,
|
281 |
+
"learning_rate": 9.275874906924796e-06,
|
282 |
+
"loss": 1.1202,
|
283 |
+
"step": 390
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.07446016381236038,
|
287 |
+
"grad_norm": 0.6681793332099915,
|
288 |
+
"learning_rate": 9.257259865971706e-06,
|
289 |
+
"loss": 1.1532,
|
290 |
+
"step": 400
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.0763216679076694,
|
294 |
+
"grad_norm": 0.6721240282058716,
|
295 |
+
"learning_rate": 9.238644825018615e-06,
|
296 |
+
"loss": 1.1127,
|
297 |
+
"step": 410
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.0781831720029784,
|
301 |
+
"grad_norm": 0.671623706817627,
|
302 |
+
"learning_rate": 9.220029784065527e-06,
|
303 |
+
"loss": 1.1213,
|
304 |
+
"step": 420
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.08004467609828742,
|
308 |
+
"grad_norm": 0.7126383185386658,
|
309 |
+
"learning_rate": 9.201414743112436e-06,
|
310 |
+
"loss": 1.1247,
|
311 |
+
"step": 430
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.08190618019359643,
|
315 |
+
"grad_norm": 0.754092276096344,
|
316 |
+
"learning_rate": 9.182799702159346e-06,
|
317 |
+
"loss": 1.1286,
|
318 |
+
"step": 440
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.08376768428890544,
|
322 |
+
"grad_norm": 0.7067962884902954,
|
323 |
+
"learning_rate": 9.164184661206256e-06,
|
324 |
+
"loss": 1.1333,
|
325 |
+
"step": 450
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.08562918838421445,
|
329 |
+
"grad_norm": 0.8112648725509644,
|
330 |
+
"learning_rate": 9.145569620253165e-06,
|
331 |
+
"loss": 1.1009,
|
332 |
+
"step": 460
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.08749069247952346,
|
336 |
+
"grad_norm": 0.683518648147583,
|
337 |
+
"learning_rate": 9.126954579300075e-06,
|
338 |
+
"loss": 1.1023,
|
339 |
+
"step": 470
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.08935219657483247,
|
343 |
+
"grad_norm": 0.7806974053382874,
|
344 |
+
"learning_rate": 9.108339538346986e-06,
|
345 |
+
"loss": 1.0988,
|
346 |
+
"step": 480
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.09121370067014148,
|
350 |
+
"grad_norm": 0.8435746431350708,
|
351 |
+
"learning_rate": 9.089724497393896e-06,
|
352 |
+
"loss": 1.1234,
|
353 |
+
"step": 490
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.09307520476545049,
|
357 |
+
"grad_norm": 0.7590988278388977,
|
358 |
+
"learning_rate": 9.071109456440805e-06,
|
359 |
+
"loss": 1.1064,
|
360 |
+
"step": 500
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.0949367088607595,
|
364 |
+
"grad_norm": 0.7976896166801453,
|
365 |
+
"learning_rate": 9.052494415487715e-06,
|
366 |
+
"loss": 1.1103,
|
367 |
+
"step": 510
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.0967982129560685,
|
371 |
+
"grad_norm": 0.7710254192352295,
|
372 |
+
"learning_rate": 9.033879374534624e-06,
|
373 |
+
"loss": 1.1019,
|
374 |
+
"step": 520
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.09865971705137751,
|
378 |
+
"grad_norm": 0.7000139355659485,
|
379 |
+
"learning_rate": 9.015264333581536e-06,
|
380 |
+
"loss": 1.1034,
|
381 |
+
"step": 530
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.10052122114668652,
|
385 |
+
"grad_norm": 0.8466401696205139,
|
386 |
+
"learning_rate": 8.996649292628445e-06,
|
387 |
+
"loss": 1.0838,
|
388 |
+
"step": 540
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.10238272524199553,
|
392 |
+
"grad_norm": 0.7491502165794373,
|
393 |
+
"learning_rate": 8.978034251675355e-06,
|
394 |
+
"loss": 1.0951,
|
395 |
+
"step": 550
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.10424422933730454,
|
399 |
+
"grad_norm": 0.8434305191040039,
|
400 |
+
"learning_rate": 8.959419210722264e-06,
|
401 |
+
"loss": 1.084,
|
402 |
+
"step": 560
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.10610573343261355,
|
406 |
+
"grad_norm": 0.6647118330001831,
|
407 |
+
"learning_rate": 8.940804169769174e-06,
|
408 |
+
"loss": 1.0806,
|
409 |
+
"step": 570
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.10796723752792256,
|
413 |
+
"grad_norm": 0.7332665920257568,
|
414 |
+
"learning_rate": 8.922189128816085e-06,
|
415 |
+
"loss": 1.1123,
|
416 |
+
"step": 580
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.10982874162323157,
|
420 |
+
"grad_norm": 0.7808273434638977,
|
421 |
+
"learning_rate": 8.903574087862995e-06,
|
422 |
+
"loss": 1.103,
|
423 |
+
"step": 590
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.11169024571854058,
|
427 |
+
"grad_norm": 0.7828446626663208,
|
428 |
+
"learning_rate": 8.884959046909903e-06,
|
429 |
+
"loss": 1.0877,
|
430 |
+
"step": 600
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.11355174981384959,
|
434 |
+
"grad_norm": 0.7924163937568665,
|
435 |
+
"learning_rate": 8.866344005956814e-06,
|
436 |
+
"loss": 1.0963,
|
437 |
+
"step": 610
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.1154132539091586,
|
441 |
+
"grad_norm": 0.8362071514129639,
|
442 |
+
"learning_rate": 8.847728965003723e-06,
|
443 |
+
"loss": 1.0709,
|
444 |
+
"step": 620
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.11727475800446761,
|
448 |
+
"grad_norm": 0.7338322401046753,
|
449 |
+
"learning_rate": 8.829113924050635e-06,
|
450 |
+
"loss": 1.1296,
|
451 |
+
"step": 630
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.11913626209977662,
|
455 |
+
"grad_norm": 0.7844275832176208,
|
456 |
+
"learning_rate": 8.810498883097544e-06,
|
457 |
+
"loss": 1.0907,
|
458 |
+
"step": 640
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.12099776619508563,
|
462 |
+
"grad_norm": 0.7330830097198486,
|
463 |
+
"learning_rate": 8.791883842144452e-06,
|
464 |
+
"loss": 1.082,
|
465 |
+
"step": 650
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.12285927029039465,
|
469 |
+
"grad_norm": 0.7563046813011169,
|
470 |
+
"learning_rate": 8.773268801191364e-06,
|
471 |
+
"loss": 1.0767,
|
472 |
+
"step": 660
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.12472077438570364,
|
476 |
+
"grad_norm": 0.8811011910438538,
|
477 |
+
"learning_rate": 8.754653760238273e-06,
|
478 |
+
"loss": 1.06,
|
479 |
+
"step": 670
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.12658227848101267,
|
483 |
+
"grad_norm": 0.8396238088607788,
|
484 |
+
"learning_rate": 8.736038719285184e-06,
|
485 |
+
"loss": 1.0827,
|
486 |
+
"step": 680
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.12844378257632166,
|
490 |
+
"grad_norm": 0.8192409873008728,
|
491 |
+
"learning_rate": 8.717423678332094e-06,
|
492 |
+
"loss": 1.0829,
|
493 |
+
"step": 690
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.1303052866716307,
|
497 |
+
"grad_norm": 0.7337971329689026,
|
498 |
+
"learning_rate": 8.698808637379002e-06,
|
499 |
+
"loss": 1.0703,
|
500 |
+
"step": 700
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.13216679076693968,
|
504 |
+
"grad_norm": 0.8743414282798767,
|
505 |
+
"learning_rate": 8.680193596425913e-06,
|
506 |
+
"loss": 1.0664,
|
507 |
+
"step": 710
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.1340282948622487,
|
511 |
+
"grad_norm": 0.7435793876647949,
|
512 |
+
"learning_rate": 8.661578555472823e-06,
|
513 |
+
"loss": 1.0623,
|
514 |
+
"step": 720
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.1358897989575577,
|
518 |
+
"grad_norm": 0.801527738571167,
|
519 |
+
"learning_rate": 8.642963514519732e-06,
|
520 |
+
"loss": 1.0836,
|
521 |
+
"step": 730
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.1377513030528667,
|
525 |
+
"grad_norm": 0.7889235615730286,
|
526 |
+
"learning_rate": 8.624348473566642e-06,
|
527 |
+
"loss": 1.0654,
|
528 |
+
"step": 740
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.13961280714817573,
|
532 |
+
"grad_norm": 0.7724790573120117,
|
533 |
+
"learning_rate": 8.605733432613551e-06,
|
534 |
+
"loss": 1.0718,
|
535 |
+
"step": 750
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.14147431124348472,
|
539 |
+
"grad_norm": 0.7666871547698975,
|
540 |
+
"learning_rate": 8.587118391660463e-06,
|
541 |
+
"loss": 1.0782,
|
542 |
+
"step": 760
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.14333581533879375,
|
546 |
+
"grad_norm": 0.8468601107597351,
|
547 |
+
"learning_rate": 8.568503350707372e-06,
|
548 |
+
"loss": 1.0585,
|
549 |
+
"step": 770
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.14519731943410275,
|
553 |
+
"grad_norm": 0.718026340007782,
|
554 |
+
"learning_rate": 8.549888309754282e-06,
|
555 |
+
"loss": 1.0753,
|
556 |
+
"step": 780
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.14705882352941177,
|
560 |
+
"grad_norm": 0.7626808881759644,
|
561 |
+
"learning_rate": 8.531273268801191e-06,
|
562 |
+
"loss": 1.0457,
|
563 |
+
"step": 790
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.14892032762472077,
|
567 |
+
"grad_norm": 0.7808538675308228,
|
568 |
+
"learning_rate": 8.512658227848101e-06,
|
569 |
+
"loss": 1.0442,
|
570 |
+
"step": 800
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.1507818317200298,
|
574 |
+
"grad_norm": 0.8262965083122253,
|
575 |
+
"learning_rate": 8.494043186895012e-06,
|
576 |
+
"loss": 1.0699,
|
577 |
+
"step": 810
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.1526433358153388,
|
581 |
+
"grad_norm": 0.7817132472991943,
|
582 |
+
"learning_rate": 8.475428145941922e-06,
|
583 |
+
"loss": 1.0725,
|
584 |
+
"step": 820
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.1545048399106478,
|
588 |
+
"grad_norm": 0.7651262879371643,
|
589 |
+
"learning_rate": 8.456813104988832e-06,
|
590 |
+
"loss": 1.0709,
|
591 |
+
"step": 830
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.1563663440059568,
|
595 |
+
"grad_norm": 0.7985157370567322,
|
596 |
+
"learning_rate": 8.438198064035741e-06,
|
597 |
+
"loss": 1.0682,
|
598 |
+
"step": 840
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.15822784810126583,
|
602 |
+
"grad_norm": 0.9404885768890381,
|
603 |
+
"learning_rate": 8.41958302308265e-06,
|
604 |
+
"loss": 1.0413,
|
605 |
+
"step": 850
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.16008935219657483,
|
609 |
+
"grad_norm": 0.7845138907432556,
|
610 |
+
"learning_rate": 8.40096798212956e-06,
|
611 |
+
"loss": 1.0606,
|
612 |
+
"step": 860
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.16195085629188385,
|
616 |
+
"grad_norm": 0.894644021987915,
|
617 |
+
"learning_rate": 8.382352941176472e-06,
|
618 |
+
"loss": 1.0589,
|
619 |
+
"step": 870
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.16381236038719285,
|
623 |
+
"grad_norm": 0.8642441630363464,
|
624 |
+
"learning_rate": 8.363737900223381e-06,
|
625 |
+
"loss": 1.0514,
|
626 |
+
"step": 880
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.16567386448250185,
|
630 |
+
"grad_norm": 0.7596301436424255,
|
631 |
+
"learning_rate": 8.34512285927029e-06,
|
632 |
+
"loss": 1.0356,
|
633 |
+
"step": 890
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.16753536857781087,
|
637 |
+
"grad_norm": 0.7968301177024841,
|
638 |
+
"learning_rate": 8.3265078183172e-06,
|
639 |
+
"loss": 1.0706,
|
640 |
+
"step": 900
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.16939687267311987,
|
644 |
+
"grad_norm": 0.7575682997703552,
|
645 |
+
"learning_rate": 8.30789277736411e-06,
|
646 |
+
"loss": 1.0554,
|
647 |
+
"step": 910
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.1712583767684289,
|
651 |
+
"grad_norm": 0.8771592378616333,
|
652 |
+
"learning_rate": 8.289277736411021e-06,
|
653 |
+
"loss": 1.0556,
|
654 |
+
"step": 920
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.1731198808637379,
|
658 |
+
"grad_norm": 0.8053440451622009,
|
659 |
+
"learning_rate": 8.27066269545793e-06,
|
660 |
+
"loss": 1.0635,
|
661 |
+
"step": 930
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.17498138495904692,
|
665 |
+
"grad_norm": 0.8692678809165955,
|
666 |
+
"learning_rate": 8.25204765450484e-06,
|
667 |
+
"loss": 1.0844,
|
668 |
+
"step": 940
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.1768428890543559,
|
672 |
+
"grad_norm": 0.8526129722595215,
|
673 |
+
"learning_rate": 8.23343261355175e-06,
|
674 |
+
"loss": 1.0478,
|
675 |
+
"step": 950
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.17870439314966494,
|
679 |
+
"grad_norm": 0.793351411819458,
|
680 |
+
"learning_rate": 8.21481757259866e-06,
|
681 |
+
"loss": 1.0419,
|
682 |
+
"step": 960
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.18056589724497393,
|
686 |
+
"grad_norm": 0.7729631066322327,
|
687 |
+
"learning_rate": 8.19620253164557e-06,
|
688 |
+
"loss": 1.0634,
|
689 |
+
"step": 970
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.18242740134028296,
|
693 |
+
"grad_norm": 0.8328572511672974,
|
694 |
+
"learning_rate": 8.17758749069248e-06,
|
695 |
+
"loss": 1.036,
|
696 |
+
"step": 980
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.18428890543559195,
|
700 |
+
"grad_norm": 0.9167013764381409,
|
701 |
+
"learning_rate": 8.15897244973939e-06,
|
702 |
+
"loss": 1.0415,
|
703 |
+
"step": 990
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.18615040953090098,
|
707 |
+
"grad_norm": 0.7979336380958557,
|
708 |
+
"learning_rate": 8.1403574087863e-06,
|
709 |
+
"loss": 1.0341,
|
710 |
+
"step": 1000
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.18615040953090098,
|
714 |
+
"eval_loss": 1.0488137006759644,
|
715 |
+
"eval_runtime": 1068.2291,
|
716 |
+
"eval_samples_per_second": 17.881,
|
717 |
+
"eval_steps_per_second": 0.559,
|
718 |
+
"step": 1000
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 0.18801191362620998,
|
722 |
+
"grad_norm": 0.8544522523880005,
|
723 |
+
"learning_rate": 8.121742367833209e-06,
|
724 |
+
"loss": 1.0473,
|
725 |
+
"step": 1010
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 0.189873417721519,
|
729 |
+
"grad_norm": 0.9185499548912048,
|
730 |
+
"learning_rate": 8.10312732688012e-06,
|
731 |
+
"loss": 1.0524,
|
732 |
+
"step": 1020
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.191734921816828,
|
736 |
+
"grad_norm": 0.7603698372840881,
|
737 |
+
"learning_rate": 8.08451228592703e-06,
|
738 |
+
"loss": 1.0812,
|
739 |
+
"step": 1030
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.193596425912137,
|
743 |
+
"grad_norm": 0.8724957704544067,
|
744 |
+
"learning_rate": 8.06589724497394e-06,
|
745 |
+
"loss": 1.041,
|
746 |
+
"step": 1040
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.19545793000744602,
|
750 |
+
"grad_norm": 0.8294175863265991,
|
751 |
+
"learning_rate": 8.047282204020849e-06,
|
752 |
+
"loss": 1.0656,
|
753 |
+
"step": 1050
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.19731943410275501,
|
757 |
+
"grad_norm": 0.8525722026824951,
|
758 |
+
"learning_rate": 8.028667163067759e-06,
|
759 |
+
"loss": 1.0734,
|
760 |
+
"step": 1060
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.19918093819806404,
|
764 |
+
"grad_norm": 0.7782772779464722,
|
765 |
+
"learning_rate": 8.010052122114668e-06,
|
766 |
+
"loss": 1.0453,
|
767 |
+
"step": 1070
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.20104244229337304,
|
771 |
+
"grad_norm": 0.9156838655471802,
|
772 |
+
"learning_rate": 7.99143708116158e-06,
|
773 |
+
"loss": 1.0543,
|
774 |
+
"step": 1080
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.20290394638868206,
|
778 |
+
"grad_norm": 0.8498939871788025,
|
779 |
+
"learning_rate": 7.97282204020849e-06,
|
780 |
+
"loss": 1.047,
|
781 |
+
"step": 1090
|
782 |
+
},
|
783 |
+
{
|
784 |
+
"epoch": 0.20476545048399106,
|
785 |
+
"grad_norm": 0.8343819975852966,
|
786 |
+
"learning_rate": 7.954206999255399e-06,
|
787 |
+
"loss": 1.0374,
|
788 |
+
"step": 1100
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 0.20662695457930008,
|
792 |
+
"grad_norm": 0.8868606090545654,
|
793 |
+
"learning_rate": 7.935591958302308e-06,
|
794 |
+
"loss": 1.0483,
|
795 |
+
"step": 1110
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.20848845867460908,
|
799 |
+
"grad_norm": 0.8131170272827148,
|
800 |
+
"learning_rate": 7.916976917349218e-06,
|
801 |
+
"loss": 1.0422,
|
802 |
+
"step": 1120
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.2103499627699181,
|
806 |
+
"grad_norm": 0.7965826988220215,
|
807 |
+
"learning_rate": 7.89836187639613e-06,
|
808 |
+
"loss": 1.0623,
|
809 |
+
"step": 1130
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 0.2122114668652271,
|
813 |
+
"grad_norm": 0.9153191447257996,
|
814 |
+
"learning_rate": 7.879746835443039e-06,
|
815 |
+
"loss": 1.0252,
|
816 |
+
"step": 1140
|
817 |
+
},
|
818 |
+
{
|
819 |
+
"epoch": 0.21407297096053612,
|
820 |
+
"grad_norm": 0.8058901429176331,
|
821 |
+
"learning_rate": 7.861131794489948e-06,
|
822 |
+
"loss": 1.0352,
|
823 |
+
"step": 1150
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.21593447505584512,
|
827 |
+
"grad_norm": 0.9619394540786743,
|
828 |
+
"learning_rate": 7.842516753536858e-06,
|
829 |
+
"loss": 1.0255,
|
830 |
+
"step": 1160
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 0.21779597915115415,
|
834 |
+
"grad_norm": 0.9062040448188782,
|
835 |
+
"learning_rate": 7.823901712583768e-06,
|
836 |
+
"loss": 1.0479,
|
837 |
+
"step": 1170
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.21965748324646314,
|
841 |
+
"grad_norm": 0.9075378179550171,
|
842 |
+
"learning_rate": 7.805286671630679e-06,
|
843 |
+
"loss": 1.0153,
|
844 |
+
"step": 1180
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 0.22151898734177214,
|
848 |
+
"grad_norm": 0.8396610617637634,
|
849 |
+
"learning_rate": 7.786671630677588e-06,
|
850 |
+
"loss": 1.0403,
|
851 |
+
"step": 1190
|
852 |
+
},
|
853 |
+
{
|
854 |
+
"epoch": 0.22338049143708116,
|
855 |
+
"grad_norm": 0.8443580865859985,
|
856 |
+
"learning_rate": 7.768056589724498e-06,
|
857 |
+
"loss": 1.0504,
|
858 |
+
"step": 1200
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.22524199553239016,
|
862 |
+
"grad_norm": 0.8694491982460022,
|
863 |
+
"learning_rate": 7.749441548771408e-06,
|
864 |
+
"loss": 1.0427,
|
865 |
+
"step": 1210
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 0.22710349962769918,
|
869 |
+
"grad_norm": 0.8548456430435181,
|
870 |
+
"learning_rate": 7.730826507818317e-06,
|
871 |
+
"loss": 1.0166,
|
872 |
+
"step": 1220
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 0.22896500372300818,
|
876 |
+
"grad_norm": 0.8547614216804504,
|
877 |
+
"learning_rate": 7.712211466865228e-06,
|
878 |
+
"loss": 1.0383,
|
879 |
+
"step": 1230
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.2308265078183172,
|
883 |
+
"grad_norm": 0.8848845958709717,
|
884 |
+
"learning_rate": 7.693596425912138e-06,
|
885 |
+
"loss": 1.0262,
|
886 |
+
"step": 1240
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 0.2326880119136262,
|
890 |
+
"grad_norm": 0.8011718988418579,
|
891 |
+
"learning_rate": 7.674981384959048e-06,
|
892 |
+
"loss": 1.0297,
|
893 |
+
"step": 1250
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 0.23454951600893523,
|
897 |
+
"grad_norm": 0.9136202931404114,
|
898 |
+
"learning_rate": 7.656366344005957e-06,
|
899 |
+
"loss": 1.0479,
|
900 |
+
"step": 1260
|
901 |
+
},
|
902 |
+
{
|
903 |
+
"epoch": 0.23641102010424422,
|
904 |
+
"grad_norm": 0.8620238900184631,
|
905 |
+
"learning_rate": 7.637751303052867e-06,
|
906 |
+
"loss": 1.0424,
|
907 |
+
"step": 1270
|
908 |
+
},
|
909 |
+
{
|
910 |
+
"epoch": 0.23827252419955325,
|
911 |
+
"grad_norm": 0.8815340995788574,
|
912 |
+
"learning_rate": 7.619136262099778e-06,
|
913 |
+
"loss": 0.9992,
|
914 |
+
"step": 1280
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.24013402829486225,
|
918 |
+
"grad_norm": 0.8765432238578796,
|
919 |
+
"learning_rate": 7.600521221146688e-06,
|
920 |
+
"loss": 1.0212,
|
921 |
+
"step": 1290
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.24199553239017127,
|
925 |
+
"grad_norm": 0.8269699811935425,
|
926 |
+
"learning_rate": 7.581906180193596e-06,
|
927 |
+
"loss": 1.0233,
|
928 |
+
"step": 1300
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 0.24385703648548027,
|
932 |
+
"grad_norm": 0.9161726832389832,
|
933 |
+
"learning_rate": 7.563291139240508e-06,
|
934 |
+
"loss": 1.0098,
|
935 |
+
"step": 1310
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 0.2457185405807893,
|
939 |
+
"grad_norm": 0.8505399823188782,
|
940 |
+
"learning_rate": 7.544676098287416e-06,
|
941 |
+
"loss": 1.0455,
|
942 |
+
"step": 1320
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"epoch": 0.2475800446760983,
|
946 |
+
"grad_norm": 0.9100832343101501,
|
947 |
+
"learning_rate": 7.526061057334326e-06,
|
948 |
+
"loss": 1.0118,
|
949 |
+
"step": 1330
|
950 |
+
},
|
951 |
+
{
|
952 |
+
"epoch": 0.24944154877140728,
|
953 |
+
"grad_norm": 0.816448450088501,
|
954 |
+
"learning_rate": 7.507446016381237e-06,
|
955 |
+
"loss": 1.0179,
|
956 |
+
"step": 1340
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 0.2513030528667163,
|
960 |
+
"grad_norm": 0.8570308685302734,
|
961 |
+
"learning_rate": 7.488830975428146e-06,
|
962 |
+
"loss": 1.0187,
|
963 |
+
"step": 1350
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.25316455696202533,
|
967 |
+
"grad_norm": 0.9182896018028259,
|
968 |
+
"learning_rate": 7.470215934475057e-06,
|
969 |
+
"loss": 1.0148,
|
970 |
+
"step": 1360
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 0.25502606105733433,
|
974 |
+
"grad_norm": 0.9258450865745544,
|
975 |
+
"learning_rate": 7.451600893521966e-06,
|
976 |
+
"loss": 1.0492,
|
977 |
+
"step": 1370
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 0.2568875651526433,
|
981 |
+
"grad_norm": 0.9341595768928528,
|
982 |
+
"learning_rate": 7.4329858525688755e-06,
|
983 |
+
"loss": 1.001,
|
984 |
+
"step": 1380
|
985 |
+
},
|
986 |
+
{
|
987 |
+
"epoch": 0.2587490692479523,
|
988 |
+
"grad_norm": 0.8474791646003723,
|
989 |
+
"learning_rate": 7.414370811615787e-06,
|
990 |
+
"loss": 1.0176,
|
991 |
+
"step": 1390
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 0.2606105733432614,
|
995 |
+
"grad_norm": 0.8248825669288635,
|
996 |
+
"learning_rate": 7.3957557706626955e-06,
|
997 |
+
"loss": 1.0388,
|
998 |
+
"step": 1400
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 0.2624720774385704,
|
1002 |
+
"grad_norm": 0.8566280007362366,
|
1003 |
+
"learning_rate": 7.377140729709607e-06,
|
1004 |
+
"loss": 1.031,
|
1005 |
+
"step": 1410
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.26433358153387937,
|
1009 |
+
"grad_norm": 0.908298134803772,
|
1010 |
+
"learning_rate": 7.3585256887565156e-06,
|
1011 |
+
"loss": 1.026,
|
1012 |
+
"step": 1420
|
1013 |
+
},
|
1014 |
+
{
|
1015 |
+
"epoch": 0.26619508562918837,
|
1016 |
+
"grad_norm": 0.8796119689941406,
|
1017 |
+
"learning_rate": 7.339910647803425e-06,
|
1018 |
+
"loss": 1.0321,
|
1019 |
+
"step": 1430
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 0.2680565897244974,
|
1023 |
+
"grad_norm": 0.8061329126358032,
|
1024 |
+
"learning_rate": 7.3212956068503364e-06,
|
1025 |
+
"loss": 1.0046,
|
1026 |
+
"step": 1440
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 0.2699180938198064,
|
1030 |
+
"grad_norm": 0.8542073965072632,
|
1031 |
+
"learning_rate": 7.302680565897245e-06,
|
1032 |
+
"loss": 1.0051,
|
1033 |
+
"step": 1450
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 0.2717795979151154,
|
1037 |
+
"grad_norm": 0.9325591921806335,
|
1038 |
+
"learning_rate": 7.284065524944155e-06,
|
1039 |
+
"loss": 1.0188,
|
1040 |
+
"step": 1460
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.2736411020104244,
|
1044 |
+
"grad_norm": 0.8798630833625793,
|
1045 |
+
"learning_rate": 7.265450483991065e-06,
|
1046 |
+
"loss": 1.0188,
|
1047 |
+
"step": 1470
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.2755026061057334,
|
1051 |
+
"grad_norm": 0.8533742427825928,
|
1052 |
+
"learning_rate": 7.246835443037975e-06,
|
1053 |
+
"loss": 1.0215,
|
1054 |
+
"step": 1480
|
1055 |
+
},
|
1056 |
+
{
|
1057 |
+
"epoch": 0.27736411020104246,
|
1058 |
+
"grad_norm": 0.787476658821106,
|
1059 |
+
"learning_rate": 7.228220402084886e-06,
|
1060 |
+
"loss": 1.0293,
|
1061 |
+
"step": 1490
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 0.27922561429635145,
|
1065 |
+
"grad_norm": 0.9893611073493958,
|
1066 |
+
"learning_rate": 7.209605361131795e-06,
|
1067 |
+
"loss": 1.0081,
|
1068 |
+
"step": 1500
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 0.28108711839166045,
|
1072 |
+
"grad_norm": 0.890211284160614,
|
1073 |
+
"learning_rate": 7.190990320178704e-06,
|
1074 |
+
"loss": 1.0352,
|
1075 |
+
"step": 1510
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 0.28294862248696945,
|
1079 |
+
"grad_norm": 0.927284300327301,
|
1080 |
+
"learning_rate": 7.172375279225615e-06,
|
1081 |
+
"loss": 0.9982,
|
1082 |
+
"step": 1520
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.2848101265822785,
|
1086 |
+
"grad_norm": 0.9046431183815002,
|
1087 |
+
"learning_rate": 7.153760238272524e-06,
|
1088 |
+
"loss": 1.011,
|
1089 |
+
"step": 1530
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.2866716306775875,
|
1093 |
+
"grad_norm": 0.8721937537193298,
|
1094 |
+
"learning_rate": 7.135145197319436e-06,
|
1095 |
+
"loss": 1.0213,
|
1096 |
+
"step": 1540
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 0.2885331347728965,
|
1100 |
+
"grad_norm": 0.9656839370727539,
|
1101 |
+
"learning_rate": 7.116530156366344e-06,
|
1102 |
+
"loss": 1.0071,
|
1103 |
+
"step": 1550
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 0.2903946388682055,
|
1107 |
+
"grad_norm": 0.8189395666122437,
|
1108 |
+
"learning_rate": 7.097915115413254e-06,
|
1109 |
+
"loss": 1.0122,
|
1110 |
+
"step": 1560
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 0.29225614296351454,
|
1114 |
+
"grad_norm": 0.8297001719474792,
|
1115 |
+
"learning_rate": 7.079300074460164e-06,
|
1116 |
+
"loss": 1.0336,
|
1117 |
+
"step": 1570
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 0.29411764705882354,
|
1121 |
+
"grad_norm": 0.8650018572807312,
|
1122 |
+
"learning_rate": 7.060685033507074e-06,
|
1123 |
+
"loss": 1.0366,
|
1124 |
+
"step": 1580
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 0.29597915115413254,
|
1128 |
+
"grad_norm": 0.9331561923027039,
|
1129 |
+
"learning_rate": 7.0420699925539836e-06,
|
1130 |
+
"loss": 1.029,
|
1131 |
+
"step": 1590
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.29784065524944153,
|
1135 |
+
"grad_norm": 0.9295797944068909,
|
1136 |
+
"learning_rate": 7.023454951600894e-06,
|
1137 |
+
"loss": 1.0071,
|
1138 |
+
"step": 1600
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 0.2997021593447506,
|
1142 |
+
"grad_norm": 0.9132567048072815,
|
1143 |
+
"learning_rate": 7.0048399106478036e-06,
|
1144 |
+
"loss": 1.0219,
|
1145 |
+
"step": 1610
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 0.3015636634400596,
|
1149 |
+
"grad_norm": 0.9104480147361755,
|
1150 |
+
"learning_rate": 6.986224869694714e-06,
|
1151 |
+
"loss": 1.0048,
|
1152 |
+
"step": 1620
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 0.3034251675353686,
|
1156 |
+
"grad_norm": 0.9631213545799255,
|
1157 |
+
"learning_rate": 6.967609828741624e-06,
|
1158 |
+
"loss": 1.0218,
|
1159 |
+
"step": 1630
|
1160 |
+
},
|
1161 |
+
{
|
1162 |
+
"epoch": 0.3052866716306776,
|
1163 |
+
"grad_norm": 0.9733109474182129,
|
1164 |
+
"learning_rate": 6.948994787788533e-06,
|
1165 |
+
"loss": 1.0174,
|
1166 |
+
"step": 1640
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.30714817572598657,
|
1170 |
+
"grad_norm": 0.8739007115364075,
|
1171 |
+
"learning_rate": 6.930379746835444e-06,
|
1172 |
+
"loss": 1.0219,
|
1173 |
+
"step": 1650
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.3090096798212956,
|
1177 |
+
"grad_norm": 0.8556765913963318,
|
1178 |
+
"learning_rate": 6.911764705882353e-06,
|
1179 |
+
"loss": 1.0065,
|
1180 |
+
"step": 1660
|
1181 |
+
},
|
1182 |
+
{
|
1183 |
+
"epoch": 0.3108711839166046,
|
1184 |
+
"grad_norm": 1.0602627992630005,
|
1185 |
+
"learning_rate": 6.893149664929264e-06,
|
1186 |
+
"loss": 1.0401,
|
1187 |
+
"step": 1670
|
1188 |
+
},
|
1189 |
+
{
|
1190 |
+
"epoch": 0.3127326880119136,
|
1191 |
+
"grad_norm": 0.8729854226112366,
|
1192 |
+
"learning_rate": 6.874534623976173e-06,
|
1193 |
+
"loss": 1.0207,
|
1194 |
+
"step": 1680
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.3145941921072226,
|
1198 |
+
"grad_norm": 0.8415886759757996,
|
1199 |
+
"learning_rate": 6.855919583023083e-06,
|
1200 |
+
"loss": 1.0251,
|
1201 |
+
"step": 1690
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 0.31645569620253167,
|
1205 |
+
"grad_norm": 0.8418084383010864,
|
1206 |
+
"learning_rate": 6.837304542069993e-06,
|
1207 |
+
"loss": 1.0145,
|
1208 |
+
"step": 1700
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 0.31831720029784066,
|
1212 |
+
"grad_norm": 0.9861761927604675,
|
1213 |
+
"learning_rate": 6.818689501116903e-06,
|
1214 |
+
"loss": 1.0052,
|
1215 |
+
"step": 1710
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.32017870439314966,
|
1219 |
+
"grad_norm": 0.9260056018829346,
|
1220 |
+
"learning_rate": 6.800074460163812e-06,
|
1221 |
+
"loss": 1.02,
|
1222 |
+
"step": 1720
|
1223 |
+
},
|
1224 |
+
{
|
1225 |
+
"epoch": 0.32204020848845866,
|
1226 |
+
"grad_norm": 0.8868281245231628,
|
1227 |
+
"learning_rate": 6.781459419210723e-06,
|
1228 |
+
"loss": 1.0041,
|
1229 |
+
"step": 1730
|
1230 |
+
},
|
1231 |
+
{
|
1232 |
+
"epoch": 0.3239017125837677,
|
1233 |
+
"grad_norm": 0.9267802834510803,
|
1234 |
+
"learning_rate": 6.762844378257632e-06,
|
1235 |
+
"loss": 1.0098,
|
1236 |
+
"step": 1740
|
1237 |
+
},
|
1238 |
+
{
|
1239 |
+
"epoch": 0.3257632166790767,
|
1240 |
+
"grad_norm": 0.9296885132789612,
|
1241 |
+
"learning_rate": 6.744229337304543e-06,
|
1242 |
+
"loss": 1.0011,
|
1243 |
+
"step": 1750
|
1244 |
+
},
|
1245 |
+
{
|
1246 |
+
"epoch": 0.3276247207743857,
|
1247 |
+
"grad_norm": 0.890703022480011,
|
1248 |
+
"learning_rate": 6.725614296351452e-06,
|
1249 |
+
"loss": 1.0189,
|
1250 |
+
"step": 1760
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.3294862248696947,
|
1254 |
+
"grad_norm": 0.984555721282959,
|
1255 |
+
"learning_rate": 6.706999255398362e-06,
|
1256 |
+
"loss": 1.0244,
|
1257 |
+
"step": 1770
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.3313477289650037,
|
1261 |
+
"grad_norm": 0.9353686571121216,
|
1262 |
+
"learning_rate": 6.688384214445272e-06,
|
1263 |
+
"loss": 0.9965,
|
1264 |
+
"step": 1780
|
1265 |
+
},
|
1266 |
+
{
|
1267 |
+
"epoch": 0.33320923306031275,
|
1268 |
+
"grad_norm": 0.9182252883911133,
|
1269 |
+
"learning_rate": 6.669769173492182e-06,
|
1270 |
+
"loss": 1.0083,
|
1271 |
+
"step": 1790
|
1272 |
+
},
|
1273 |
+
{
|
1274 |
+
"epoch": 0.33507073715562175,
|
1275 |
+
"grad_norm": 0.9387986660003662,
|
1276 |
+
"learning_rate": 6.651154132539092e-06,
|
1277 |
+
"loss": 0.988,
|
1278 |
+
"step": 1800
|
1279 |
+
},
|
1280 |
+
{
|
1281 |
+
"epoch": 0.33693224125093074,
|
1282 |
+
"grad_norm": 0.8640313148498535,
|
1283 |
+
"learning_rate": 6.632539091586002e-06,
|
1284 |
+
"loss": 1.0198,
|
1285 |
+
"step": 1810
|
1286 |
+
},
|
1287 |
+
{
|
1288 |
+
"epoch": 0.33879374534623974,
|
1289 |
+
"grad_norm": 0.835686206817627,
|
1290 |
+
"learning_rate": 6.613924050632912e-06,
|
1291 |
+
"loss": 1.0147,
|
1292 |
+
"step": 1820
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 0.3406552494415488,
|
1296 |
+
"grad_norm": 0.9717905521392822,
|
1297 |
+
"learning_rate": 6.595309009679822e-06,
|
1298 |
+
"loss": 1.0186,
|
1299 |
+
"step": 1830
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.3425167535368578,
|
1303 |
+
"grad_norm": 0.8895915150642395,
|
1304 |
+
"learning_rate": 6.576693968726732e-06,
|
1305 |
+
"loss": 1.0097,
|
1306 |
+
"step": 1840
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 0.3443782576321668,
|
1310 |
+
"grad_norm": 0.9292529225349426,
|
1311 |
+
"learning_rate": 6.558078927773641e-06,
|
1312 |
+
"loss": 0.9973,
|
1313 |
+
"step": 1850
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 0.3462397617274758,
|
1317 |
+
"grad_norm": 0.889236569404602,
|
1318 |
+
"learning_rate": 6.539463886820552e-06,
|
1319 |
+
"loss": 1.0353,
|
1320 |
+
"step": 1860
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 0.34810126582278483,
|
1324 |
+
"grad_norm": 0.9049444198608398,
|
1325 |
+
"learning_rate": 6.520848845867461e-06,
|
1326 |
+
"loss": 1.0219,
|
1327 |
+
"step": 1870
|
1328 |
+
},
|
1329 |
+
{
|
1330 |
+
"epoch": 0.34996276991809383,
|
1331 |
+
"grad_norm": 0.9182834029197693,
|
1332 |
+
"learning_rate": 6.502233804914372e-06,
|
1333 |
+
"loss": 1.0049,
|
1334 |
+
"step": 1880
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 0.3518242740134028,
|
1338 |
+
"grad_norm": 0.9599704146385193,
|
1339 |
+
"learning_rate": 6.483618763961281e-06,
|
1340 |
+
"loss": 1.0106,
|
1341 |
+
"step": 1890
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 0.3536857781087118,
|
1345 |
+
"grad_norm": 0.9892078638076782,
|
1346 |
+
"learning_rate": 6.465003723008191e-06,
|
1347 |
+
"loss": 1.0102,
|
1348 |
+
"step": 1900
|
1349 |
+
},
|
1350 |
+
{
|
1351 |
+
"epoch": 0.3555472822040209,
|
1352 |
+
"grad_norm": 0.9587261080741882,
|
1353 |
+
"learning_rate": 6.446388682055101e-06,
|
1354 |
+
"loss": 0.976,
|
1355 |
+
"step": 1910
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 0.3574087862993299,
|
1359 |
+
"grad_norm": 0.9415343403816223,
|
1360 |
+
"learning_rate": 6.427773641102011e-06,
|
1361 |
+
"loss": 1.0416,
|
1362 |
+
"step": 1920
|
1363 |
+
},
|
1364 |
+
{
|
1365 |
+
"epoch": 0.35927029039463887,
|
1366 |
+
"grad_norm": 0.9060238599777222,
|
1367 |
+
"learning_rate": 6.40915860014892e-06,
|
1368 |
+
"loss": 1.0257,
|
1369 |
+
"step": 1930
|
1370 |
+
},
|
1371 |
+
{
|
1372 |
+
"epoch": 0.36113179448994787,
|
1373 |
+
"grad_norm": 1.0089079141616821,
|
1374 |
+
"learning_rate": 6.390543559195831e-06,
|
1375 |
+
"loss": 0.9887,
|
1376 |
+
"step": 1940
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 0.36299329858525686,
|
1380 |
+
"grad_norm": 1.043312907218933,
|
1381 |
+
"learning_rate": 6.37192851824274e-06,
|
1382 |
+
"loss": 1.0021,
|
1383 |
+
"step": 1950
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 0.3648548026805659,
|
1387 |
+
"grad_norm": 0.8814155459403992,
|
1388 |
+
"learning_rate": 6.353313477289651e-06,
|
1389 |
+
"loss": 1.0325,
|
1390 |
+
"step": 1960
|
1391 |
+
},
|
1392 |
+
{
|
1393 |
+
"epoch": 0.3667163067758749,
|
1394 |
+
"grad_norm": 1.0266395807266235,
|
1395 |
+
"learning_rate": 6.3346984363365604e-06,
|
1396 |
+
"loss": 1.0037,
|
1397 |
+
"step": 1970
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 0.3685778108711839,
|
1401 |
+
"grad_norm": 0.9735901355743408,
|
1402 |
+
"learning_rate": 6.31608339538347e-06,
|
1403 |
+
"loss": 1.0195,
|
1404 |
+
"step": 1980
|
1405 |
+
},
|
1406 |
+
{
|
1407 |
+
"epoch": 0.3704393149664929,
|
1408 |
+
"grad_norm": 0.8415465354919434,
|
1409 |
+
"learning_rate": 6.2974683544303804e-06,
|
1410 |
+
"loss": 0.9885,
|
1411 |
+
"step": 1990
|
1412 |
+
},
|
1413 |
+
{
|
1414 |
+
"epoch": 0.37230081906180196,
|
1415 |
+
"grad_norm": 0.9171274304389954,
|
1416 |
+
"learning_rate": 6.27885331347729e-06,
|
1417 |
+
"loss": 1.0092,
|
1418 |
+
"step": 2000
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 0.37230081906180196,
|
1422 |
+
"eval_loss": 1.00629723072052,
|
1423 |
+
"eval_runtime": 1069.9825,
|
1424 |
+
"eval_samples_per_second": 17.852,
|
1425 |
+
"eval_steps_per_second": 0.558,
|
1426 |
+
"step": 2000
|
1427 |
+
},
|
1428 |
+
{
|
1429 |
+
"epoch": 0.37416232315711095,
|
1430 |
+
"grad_norm": 0.9398316740989685,
|
1431 |
+
"learning_rate": 6.2602382725242005e-06,
|
1432 |
+
"loss": 1.0176,
|
1433 |
+
"step": 2010
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 0.37602382725241995,
|
1437 |
+
"grad_norm": 0.9056214094161987,
|
1438 |
+
"learning_rate": 6.24162323157111e-06,
|
1439 |
+
"loss": 1.0039,
|
1440 |
+
"step": 2020
|
1441 |
+
},
|
1442 |
+
{
|
1443 |
+
"epoch": 0.37788533134772895,
|
1444 |
+
"grad_norm": 0.9024308323860168,
|
1445 |
+
"learning_rate": 6.22300819061802e-06,
|
1446 |
+
"loss": 1.0266,
|
1447 |
+
"step": 2030
|
1448 |
+
},
|
1449 |
+
{
|
1450 |
+
"epoch": 0.379746835443038,
|
1451 |
+
"grad_norm": 0.902384877204895,
|
1452 |
+
"learning_rate": 6.20439314966493e-06,
|
1453 |
+
"loss": 0.9924,
|
1454 |
+
"step": 2040
|
1455 |
+
},
|
1456 |
+
{
|
1457 |
+
"epoch": 0.381608339538347,
|
1458 |
+
"grad_norm": 0.866256058216095,
|
1459 |
+
"learning_rate": 6.18577810871184e-06,
|
1460 |
+
"loss": 1.0487,
|
1461 |
+
"step": 2050
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 0.383469843633656,
|
1465 |
+
"grad_norm": 0.8996155858039856,
|
1466 |
+
"learning_rate": 6.167163067758749e-06,
|
1467 |
+
"loss": 1.0223,
|
1468 |
+
"step": 2060
|
1469 |
+
},
|
1470 |
+
{
|
1471 |
+
"epoch": 0.385331347728965,
|
1472 |
+
"grad_norm": 0.9436926245689392,
|
1473 |
+
"learning_rate": 6.14854802680566e-06,
|
1474 |
+
"loss": 0.9949,
|
1475 |
+
"step": 2070
|
1476 |
+
},
|
1477 |
+
{
|
1478 |
+
"epoch": 0.387192851824274,
|
1479 |
+
"grad_norm": 0.9145451188087463,
|
1480 |
+
"learning_rate": 6.129932985852569e-06,
|
1481 |
+
"loss": 0.9886,
|
1482 |
+
"step": 2080
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 0.38905435591958304,
|
1486 |
+
"grad_norm": 0.8765755891799927,
|
1487 |
+
"learning_rate": 6.11131794489948e-06,
|
1488 |
+
"loss": 0.9872,
|
1489 |
+
"step": 2090
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 0.39091586001489204,
|
1493 |
+
"grad_norm": 0.9102899432182312,
|
1494 |
+
"learning_rate": 6.092702903946389e-06,
|
1495 |
+
"loss": 0.9908,
|
1496 |
+
"step": 2100
|
1497 |
+
},
|
1498 |
+
{
|
1499 |
+
"epoch": 0.39277736411020103,
|
1500 |
+
"grad_norm": 1.0503920316696167,
|
1501 |
+
"learning_rate": 6.074087862993299e-06,
|
1502 |
+
"loss": 1.0198,
|
1503 |
+
"step": 2110
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 0.39463886820551003,
|
1507 |
+
"grad_norm": 0.8686490058898926,
|
1508 |
+
"learning_rate": 6.055472822040209e-06,
|
1509 |
+
"loss": 1.0109,
|
1510 |
+
"step": 2120
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 0.3965003723008191,
|
1514 |
+
"grad_norm": 0.9022567868232727,
|
1515 |
+
"learning_rate": 6.036857781087119e-06,
|
1516 |
+
"loss": 0.9814,
|
1517 |
+
"step": 2130
|
1518 |
+
},
|
1519 |
+
{
|
1520 |
+
"epoch": 0.3983618763961281,
|
1521 |
+
"grad_norm": 0.9849201440811157,
|
1522 |
+
"learning_rate": 6.018242740134029e-06,
|
1523 |
+
"loss": 1.0101,
|
1524 |
+
"step": 2140
|
1525 |
+
},
|
1526 |
+
{
|
1527 |
+
"epoch": 0.4002233804914371,
|
1528 |
+
"grad_norm": 0.9130750298500061,
|
1529 |
+
"learning_rate": 5.999627699180939e-06,
|
1530 |
+
"loss": 1.0123,
|
1531 |
+
"step": 2150
|
1532 |
+
},
|
1533 |
+
{
|
1534 |
+
"epoch": 0.40208488458674607,
|
1535 |
+
"grad_norm": 0.9186067581176758,
|
1536 |
+
"learning_rate": 5.9810126582278484e-06,
|
1537 |
+
"loss": 1.0031,
|
1538 |
+
"step": 2160
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 0.4039463886820551,
|
1542 |
+
"grad_norm": 0.9894231557846069,
|
1543 |
+
"learning_rate": 5.962397617274759e-06,
|
1544 |
+
"loss": 0.9967,
|
1545 |
+
"step": 2170
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 0.4058078927773641,
|
1549 |
+
"grad_norm": 0.8997127413749695,
|
1550 |
+
"learning_rate": 5.9437825763216684e-06,
|
1551 |
+
"loss": 1.0126,
|
1552 |
+
"step": 2180
|
1553 |
+
},
|
1554 |
+
{
|
1555 |
+
"epoch": 0.4076693968726731,
|
1556 |
+
"grad_norm": 0.8942683935165405,
|
1557 |
+
"learning_rate": 5.925167535368578e-06,
|
1558 |
+
"loss": 1.0295,
|
1559 |
+
"step": 2190
|
1560 |
+
},
|
1561 |
+
{
|
1562 |
+
"epoch": 0.4095309009679821,
|
1563 |
+
"grad_norm": 0.946066677570343,
|
1564 |
+
"learning_rate": 5.9065524944154885e-06,
|
1565 |
+
"loss": 0.9757,
|
1566 |
+
"step": 2200
|
1567 |
+
},
|
1568 |
+
{
|
1569 |
+
"epoch": 0.41139240506329117,
|
1570 |
+
"grad_norm": 0.9872490763664246,
|
1571 |
+
"learning_rate": 5.887937453462398e-06,
|
1572 |
+
"loss": 0.9908,
|
1573 |
+
"step": 2210
|
1574 |
+
},
|
1575 |
+
{
|
1576 |
+
"epoch": 0.41325390915860016,
|
1577 |
+
"grad_norm": 0.891007661819458,
|
1578 |
+
"learning_rate": 5.8693224125093085e-06,
|
1579 |
+
"loss": 0.9868,
|
1580 |
+
"step": 2220
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"epoch": 0.41511541325390916,
|
1584 |
+
"grad_norm": 0.94728022813797,
|
1585 |
+
"learning_rate": 5.850707371556218e-06,
|
1586 |
+
"loss": 0.9889,
|
1587 |
+
"step": 2230
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 0.41697691734921816,
|
1591 |
+
"grad_norm": 0.8767345547676086,
|
1592 |
+
"learning_rate": 5.832092330603128e-06,
|
1593 |
+
"loss": 0.9794,
|
1594 |
+
"step": 2240
|
1595 |
+
},
|
1596 |
+
{
|
1597 |
+
"epoch": 0.41883842144452715,
|
1598 |
+
"grad_norm": 0.9678050875663757,
|
1599 |
+
"learning_rate": 5.813477289650038e-06,
|
1600 |
+
"loss": 0.9984,
|
1601 |
+
"step": 2250
|
1602 |
+
},
|
1603 |
+
{
|
1604 |
+
"epoch": 0.4206999255398362,
|
1605 |
+
"grad_norm": 0.9630270600318909,
|
1606 |
+
"learning_rate": 5.794862248696948e-06,
|
1607 |
+
"loss": 1.0189,
|
1608 |
+
"step": 2260
|
1609 |
+
},
|
1610 |
+
{
|
1611 |
+
"epoch": 0.4225614296351452,
|
1612 |
+
"grad_norm": 0.8563063144683838,
|
1613 |
+
"learning_rate": 5.776247207743858e-06,
|
1614 |
+
"loss": 0.9911,
|
1615 |
+
"step": 2270
|
1616 |
+
},
|
1617 |
+
{
|
1618 |
+
"epoch": 0.4244229337304542,
|
1619 |
+
"grad_norm": 0.9688002467155457,
|
1620 |
+
"learning_rate": 5.757632166790768e-06,
|
1621 |
+
"loss": 0.9691,
|
1622 |
+
"step": 2280
|
1623 |
+
},
|
1624 |
+
{
|
1625 |
+
"epoch": 0.4262844378257632,
|
1626 |
+
"grad_norm": 0.9500530958175659,
|
1627 |
+
"learning_rate": 5.739017125837677e-06,
|
1628 |
+
"loss": 1.0156,
|
1629 |
+
"step": 2290
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 0.42814594192107225,
|
1633 |
+
"grad_norm": 0.8952423930168152,
|
1634 |
+
"learning_rate": 5.720402084884588e-06,
|
1635 |
+
"loss": 1.0116,
|
1636 |
+
"step": 2300
|
1637 |
+
},
|
1638 |
+
{
|
1639 |
+
"epoch": 0.43000744601638125,
|
1640 |
+
"grad_norm": 0.9344154596328735,
|
1641 |
+
"learning_rate": 5.701787043931497e-06,
|
1642 |
+
"loss": 0.9988,
|
1643 |
+
"step": 2310
|
1644 |
+
},
|
1645 |
+
{
|
1646 |
+
"epoch": 0.43186895011169024,
|
1647 |
+
"grad_norm": 0.8889378309249878,
|
1648 |
+
"learning_rate": 5.683172002978407e-06,
|
1649 |
+
"loss": 0.9769,
|
1650 |
+
"step": 2320
|
1651 |
+
},
|
1652 |
+
{
|
1653 |
+
"epoch": 0.43373045420699924,
|
1654 |
+
"grad_norm": 0.9577843546867371,
|
1655 |
+
"learning_rate": 5.664556962025317e-06,
|
1656 |
+
"loss": 0.9796,
|
1657 |
+
"step": 2330
|
1658 |
+
},
|
1659 |
+
{
|
1660 |
+
"epoch": 0.4355919583023083,
|
1661 |
+
"grad_norm": 0.9781843423843384,
|
1662 |
+
"learning_rate": 5.645941921072227e-06,
|
1663 |
+
"loss": 0.9725,
|
1664 |
+
"step": 2340
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 0.4374534623976173,
|
1668 |
+
"grad_norm": 0.9555472731590271,
|
1669 |
+
"learning_rate": 5.627326880119137e-06,
|
1670 |
+
"loss": 0.9933,
|
1671 |
+
"step": 2350
|
1672 |
+
},
|
1673 |
+
{
|
1674 |
+
"epoch": 0.4393149664929263,
|
1675 |
+
"grad_norm": 0.9150035977363586,
|
1676 |
+
"learning_rate": 5.608711839166047e-06,
|
1677 |
+
"loss": 0.9739,
|
1678 |
+
"step": 2360
|
1679 |
+
},
|
1680 |
+
{
|
1681 |
+
"epoch": 0.4411764705882353,
|
1682 |
+
"grad_norm": 0.9557597041130066,
|
1683 |
+
"learning_rate": 5.5900967982129565e-06,
|
1684 |
+
"loss": 0.9772,
|
1685 |
+
"step": 2370
|
1686 |
+
},
|
1687 |
+
{
|
1688 |
+
"epoch": 0.4430379746835443,
|
1689 |
+
"grad_norm": 0.9111446142196655,
|
1690 |
+
"learning_rate": 5.571481757259867e-06,
|
1691 |
+
"loss": 0.9669,
|
1692 |
+
"step": 2380
|
1693 |
+
},
|
1694 |
+
{
|
1695 |
+
"epoch": 0.44489947877885333,
|
1696 |
+
"grad_norm": 0.8984286785125732,
|
1697 |
+
"learning_rate": 5.5528667163067765e-06,
|
1698 |
+
"loss": 1.005,
|
1699 |
+
"step": 2390
|
1700 |
+
},
|
1701 |
+
{
|
1702 |
+
"epoch": 0.4467609828741623,
|
1703 |
+
"grad_norm": 0.9852848052978516,
|
1704 |
+
"learning_rate": 5.534251675353686e-06,
|
1705 |
+
"loss": 1.009,
|
1706 |
+
"step": 2400
|
1707 |
+
},
|
1708 |
+
{
|
1709 |
+
"epoch": 0.4486224869694713,
|
1710 |
+
"grad_norm": 0.9443567395210266,
|
1711 |
+
"learning_rate": 5.5156366344005965e-06,
|
1712 |
+
"loss": 0.9992,
|
1713 |
+
"step": 2410
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"epoch": 0.4504839910647803,
|
1717 |
+
"grad_norm": 0.9576156139373779,
|
1718 |
+
"learning_rate": 5.497021593447506e-06,
|
1719 |
+
"loss": 1.0064,
|
1720 |
+
"step": 2420
|
1721 |
+
},
|
1722 |
+
{
|
1723 |
+
"epoch": 0.4523454951600894,
|
1724 |
+
"grad_norm": 0.9496288895606995,
|
1725 |
+
"learning_rate": 5.4784065524944165e-06,
|
1726 |
+
"loss": 0.9845,
|
1727 |
+
"step": 2430
|
1728 |
+
},
|
1729 |
+
{
|
1730 |
+
"epoch": 0.45420699925539837,
|
1731 |
+
"grad_norm": 0.8849292397499084,
|
1732 |
+
"learning_rate": 5.459791511541326e-06,
|
1733 |
+
"loss": 1.0019,
|
1734 |
+
"step": 2440
|
1735 |
+
},
|
1736 |
+
{
|
1737 |
+
"epoch": 0.45606850335070737,
|
1738 |
+
"grad_norm": 0.8832285404205322,
|
1739 |
+
"learning_rate": 5.441176470588236e-06,
|
1740 |
+
"loss": 0.9866,
|
1741 |
+
"step": 2450
|
1742 |
+
},
|
1743 |
+
{
|
1744 |
+
"epoch": 0.45793000744601636,
|
1745 |
+
"grad_norm": 0.9402060508728027,
|
1746 |
+
"learning_rate": 5.422561429635146e-06,
|
1747 |
+
"loss": 1.0138,
|
1748 |
+
"step": 2460
|
1749 |
+
},
|
1750 |
+
{
|
1751 |
+
"epoch": 0.4597915115413254,
|
1752 |
+
"grad_norm": 0.9651751518249512,
|
1753 |
+
"learning_rate": 5.403946388682056e-06,
|
1754 |
+
"loss": 1.007,
|
1755 |
+
"step": 2470
|
1756 |
+
},
|
1757 |
+
{
|
1758 |
+
"epoch": 0.4616530156366344,
|
1759 |
+
"grad_norm": 0.9160338640213013,
|
1760 |
+
"learning_rate": 5.385331347728966e-06,
|
1761 |
+
"loss": 0.9963,
|
1762 |
+
"step": 2480
|
1763 |
+
},
|
1764 |
+
{
|
1765 |
+
"epoch": 0.4635145197319434,
|
1766 |
+
"grad_norm": 0.9223355054855347,
|
1767 |
+
"learning_rate": 5.366716306775876e-06,
|
1768 |
+
"loss": 0.9978,
|
1769 |
+
"step": 2490
|
1770 |
+
},
|
1771 |
+
{
|
1772 |
+
"epoch": 0.4653760238272524,
|
1773 |
+
"grad_norm": 0.9482707977294922,
|
1774 |
+
"learning_rate": 5.348101265822785e-06,
|
1775 |
+
"loss": 1.0065,
|
1776 |
+
"step": 2500
|
1777 |
+
},
|
1778 |
+
{
|
1779 |
+
"epoch": 0.4672375279225614,
|
1780 |
+
"grad_norm": 0.93135666847229,
|
1781 |
+
"learning_rate": 5.329486224869696e-06,
|
1782 |
+
"loss": 1.0002,
|
1783 |
+
"step": 2510
|
1784 |
+
},
|
1785 |
+
{
|
1786 |
+
"epoch": 0.46909903201787045,
|
1787 |
+
"grad_norm": 0.9939650297164917,
|
1788 |
+
"learning_rate": 5.310871183916605e-06,
|
1789 |
+
"loss": 0.987,
|
1790 |
+
"step": 2520
|
1791 |
+
},
|
1792 |
+
{
|
1793 |
+
"epoch": 0.47096053611317945,
|
1794 |
+
"grad_norm": 0.9754669666290283,
|
1795 |
+
"learning_rate": 5.292256142963514e-06,
|
1796 |
+
"loss": 0.9852,
|
1797 |
+
"step": 2530
|
1798 |
+
},
|
1799 |
+
{
|
1800 |
+
"epoch": 0.47282204020848845,
|
1801 |
+
"grad_norm": 0.911465585231781,
|
1802 |
+
"learning_rate": 5.273641102010425e-06,
|
1803 |
+
"loss": 0.9999,
|
1804 |
+
"step": 2540
|
1805 |
+
},
|
1806 |
+
{
|
1807 |
+
"epoch": 0.47468354430379744,
|
1808 |
+
"grad_norm": 0.9288020730018616,
|
1809 |
+
"learning_rate": 5.255026061057335e-06,
|
1810 |
+
"loss": 0.9767,
|
1811 |
+
"step": 2550
|
1812 |
+
},
|
1813 |
+
{
|
1814 |
+
"epoch": 0.4765450483991065,
|
1815 |
+
"grad_norm": 0.9005303382873535,
|
1816 |
+
"learning_rate": 5.236411020104245e-06,
|
1817 |
+
"loss": 0.9946,
|
1818 |
+
"step": 2560
|
1819 |
+
},
|
1820 |
+
{
|
1821 |
+
"epoch": 0.4784065524944155,
|
1822 |
+
"grad_norm": 1.0648926496505737,
|
1823 |
+
"learning_rate": 5.217795979151155e-06,
|
1824 |
+
"loss": 0.9938,
|
1825 |
+
"step": 2570
|
1826 |
+
},
|
1827 |
+
{
|
1828 |
+
"epoch": 0.4802680565897245,
|
1829 |
+
"grad_norm": 1.0463746786117554,
|
1830 |
+
"learning_rate": 5.199180938198064e-06,
|
1831 |
+
"loss": 1.0056,
|
1832 |
+
"step": 2580
|
1833 |
+
},
|
1834 |
+
{
|
1835 |
+
"epoch": 0.4821295606850335,
|
1836 |
+
"grad_norm": 1.0113776922225952,
|
1837 |
+
"learning_rate": 5.180565897244975e-06,
|
1838 |
+
"loss": 0.9553,
|
1839 |
+
"step": 2590
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 0.48399106478034254,
|
1843 |
+
"grad_norm": 0.9221078753471375,
|
1844 |
+
"learning_rate": 5.1619508562918845e-06,
|
1845 |
+
"loss": 0.9856,
|
1846 |
+
"step": 2600
|
1847 |
+
},
|
1848 |
+
{
|
1849 |
+
"epoch": 0.48585256887565154,
|
1850 |
+
"grad_norm": 0.9816900491714478,
|
1851 |
+
"learning_rate": 5.143335815338795e-06,
|
1852 |
+
"loss": 0.9898,
|
1853 |
+
"step": 2610
|
1854 |
+
},
|
1855 |
+
{
|
1856 |
+
"epoch": 0.48771407297096053,
|
1857 |
+
"grad_norm": 0.7996393442153931,
|
1858 |
+
"learning_rate": 5.1247207743857045e-06,
|
1859 |
+
"loss": 1.0028,
|
1860 |
+
"step": 2620
|
1861 |
+
},
|
1862 |
+
{
|
1863 |
+
"epoch": 0.48957557706626953,
|
1864 |
+
"grad_norm": 0.9347983598709106,
|
1865 |
+
"learning_rate": 5.106105733432613e-06,
|
1866 |
+
"loss": 0.9891,
|
1867 |
+
"step": 2630
|
1868 |
+
},
|
1869 |
+
{
|
1870 |
+
"epoch": 0.4914370811615786,
|
1871 |
+
"grad_norm": 0.963764488697052,
|
1872 |
+
"learning_rate": 5.0874906924795245e-06,
|
1873 |
+
"loss": 0.9791,
|
1874 |
+
"step": 2640
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 0.4932985852568876,
|
1878 |
+
"grad_norm": 0.9388765692710876,
|
1879 |
+
"learning_rate": 5.068875651526434e-06,
|
1880 |
+
"loss": 0.9882,
|
1881 |
+
"step": 2650
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 0.4951600893521966,
|
1885 |
+
"grad_norm": 0.934416651725769,
|
1886 |
+
"learning_rate": 5.050260610573343e-06,
|
1887 |
+
"loss": 0.984,
|
1888 |
+
"step": 2660
|
1889 |
+
},
|
1890 |
+
{
|
1891 |
+
"epoch": 0.49702159344750557,
|
1892 |
+
"grad_norm": 0.928064227104187,
|
1893 |
+
"learning_rate": 5.031645569620254e-06,
|
1894 |
+
"loss": 1.0006,
|
1895 |
+
"step": 2670
|
1896 |
+
},
|
1897 |
+
{
|
1898 |
+
"epoch": 0.49888309754281457,
|
1899 |
+
"grad_norm": 0.9881389141082764,
|
1900 |
+
"learning_rate": 5.013030528667163e-06,
|
1901 |
+
"loss": 1.0019,
|
1902 |
+
"step": 2680
|
1903 |
+
},
|
1904 |
+
{
|
1905 |
+
"epoch": 0.5007446016381236,
|
1906 |
+
"grad_norm": 0.9684934616088867,
|
1907 |
+
"learning_rate": 4.994415487714073e-06,
|
1908 |
+
"loss": 1.0139,
|
1909 |
+
"step": 2690
|
1910 |
+
},
|
1911 |
+
{
|
1912 |
+
"epoch": 0.5026061057334326,
|
1913 |
+
"grad_norm": 0.9488608837127686,
|
1914 |
+
"learning_rate": 4.975800446760983e-06,
|
1915 |
+
"loss": 0.9994,
|
1916 |
+
"step": 2700
|
1917 |
+
},
|
1918 |
+
{
|
1919 |
+
"epoch": 0.5044676098287416,
|
1920 |
+
"grad_norm": 0.8798834085464478,
|
1921 |
+
"learning_rate": 4.957185405807893e-06,
|
1922 |
+
"loss": 0.9718,
|
1923 |
+
"step": 2710
|
1924 |
+
},
|
1925 |
+
{
|
1926 |
+
"epoch": 0.5063291139240507,
|
1927 |
+
"grad_norm": 0.9702854752540588,
|
1928 |
+
"learning_rate": 4.938570364854804e-06,
|
1929 |
+
"loss": 0.9951,
|
1930 |
+
"step": 2720
|
1931 |
+
},
|
1932 |
+
{
|
1933 |
+
"epoch": 0.5081906180193596,
|
1934 |
+
"grad_norm": 0.9347551465034485,
|
1935 |
+
"learning_rate": 4.9199553239017125e-06,
|
1936 |
+
"loss": 1.0111,
|
1937 |
+
"step": 2730
|
1938 |
+
},
|
1939 |
+
{
|
1940 |
+
"epoch": 0.5100521221146687,
|
1941 |
+
"grad_norm": 0.9056432247161865,
|
1942 |
+
"learning_rate": 4.901340282948623e-06,
|
1943 |
+
"loss": 1.0045,
|
1944 |
+
"step": 2740
|
1945 |
+
},
|
1946 |
+
{
|
1947 |
+
"epoch": 0.5119136262099777,
|
1948 |
+
"grad_norm": 0.8823024034500122,
|
1949 |
+
"learning_rate": 4.8827252419955325e-06,
|
1950 |
+
"loss": 1.0103,
|
1951 |
+
"step": 2750
|
1952 |
+
},
|
1953 |
+
{
|
1954 |
+
"epoch": 0.5137751303052867,
|
1955 |
+
"grad_norm": 0.9335477352142334,
|
1956 |
+
"learning_rate": 4.864110201042443e-06,
|
1957 |
+
"loss": 1.0012,
|
1958 |
+
"step": 2760
|
1959 |
+
},
|
1960 |
+
{
|
1961 |
+
"epoch": 0.5156366344005957,
|
1962 |
+
"grad_norm": 0.9590019583702087,
|
1963 |
+
"learning_rate": 4.8454951600893525e-06,
|
1964 |
+
"loss": 1.0024,
|
1965 |
+
"step": 2770
|
1966 |
+
},
|
1967 |
+
{
|
1968 |
+
"epoch": 0.5174981384959046,
|
1969 |
+
"grad_norm": 1.0436668395996094,
|
1970 |
+
"learning_rate": 4.826880119136262e-06,
|
1971 |
+
"loss": 0.9914,
|
1972 |
+
"step": 2780
|
1973 |
+
},
|
1974 |
+
{
|
1975 |
+
"epoch": 0.5193596425912137,
|
1976 |
+
"grad_norm": 0.8879066109657288,
|
1977 |
+
"learning_rate": 4.8082650781831725e-06,
|
1978 |
+
"loss": 0.9865,
|
1979 |
+
"step": 2790
|
1980 |
+
},
|
1981 |
+
{
|
1982 |
+
"epoch": 0.5212211466865228,
|
1983 |
+
"grad_norm": 0.889061689376831,
|
1984 |
+
"learning_rate": 4.789650037230082e-06,
|
1985 |
+
"loss": 0.9699,
|
1986 |
+
"step": 2800
|
1987 |
+
},
|
1988 |
+
{
|
1989 |
+
"epoch": 0.5230826507818317,
|
1990 |
+
"grad_norm": 1.0462664365768433,
|
1991 |
+
"learning_rate": 4.771034996276992e-06,
|
1992 |
+
"loss": 0.9969,
|
1993 |
+
"step": 2810
|
1994 |
+
},
|
1995 |
+
{
|
1996 |
+
"epoch": 0.5249441548771407,
|
1997 |
+
"grad_norm": 0.9901588559150696,
|
1998 |
+
"learning_rate": 4.752419955323902e-06,
|
1999 |
+
"loss": 0.9788,
|
2000 |
+
"step": 2820
|
2001 |
+
},
|
2002 |
+
{
|
2003 |
+
"epoch": 0.5268056589724497,
|
2004 |
+
"grad_norm": 0.9645290374755859,
|
2005 |
+
"learning_rate": 4.733804914370812e-06,
|
2006 |
+
"loss": 0.9892,
|
2007 |
+
"step": 2830
|
2008 |
+
},
|
2009 |
+
{
|
2010 |
+
"epoch": 0.5286671630677587,
|
2011 |
+
"grad_norm": 1.0000883340835571,
|
2012 |
+
"learning_rate": 4.715189873417722e-06,
|
2013 |
+
"loss": 0.9578,
|
2014 |
+
"step": 2840
|
2015 |
+
},
|
2016 |
+
{
|
2017 |
+
"epoch": 0.5305286671630678,
|
2018 |
+
"grad_norm": 0.9502646923065186,
|
2019 |
+
"learning_rate": 4.696574832464632e-06,
|
2020 |
+
"loss": 1.0068,
|
2021 |
+
"step": 2850
|
2022 |
+
},
|
2023 |
+
{
|
2024 |
+
"epoch": 0.5323901712583767,
|
2025 |
+
"grad_norm": 0.8752572536468506,
|
2026 |
+
"learning_rate": 4.677959791511541e-06,
|
2027 |
+
"loss": 1.0039,
|
2028 |
+
"step": 2860
|
2029 |
+
},
|
2030 |
+
{
|
2031 |
+
"epoch": 0.5342516753536858,
|
2032 |
+
"grad_norm": 0.9260790348052979,
|
2033 |
+
"learning_rate": 4.659344750558452e-06,
|
2034 |
+
"loss": 1.0158,
|
2035 |
+
"step": 2870
|
2036 |
+
},
|
2037 |
+
{
|
2038 |
+
"epoch": 0.5361131794489948,
|
2039 |
+
"grad_norm": 1.008202075958252,
|
2040 |
+
"learning_rate": 4.640729709605361e-06,
|
2041 |
+
"loss": 0.982,
|
2042 |
+
"step": 2880
|
2043 |
+
},
|
2044 |
+
{
|
2045 |
+
"epoch": 0.5379746835443038,
|
2046 |
+
"grad_norm": 1.071338415145874,
|
2047 |
+
"learning_rate": 4.622114668652272e-06,
|
2048 |
+
"loss": 0.9467,
|
2049 |
+
"step": 2890
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 0.5398361876396128,
|
2053 |
+
"grad_norm": 1.03144371509552,
|
2054 |
+
"learning_rate": 4.603499627699181e-06,
|
2055 |
+
"loss": 0.9884,
|
2056 |
+
"step": 2900
|
2057 |
+
},
|
2058 |
+
{
|
2059 |
+
"epoch": 0.5416976917349218,
|
2060 |
+
"grad_norm": 0.9676874279975891,
|
2061 |
+
"learning_rate": 4.584884586746091e-06,
|
2062 |
+
"loss": 0.9678,
|
2063 |
+
"step": 2910
|
2064 |
+
},
|
2065 |
+
{
|
2066 |
+
"epoch": 0.5435591958302308,
|
2067 |
+
"grad_norm": 0.9647573232650757,
|
2068 |
+
"learning_rate": 4.566269545793001e-06,
|
2069 |
+
"loss": 0.9939,
|
2070 |
+
"step": 2920
|
2071 |
+
},
|
2072 |
+
{
|
2073 |
+
"epoch": 0.5454206999255399,
|
2074 |
+
"grad_norm": 0.9683008193969727,
|
2075 |
+
"learning_rate": 4.547654504839911e-06,
|
2076 |
+
"loss": 0.9855,
|
2077 |
+
"step": 2930
|
2078 |
+
},
|
2079 |
+
{
|
2080 |
+
"epoch": 0.5472822040208488,
|
2081 |
+
"grad_norm": 0.9874380230903625,
|
2082 |
+
"learning_rate": 4.5290394638868205e-06,
|
2083 |
+
"loss": 0.992,
|
2084 |
+
"step": 2940
|
2085 |
+
},
|
2086 |
+
{
|
2087 |
+
"epoch": 0.5491437081161579,
|
2088 |
+
"grad_norm": 1.0078530311584473,
|
2089 |
+
"learning_rate": 4.510424422933731e-06,
|
2090 |
+
"loss": 0.9633,
|
2091 |
+
"step": 2950
|
2092 |
+
},
|
2093 |
+
{
|
2094 |
+
"epoch": 0.5510052122114668,
|
2095 |
+
"grad_norm": 0.9944348931312561,
|
2096 |
+
"learning_rate": 4.4918093819806405e-06,
|
2097 |
+
"loss": 1.0,
|
2098 |
+
"step": 2960
|
2099 |
+
},
|
2100 |
+
{
|
2101 |
+
"epoch": 0.5528667163067759,
|
2102 |
+
"grad_norm": 1.0273864269256592,
|
2103 |
+
"learning_rate": 4.473194341027551e-06,
|
2104 |
+
"loss": 0.9713,
|
2105 |
+
"step": 2970
|
2106 |
+
},
|
2107 |
+
{
|
2108 |
+
"epoch": 0.5547282204020849,
|
2109 |
+
"grad_norm": 1.0042091608047485,
|
2110 |
+
"learning_rate": 4.4545793000744605e-06,
|
2111 |
+
"loss": 0.9758,
|
2112 |
+
"step": 2980
|
2113 |
+
},
|
2114 |
+
{
|
2115 |
+
"epoch": 0.5565897244973939,
|
2116 |
+
"grad_norm": 0.9716913104057312,
|
2117 |
+
"learning_rate": 4.43596425912137e-06,
|
2118 |
+
"loss": 0.9592,
|
2119 |
+
"step": 2990
|
2120 |
+
},
|
2121 |
+
{
|
2122 |
+
"epoch": 0.5584512285927029,
|
2123 |
+
"grad_norm": 1.0423681735992432,
|
2124 |
+
"learning_rate": 4.4173492181682805e-06,
|
2125 |
+
"loss": 0.9902,
|
2126 |
+
"step": 3000
|
2127 |
+
},
|
2128 |
+
{
|
2129 |
+
"epoch": 0.5584512285927029,
|
2130 |
+
"eval_loss": 0.9846093654632568,
|
2131 |
+
"eval_runtime": 1069.2181,
|
2132 |
+
"eval_samples_per_second": 17.864,
|
2133 |
+
"eval_steps_per_second": 0.558,
|
2134 |
+
"step": 3000
|
2135 |
+
}
|
2136 |
+
],
|
2137 |
+
"logging_steps": 10,
|
2138 |
+
"max_steps": 5372,
|
2139 |
+
"num_input_tokens_seen": 0,
|
2140 |
+
"num_train_epochs": 1,
|
2141 |
+
"save_steps": 1000,
|
2142 |
+
"stateful_callbacks": {
|
2143 |
+
"TrainerControl": {
|
2144 |
+
"args": {
|
2145 |
+
"should_epoch_stop": false,
|
2146 |
+
"should_evaluate": false,
|
2147 |
+
"should_log": false,
|
2148 |
+
"should_save": true,
|
2149 |
+
"should_training_stop": false
|
2150 |
+
},
|
2151 |
+
"attributes": {}
|
2152 |
+
}
|
2153 |
+
},
|
2154 |
+
"total_flos": 2.914805497032868e+19,
|
2155 |
+
"train_batch_size": 16,
|
2156 |
+
"trial_name": null,
|
2157 |
+
"trial_params": null
|
2158 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f451ae945f5c52261ae5985e34d9d7bf418aada5d661438fb74a55e6d40e5427
|
3 |
+
size 5777
|