Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +59 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- all_results.json +8 -0
- chat_template.jinja +1 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2068 -0
- train_results.json +8 -0
- trainer_log.jsonl +1 -0
- trainer_state.json +2556 -0
- training_args.bin +3 -0
- training_loss.png +0 -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 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
license: other
|
4 |
+
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
|
5 |
+
tags:
|
6 |
+
- llama-factory
|
7 |
+
- lora
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: dpsk-r1-dis-llama-8b_eqa_lora_sft
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# dpsk-r1-dis-llama-8b_eqa_lora_sft
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) on the energy_qa_alpaca dataset.
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0001
|
39 |
+
- train_batch_size: 1
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 8
|
43 |
+
- total_train_batch_size: 8
|
44 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
47 |
+
- num_epochs: 1.0
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- PEFT 0.15.2
|
56 |
+
- Transformers 4.52.4
|
57 |
+
- Pytorch 2.7.0+cu126
|
58 |
+
- Datasets 3.6.0
|
59 |
+
- Tokenizers 0.21.1
|
adapter_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
|
5 |
+
"bias": "none",
|
6 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 16,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0.0,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": null,
|
22 |
+
"peft_type": "LORA",
|
23 |
+
"r": 8,
|
24 |
+
"rank_pattern": {},
|
25 |
+
"revision": null,
|
26 |
+
"target_modules": [
|
27 |
+
"gate_proj",
|
28 |
+
"k_proj",
|
29 |
+
"q_proj",
|
30 |
+
"up_proj",
|
31 |
+
"v_proj",
|
32 |
+
"o_proj",
|
33 |
+
"down_proj"
|
34 |
+
],
|
35 |
+
"task_type": "CAUSAL_LM",
|
36 |
+
"trainable_token_indices": null,
|
37 |
+
"use_dora": false,
|
38 |
+
"use_rslora": false
|
39 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3de331e9550440f04fecd60a280e2d61ab7b5f083d6fb2eea9aaea59d157be89
|
3 |
+
size 83945296
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 1.3861725429517517e+17,
|
4 |
+
"train_loss": 0.0,
|
5 |
+
"train_runtime": 0.8982,
|
6 |
+
"train_samples_per_second": 15978.88,
|
7 |
+
"train_steps_per_second": 1998.334
|
8 |
+
}
|
chat_template.jinja
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\n'}}{% endif %}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end▁of▁sentence|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end▁of▁sentence|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
|
3 |
+
size 17209530
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2068 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"128000": {
|
7 |
+
"content": "<|begin▁of▁sentence|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"128001": {
|
15 |
+
"content": "<|end▁of▁sentence|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"128002": {
|
23 |
+
"content": "<|reserved_special_token_0|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"128003": {
|
31 |
+
"content": "<|reserved_special_token_1|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"128004": {
|
39 |
+
"content": "<|finetune_right_pad_id|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"128005": {
|
47 |
+
"content": "<|reserved_special_token_2|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"128006": {
|
55 |
+
"content": "<|start_header_id|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"128007": {
|
63 |
+
"content": "<|end_header_id|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": false,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"128008": {
|
71 |
+
"content": "<|eom_id|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": false,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"128009": {
|
79 |
+
"content": "<|eot_id|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": false,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"128010": {
|
87 |
+
"content": "<|python_tag|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": false,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"128011": {
|
95 |
+
"content": "<|User|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"128012": {
|
103 |
+
"content": "<|Assistant|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": false,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"128013": {
|
111 |
+
"content": "<think>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": false,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"128014": {
|
119 |
+
"content": "</think>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"128015": {
|
127 |
+
"content": "<|▁pad▁|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": false,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": true
|
133 |
+
},
|
134 |
+
"128016": {
|
135 |
+
"content": "<|reserved_special_token_8|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": false,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": true
|
141 |
+
},
|
142 |
+
"128017": {
|
143 |
+
"content": "<|reserved_special_token_9|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": false,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": true
|
149 |
+
},
|
150 |
+
"128018": {
|
151 |
+
"content": "<|reserved_special_token_10|>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": true
|
157 |
+
},
|
158 |
+
"128019": {
|
159 |
+
"content": "<|reserved_special_token_11|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": false,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": true
|
165 |
+
},
|
166 |
+
"128020": {
|
167 |
+
"content": "<|reserved_special_token_12|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": false,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": true
|
173 |
+
},
|
174 |
+
"128021": {
|
175 |
+
"content": "<|reserved_special_token_13|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": false,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": true
|
181 |
+
},
|
182 |
+
"128022": {
|
183 |
+
"content": "<|reserved_special_token_14|>",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": false,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": true
|
189 |
+
},
|
190 |
+
"128023": {
|
191 |
+
"content": "<|reserved_special_token_15|>",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": false,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": true
|
197 |
+
},
|
198 |
+
"128024": {
|
199 |
+
"content": "<|reserved_special_token_16|>",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": false,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": true
|
205 |
+
},
|
206 |
+
"128025": {
|
207 |
+
"content": "<|reserved_special_token_17|>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": true
|
213 |
+
},
|
214 |
+
"128026": {
|
215 |
+
"content": "<|reserved_special_token_18|>",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": false,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": true
|
221 |
+
},
|
222 |
+
"128027": {
|
223 |
+
"content": "<|reserved_special_token_19|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
},
|
230 |
+
"128028": {
|
231 |
+
"content": "<|reserved_special_token_20|>",
|
232 |
+
"lstrip": false,
|
233 |
+
"normalized": false,
|
234 |
+
"rstrip": false,
|
235 |
+
"single_word": false,
|
236 |
+
"special": true
|
237 |
+
},
|
238 |
+
"128029": {
|
239 |
+
"content": "<|reserved_special_token_21|>",
|
240 |
+
"lstrip": false,
|
241 |
+
"normalized": false,
|
242 |
+
"rstrip": false,
|
243 |
+
"single_word": false,
|
244 |
+
"special": true
|
245 |
+
},
|
246 |
+
"128030": {
|
247 |
+
"content": "<|reserved_special_token_22|>",
|
248 |
+
"lstrip": false,
|
249 |
+
"normalized": false,
|
250 |
+
"rstrip": false,
|
251 |
+
"single_word": false,
|
252 |
+
"special": true
|
253 |
+
},
|
254 |
+
"128031": {
|
255 |
+
"content": "<|reserved_special_token_23|>",
|
256 |
+
"lstrip": false,
|
257 |
+
"normalized": false,
|
258 |
+
"rstrip": false,
|
259 |
+
"single_word": false,
|
260 |
+
"special": true
|
261 |
+
},
|
262 |
+
"128032": {
|
263 |
+
"content": "<|reserved_special_token_24|>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false,
|
268 |
+
"special": true
|
269 |
+
},
|
270 |
+
"128033": {
|
271 |
+
"content": "<|reserved_special_token_25|>",
|
272 |
+
"lstrip": false,
|
273 |
+
"normalized": false,
|
274 |
+
"rstrip": false,
|
275 |
+
"single_word": false,
|
276 |
+
"special": true
|
277 |
+
},
|
278 |
+
"128034": {
|
279 |
+
"content": "<|reserved_special_token_26|>",
|
280 |
+
"lstrip": false,
|
281 |
+
"normalized": false,
|
282 |
+
"rstrip": false,
|
283 |
+
"single_word": false,
|
284 |
+
"special": true
|
285 |
+
},
|
286 |
+
"128035": {
|
287 |
+
"content": "<|reserved_special_token_27|>",
|
288 |
+
"lstrip": false,
|
289 |
+
"normalized": false,
|
290 |
+
"rstrip": false,
|
291 |
+
"single_word": false,
|
292 |
+
"special": true
|
293 |
+
},
|
294 |
+
"128036": {
|
295 |
+
"content": "<|reserved_special_token_28|>",
|
296 |
+
"lstrip": false,
|
297 |
+
"normalized": false,
|
298 |
+
"rstrip": false,
|
299 |
+
"single_word": false,
|
300 |
+
"special": true
|
301 |
+
},
|
302 |
+
"128037": {
|
303 |
+
"content": "<|reserved_special_token_29|>",
|
304 |
+
"lstrip": false,
|
305 |
+
"normalized": false,
|
306 |
+
"rstrip": false,
|
307 |
+
"single_word": false,
|
308 |
+
"special": true
|
309 |
+
},
|
310 |
+
"128038": {
|
311 |
+
"content": "<|reserved_special_token_30|>",
|
312 |
+
"lstrip": false,
|
313 |
+
"normalized": false,
|
314 |
+
"rstrip": false,
|
315 |
+
"single_word": false,
|
316 |
+
"special": true
|
317 |
+
},
|
318 |
+
"128039": {
|
319 |
+
"content": "<|reserved_special_token_31|>",
|
320 |
+
"lstrip": false,
|
321 |
+
"normalized": false,
|
322 |
+
"rstrip": false,
|
323 |
+
"single_word": false,
|
324 |
+
"special": true
|
325 |
+
},
|
326 |
+
"128040": {
|
327 |
+
"content": "<|reserved_special_token_32|>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false,
|
332 |
+
"special": true
|
333 |
+
},
|
334 |
+
"128041": {
|
335 |
+
"content": "<|reserved_special_token_33|>",
|
336 |
+
"lstrip": false,
|
337 |
+
"normalized": false,
|
338 |
+
"rstrip": false,
|
339 |
+
"single_word": false,
|
340 |
+
"special": true
|
341 |
+
},
|
342 |
+
"128042": {
|
343 |
+
"content": "<|reserved_special_token_34|>",
|
344 |
+
"lstrip": false,
|
345 |
+
"normalized": false,
|
346 |
+
"rstrip": false,
|
347 |
+
"single_word": false,
|
348 |
+
"special": true
|
349 |
+
},
|
350 |
+
"128043": {
|
351 |
+
"content": "<|reserved_special_token_35|>",
|
352 |
+
"lstrip": false,
|
353 |
+
"normalized": false,
|
354 |
+
"rstrip": false,
|
355 |
+
"single_word": false,
|
356 |
+
"special": true
|
357 |
+
},
|
358 |
+
"128044": {
|
359 |
+
"content": "<|reserved_special_token_36|>",
|
360 |
+
"lstrip": false,
|
361 |
+
"normalized": false,
|
362 |
+
"rstrip": false,
|
363 |
+
"single_word": false,
|
364 |
+
"special": true
|
365 |
+
},
|
366 |
+
"128045": {
|
367 |
+
"content": "<|reserved_special_token_37|>",
|
368 |
+
"lstrip": false,
|
369 |
+
"normalized": false,
|
370 |
+
"rstrip": false,
|
371 |
+
"single_word": false,
|
372 |
+
"special": true
|
373 |
+
},
|
374 |
+
"128046": {
|
375 |
+
"content": "<|reserved_special_token_38|>",
|
376 |
+
"lstrip": false,
|
377 |
+
"normalized": false,
|
378 |
+
"rstrip": false,
|
379 |
+
"single_word": false,
|
380 |
+
"special": true
|
381 |
+
},
|
382 |
+
"128047": {
|
383 |
+
"content": "<|reserved_special_token_39|>",
|
384 |
+
"lstrip": false,
|
385 |
+
"normalized": false,
|
386 |
+
"rstrip": false,
|
387 |
+
"single_word": false,
|
388 |
+
"special": true
|
389 |
+
},
|
390 |
+
"128048": {
|
391 |
+
"content": "<|reserved_special_token_40|>",
|
392 |
+
"lstrip": false,
|
393 |
+
"normalized": false,
|
394 |
+
"rstrip": false,
|
395 |
+
"single_word": false,
|
396 |
+
"special": true
|
397 |
+
},
|
398 |
+
"128049": {
|
399 |
+
"content": "<|reserved_special_token_41|>",
|
400 |
+
"lstrip": false,
|
401 |
+
"normalized": false,
|
402 |
+
"rstrip": false,
|
403 |
+
"single_word": false,
|
404 |
+
"special": true
|
405 |
+
},
|
406 |
+
"128050": {
|
407 |
+
"content": "<|reserved_special_token_42|>",
|
408 |
+
"lstrip": false,
|
409 |
+
"normalized": false,
|
410 |
+
"rstrip": false,
|
411 |
+
"single_word": false,
|
412 |
+
"special": true
|
413 |
+
},
|
414 |
+
"128051": {
|
415 |
+
"content": "<|reserved_special_token_43|>",
|
416 |
+
"lstrip": false,
|
417 |
+
"normalized": false,
|
418 |
+
"rstrip": false,
|
419 |
+
"single_word": false,
|
420 |
+
"special": true
|
421 |
+
},
|
422 |
+
"128052": {
|
423 |
+
"content": "<|reserved_special_token_44|>",
|
424 |
+
"lstrip": false,
|
425 |
+
"normalized": false,
|
426 |
+
"rstrip": false,
|
427 |
+
"single_word": false,
|
428 |
+
"special": true
|
429 |
+
},
|
430 |
+
"128053": {
|
431 |
+
"content": "<|reserved_special_token_45|>",
|
432 |
+
"lstrip": false,
|
433 |
+
"normalized": false,
|
434 |
+
"rstrip": false,
|
435 |
+
"single_word": false,
|
436 |
+
"special": true
|
437 |
+
},
|
438 |
+
"128054": {
|
439 |
+
"content": "<|reserved_special_token_46|>",
|
440 |
+
"lstrip": false,
|
441 |
+
"normalized": false,
|
442 |
+
"rstrip": false,
|
443 |
+
"single_word": false,
|
444 |
+
"special": true
|
445 |
+
},
|
446 |
+
"128055": {
|
447 |
+
"content": "<|reserved_special_token_47|>",
|
448 |
+
"lstrip": false,
|
449 |
+
"normalized": false,
|
450 |
+
"rstrip": false,
|
451 |
+
"single_word": false,
|
452 |
+
"special": true
|
453 |
+
},
|
454 |
+
"128056": {
|
455 |
+
"content": "<|reserved_special_token_48|>",
|
456 |
+
"lstrip": false,
|
457 |
+
"normalized": false,
|
458 |
+
"rstrip": false,
|
459 |
+
"single_word": false,
|
460 |
+
"special": true
|
461 |
+
},
|
462 |
+
"128057": {
|
463 |
+
"content": "<|reserved_special_token_49|>",
|
464 |
+
"lstrip": false,
|
465 |
+
"normalized": false,
|
466 |
+
"rstrip": false,
|
467 |
+
"single_word": false,
|
468 |
+
"special": true
|
469 |
+
},
|
470 |
+
"128058": {
|
471 |
+
"content": "<|reserved_special_token_50|>",
|
472 |
+
"lstrip": false,
|
473 |
+
"normalized": false,
|
474 |
+
"rstrip": false,
|
475 |
+
"single_word": false,
|
476 |
+
"special": true
|
477 |
+
},
|
478 |
+
"128059": {
|
479 |
+
"content": "<|reserved_special_token_51|>",
|
480 |
+
"lstrip": false,
|
481 |
+
"normalized": false,
|
482 |
+
"rstrip": false,
|
483 |
+
"single_word": false,
|
484 |
+
"special": true
|
485 |
+
},
|
486 |
+
"128060": {
|
487 |
+
"content": "<|reserved_special_token_52|>",
|
488 |
+
"lstrip": false,
|
489 |
+
"normalized": false,
|
490 |
+
"rstrip": false,
|
491 |
+
"single_word": false,
|
492 |
+
"special": true
|
493 |
+
},
|
494 |
+
"128061": {
|
495 |
+
"content": "<|reserved_special_token_53|>",
|
496 |
+
"lstrip": false,
|
497 |
+
"normalized": false,
|
498 |
+
"rstrip": false,
|
499 |
+
"single_word": false,
|
500 |
+
"special": true
|
501 |
+
},
|
502 |
+
"128062": {
|
503 |
+
"content": "<|reserved_special_token_54|>",
|
504 |
+
"lstrip": false,
|
505 |
+
"normalized": false,
|
506 |
+
"rstrip": false,
|
507 |
+
"single_word": false,
|
508 |
+
"special": true
|
509 |
+
},
|
510 |
+
"128063": {
|
511 |
+
"content": "<|reserved_special_token_55|>",
|
512 |
+
"lstrip": false,
|
513 |
+
"normalized": false,
|
514 |
+
"rstrip": false,
|
515 |
+
"single_word": false,
|
516 |
+
"special": true
|
517 |
+
},
|
518 |
+
"128064": {
|
519 |
+
"content": "<|reserved_special_token_56|>",
|
520 |
+
"lstrip": false,
|
521 |
+
"normalized": false,
|
522 |
+
"rstrip": false,
|
523 |
+
"single_word": false,
|
524 |
+
"special": true
|
525 |
+
},
|
526 |
+
"128065": {
|
527 |
+
"content": "<|reserved_special_token_57|>",
|
528 |
+
"lstrip": false,
|
529 |
+
"normalized": false,
|
530 |
+
"rstrip": false,
|
531 |
+
"single_word": false,
|
532 |
+
"special": true
|
533 |
+
},
|
534 |
+
"128066": {
|
535 |
+
"content": "<|reserved_special_token_58|>",
|
536 |
+
"lstrip": false,
|
537 |
+
"normalized": false,
|
538 |
+
"rstrip": false,
|
539 |
+
"single_word": false,
|
540 |
+
"special": true
|
541 |
+
},
|
542 |
+
"128067": {
|
543 |
+
"content": "<|reserved_special_token_59|>",
|
544 |
+
"lstrip": false,
|
545 |
+
"normalized": false,
|
546 |
+
"rstrip": false,
|
547 |
+
"single_word": false,
|
548 |
+
"special": true
|
549 |
+
},
|
550 |
+
"128068": {
|
551 |
+
"content": "<|reserved_special_token_60|>",
|
552 |
+
"lstrip": false,
|
553 |
+
"normalized": false,
|
554 |
+
"rstrip": false,
|
555 |
+
"single_word": false,
|
556 |
+
"special": true
|
557 |
+
},
|
558 |
+
"128069": {
|
559 |
+
"content": "<|reserved_special_token_61|>",
|
560 |
+
"lstrip": false,
|
561 |
+
"normalized": false,
|
562 |
+
"rstrip": false,
|
563 |
+
"single_word": false,
|
564 |
+
"special": true
|
565 |
+
},
|
566 |
+
"128070": {
|
567 |
+
"content": "<|reserved_special_token_62|>",
|
568 |
+
"lstrip": false,
|
569 |
+
"normalized": false,
|
570 |
+
"rstrip": false,
|
571 |
+
"single_word": false,
|
572 |
+
"special": true
|
573 |
+
},
|
574 |
+
"128071": {
|
575 |
+
"content": "<|reserved_special_token_63|>",
|
576 |
+
"lstrip": false,
|
577 |
+
"normalized": false,
|
578 |
+
"rstrip": false,
|
579 |
+
"single_word": false,
|
580 |
+
"special": true
|
581 |
+
},
|
582 |
+
"128072": {
|
583 |
+
"content": "<|reserved_special_token_64|>",
|
584 |
+
"lstrip": false,
|
585 |
+
"normalized": false,
|
586 |
+
"rstrip": false,
|
587 |
+
"single_word": false,
|
588 |
+
"special": true
|
589 |
+
},
|
590 |
+
"128073": {
|
591 |
+
"content": "<|reserved_special_token_65|>",
|
592 |
+
"lstrip": false,
|
593 |
+
"normalized": false,
|
594 |
+
"rstrip": false,
|
595 |
+
"single_word": false,
|
596 |
+
"special": true
|
597 |
+
},
|
598 |
+
"128074": {
|
599 |
+
"content": "<|reserved_special_token_66|>",
|
600 |
+
"lstrip": false,
|
601 |
+
"normalized": false,
|
602 |
+
"rstrip": false,
|
603 |
+
"single_word": false,
|
604 |
+
"special": true
|
605 |
+
},
|
606 |
+
"128075": {
|
607 |
+
"content": "<|reserved_special_token_67|>",
|
608 |
+
"lstrip": false,
|
609 |
+
"normalized": false,
|
610 |
+
"rstrip": false,
|
611 |
+
"single_word": false,
|
612 |
+
"special": true
|
613 |
+
},
|
614 |
+
"128076": {
|
615 |
+
"content": "<|reserved_special_token_68|>",
|
616 |
+
"lstrip": false,
|
617 |
+
"normalized": false,
|
618 |
+
"rstrip": false,
|
619 |
+
"single_word": false,
|
620 |
+
"special": true
|
621 |
+
},
|
622 |
+
"128077": {
|
623 |
+
"content": "<|reserved_special_token_69|>",
|
624 |
+
"lstrip": false,
|
625 |
+
"normalized": false,
|
626 |
+
"rstrip": false,
|
627 |
+
"single_word": false,
|
628 |
+
"special": true
|
629 |
+
},
|
630 |
+
"128078": {
|
631 |
+
"content": "<|reserved_special_token_70|>",
|
632 |
+
"lstrip": false,
|
633 |
+
"normalized": false,
|
634 |
+
"rstrip": false,
|
635 |
+
"single_word": false,
|
636 |
+
"special": true
|
637 |
+
},
|
638 |
+
"128079": {
|
639 |
+
"content": "<|reserved_special_token_71|>",
|
640 |
+
"lstrip": false,
|
641 |
+
"normalized": false,
|
642 |
+
"rstrip": false,
|
643 |
+
"single_word": false,
|
644 |
+
"special": true
|
645 |
+
},
|
646 |
+
"128080": {
|
647 |
+
"content": "<|reserved_special_token_72|>",
|
648 |
+
"lstrip": false,
|
649 |
+
"normalized": false,
|
650 |
+
"rstrip": false,
|
651 |
+
"single_word": false,
|
652 |
+
"special": true
|
653 |
+
},
|
654 |
+
"128081": {
|
655 |
+
"content": "<|reserved_special_token_73|>",
|
656 |
+
"lstrip": false,
|
657 |
+
"normalized": false,
|
658 |
+
"rstrip": false,
|
659 |
+
"single_word": false,
|
660 |
+
"special": true
|
661 |
+
},
|
662 |
+
"128082": {
|
663 |
+
"content": "<|reserved_special_token_74|>",
|
664 |
+
"lstrip": false,
|
665 |
+
"normalized": false,
|
666 |
+
"rstrip": false,
|
667 |
+
"single_word": false,
|
668 |
+
"special": true
|
669 |
+
},
|
670 |
+
"128083": {
|
671 |
+
"content": "<|reserved_special_token_75|>",
|
672 |
+
"lstrip": false,
|
673 |
+
"normalized": false,
|
674 |
+
"rstrip": false,
|
675 |
+
"single_word": false,
|
676 |
+
"special": true
|
677 |
+
},
|
678 |
+
"128084": {
|
679 |
+
"content": "<|reserved_special_token_76|>",
|
680 |
+
"lstrip": false,
|
681 |
+
"normalized": false,
|
682 |
+
"rstrip": false,
|
683 |
+
"single_word": false,
|
684 |
+
"special": true
|
685 |
+
},
|
686 |
+
"128085": {
|
687 |
+
"content": "<|reserved_special_token_77|>",
|
688 |
+
"lstrip": false,
|
689 |
+
"normalized": false,
|
690 |
+
"rstrip": false,
|
691 |
+
"single_word": false,
|
692 |
+
"special": true
|
693 |
+
},
|
694 |
+
"128086": {
|
695 |
+
"content": "<|reserved_special_token_78|>",
|
696 |
+
"lstrip": false,
|
697 |
+
"normalized": false,
|
698 |
+
"rstrip": false,
|
699 |
+
"single_word": false,
|
700 |
+
"special": true
|
701 |
+
},
|
702 |
+
"128087": {
|
703 |
+
"content": "<|reserved_special_token_79|>",
|
704 |
+
"lstrip": false,
|
705 |
+
"normalized": false,
|
706 |
+
"rstrip": false,
|
707 |
+
"single_word": false,
|
708 |
+
"special": true
|
709 |
+
},
|
710 |
+
"128088": {
|
711 |
+
"content": "<|reserved_special_token_80|>",
|
712 |
+
"lstrip": false,
|
713 |
+
"normalized": false,
|
714 |
+
"rstrip": false,
|
715 |
+
"single_word": false,
|
716 |
+
"special": true
|
717 |
+
},
|
718 |
+
"128089": {
|
719 |
+
"content": "<|reserved_special_token_81|>",
|
720 |
+
"lstrip": false,
|
721 |
+
"normalized": false,
|
722 |
+
"rstrip": false,
|
723 |
+
"single_word": false,
|
724 |
+
"special": true
|
725 |
+
},
|
726 |
+
"128090": {
|
727 |
+
"content": "<|reserved_special_token_82|>",
|
728 |
+
"lstrip": false,
|
729 |
+
"normalized": false,
|
730 |
+
"rstrip": false,
|
731 |
+
"single_word": false,
|
732 |
+
"special": true
|
733 |
+
},
|
734 |
+
"128091": {
|
735 |
+
"content": "<|reserved_special_token_83|>",
|
736 |
+
"lstrip": false,
|
737 |
+
"normalized": false,
|
738 |
+
"rstrip": false,
|
739 |
+
"single_word": false,
|
740 |
+
"special": true
|
741 |
+
},
|
742 |
+
"128092": {
|
743 |
+
"content": "<|reserved_special_token_84|>",
|
744 |
+
"lstrip": false,
|
745 |
+
"normalized": false,
|
746 |
+
"rstrip": false,
|
747 |
+
"single_word": false,
|
748 |
+
"special": true
|
749 |
+
},
|
750 |
+
"128093": {
|
751 |
+
"content": "<|reserved_special_token_85|>",
|
752 |
+
"lstrip": false,
|
753 |
+
"normalized": false,
|
754 |
+
"rstrip": false,
|
755 |
+
"single_word": false,
|
756 |
+
"special": true
|
757 |
+
},
|
758 |
+
"128094": {
|
759 |
+
"content": "<|reserved_special_token_86|>",
|
760 |
+
"lstrip": false,
|
761 |
+
"normalized": false,
|
762 |
+
"rstrip": false,
|
763 |
+
"single_word": false,
|
764 |
+
"special": true
|
765 |
+
},
|
766 |
+
"128095": {
|
767 |
+
"content": "<|reserved_special_token_87|>",
|
768 |
+
"lstrip": false,
|
769 |
+
"normalized": false,
|
770 |
+
"rstrip": false,
|
771 |
+
"single_word": false,
|
772 |
+
"special": true
|
773 |
+
},
|
774 |
+
"128096": {
|
775 |
+
"content": "<|reserved_special_token_88|>",
|
776 |
+
"lstrip": false,
|
777 |
+
"normalized": false,
|
778 |
+
"rstrip": false,
|
779 |
+
"single_word": false,
|
780 |
+
"special": true
|
781 |
+
},
|
782 |
+
"128097": {
|
783 |
+
"content": "<|reserved_special_token_89|>",
|
784 |
+
"lstrip": false,
|
785 |
+
"normalized": false,
|
786 |
+
"rstrip": false,
|
787 |
+
"single_word": false,
|
788 |
+
"special": true
|
789 |
+
},
|
790 |
+
"128098": {
|
791 |
+
"content": "<|reserved_special_token_90|>",
|
792 |
+
"lstrip": false,
|
793 |
+
"normalized": false,
|
794 |
+
"rstrip": false,
|
795 |
+
"single_word": false,
|
796 |
+
"special": true
|
797 |
+
},
|
798 |
+
"128099": {
|
799 |
+
"content": "<|reserved_special_token_91|>",
|
800 |
+
"lstrip": false,
|
801 |
+
"normalized": false,
|
802 |
+
"rstrip": false,
|
803 |
+
"single_word": false,
|
804 |
+
"special": true
|
805 |
+
},
|
806 |
+
"128100": {
|
807 |
+
"content": "<|reserved_special_token_92|>",
|
808 |
+
"lstrip": false,
|
809 |
+
"normalized": false,
|
810 |
+
"rstrip": false,
|
811 |
+
"single_word": false,
|
812 |
+
"special": true
|
813 |
+
},
|
814 |
+
"128101": {
|
815 |
+
"content": "<|reserved_special_token_93|>",
|
816 |
+
"lstrip": false,
|
817 |
+
"normalized": false,
|
818 |
+
"rstrip": false,
|
819 |
+
"single_word": false,
|
820 |
+
"special": true
|
821 |
+
},
|
822 |
+
"128102": {
|
823 |
+
"content": "<|reserved_special_token_94|>",
|
824 |
+
"lstrip": false,
|
825 |
+
"normalized": false,
|
826 |
+
"rstrip": false,
|
827 |
+
"single_word": false,
|
828 |
+
"special": true
|
829 |
+
},
|
830 |
+
"128103": {
|
831 |
+
"content": "<|reserved_special_token_95|>",
|
832 |
+
"lstrip": false,
|
833 |
+
"normalized": false,
|
834 |
+
"rstrip": false,
|
835 |
+
"single_word": false,
|
836 |
+
"special": true
|
837 |
+
},
|
838 |
+
"128104": {
|
839 |
+
"content": "<|reserved_special_token_96|>",
|
840 |
+
"lstrip": false,
|
841 |
+
"normalized": false,
|
842 |
+
"rstrip": false,
|
843 |
+
"single_word": false,
|
844 |
+
"special": true
|
845 |
+
},
|
846 |
+
"128105": {
|
847 |
+
"content": "<|reserved_special_token_97|>",
|
848 |
+
"lstrip": false,
|
849 |
+
"normalized": false,
|
850 |
+
"rstrip": false,
|
851 |
+
"single_word": false,
|
852 |
+
"special": true
|
853 |
+
},
|
854 |
+
"128106": {
|
855 |
+
"content": "<|reserved_special_token_98|>",
|
856 |
+
"lstrip": false,
|
857 |
+
"normalized": false,
|
858 |
+
"rstrip": false,
|
859 |
+
"single_word": false,
|
860 |
+
"special": true
|
861 |
+
},
|
862 |
+
"128107": {
|
863 |
+
"content": "<|reserved_special_token_99|>",
|
864 |
+
"lstrip": false,
|
865 |
+
"normalized": false,
|
866 |
+
"rstrip": false,
|
867 |
+
"single_word": false,
|
868 |
+
"special": true
|
869 |
+
},
|
870 |
+
"128108": {
|
871 |
+
"content": "<|reserved_special_token_100|>",
|
872 |
+
"lstrip": false,
|
873 |
+
"normalized": false,
|
874 |
+
"rstrip": false,
|
875 |
+
"single_word": false,
|
876 |
+
"special": true
|
877 |
+
},
|
878 |
+
"128109": {
|
879 |
+
"content": "<|reserved_special_token_101|>",
|
880 |
+
"lstrip": false,
|
881 |
+
"normalized": false,
|
882 |
+
"rstrip": false,
|
883 |
+
"single_word": false,
|
884 |
+
"special": true
|
885 |
+
},
|
886 |
+
"128110": {
|
887 |
+
"content": "<|reserved_special_token_102|>",
|
888 |
+
"lstrip": false,
|
889 |
+
"normalized": false,
|
890 |
+
"rstrip": false,
|
891 |
+
"single_word": false,
|
892 |
+
"special": true
|
893 |
+
},
|
894 |
+
"128111": {
|
895 |
+
"content": "<|reserved_special_token_103|>",
|
896 |
+
"lstrip": false,
|
897 |
+
"normalized": false,
|
898 |
+
"rstrip": false,
|
899 |
+
"single_word": false,
|
900 |
+
"special": true
|
901 |
+
},
|
902 |
+
"128112": {
|
903 |
+
"content": "<|reserved_special_token_104|>",
|
904 |
+
"lstrip": false,
|
905 |
+
"normalized": false,
|
906 |
+
"rstrip": false,
|
907 |
+
"single_word": false,
|
908 |
+
"special": true
|
909 |
+
},
|
910 |
+
"128113": {
|
911 |
+
"content": "<|reserved_special_token_105|>",
|
912 |
+
"lstrip": false,
|
913 |
+
"normalized": false,
|
914 |
+
"rstrip": false,
|
915 |
+
"single_word": false,
|
916 |
+
"special": true
|
917 |
+
},
|
918 |
+
"128114": {
|
919 |
+
"content": "<|reserved_special_token_106|>",
|
920 |
+
"lstrip": false,
|
921 |
+
"normalized": false,
|
922 |
+
"rstrip": false,
|
923 |
+
"single_word": false,
|
924 |
+
"special": true
|
925 |
+
},
|
926 |
+
"128115": {
|
927 |
+
"content": "<|reserved_special_token_107|>",
|
928 |
+
"lstrip": false,
|
929 |
+
"normalized": false,
|
930 |
+
"rstrip": false,
|
931 |
+
"single_word": false,
|
932 |
+
"special": true
|
933 |
+
},
|
934 |
+
"128116": {
|
935 |
+
"content": "<|reserved_special_token_108|>",
|
936 |
+
"lstrip": false,
|
937 |
+
"normalized": false,
|
938 |
+
"rstrip": false,
|
939 |
+
"single_word": false,
|
940 |
+
"special": true
|
941 |
+
},
|
942 |
+
"128117": {
|
943 |
+
"content": "<|reserved_special_token_109|>",
|
944 |
+
"lstrip": false,
|
945 |
+
"normalized": false,
|
946 |
+
"rstrip": false,
|
947 |
+
"single_word": false,
|
948 |
+
"special": true
|
949 |
+
},
|
950 |
+
"128118": {
|
951 |
+
"content": "<|reserved_special_token_110|>",
|
952 |
+
"lstrip": false,
|
953 |
+
"normalized": false,
|
954 |
+
"rstrip": false,
|
955 |
+
"single_word": false,
|
956 |
+
"special": true
|
957 |
+
},
|
958 |
+
"128119": {
|
959 |
+
"content": "<|reserved_special_token_111|>",
|
960 |
+
"lstrip": false,
|
961 |
+
"normalized": false,
|
962 |
+
"rstrip": false,
|
963 |
+
"single_word": false,
|
964 |
+
"special": true
|
965 |
+
},
|
966 |
+
"128120": {
|
967 |
+
"content": "<|reserved_special_token_112|>",
|
968 |
+
"lstrip": false,
|
969 |
+
"normalized": false,
|
970 |
+
"rstrip": false,
|
971 |
+
"single_word": false,
|
972 |
+
"special": true
|
973 |
+
},
|
974 |
+
"128121": {
|
975 |
+
"content": "<|reserved_special_token_113|>",
|
976 |
+
"lstrip": false,
|
977 |
+
"normalized": false,
|
978 |
+
"rstrip": false,
|
979 |
+
"single_word": false,
|
980 |
+
"special": true
|
981 |
+
},
|
982 |
+
"128122": {
|
983 |
+
"content": "<|reserved_special_token_114|>",
|
984 |
+
"lstrip": false,
|
985 |
+
"normalized": false,
|
986 |
+
"rstrip": false,
|
987 |
+
"single_word": false,
|
988 |
+
"special": true
|
989 |
+
},
|
990 |
+
"128123": {
|
991 |
+
"content": "<|reserved_special_token_115|>",
|
992 |
+
"lstrip": false,
|
993 |
+
"normalized": false,
|
994 |
+
"rstrip": false,
|
995 |
+
"single_word": false,
|
996 |
+
"special": true
|
997 |
+
},
|
998 |
+
"128124": {
|
999 |
+
"content": "<|reserved_special_token_116|>",
|
1000 |
+
"lstrip": false,
|
1001 |
+
"normalized": false,
|
1002 |
+
"rstrip": false,
|
1003 |
+
"single_word": false,
|
1004 |
+
"special": true
|
1005 |
+
},
|
1006 |
+
"128125": {
|
1007 |
+
"content": "<|reserved_special_token_117|>",
|
1008 |
+
"lstrip": false,
|
1009 |
+
"normalized": false,
|
1010 |
+
"rstrip": false,
|
1011 |
+
"single_word": false,
|
1012 |
+
"special": true
|
1013 |
+
},
|
1014 |
+
"128126": {
|
1015 |
+
"content": "<|reserved_special_token_118|>",
|
1016 |
+
"lstrip": false,
|
1017 |
+
"normalized": false,
|
1018 |
+
"rstrip": false,
|
1019 |
+
"single_word": false,
|
1020 |
+
"special": true
|
1021 |
+
},
|
1022 |
+
"128127": {
|
1023 |
+
"content": "<|reserved_special_token_119|>",
|
1024 |
+
"lstrip": false,
|
1025 |
+
"normalized": false,
|
1026 |
+
"rstrip": false,
|
1027 |
+
"single_word": false,
|
1028 |
+
"special": true
|
1029 |
+
},
|
1030 |
+
"128128": {
|
1031 |
+
"content": "<|reserved_special_token_120|>",
|
1032 |
+
"lstrip": false,
|
1033 |
+
"normalized": false,
|
1034 |
+
"rstrip": false,
|
1035 |
+
"single_word": false,
|
1036 |
+
"special": true
|
1037 |
+
},
|
1038 |
+
"128129": {
|
1039 |
+
"content": "<|reserved_special_token_121|>",
|
1040 |
+
"lstrip": false,
|
1041 |
+
"normalized": false,
|
1042 |
+
"rstrip": false,
|
1043 |
+
"single_word": false,
|
1044 |
+
"special": true
|
1045 |
+
},
|
1046 |
+
"128130": {
|
1047 |
+
"content": "<|reserved_special_token_122|>",
|
1048 |
+
"lstrip": false,
|
1049 |
+
"normalized": false,
|
1050 |
+
"rstrip": false,
|
1051 |
+
"single_word": false,
|
1052 |
+
"special": true
|
1053 |
+
},
|
1054 |
+
"128131": {
|
1055 |
+
"content": "<|reserved_special_token_123|>",
|
1056 |
+
"lstrip": false,
|
1057 |
+
"normalized": false,
|
1058 |
+
"rstrip": false,
|
1059 |
+
"single_word": false,
|
1060 |
+
"special": true
|
1061 |
+
},
|
1062 |
+
"128132": {
|
1063 |
+
"content": "<|reserved_special_token_124|>",
|
1064 |
+
"lstrip": false,
|
1065 |
+
"normalized": false,
|
1066 |
+
"rstrip": false,
|
1067 |
+
"single_word": false,
|
1068 |
+
"special": true
|
1069 |
+
},
|
1070 |
+
"128133": {
|
1071 |
+
"content": "<|reserved_special_token_125|>",
|
1072 |
+
"lstrip": false,
|
1073 |
+
"normalized": false,
|
1074 |
+
"rstrip": false,
|
1075 |
+
"single_word": false,
|
1076 |
+
"special": true
|
1077 |
+
},
|
1078 |
+
"128134": {
|
1079 |
+
"content": "<|reserved_special_token_126|>",
|
1080 |
+
"lstrip": false,
|
1081 |
+
"normalized": false,
|
1082 |
+
"rstrip": false,
|
1083 |
+
"single_word": false,
|
1084 |
+
"special": true
|
1085 |
+
},
|
1086 |
+
"128135": {
|
1087 |
+
"content": "<|reserved_special_token_127|>",
|
1088 |
+
"lstrip": false,
|
1089 |
+
"normalized": false,
|
1090 |
+
"rstrip": false,
|
1091 |
+
"single_word": false,
|
1092 |
+
"special": true
|
1093 |
+
},
|
1094 |
+
"128136": {
|
1095 |
+
"content": "<|reserved_special_token_128|>",
|
1096 |
+
"lstrip": false,
|
1097 |
+
"normalized": false,
|
1098 |
+
"rstrip": false,
|
1099 |
+
"single_word": false,
|
1100 |
+
"special": true
|
1101 |
+
},
|
1102 |
+
"128137": {
|
1103 |
+
"content": "<|reserved_special_token_129|>",
|
1104 |
+
"lstrip": false,
|
1105 |
+
"normalized": false,
|
1106 |
+
"rstrip": false,
|
1107 |
+
"single_word": false,
|
1108 |
+
"special": true
|
1109 |
+
},
|
1110 |
+
"128138": {
|
1111 |
+
"content": "<|reserved_special_token_130|>",
|
1112 |
+
"lstrip": false,
|
1113 |
+
"normalized": false,
|
1114 |
+
"rstrip": false,
|
1115 |
+
"single_word": false,
|
1116 |
+
"special": true
|
1117 |
+
},
|
1118 |
+
"128139": {
|
1119 |
+
"content": "<|reserved_special_token_131|>",
|
1120 |
+
"lstrip": false,
|
1121 |
+
"normalized": false,
|
1122 |
+
"rstrip": false,
|
1123 |
+
"single_word": false,
|
1124 |
+
"special": true
|
1125 |
+
},
|
1126 |
+
"128140": {
|
1127 |
+
"content": "<|reserved_special_token_132|>",
|
1128 |
+
"lstrip": false,
|
1129 |
+
"normalized": false,
|
1130 |
+
"rstrip": false,
|
1131 |
+
"single_word": false,
|
1132 |
+
"special": true
|
1133 |
+
},
|
1134 |
+
"128141": {
|
1135 |
+
"content": "<|reserved_special_token_133|>",
|
1136 |
+
"lstrip": false,
|
1137 |
+
"normalized": false,
|
1138 |
+
"rstrip": false,
|
1139 |
+
"single_word": false,
|
1140 |
+
"special": true
|
1141 |
+
},
|
1142 |
+
"128142": {
|
1143 |
+
"content": "<|reserved_special_token_134|>",
|
1144 |
+
"lstrip": false,
|
1145 |
+
"normalized": false,
|
1146 |
+
"rstrip": false,
|
1147 |
+
"single_word": false,
|
1148 |
+
"special": true
|
1149 |
+
},
|
1150 |
+
"128143": {
|
1151 |
+
"content": "<|reserved_special_token_135|>",
|
1152 |
+
"lstrip": false,
|
1153 |
+
"normalized": false,
|
1154 |
+
"rstrip": false,
|
1155 |
+
"single_word": false,
|
1156 |
+
"special": true
|
1157 |
+
},
|
1158 |
+
"128144": {
|
1159 |
+
"content": "<|reserved_special_token_136|>",
|
1160 |
+
"lstrip": false,
|
1161 |
+
"normalized": false,
|
1162 |
+
"rstrip": false,
|
1163 |
+
"single_word": false,
|
1164 |
+
"special": true
|
1165 |
+
},
|
1166 |
+
"128145": {
|
1167 |
+
"content": "<|reserved_special_token_137|>",
|
1168 |
+
"lstrip": false,
|
1169 |
+
"normalized": false,
|
1170 |
+
"rstrip": false,
|
1171 |
+
"single_word": false,
|
1172 |
+
"special": true
|
1173 |
+
},
|
1174 |
+
"128146": {
|
1175 |
+
"content": "<|reserved_special_token_138|>",
|
1176 |
+
"lstrip": false,
|
1177 |
+
"normalized": false,
|
1178 |
+
"rstrip": false,
|
1179 |
+
"single_word": false,
|
1180 |
+
"special": true
|
1181 |
+
},
|
1182 |
+
"128147": {
|
1183 |
+
"content": "<|reserved_special_token_139|>",
|
1184 |
+
"lstrip": false,
|
1185 |
+
"normalized": false,
|
1186 |
+
"rstrip": false,
|
1187 |
+
"single_word": false,
|
1188 |
+
"special": true
|
1189 |
+
},
|
1190 |
+
"128148": {
|
1191 |
+
"content": "<|reserved_special_token_140|>",
|
1192 |
+
"lstrip": false,
|
1193 |
+
"normalized": false,
|
1194 |
+
"rstrip": false,
|
1195 |
+
"single_word": false,
|
1196 |
+
"special": true
|
1197 |
+
},
|
1198 |
+
"128149": {
|
1199 |
+
"content": "<|reserved_special_token_141|>",
|
1200 |
+
"lstrip": false,
|
1201 |
+
"normalized": false,
|
1202 |
+
"rstrip": false,
|
1203 |
+
"single_word": false,
|
1204 |
+
"special": true
|
1205 |
+
},
|
1206 |
+
"128150": {
|
1207 |
+
"content": "<|reserved_special_token_142|>",
|
1208 |
+
"lstrip": false,
|
1209 |
+
"normalized": false,
|
1210 |
+
"rstrip": false,
|
1211 |
+
"single_word": false,
|
1212 |
+
"special": true
|
1213 |
+
},
|
1214 |
+
"128151": {
|
1215 |
+
"content": "<|reserved_special_token_143|>",
|
1216 |
+
"lstrip": false,
|
1217 |
+
"normalized": false,
|
1218 |
+
"rstrip": false,
|
1219 |
+
"single_word": false,
|
1220 |
+
"special": true
|
1221 |
+
},
|
1222 |
+
"128152": {
|
1223 |
+
"content": "<|reserved_special_token_144|>",
|
1224 |
+
"lstrip": false,
|
1225 |
+
"normalized": false,
|
1226 |
+
"rstrip": false,
|
1227 |
+
"single_word": false,
|
1228 |
+
"special": true
|
1229 |
+
},
|
1230 |
+
"128153": {
|
1231 |
+
"content": "<|reserved_special_token_145|>",
|
1232 |
+
"lstrip": false,
|
1233 |
+
"normalized": false,
|
1234 |
+
"rstrip": false,
|
1235 |
+
"single_word": false,
|
1236 |
+
"special": true
|
1237 |
+
},
|
1238 |
+
"128154": {
|
1239 |
+
"content": "<|reserved_special_token_146|>",
|
1240 |
+
"lstrip": false,
|
1241 |
+
"normalized": false,
|
1242 |
+
"rstrip": false,
|
1243 |
+
"single_word": false,
|
1244 |
+
"special": true
|
1245 |
+
},
|
1246 |
+
"128155": {
|
1247 |
+
"content": "<|reserved_special_token_147|>",
|
1248 |
+
"lstrip": false,
|
1249 |
+
"normalized": false,
|
1250 |
+
"rstrip": false,
|
1251 |
+
"single_word": false,
|
1252 |
+
"special": true
|
1253 |
+
},
|
1254 |
+
"128156": {
|
1255 |
+
"content": "<|reserved_special_token_148|>",
|
1256 |
+
"lstrip": false,
|
1257 |
+
"normalized": false,
|
1258 |
+
"rstrip": false,
|
1259 |
+
"single_word": false,
|
1260 |
+
"special": true
|
1261 |
+
},
|
1262 |
+
"128157": {
|
1263 |
+
"content": "<|reserved_special_token_149|>",
|
1264 |
+
"lstrip": false,
|
1265 |
+
"normalized": false,
|
1266 |
+
"rstrip": false,
|
1267 |
+
"single_word": false,
|
1268 |
+
"special": true
|
1269 |
+
},
|
1270 |
+
"128158": {
|
1271 |
+
"content": "<|reserved_special_token_150|>",
|
1272 |
+
"lstrip": false,
|
1273 |
+
"normalized": false,
|
1274 |
+
"rstrip": false,
|
1275 |
+
"single_word": false,
|
1276 |
+
"special": true
|
1277 |
+
},
|
1278 |
+
"128159": {
|
1279 |
+
"content": "<|reserved_special_token_151|>",
|
1280 |
+
"lstrip": false,
|
1281 |
+
"normalized": false,
|
1282 |
+
"rstrip": false,
|
1283 |
+
"single_word": false,
|
1284 |
+
"special": true
|
1285 |
+
},
|
1286 |
+
"128160": {
|
1287 |
+
"content": "<|reserved_special_token_152|>",
|
1288 |
+
"lstrip": false,
|
1289 |
+
"normalized": false,
|
1290 |
+
"rstrip": false,
|
1291 |
+
"single_word": false,
|
1292 |
+
"special": true
|
1293 |
+
},
|
1294 |
+
"128161": {
|
1295 |
+
"content": "<|reserved_special_token_153|>",
|
1296 |
+
"lstrip": false,
|
1297 |
+
"normalized": false,
|
1298 |
+
"rstrip": false,
|
1299 |
+
"single_word": false,
|
1300 |
+
"special": true
|
1301 |
+
},
|
1302 |
+
"128162": {
|
1303 |
+
"content": "<|reserved_special_token_154|>",
|
1304 |
+
"lstrip": false,
|
1305 |
+
"normalized": false,
|
1306 |
+
"rstrip": false,
|
1307 |
+
"single_word": false,
|
1308 |
+
"special": true
|
1309 |
+
},
|
1310 |
+
"128163": {
|
1311 |
+
"content": "<|reserved_special_token_155|>",
|
1312 |
+
"lstrip": false,
|
1313 |
+
"normalized": false,
|
1314 |
+
"rstrip": false,
|
1315 |
+
"single_word": false,
|
1316 |
+
"special": true
|
1317 |
+
},
|
1318 |
+
"128164": {
|
1319 |
+
"content": "<|reserved_special_token_156|>",
|
1320 |
+
"lstrip": false,
|
1321 |
+
"normalized": false,
|
1322 |
+
"rstrip": false,
|
1323 |
+
"single_word": false,
|
1324 |
+
"special": true
|
1325 |
+
},
|
1326 |
+
"128165": {
|
1327 |
+
"content": "<|reserved_special_token_157|>",
|
1328 |
+
"lstrip": false,
|
1329 |
+
"normalized": false,
|
1330 |
+
"rstrip": false,
|
1331 |
+
"single_word": false,
|
1332 |
+
"special": true
|
1333 |
+
},
|
1334 |
+
"128166": {
|
1335 |
+
"content": "<|reserved_special_token_158|>",
|
1336 |
+
"lstrip": false,
|
1337 |
+
"normalized": false,
|
1338 |
+
"rstrip": false,
|
1339 |
+
"single_word": false,
|
1340 |
+
"special": true
|
1341 |
+
},
|
1342 |
+
"128167": {
|
1343 |
+
"content": "<|reserved_special_token_159|>",
|
1344 |
+
"lstrip": false,
|
1345 |
+
"normalized": false,
|
1346 |
+
"rstrip": false,
|
1347 |
+
"single_word": false,
|
1348 |
+
"special": true
|
1349 |
+
},
|
1350 |
+
"128168": {
|
1351 |
+
"content": "<|reserved_special_token_160|>",
|
1352 |
+
"lstrip": false,
|
1353 |
+
"normalized": false,
|
1354 |
+
"rstrip": false,
|
1355 |
+
"single_word": false,
|
1356 |
+
"special": true
|
1357 |
+
},
|
1358 |
+
"128169": {
|
1359 |
+
"content": "<|reserved_special_token_161|>",
|
1360 |
+
"lstrip": false,
|
1361 |
+
"normalized": false,
|
1362 |
+
"rstrip": false,
|
1363 |
+
"single_word": false,
|
1364 |
+
"special": true
|
1365 |
+
},
|
1366 |
+
"128170": {
|
1367 |
+
"content": "<|reserved_special_token_162|>",
|
1368 |
+
"lstrip": false,
|
1369 |
+
"normalized": false,
|
1370 |
+
"rstrip": false,
|
1371 |
+
"single_word": false,
|
1372 |
+
"special": true
|
1373 |
+
},
|
1374 |
+
"128171": {
|
1375 |
+
"content": "<|reserved_special_token_163|>",
|
1376 |
+
"lstrip": false,
|
1377 |
+
"normalized": false,
|
1378 |
+
"rstrip": false,
|
1379 |
+
"single_word": false,
|
1380 |
+
"special": true
|
1381 |
+
},
|
1382 |
+
"128172": {
|
1383 |
+
"content": "<|reserved_special_token_164|>",
|
1384 |
+
"lstrip": false,
|
1385 |
+
"normalized": false,
|
1386 |
+
"rstrip": false,
|
1387 |
+
"single_word": false,
|
1388 |
+
"special": true
|
1389 |
+
},
|
1390 |
+
"128173": {
|
1391 |
+
"content": "<|reserved_special_token_165|>",
|
1392 |
+
"lstrip": false,
|
1393 |
+
"normalized": false,
|
1394 |
+
"rstrip": false,
|
1395 |
+
"single_word": false,
|
1396 |
+
"special": true
|
1397 |
+
},
|
1398 |
+
"128174": {
|
1399 |
+
"content": "<|reserved_special_token_166|>",
|
1400 |
+
"lstrip": false,
|
1401 |
+
"normalized": false,
|
1402 |
+
"rstrip": false,
|
1403 |
+
"single_word": false,
|
1404 |
+
"special": true
|
1405 |
+
},
|
1406 |
+
"128175": {
|
1407 |
+
"content": "<|reserved_special_token_167|>",
|
1408 |
+
"lstrip": false,
|
1409 |
+
"normalized": false,
|
1410 |
+
"rstrip": false,
|
1411 |
+
"single_word": false,
|
1412 |
+
"special": true
|
1413 |
+
},
|
1414 |
+
"128176": {
|
1415 |
+
"content": "<|reserved_special_token_168|>",
|
1416 |
+
"lstrip": false,
|
1417 |
+
"normalized": false,
|
1418 |
+
"rstrip": false,
|
1419 |
+
"single_word": false,
|
1420 |
+
"special": true
|
1421 |
+
},
|
1422 |
+
"128177": {
|
1423 |
+
"content": "<|reserved_special_token_169|>",
|
1424 |
+
"lstrip": false,
|
1425 |
+
"normalized": false,
|
1426 |
+
"rstrip": false,
|
1427 |
+
"single_word": false,
|
1428 |
+
"special": true
|
1429 |
+
},
|
1430 |
+
"128178": {
|
1431 |
+
"content": "<|reserved_special_token_170|>",
|
1432 |
+
"lstrip": false,
|
1433 |
+
"normalized": false,
|
1434 |
+
"rstrip": false,
|
1435 |
+
"single_word": false,
|
1436 |
+
"special": true
|
1437 |
+
},
|
1438 |
+
"128179": {
|
1439 |
+
"content": "<|reserved_special_token_171|>",
|
1440 |
+
"lstrip": false,
|
1441 |
+
"normalized": false,
|
1442 |
+
"rstrip": false,
|
1443 |
+
"single_word": false,
|
1444 |
+
"special": true
|
1445 |
+
},
|
1446 |
+
"128180": {
|
1447 |
+
"content": "<|reserved_special_token_172|>",
|
1448 |
+
"lstrip": false,
|
1449 |
+
"normalized": false,
|
1450 |
+
"rstrip": false,
|
1451 |
+
"single_word": false,
|
1452 |
+
"special": true
|
1453 |
+
},
|
1454 |
+
"128181": {
|
1455 |
+
"content": "<|reserved_special_token_173|>",
|
1456 |
+
"lstrip": false,
|
1457 |
+
"normalized": false,
|
1458 |
+
"rstrip": false,
|
1459 |
+
"single_word": false,
|
1460 |
+
"special": true
|
1461 |
+
},
|
1462 |
+
"128182": {
|
1463 |
+
"content": "<|reserved_special_token_174|>",
|
1464 |
+
"lstrip": false,
|
1465 |
+
"normalized": false,
|
1466 |
+
"rstrip": false,
|
1467 |
+
"single_word": false,
|
1468 |
+
"special": true
|
1469 |
+
},
|
1470 |
+
"128183": {
|
1471 |
+
"content": "<|reserved_special_token_175|>",
|
1472 |
+
"lstrip": false,
|
1473 |
+
"normalized": false,
|
1474 |
+
"rstrip": false,
|
1475 |
+
"single_word": false,
|
1476 |
+
"special": true
|
1477 |
+
},
|
1478 |
+
"128184": {
|
1479 |
+
"content": "<|reserved_special_token_176|>",
|
1480 |
+
"lstrip": false,
|
1481 |
+
"normalized": false,
|
1482 |
+
"rstrip": false,
|
1483 |
+
"single_word": false,
|
1484 |
+
"special": true
|
1485 |
+
},
|
1486 |
+
"128185": {
|
1487 |
+
"content": "<|reserved_special_token_177|>",
|
1488 |
+
"lstrip": false,
|
1489 |
+
"normalized": false,
|
1490 |
+
"rstrip": false,
|
1491 |
+
"single_word": false,
|
1492 |
+
"special": true
|
1493 |
+
},
|
1494 |
+
"128186": {
|
1495 |
+
"content": "<|reserved_special_token_178|>",
|
1496 |
+
"lstrip": false,
|
1497 |
+
"normalized": false,
|
1498 |
+
"rstrip": false,
|
1499 |
+
"single_word": false,
|
1500 |
+
"special": true
|
1501 |
+
},
|
1502 |
+
"128187": {
|
1503 |
+
"content": "<|reserved_special_token_179|>",
|
1504 |
+
"lstrip": false,
|
1505 |
+
"normalized": false,
|
1506 |
+
"rstrip": false,
|
1507 |
+
"single_word": false,
|
1508 |
+
"special": true
|
1509 |
+
},
|
1510 |
+
"128188": {
|
1511 |
+
"content": "<|reserved_special_token_180|>",
|
1512 |
+
"lstrip": false,
|
1513 |
+
"normalized": false,
|
1514 |
+
"rstrip": false,
|
1515 |
+
"single_word": false,
|
1516 |
+
"special": true
|
1517 |
+
},
|
1518 |
+
"128189": {
|
1519 |
+
"content": "<|reserved_special_token_181|>",
|
1520 |
+
"lstrip": false,
|
1521 |
+
"normalized": false,
|
1522 |
+
"rstrip": false,
|
1523 |
+
"single_word": false,
|
1524 |
+
"special": true
|
1525 |
+
},
|
1526 |
+
"128190": {
|
1527 |
+
"content": "<|reserved_special_token_182|>",
|
1528 |
+
"lstrip": false,
|
1529 |
+
"normalized": false,
|
1530 |
+
"rstrip": false,
|
1531 |
+
"single_word": false,
|
1532 |
+
"special": true
|
1533 |
+
},
|
1534 |
+
"128191": {
|
1535 |
+
"content": "<|reserved_special_token_183|>",
|
1536 |
+
"lstrip": false,
|
1537 |
+
"normalized": false,
|
1538 |
+
"rstrip": false,
|
1539 |
+
"single_word": false,
|
1540 |
+
"special": true
|
1541 |
+
},
|
1542 |
+
"128192": {
|
1543 |
+
"content": "<|reserved_special_token_184|>",
|
1544 |
+
"lstrip": false,
|
1545 |
+
"normalized": false,
|
1546 |
+
"rstrip": false,
|
1547 |
+
"single_word": false,
|
1548 |
+
"special": true
|
1549 |
+
},
|
1550 |
+
"128193": {
|
1551 |
+
"content": "<|reserved_special_token_185|>",
|
1552 |
+
"lstrip": false,
|
1553 |
+
"normalized": false,
|
1554 |
+
"rstrip": false,
|
1555 |
+
"single_word": false,
|
1556 |
+
"special": true
|
1557 |
+
},
|
1558 |
+
"128194": {
|
1559 |
+
"content": "<|reserved_special_token_186|>",
|
1560 |
+
"lstrip": false,
|
1561 |
+
"normalized": false,
|
1562 |
+
"rstrip": false,
|
1563 |
+
"single_word": false,
|
1564 |
+
"special": true
|
1565 |
+
},
|
1566 |
+
"128195": {
|
1567 |
+
"content": "<|reserved_special_token_187|>",
|
1568 |
+
"lstrip": false,
|
1569 |
+
"normalized": false,
|
1570 |
+
"rstrip": false,
|
1571 |
+
"single_word": false,
|
1572 |
+
"special": true
|
1573 |
+
},
|
1574 |
+
"128196": {
|
1575 |
+
"content": "<|reserved_special_token_188|>",
|
1576 |
+
"lstrip": false,
|
1577 |
+
"normalized": false,
|
1578 |
+
"rstrip": false,
|
1579 |
+
"single_word": false,
|
1580 |
+
"special": true
|
1581 |
+
},
|
1582 |
+
"128197": {
|
1583 |
+
"content": "<|reserved_special_token_189|>",
|
1584 |
+
"lstrip": false,
|
1585 |
+
"normalized": false,
|
1586 |
+
"rstrip": false,
|
1587 |
+
"single_word": false,
|
1588 |
+
"special": true
|
1589 |
+
},
|
1590 |
+
"128198": {
|
1591 |
+
"content": "<|reserved_special_token_190|>",
|
1592 |
+
"lstrip": false,
|
1593 |
+
"normalized": false,
|
1594 |
+
"rstrip": false,
|
1595 |
+
"single_word": false,
|
1596 |
+
"special": true
|
1597 |
+
},
|
1598 |
+
"128199": {
|
1599 |
+
"content": "<|reserved_special_token_191|>",
|
1600 |
+
"lstrip": false,
|
1601 |
+
"normalized": false,
|
1602 |
+
"rstrip": false,
|
1603 |
+
"single_word": false,
|
1604 |
+
"special": true
|
1605 |
+
},
|
1606 |
+
"128200": {
|
1607 |
+
"content": "<|reserved_special_token_192|>",
|
1608 |
+
"lstrip": false,
|
1609 |
+
"normalized": false,
|
1610 |
+
"rstrip": false,
|
1611 |
+
"single_word": false,
|
1612 |
+
"special": true
|
1613 |
+
},
|
1614 |
+
"128201": {
|
1615 |
+
"content": "<|reserved_special_token_193|>",
|
1616 |
+
"lstrip": false,
|
1617 |
+
"normalized": false,
|
1618 |
+
"rstrip": false,
|
1619 |
+
"single_word": false,
|
1620 |
+
"special": true
|
1621 |
+
},
|
1622 |
+
"128202": {
|
1623 |
+
"content": "<|reserved_special_token_194|>",
|
1624 |
+
"lstrip": false,
|
1625 |
+
"normalized": false,
|
1626 |
+
"rstrip": false,
|
1627 |
+
"single_word": false,
|
1628 |
+
"special": true
|
1629 |
+
},
|
1630 |
+
"128203": {
|
1631 |
+
"content": "<|reserved_special_token_195|>",
|
1632 |
+
"lstrip": false,
|
1633 |
+
"normalized": false,
|
1634 |
+
"rstrip": false,
|
1635 |
+
"single_word": false,
|
1636 |
+
"special": true
|
1637 |
+
},
|
1638 |
+
"128204": {
|
1639 |
+
"content": "<|reserved_special_token_196|>",
|
1640 |
+
"lstrip": false,
|
1641 |
+
"normalized": false,
|
1642 |
+
"rstrip": false,
|
1643 |
+
"single_word": false,
|
1644 |
+
"special": true
|
1645 |
+
},
|
1646 |
+
"128205": {
|
1647 |
+
"content": "<|reserved_special_token_197|>",
|
1648 |
+
"lstrip": false,
|
1649 |
+
"normalized": false,
|
1650 |
+
"rstrip": false,
|
1651 |
+
"single_word": false,
|
1652 |
+
"special": true
|
1653 |
+
},
|
1654 |
+
"128206": {
|
1655 |
+
"content": "<|reserved_special_token_198|>",
|
1656 |
+
"lstrip": false,
|
1657 |
+
"normalized": false,
|
1658 |
+
"rstrip": false,
|
1659 |
+
"single_word": false,
|
1660 |
+
"special": true
|
1661 |
+
},
|
1662 |
+
"128207": {
|
1663 |
+
"content": "<|reserved_special_token_199|>",
|
1664 |
+
"lstrip": false,
|
1665 |
+
"normalized": false,
|
1666 |
+
"rstrip": false,
|
1667 |
+
"single_word": false,
|
1668 |
+
"special": true
|
1669 |
+
},
|
1670 |
+
"128208": {
|
1671 |
+
"content": "<|reserved_special_token_200|>",
|
1672 |
+
"lstrip": false,
|
1673 |
+
"normalized": false,
|
1674 |
+
"rstrip": false,
|
1675 |
+
"single_word": false,
|
1676 |
+
"special": true
|
1677 |
+
},
|
1678 |
+
"128209": {
|
1679 |
+
"content": "<|reserved_special_token_201|>",
|
1680 |
+
"lstrip": false,
|
1681 |
+
"normalized": false,
|
1682 |
+
"rstrip": false,
|
1683 |
+
"single_word": false,
|
1684 |
+
"special": true
|
1685 |
+
},
|
1686 |
+
"128210": {
|
1687 |
+
"content": "<|reserved_special_token_202|>",
|
1688 |
+
"lstrip": false,
|
1689 |
+
"normalized": false,
|
1690 |
+
"rstrip": false,
|
1691 |
+
"single_word": false,
|
1692 |
+
"special": true
|
1693 |
+
},
|
1694 |
+
"128211": {
|
1695 |
+
"content": "<|reserved_special_token_203|>",
|
1696 |
+
"lstrip": false,
|
1697 |
+
"normalized": false,
|
1698 |
+
"rstrip": false,
|
1699 |
+
"single_word": false,
|
1700 |
+
"special": true
|
1701 |
+
},
|
1702 |
+
"128212": {
|
1703 |
+
"content": "<|reserved_special_token_204|>",
|
1704 |
+
"lstrip": false,
|
1705 |
+
"normalized": false,
|
1706 |
+
"rstrip": false,
|
1707 |
+
"single_word": false,
|
1708 |
+
"special": true
|
1709 |
+
},
|
1710 |
+
"128213": {
|
1711 |
+
"content": "<|reserved_special_token_205|>",
|
1712 |
+
"lstrip": false,
|
1713 |
+
"normalized": false,
|
1714 |
+
"rstrip": false,
|
1715 |
+
"single_word": false,
|
1716 |
+
"special": true
|
1717 |
+
},
|
1718 |
+
"128214": {
|
1719 |
+
"content": "<|reserved_special_token_206|>",
|
1720 |
+
"lstrip": false,
|
1721 |
+
"normalized": false,
|
1722 |
+
"rstrip": false,
|
1723 |
+
"single_word": false,
|
1724 |
+
"special": true
|
1725 |
+
},
|
1726 |
+
"128215": {
|
1727 |
+
"content": "<|reserved_special_token_207|>",
|
1728 |
+
"lstrip": false,
|
1729 |
+
"normalized": false,
|
1730 |
+
"rstrip": false,
|
1731 |
+
"single_word": false,
|
1732 |
+
"special": true
|
1733 |
+
},
|
1734 |
+
"128216": {
|
1735 |
+
"content": "<|reserved_special_token_208|>",
|
1736 |
+
"lstrip": false,
|
1737 |
+
"normalized": false,
|
1738 |
+
"rstrip": false,
|
1739 |
+
"single_word": false,
|
1740 |
+
"special": true
|
1741 |
+
},
|
1742 |
+
"128217": {
|
1743 |
+
"content": "<|reserved_special_token_209|>",
|
1744 |
+
"lstrip": false,
|
1745 |
+
"normalized": false,
|
1746 |
+
"rstrip": false,
|
1747 |
+
"single_word": false,
|
1748 |
+
"special": true
|
1749 |
+
},
|
1750 |
+
"128218": {
|
1751 |
+
"content": "<|reserved_special_token_210|>",
|
1752 |
+
"lstrip": false,
|
1753 |
+
"normalized": false,
|
1754 |
+
"rstrip": false,
|
1755 |
+
"single_word": false,
|
1756 |
+
"special": true
|
1757 |
+
},
|
1758 |
+
"128219": {
|
1759 |
+
"content": "<|reserved_special_token_211|>",
|
1760 |
+
"lstrip": false,
|
1761 |
+
"normalized": false,
|
1762 |
+
"rstrip": false,
|
1763 |
+
"single_word": false,
|
1764 |
+
"special": true
|
1765 |
+
},
|
1766 |
+
"128220": {
|
1767 |
+
"content": "<|reserved_special_token_212|>",
|
1768 |
+
"lstrip": false,
|
1769 |
+
"normalized": false,
|
1770 |
+
"rstrip": false,
|
1771 |
+
"single_word": false,
|
1772 |
+
"special": true
|
1773 |
+
},
|
1774 |
+
"128221": {
|
1775 |
+
"content": "<|reserved_special_token_213|>",
|
1776 |
+
"lstrip": false,
|
1777 |
+
"normalized": false,
|
1778 |
+
"rstrip": false,
|
1779 |
+
"single_word": false,
|
1780 |
+
"special": true
|
1781 |
+
},
|
1782 |
+
"128222": {
|
1783 |
+
"content": "<|reserved_special_token_214|>",
|
1784 |
+
"lstrip": false,
|
1785 |
+
"normalized": false,
|
1786 |
+
"rstrip": false,
|
1787 |
+
"single_word": false,
|
1788 |
+
"special": true
|
1789 |
+
},
|
1790 |
+
"128223": {
|
1791 |
+
"content": "<|reserved_special_token_215|>",
|
1792 |
+
"lstrip": false,
|
1793 |
+
"normalized": false,
|
1794 |
+
"rstrip": false,
|
1795 |
+
"single_word": false,
|
1796 |
+
"special": true
|
1797 |
+
},
|
1798 |
+
"128224": {
|
1799 |
+
"content": "<|reserved_special_token_216|>",
|
1800 |
+
"lstrip": false,
|
1801 |
+
"normalized": false,
|
1802 |
+
"rstrip": false,
|
1803 |
+
"single_word": false,
|
1804 |
+
"special": true
|
1805 |
+
},
|
1806 |
+
"128225": {
|
1807 |
+
"content": "<|reserved_special_token_217|>",
|
1808 |
+
"lstrip": false,
|
1809 |
+
"normalized": false,
|
1810 |
+
"rstrip": false,
|
1811 |
+
"single_word": false,
|
1812 |
+
"special": true
|
1813 |
+
},
|
1814 |
+
"128226": {
|
1815 |
+
"content": "<|reserved_special_token_218|>",
|
1816 |
+
"lstrip": false,
|
1817 |
+
"normalized": false,
|
1818 |
+
"rstrip": false,
|
1819 |
+
"single_word": false,
|
1820 |
+
"special": true
|
1821 |
+
},
|
1822 |
+
"128227": {
|
1823 |
+
"content": "<|reserved_special_token_219|>",
|
1824 |
+
"lstrip": false,
|
1825 |
+
"normalized": false,
|
1826 |
+
"rstrip": false,
|
1827 |
+
"single_word": false,
|
1828 |
+
"special": true
|
1829 |
+
},
|
1830 |
+
"128228": {
|
1831 |
+
"content": "<|reserved_special_token_220|>",
|
1832 |
+
"lstrip": false,
|
1833 |
+
"normalized": false,
|
1834 |
+
"rstrip": false,
|
1835 |
+
"single_word": false,
|
1836 |
+
"special": true
|
1837 |
+
},
|
1838 |
+
"128229": {
|
1839 |
+
"content": "<|reserved_special_token_221|>",
|
1840 |
+
"lstrip": false,
|
1841 |
+
"normalized": false,
|
1842 |
+
"rstrip": false,
|
1843 |
+
"single_word": false,
|
1844 |
+
"special": true
|
1845 |
+
},
|
1846 |
+
"128230": {
|
1847 |
+
"content": "<|reserved_special_token_222|>",
|
1848 |
+
"lstrip": false,
|
1849 |
+
"normalized": false,
|
1850 |
+
"rstrip": false,
|
1851 |
+
"single_word": false,
|
1852 |
+
"special": true
|
1853 |
+
},
|
1854 |
+
"128231": {
|
1855 |
+
"content": "<|reserved_special_token_223|>",
|
1856 |
+
"lstrip": false,
|
1857 |
+
"normalized": false,
|
1858 |
+
"rstrip": false,
|
1859 |
+
"single_word": false,
|
1860 |
+
"special": true
|
1861 |
+
},
|
1862 |
+
"128232": {
|
1863 |
+
"content": "<|reserved_special_token_224|>",
|
1864 |
+
"lstrip": false,
|
1865 |
+
"normalized": false,
|
1866 |
+
"rstrip": false,
|
1867 |
+
"single_word": false,
|
1868 |
+
"special": true
|
1869 |
+
},
|
1870 |
+
"128233": {
|
1871 |
+
"content": "<|reserved_special_token_225|>",
|
1872 |
+
"lstrip": false,
|
1873 |
+
"normalized": false,
|
1874 |
+
"rstrip": false,
|
1875 |
+
"single_word": false,
|
1876 |
+
"special": true
|
1877 |
+
},
|
1878 |
+
"128234": {
|
1879 |
+
"content": "<|reserved_special_token_226|>",
|
1880 |
+
"lstrip": false,
|
1881 |
+
"normalized": false,
|
1882 |
+
"rstrip": false,
|
1883 |
+
"single_word": false,
|
1884 |
+
"special": true
|
1885 |
+
},
|
1886 |
+
"128235": {
|
1887 |
+
"content": "<|reserved_special_token_227|>",
|
1888 |
+
"lstrip": false,
|
1889 |
+
"normalized": false,
|
1890 |
+
"rstrip": false,
|
1891 |
+
"single_word": false,
|
1892 |
+
"special": true
|
1893 |
+
},
|
1894 |
+
"128236": {
|
1895 |
+
"content": "<|reserved_special_token_228|>",
|
1896 |
+
"lstrip": false,
|
1897 |
+
"normalized": false,
|
1898 |
+
"rstrip": false,
|
1899 |
+
"single_word": false,
|
1900 |
+
"special": true
|
1901 |
+
},
|
1902 |
+
"128237": {
|
1903 |
+
"content": "<|reserved_special_token_229|>",
|
1904 |
+
"lstrip": false,
|
1905 |
+
"normalized": false,
|
1906 |
+
"rstrip": false,
|
1907 |
+
"single_word": false,
|
1908 |
+
"special": true
|
1909 |
+
},
|
1910 |
+
"128238": {
|
1911 |
+
"content": "<|reserved_special_token_230|>",
|
1912 |
+
"lstrip": false,
|
1913 |
+
"normalized": false,
|
1914 |
+
"rstrip": false,
|
1915 |
+
"single_word": false,
|
1916 |
+
"special": true
|
1917 |
+
},
|
1918 |
+
"128239": {
|
1919 |
+
"content": "<|reserved_special_token_231|>",
|
1920 |
+
"lstrip": false,
|
1921 |
+
"normalized": false,
|
1922 |
+
"rstrip": false,
|
1923 |
+
"single_word": false,
|
1924 |
+
"special": true
|
1925 |
+
},
|
1926 |
+
"128240": {
|
1927 |
+
"content": "<|reserved_special_token_232|>",
|
1928 |
+
"lstrip": false,
|
1929 |
+
"normalized": false,
|
1930 |
+
"rstrip": false,
|
1931 |
+
"single_word": false,
|
1932 |
+
"special": true
|
1933 |
+
},
|
1934 |
+
"128241": {
|
1935 |
+
"content": "<|reserved_special_token_233|>",
|
1936 |
+
"lstrip": false,
|
1937 |
+
"normalized": false,
|
1938 |
+
"rstrip": false,
|
1939 |
+
"single_word": false,
|
1940 |
+
"special": true
|
1941 |
+
},
|
1942 |
+
"128242": {
|
1943 |
+
"content": "<|reserved_special_token_234|>",
|
1944 |
+
"lstrip": false,
|
1945 |
+
"normalized": false,
|
1946 |
+
"rstrip": false,
|
1947 |
+
"single_word": false,
|
1948 |
+
"special": true
|
1949 |
+
},
|
1950 |
+
"128243": {
|
1951 |
+
"content": "<|reserved_special_token_235|>",
|
1952 |
+
"lstrip": false,
|
1953 |
+
"normalized": false,
|
1954 |
+
"rstrip": false,
|
1955 |
+
"single_word": false,
|
1956 |
+
"special": true
|
1957 |
+
},
|
1958 |
+
"128244": {
|
1959 |
+
"content": "<|reserved_special_token_236|>",
|
1960 |
+
"lstrip": false,
|
1961 |
+
"normalized": false,
|
1962 |
+
"rstrip": false,
|
1963 |
+
"single_word": false,
|
1964 |
+
"special": true
|
1965 |
+
},
|
1966 |
+
"128245": {
|
1967 |
+
"content": "<|reserved_special_token_237|>",
|
1968 |
+
"lstrip": false,
|
1969 |
+
"normalized": false,
|
1970 |
+
"rstrip": false,
|
1971 |
+
"single_word": false,
|
1972 |
+
"special": true
|
1973 |
+
},
|
1974 |
+
"128246": {
|
1975 |
+
"content": "<|reserved_special_token_238|>",
|
1976 |
+
"lstrip": false,
|
1977 |
+
"normalized": false,
|
1978 |
+
"rstrip": false,
|
1979 |
+
"single_word": false,
|
1980 |
+
"special": true
|
1981 |
+
},
|
1982 |
+
"128247": {
|
1983 |
+
"content": "<|reserved_special_token_239|>",
|
1984 |
+
"lstrip": false,
|
1985 |
+
"normalized": false,
|
1986 |
+
"rstrip": false,
|
1987 |
+
"single_word": false,
|
1988 |
+
"special": true
|
1989 |
+
},
|
1990 |
+
"128248": {
|
1991 |
+
"content": "<|reserved_special_token_240|>",
|
1992 |
+
"lstrip": false,
|
1993 |
+
"normalized": false,
|
1994 |
+
"rstrip": false,
|
1995 |
+
"single_word": false,
|
1996 |
+
"special": true
|
1997 |
+
},
|
1998 |
+
"128249": {
|
1999 |
+
"content": "<|reserved_special_token_241|>",
|
2000 |
+
"lstrip": false,
|
2001 |
+
"normalized": false,
|
2002 |
+
"rstrip": false,
|
2003 |
+
"single_word": false,
|
2004 |
+
"special": true
|
2005 |
+
},
|
2006 |
+
"128250": {
|
2007 |
+
"content": "<|reserved_special_token_242|>",
|
2008 |
+
"lstrip": false,
|
2009 |
+
"normalized": false,
|
2010 |
+
"rstrip": false,
|
2011 |
+
"single_word": false,
|
2012 |
+
"special": true
|
2013 |
+
},
|
2014 |
+
"128251": {
|
2015 |
+
"content": "<|reserved_special_token_243|>",
|
2016 |
+
"lstrip": false,
|
2017 |
+
"normalized": false,
|
2018 |
+
"rstrip": false,
|
2019 |
+
"single_word": false,
|
2020 |
+
"special": true
|
2021 |
+
},
|
2022 |
+
"128252": {
|
2023 |
+
"content": "<|reserved_special_token_244|>",
|
2024 |
+
"lstrip": false,
|
2025 |
+
"normalized": false,
|
2026 |
+
"rstrip": false,
|
2027 |
+
"single_word": false,
|
2028 |
+
"special": true
|
2029 |
+
},
|
2030 |
+
"128253": {
|
2031 |
+
"content": "<|reserved_special_token_245|>",
|
2032 |
+
"lstrip": false,
|
2033 |
+
"normalized": false,
|
2034 |
+
"rstrip": false,
|
2035 |
+
"single_word": false,
|
2036 |
+
"special": true
|
2037 |
+
},
|
2038 |
+
"128254": {
|
2039 |
+
"content": "<|reserved_special_token_246|>",
|
2040 |
+
"lstrip": false,
|
2041 |
+
"normalized": false,
|
2042 |
+
"rstrip": false,
|
2043 |
+
"single_word": false,
|
2044 |
+
"special": true
|
2045 |
+
},
|
2046 |
+
"128255": {
|
2047 |
+
"content": "<|reserved_special_token_247|>",
|
2048 |
+
"lstrip": false,
|
2049 |
+
"normalized": false,
|
2050 |
+
"rstrip": false,
|
2051 |
+
"single_word": false,
|
2052 |
+
"special": true
|
2053 |
+
}
|
2054 |
+
},
|
2055 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
2056 |
+
"clean_up_tokenization_spaces": false,
|
2057 |
+
"eos_token": "<|end▁of▁sentence|>",
|
2058 |
+
"extra_special_tokens": {},
|
2059 |
+
"legacy": true,
|
2060 |
+
"model_max_length": 16384,
|
2061 |
+
"pad_token": "<|end▁of▁sentence|>",
|
2062 |
+
"padding_side": "right",
|
2063 |
+
"sp_model_kwargs": {},
|
2064 |
+
"split_special_tokens": false,
|
2065 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
2066 |
+
"unk_token": null,
|
2067 |
+
"use_default_system_prompt": false
|
2068 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"total_flos": 1.3861725429517517e+17,
|
4 |
+
"train_loss": 0.0,
|
5 |
+
"train_runtime": 0.8982,
|
6 |
+
"train_samples_per_second": 15978.88,
|
7 |
+
"train_steps_per_second": 1998.334
|
8 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"current_steps": 1795, "total_steps": 1795, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
@@ -0,0 +1,2556 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": null,
|
3 |
+
"best_metric": null,
|
4 |
+
"best_model_checkpoint": null,
|
5 |
+
"epoch": 1.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 1795,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 0.0027868738242876052,
|
14 |
+
"grad_norm": 1.3125083446502686,
|
15 |
+
"learning_rate": 2.2222222222222225e-06,
|
16 |
+
"loss": 2.2127,
|
17 |
+
"step": 5
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.0055737476485752105,
|
21 |
+
"grad_norm": 1.2902835607528687,
|
22 |
+
"learning_rate": 5e-06,
|
23 |
+
"loss": 2.1685,
|
24 |
+
"step": 10
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.008360621472862817,
|
28 |
+
"grad_norm": 1.260772466659546,
|
29 |
+
"learning_rate": 7.777777777777777e-06,
|
30 |
+
"loss": 2.1734,
|
31 |
+
"step": 15
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.011147495297150421,
|
35 |
+
"grad_norm": 1.2492824792861938,
|
36 |
+
"learning_rate": 1.0555555555555555e-05,
|
37 |
+
"loss": 2.1881,
|
38 |
+
"step": 20
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.013934369121438027,
|
42 |
+
"grad_norm": 1.8405438661575317,
|
43 |
+
"learning_rate": 1.3333333333333333e-05,
|
44 |
+
"loss": 2.1732,
|
45 |
+
"step": 25
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.016721242945725634,
|
49 |
+
"grad_norm": 2.053272247314453,
|
50 |
+
"learning_rate": 1.6111111111111115e-05,
|
51 |
+
"loss": 2.1535,
|
52 |
+
"step": 30
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.019508116770013236,
|
56 |
+
"grad_norm": 1.6805298328399658,
|
57 |
+
"learning_rate": 1.888888888888889e-05,
|
58 |
+
"loss": 1.9838,
|
59 |
+
"step": 35
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.022294990594300842,
|
63 |
+
"grad_norm": 1.5838550329208374,
|
64 |
+
"learning_rate": 2.1666666666666667e-05,
|
65 |
+
"loss": 1.7728,
|
66 |
+
"step": 40
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.025081864418588447,
|
70 |
+
"grad_norm": 1.1088097095489502,
|
71 |
+
"learning_rate": 2.4444444444444445e-05,
|
72 |
+
"loss": 1.7897,
|
73 |
+
"step": 45
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.027868738242876053,
|
77 |
+
"grad_norm": 1.060654878616333,
|
78 |
+
"learning_rate": 2.7222222222222223e-05,
|
79 |
+
"loss": 1.6669,
|
80 |
+
"step": 50
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.03065561206716366,
|
84 |
+
"grad_norm": 0.9146080017089844,
|
85 |
+
"learning_rate": 3e-05,
|
86 |
+
"loss": 1.5346,
|
87 |
+
"step": 55
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.03344248589145127,
|
91 |
+
"grad_norm": 0.811827540397644,
|
92 |
+
"learning_rate": 3.277777777777778e-05,
|
93 |
+
"loss": 1.6357,
|
94 |
+
"step": 60
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.03622935971573887,
|
98 |
+
"grad_norm": 1.025479793548584,
|
99 |
+
"learning_rate": 3.555555555555556e-05,
|
100 |
+
"loss": 1.5798,
|
101 |
+
"step": 65
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.03901623354002647,
|
105 |
+
"grad_norm": 0.8861313462257385,
|
106 |
+
"learning_rate": 3.8333333333333334e-05,
|
107 |
+
"loss": 1.4825,
|
108 |
+
"step": 70
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.04180310736431408,
|
112 |
+
"grad_norm": 1.0417464971542358,
|
113 |
+
"learning_rate": 4.111111111111111e-05,
|
114 |
+
"loss": 1.5584,
|
115 |
+
"step": 75
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.044589981188601684,
|
119 |
+
"grad_norm": 0.9840788245201111,
|
120 |
+
"learning_rate": 4.388888888888889e-05,
|
121 |
+
"loss": 1.4355,
|
122 |
+
"step": 80
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.04737685501288929,
|
126 |
+
"grad_norm": 0.9761689901351929,
|
127 |
+
"learning_rate": 4.666666666666667e-05,
|
128 |
+
"loss": 1.5785,
|
129 |
+
"step": 85
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.050163728837176895,
|
133 |
+
"grad_norm": 1.0217355489730835,
|
134 |
+
"learning_rate": 4.9444444444444446e-05,
|
135 |
+
"loss": 1.477,
|
136 |
+
"step": 90
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.0529506026614645,
|
140 |
+
"grad_norm": 1.0723602771759033,
|
141 |
+
"learning_rate": 5.222222222222223e-05,
|
142 |
+
"loss": 1.4874,
|
143 |
+
"step": 95
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.055737476485752106,
|
147 |
+
"grad_norm": 1.0415840148925781,
|
148 |
+
"learning_rate": 5.500000000000001e-05,
|
149 |
+
"loss": 1.3867,
|
150 |
+
"step": 100
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.05852435031003971,
|
154 |
+
"grad_norm": 0.9482999444007874,
|
155 |
+
"learning_rate": 5.7777777777777776e-05,
|
156 |
+
"loss": 1.4529,
|
157 |
+
"step": 105
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.06131122413432732,
|
161 |
+
"grad_norm": 1.2104490995407104,
|
162 |
+
"learning_rate": 6.055555555555555e-05,
|
163 |
+
"loss": 1.5199,
|
164 |
+
"step": 110
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.06409809795861493,
|
168 |
+
"grad_norm": 1.095499873161316,
|
169 |
+
"learning_rate": 6.333333333333333e-05,
|
170 |
+
"loss": 1.4173,
|
171 |
+
"step": 115
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.06688497178290254,
|
175 |
+
"grad_norm": 1.0751917362213135,
|
176 |
+
"learning_rate": 6.611111111111111e-05,
|
177 |
+
"loss": 1.4632,
|
178 |
+
"step": 120
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.06967184560719013,
|
182 |
+
"grad_norm": 1.1421129703521729,
|
183 |
+
"learning_rate": 6.88888888888889e-05,
|
184 |
+
"loss": 1.4691,
|
185 |
+
"step": 125
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.07245871943147773,
|
189 |
+
"grad_norm": 1.0927807092666626,
|
190 |
+
"learning_rate": 7.166666666666667e-05,
|
191 |
+
"loss": 1.4509,
|
192 |
+
"step": 130
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.07524559325576534,
|
196 |
+
"grad_norm": 1.067568302154541,
|
197 |
+
"learning_rate": 7.444444444444444e-05,
|
198 |
+
"loss": 1.4235,
|
199 |
+
"step": 135
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.07803246708005294,
|
203 |
+
"grad_norm": 1.159364104270935,
|
204 |
+
"learning_rate": 7.722222222222223e-05,
|
205 |
+
"loss": 1.4362,
|
206 |
+
"step": 140
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.08081934090434055,
|
210 |
+
"grad_norm": 1.0486923456192017,
|
211 |
+
"learning_rate": 8e-05,
|
212 |
+
"loss": 1.503,
|
213 |
+
"step": 145
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.08360621472862816,
|
217 |
+
"grad_norm": 1.1524556875228882,
|
218 |
+
"learning_rate": 8.277777777777778e-05,
|
219 |
+
"loss": 1.4556,
|
220 |
+
"step": 150
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.08639308855291576,
|
224 |
+
"grad_norm": 1.0299068689346313,
|
225 |
+
"learning_rate": 8.555555555555556e-05,
|
226 |
+
"loss": 1.3988,
|
227 |
+
"step": 155
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.08917996237720337,
|
231 |
+
"grad_norm": 1.0863871574401855,
|
232 |
+
"learning_rate": 8.833333333333333e-05,
|
233 |
+
"loss": 1.37,
|
234 |
+
"step": 160
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.09196683620149097,
|
238 |
+
"grad_norm": 1.1330057382583618,
|
239 |
+
"learning_rate": 9.111111111111112e-05,
|
240 |
+
"loss": 1.3879,
|
241 |
+
"step": 165
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.09475371002577858,
|
245 |
+
"grad_norm": 1.0953528881072998,
|
246 |
+
"learning_rate": 9.388888888888889e-05,
|
247 |
+
"loss": 1.415,
|
248 |
+
"step": 170
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.09754058385006618,
|
252 |
+
"grad_norm": 1.0204545259475708,
|
253 |
+
"learning_rate": 9.666666666666667e-05,
|
254 |
+
"loss": 1.4199,
|
255 |
+
"step": 175
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.10032745767435379,
|
259 |
+
"grad_norm": 1.0416138172149658,
|
260 |
+
"learning_rate": 9.944444444444446e-05,
|
261 |
+
"loss": 1.3911,
|
262 |
+
"step": 180
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.1031143314986414,
|
266 |
+
"grad_norm": 1.0255354642868042,
|
267 |
+
"learning_rate": 9.999848639521432e-05,
|
268 |
+
"loss": 1.382,
|
269 |
+
"step": 185
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.105901205322929,
|
273 |
+
"grad_norm": 1.0507235527038574,
|
274 |
+
"learning_rate": 9.999233753283091e-05,
|
275 |
+
"loss": 1.3531,
|
276 |
+
"step": 190
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.1086880791472166,
|
280 |
+
"grad_norm": 1.1468594074249268,
|
281 |
+
"learning_rate": 9.998145939378577e-05,
|
282 |
+
"loss": 1.3873,
|
283 |
+
"step": 195
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.11147495297150421,
|
287 |
+
"grad_norm": 1.1430379152297974,
|
288 |
+
"learning_rate": 9.996585300715116e-05,
|
289 |
+
"loss": 1.4215,
|
290 |
+
"step": 200
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.11426182679579182,
|
294 |
+
"grad_norm": 1.029249668121338,
|
295 |
+
"learning_rate": 9.994551984929175e-05,
|
296 |
+
"loss": 1.3678,
|
297 |
+
"step": 205
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.11704870062007942,
|
301 |
+
"grad_norm": 0.9233781099319458,
|
302 |
+
"learning_rate": 9.992046184372492e-05,
|
303 |
+
"loss": 1.403,
|
304 |
+
"step": 210
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.11983557444436703,
|
308 |
+
"grad_norm": 0.9915686845779419,
|
309 |
+
"learning_rate": 9.989068136093873e-05,
|
310 |
+
"loss": 1.3518,
|
311 |
+
"step": 215
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.12262244826865464,
|
315 |
+
"grad_norm": 0.9875094294548035,
|
316 |
+
"learning_rate": 9.985618121816779e-05,
|
317 |
+
"loss": 1.4272,
|
318 |
+
"step": 220
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.12540932209294225,
|
322 |
+
"grad_norm": 0.9711189866065979,
|
323 |
+
"learning_rate": 9.981696467912664e-05,
|
324 |
+
"loss": 1.3453,
|
325 |
+
"step": 225
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.12819619591722986,
|
329 |
+
"grad_norm": 1.0352520942687988,
|
330 |
+
"learning_rate": 9.97730354537011e-05,
|
331 |
+
"loss": 1.3668,
|
332 |
+
"step": 230
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.13098306974151747,
|
336 |
+
"grad_norm": 0.957478940486908,
|
337 |
+
"learning_rate": 9.972439769759722e-05,
|
338 |
+
"loss": 1.3027,
|
339 |
+
"step": 235
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.13376994356580507,
|
343 |
+
"grad_norm": 1.0086779594421387,
|
344 |
+
"learning_rate": 9.967105601194823e-05,
|
345 |
+
"loss": 1.4556,
|
346 |
+
"step": 240
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.13655681739009268,
|
350 |
+
"grad_norm": 0.9436930418014526,
|
351 |
+
"learning_rate": 9.961301544287922e-05,
|
352 |
+
"loss": 1.3322,
|
353 |
+
"step": 245
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.13934369121438026,
|
357 |
+
"grad_norm": 1.000581979751587,
|
358 |
+
"learning_rate": 9.955028148102979e-05,
|
359 |
+
"loss": 1.303,
|
360 |
+
"step": 250
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.14213056503866786,
|
364 |
+
"grad_norm": 0.9896969795227051,
|
365 |
+
"learning_rate": 9.948286006103466e-05,
|
366 |
+
"loss": 1.4694,
|
367 |
+
"step": 255
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.14491743886295547,
|
371 |
+
"grad_norm": 1.0205310583114624,
|
372 |
+
"learning_rate": 9.941075756096226e-05,
|
373 |
+
"loss": 1.36,
|
374 |
+
"step": 260
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.14770431268724307,
|
378 |
+
"grad_norm": 1.0231329202651978,
|
379 |
+
"learning_rate": 9.933398080171123e-05,
|
380 |
+
"loss": 1.3808,
|
381 |
+
"step": 265
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.15049118651153068,
|
385 |
+
"grad_norm": 0.9146262407302856,
|
386 |
+
"learning_rate": 9.925253704636543e-05,
|
387 |
+
"loss": 1.3177,
|
388 |
+
"step": 270
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.15327806033581828,
|
392 |
+
"grad_norm": 0.9757639765739441,
|
393 |
+
"learning_rate": 9.916643399950656e-05,
|
394 |
+
"loss": 1.3462,
|
395 |
+
"step": 275
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.1560649341601059,
|
399 |
+
"grad_norm": 0.9955347180366516,
|
400 |
+
"learning_rate": 9.907567980648549e-05,
|
401 |
+
"loss": 1.3365,
|
402 |
+
"step": 280
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.1588518079843935,
|
406 |
+
"grad_norm": 0.9526458978652954,
|
407 |
+
"learning_rate": 9.898028305265169e-05,
|
408 |
+
"loss": 1.4223,
|
409 |
+
"step": 285
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.1616386818086811,
|
413 |
+
"grad_norm": 0.8748807907104492,
|
414 |
+
"learning_rate": 9.888025276254096e-05,
|
415 |
+
"loss": 1.3659,
|
416 |
+
"step": 290
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.1644255556329687,
|
420 |
+
"grad_norm": 0.9113283157348633,
|
421 |
+
"learning_rate": 9.877559839902184e-05,
|
422 |
+
"loss": 1.3677,
|
423 |
+
"step": 295
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.1672124294572563,
|
427 |
+
"grad_norm": 0.9735001921653748,
|
428 |
+
"learning_rate": 9.86663298624003e-05,
|
429 |
+
"loss": 1.3083,
|
430 |
+
"step": 300
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.16999930328154392,
|
434 |
+
"grad_norm": 0.9326124787330627,
|
435 |
+
"learning_rate": 9.855245748948326e-05,
|
436 |
+
"loss": 1.3757,
|
437 |
+
"step": 305
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.17278617710583152,
|
441 |
+
"grad_norm": 0.8787973523139954,
|
442 |
+
"learning_rate": 9.843399205260068e-05,
|
443 |
+
"loss": 1.36,
|
444 |
+
"step": 310
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.17557305093011913,
|
448 |
+
"grad_norm": 1.017393708229065,
|
449 |
+
"learning_rate": 9.831094475858652e-05,
|
450 |
+
"loss": 1.3754,
|
451 |
+
"step": 315
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.17835992475440673,
|
455 |
+
"grad_norm": 0.8852056264877319,
|
456 |
+
"learning_rate": 9.818332724771857e-05,
|
457 |
+
"loss": 1.4008,
|
458 |
+
"step": 320
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.18114679857869434,
|
462 |
+
"grad_norm": 0.9435309171676636,
|
463 |
+
"learning_rate": 9.805115159261726e-05,
|
464 |
+
"loss": 1.3145,
|
465 |
+
"step": 325
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.18393367240298195,
|
469 |
+
"grad_norm": 0.9178583025932312,
|
470 |
+
"learning_rate": 9.791443029710361e-05,
|
471 |
+
"loss": 1.3052,
|
472 |
+
"step": 330
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.18672054622726955,
|
476 |
+
"grad_norm": 0.9663990139961243,
|
477 |
+
"learning_rate": 9.777317629501636e-05,
|
478 |
+
"loss": 1.3237,
|
479 |
+
"step": 335
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.18950742005155716,
|
483 |
+
"grad_norm": 0.8486679792404175,
|
484 |
+
"learning_rate": 9.762740294898846e-05,
|
485 |
+
"loss": 1.2913,
|
486 |
+
"step": 340
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.19229429387584476,
|
490 |
+
"grad_norm": 0.960027277469635,
|
491 |
+
"learning_rate": 9.747712404918286e-05,
|
492 |
+
"loss": 1.2583,
|
493 |
+
"step": 345
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.19508116770013237,
|
497 |
+
"grad_norm": 1.0241199731826782,
|
498 |
+
"learning_rate": 9.732235381198813e-05,
|
499 |
+
"loss": 1.3535,
|
500 |
+
"step": 350
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.19786804152441997,
|
504 |
+
"grad_norm": 0.8933882713317871,
|
505 |
+
"learning_rate": 9.716310687867342e-05,
|
506 |
+
"loss": 1.2532,
|
507 |
+
"step": 355
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.20065491534870758,
|
511 |
+
"grad_norm": 0.917148232460022,
|
512 |
+
"learning_rate": 9.699939831400351e-05,
|
513 |
+
"loss": 1.4276,
|
514 |
+
"step": 360
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.20344178917299519,
|
518 |
+
"grad_norm": 0.9412631392478943,
|
519 |
+
"learning_rate": 9.683124360481364e-05,
|
520 |
+
"loss": 1.3184,
|
521 |
+
"step": 365
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.2062286629972828,
|
525 |
+
"grad_norm": 0.9783531427383423,
|
526 |
+
"learning_rate": 9.665865865854445e-05,
|
527 |
+
"loss": 1.3137,
|
528 |
+
"step": 370
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.2090155368215704,
|
532 |
+
"grad_norm": 0.933350682258606,
|
533 |
+
"learning_rate": 9.648165980173712e-05,
|
534 |
+
"loss": 1.3405,
|
535 |
+
"step": 375
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.211802410645858,
|
539 |
+
"grad_norm": 0.9554056525230408,
|
540 |
+
"learning_rate": 9.630026377848892e-05,
|
541 |
+
"loss": 1.3246,
|
542 |
+
"step": 380
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.2145892844701456,
|
546 |
+
"grad_norm": 0.8970703482627869,
|
547 |
+
"learning_rate": 9.611448774886924e-05,
|
548 |
+
"loss": 1.325,
|
549 |
+
"step": 385
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.2173761582944332,
|
553 |
+
"grad_norm": 0.9755475521087646,
|
554 |
+
"learning_rate": 9.592434928729616e-05,
|
555 |
+
"loss": 1.3922,
|
556 |
+
"step": 390
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.22016303211872082,
|
560 |
+
"grad_norm": 0.9652612805366516,
|
561 |
+
"learning_rate": 9.572986638087396e-05,
|
562 |
+
"loss": 1.3513,
|
563 |
+
"step": 395
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.22294990594300843,
|
567 |
+
"grad_norm": 0.9211638569831848,
|
568 |
+
"learning_rate": 9.553105742769154e-05,
|
569 |
+
"loss": 1.3104,
|
570 |
+
"step": 400
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.22573677976729603,
|
574 |
+
"grad_norm": 0.9684194326400757,
|
575 |
+
"learning_rate": 9.532794123508197e-05,
|
576 |
+
"loss": 1.23,
|
577 |
+
"step": 405
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.22852365359158364,
|
581 |
+
"grad_norm": 0.9077541828155518,
|
582 |
+
"learning_rate": 9.512053701784329e-05,
|
583 |
+
"loss": 1.3236,
|
584 |
+
"step": 410
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.23131052741587124,
|
588 |
+
"grad_norm": 0.9119937419891357,
|
589 |
+
"learning_rate": 9.490886439642081e-05,
|
590 |
+
"loss": 1.3159,
|
591 |
+
"step": 415
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.23409740124015885,
|
595 |
+
"grad_norm": 0.9030479192733765,
|
596 |
+
"learning_rate": 9.469294339505098e-05,
|
597 |
+
"loss": 1.3789,
|
598 |
+
"step": 420
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.23688427506444645,
|
602 |
+
"grad_norm": 0.9020025134086609,
|
603 |
+
"learning_rate": 9.447279443986716e-05,
|
604 |
+
"loss": 1.2921,
|
605 |
+
"step": 425
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.23967114888873406,
|
609 |
+
"grad_norm": 0.980591356754303,
|
610 |
+
"learning_rate": 9.424843835696724e-05,
|
611 |
+
"loss": 1.3361,
|
612 |
+
"step": 430
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.24245802271302166,
|
616 |
+
"grad_norm": 1.0082863569259644,
|
617 |
+
"learning_rate": 9.401989637044355e-05,
|
618 |
+
"loss": 1.2721,
|
619 |
+
"step": 435
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.24524489653730927,
|
623 |
+
"grad_norm": 0.9218441843986511,
|
624 |
+
"learning_rate": 9.3787190100375e-05,
|
625 |
+
"loss": 1.3214,
|
626 |
+
"step": 440
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.24803177036159688,
|
630 |
+
"grad_norm": 0.8562553524971008,
|
631 |
+
"learning_rate": 9.355034156078188e-05,
|
632 |
+
"loss": 1.2835,
|
633 |
+
"step": 445
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.2508186441858845,
|
637 |
+
"grad_norm": 0.8887034058570862,
|
638 |
+
"learning_rate": 9.330937315754329e-05,
|
639 |
+
"loss": 1.2917,
|
640 |
+
"step": 450
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.2536055180101721,
|
644 |
+
"grad_norm": 0.944468080997467,
|
645 |
+
"learning_rate": 9.306430768627753e-05,
|
646 |
+
"loss": 1.2844,
|
647 |
+
"step": 455
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.2563923918344597,
|
651 |
+
"grad_norm": 0.9446823000907898,
|
652 |
+
"learning_rate": 9.281516833018571e-05,
|
653 |
+
"loss": 1.2999,
|
654 |
+
"step": 460
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.2591792656587473,
|
658 |
+
"grad_norm": 0.9115864634513855,
|
659 |
+
"learning_rate": 9.256197865785854e-05,
|
660 |
+
"loss": 1.3846,
|
661 |
+
"step": 465
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.26196613948303493,
|
665 |
+
"grad_norm": 0.8051035404205322,
|
666 |
+
"learning_rate": 9.230476262104677e-05,
|
667 |
+
"loss": 1.3087,
|
668 |
+
"step": 470
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.26475301330732254,
|
672 |
+
"grad_norm": 0.9236623048782349,
|
673 |
+
"learning_rate": 9.204354455239539e-05,
|
674 |
+
"loss": 1.337,
|
675 |
+
"step": 475
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.26753988713161014,
|
679 |
+
"grad_norm": 0.9063863754272461,
|
680 |
+
"learning_rate": 9.177834916314165e-05,
|
681 |
+
"loss": 1.327,
|
682 |
+
"step": 480
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.27032676095589775,
|
686 |
+
"grad_norm": 0.8260522484779358,
|
687 |
+
"learning_rate": 9.150920154077754e-05,
|
688 |
+
"loss": 1.2957,
|
689 |
+
"step": 485
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.27311363478018535,
|
693 |
+
"grad_norm": 0.903109610080719,
|
694 |
+
"learning_rate": 9.123612714667634e-05,
|
695 |
+
"loss": 1.3345,
|
696 |
+
"step": 490
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.2759005086044729,
|
700 |
+
"grad_norm": 0.8636733293533325,
|
701 |
+
"learning_rate": 9.095915181368412e-05,
|
702 |
+
"loss": 1.3918,
|
703 |
+
"step": 495
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.2786873824287605,
|
707 |
+
"grad_norm": 0.9395173788070679,
|
708 |
+
"learning_rate": 9.067830174367586e-05,
|
709 |
+
"loss": 1.3573,
|
710 |
+
"step": 500
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.2814742562530481,
|
714 |
+
"grad_norm": 0.8924953937530518,
|
715 |
+
"learning_rate": 9.039360350507679e-05,
|
716 |
+
"loss": 1.3344,
|
717 |
+
"step": 505
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.2842611300773357,
|
721 |
+
"grad_norm": 0.8831427097320557,
|
722 |
+
"learning_rate": 9.010508403034898e-05,
|
723 |
+
"loss": 1.3086,
|
724 |
+
"step": 510
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.2870480039016233,
|
728 |
+
"grad_norm": 0.8781440854072571,
|
729 |
+
"learning_rate": 8.98127706134436e-05,
|
730 |
+
"loss": 1.3186,
|
731 |
+
"step": 515
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 0.28983487772591093,
|
735 |
+
"grad_norm": 0.9398754835128784,
|
736 |
+
"learning_rate": 8.951669090721881e-05,
|
737 |
+
"loss": 1.308,
|
738 |
+
"step": 520
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.29262175155019854,
|
742 |
+
"grad_norm": 0.9422699213027954,
|
743 |
+
"learning_rate": 8.921687292082393e-05,
|
744 |
+
"loss": 1.2642,
|
745 |
+
"step": 525
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.29540862537448614,
|
749 |
+
"grad_norm": 0.8490906357765198,
|
750 |
+
"learning_rate": 8.891334501704962e-05,
|
751 |
+
"loss": 1.3098,
|
752 |
+
"step": 530
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.29819549919877375,
|
756 |
+
"grad_norm": 0.9390639662742615,
|
757 |
+
"learning_rate": 8.86061359096449e-05,
|
758 |
+
"loss": 1.2832,
|
759 |
+
"step": 535
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.30098237302306136,
|
763 |
+
"grad_norm": 0.9434688687324524,
|
764 |
+
"learning_rate": 8.829527466060072e-05,
|
765 |
+
"loss": 1.1985,
|
766 |
+
"step": 540
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.30376924684734896,
|
770 |
+
"grad_norm": 0.8724851608276367,
|
771 |
+
"learning_rate": 8.798079067740077e-05,
|
772 |
+
"loss": 1.3901,
|
773 |
+
"step": 545
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.30655612067163657,
|
777 |
+
"grad_norm": 0.9250208139419556,
|
778 |
+
"learning_rate": 8.766271371023948e-05,
|
779 |
+
"loss": 1.2924,
|
780 |
+
"step": 550
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.3093429944959242,
|
784 |
+
"grad_norm": 0.9672542810440063,
|
785 |
+
"learning_rate": 8.73410738492077e-05,
|
786 |
+
"loss": 1.2702,
|
787 |
+
"step": 555
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.3121298683202118,
|
791 |
+
"grad_norm": 0.90570467710495,
|
792 |
+
"learning_rate": 8.701590152144612e-05,
|
793 |
+
"loss": 1.2631,
|
794 |
+
"step": 560
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.3149167421444994,
|
798 |
+
"grad_norm": 0.8750013113021851,
|
799 |
+
"learning_rate": 8.668722748826693e-05,
|
800 |
+
"loss": 1.2645,
|
801 |
+
"step": 565
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.317703615968787,
|
805 |
+
"grad_norm": 0.903086245059967,
|
806 |
+
"learning_rate": 8.635508284224371e-05,
|
807 |
+
"loss": 1.38,
|
808 |
+
"step": 570
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.3204904897930746,
|
812 |
+
"grad_norm": 0.8661080598831177,
|
813 |
+
"learning_rate": 8.601949900427016e-05,
|
814 |
+
"loss": 1.2704,
|
815 |
+
"step": 575
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 0.3232773636173622,
|
819 |
+
"grad_norm": 0.9066647887229919,
|
820 |
+
"learning_rate": 8.568050772058762e-05,
|
821 |
+
"loss": 1.2938,
|
822 |
+
"step": 580
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.3260642374416498,
|
826 |
+
"grad_norm": 0.8687067627906799,
|
827 |
+
"learning_rate": 8.533814105978191e-05,
|
828 |
+
"loss": 1.2757,
|
829 |
+
"step": 585
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.3288511112659374,
|
833 |
+
"grad_norm": 0.8991963863372803,
|
834 |
+
"learning_rate": 8.499243140974966e-05,
|
835 |
+
"loss": 1.2832,
|
836 |
+
"step": 590
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.331637985090225,
|
840 |
+
"grad_norm": 0.8930802345275879,
|
841 |
+
"learning_rate": 8.464341147463431e-05,
|
842 |
+
"loss": 1.2754,
|
843 |
+
"step": 595
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.3344248589145126,
|
847 |
+
"grad_norm": 0.9218065738677979,
|
848 |
+
"learning_rate": 8.429111427173241e-05,
|
849 |
+
"loss": 1.2417,
|
850 |
+
"step": 600
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 0.33721173273880023,
|
854 |
+
"grad_norm": 0.851839542388916,
|
855 |
+
"learning_rate": 8.393557312837018e-05,
|
856 |
+
"loss": 1.2424,
|
857 |
+
"step": 605
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 0.33999860656308784,
|
861 |
+
"grad_norm": 0.8438836336135864,
|
862 |
+
"learning_rate": 8.357682167875062e-05,
|
863 |
+
"loss": 1.3203,
|
864 |
+
"step": 610
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.34278548038737544,
|
868 |
+
"grad_norm": 0.926641047000885,
|
869 |
+
"learning_rate": 8.321489386077192e-05,
|
870 |
+
"loss": 1.2793,
|
871 |
+
"step": 615
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.34557235421166305,
|
875 |
+
"grad_norm": 0.8907529711723328,
|
876 |
+
"learning_rate": 8.28498239128167e-05,
|
877 |
+
"loss": 1.2911,
|
878 |
+
"step": 620
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.34835922803595065,
|
882 |
+
"grad_norm": 0.9093756675720215,
|
883 |
+
"learning_rate": 8.248164637051321e-05,
|
884 |
+
"loss": 1.2544,
|
885 |
+
"step": 625
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.35114610186023826,
|
889 |
+
"grad_norm": 0.8902727961540222,
|
890 |
+
"learning_rate": 8.211039606346826e-05,
|
891 |
+
"loss": 1.3249,
|
892 |
+
"step": 630
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.35393297568452586,
|
896 |
+
"grad_norm": 0.8554810285568237,
|
897 |
+
"learning_rate": 8.173610811197226e-05,
|
898 |
+
"loss": 1.2805,
|
899 |
+
"step": 635
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 0.35671984950881347,
|
903 |
+
"grad_norm": 0.864427387714386,
|
904 |
+
"learning_rate": 8.135881792367686e-05,
|
905 |
+
"loss": 1.3051,
|
906 |
+
"step": 640
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.3595067233331011,
|
910 |
+
"grad_norm": 0.925584077835083,
|
911 |
+
"learning_rate": 8.097856119024545e-05,
|
912 |
+
"loss": 1.3623,
|
913 |
+
"step": 645
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.3622935971573887,
|
917 |
+
"grad_norm": 0.8400620222091675,
|
918 |
+
"learning_rate": 8.059537388397665e-05,
|
919 |
+
"loss": 1.2708,
|
920 |
+
"step": 650
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.3650804709816763,
|
924 |
+
"grad_norm": 0.9252070784568787,
|
925 |
+
"learning_rate": 8.020929225440137e-05,
|
926 |
+
"loss": 1.3025,
|
927 |
+
"step": 655
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.3678673448059639,
|
931 |
+
"grad_norm": 0.8931984305381775,
|
932 |
+
"learning_rate": 7.98203528248536e-05,
|
933 |
+
"loss": 1.2877,
|
934 |
+
"step": 660
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.3706542186302515,
|
938 |
+
"grad_norm": 0.888062059879303,
|
939 |
+
"learning_rate": 7.942859238901528e-05,
|
940 |
+
"loss": 1.3231,
|
941 |
+
"step": 665
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.3734410924545391,
|
945 |
+
"grad_norm": 1.0426568984985352,
|
946 |
+
"learning_rate": 7.903404800743564e-05,
|
947 |
+
"loss": 1.3333,
|
948 |
+
"step": 670
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.3762279662788267,
|
952 |
+
"grad_norm": 0.994853138923645,
|
953 |
+
"learning_rate": 7.863675700402526e-05,
|
954 |
+
"loss": 1.2642,
|
955 |
+
"step": 675
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 0.3790148401031143,
|
959 |
+
"grad_norm": 0.9480583667755127,
|
960 |
+
"learning_rate": 7.823675696252524e-05,
|
961 |
+
"loss": 1.3738,
|
962 |
+
"step": 680
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.3818017139274019,
|
966 |
+
"grad_norm": 0.8688267469406128,
|
967 |
+
"learning_rate": 7.783408572295174e-05,
|
968 |
+
"loss": 1.3444,
|
969 |
+
"step": 685
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.3845885877516895,
|
973 |
+
"grad_norm": 0.8878870010375977,
|
974 |
+
"learning_rate": 7.742878137801639e-05,
|
975 |
+
"loss": 1.2826,
|
976 |
+
"step": 690
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.38737546157597713,
|
980 |
+
"grad_norm": 0.9165365099906921,
|
981 |
+
"learning_rate": 7.702088226952258e-05,
|
982 |
+
"loss": 1.282,
|
983 |
+
"step": 695
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.39016233540026474,
|
987 |
+
"grad_norm": 0.9026569724082947,
|
988 |
+
"learning_rate": 7.661042698473853e-05,
|
989 |
+
"loss": 1.2294,
|
990 |
+
"step": 700
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.39294920922455234,
|
994 |
+
"grad_norm": 0.8386527299880981,
|
995 |
+
"learning_rate": 7.619745435274667e-05,
|
996 |
+
"loss": 1.2249,
|
997 |
+
"step": 705
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 0.39573608304883995,
|
1001 |
+
"grad_norm": 0.8767593502998352,
|
1002 |
+
"learning_rate": 7.578200344077073e-05,
|
1003 |
+
"loss": 1.2863,
|
1004 |
+
"step": 710
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.39852295687312755,
|
1008 |
+
"grad_norm": 0.8485695719718933,
|
1009 |
+
"learning_rate": 7.536411355047964e-05,
|
1010 |
+
"loss": 1.2873,
|
1011 |
+
"step": 715
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.40130983069741516,
|
1015 |
+
"grad_norm": 0.8822951912879944,
|
1016 |
+
"learning_rate": 7.494382421426984e-05,
|
1017 |
+
"loss": 1.3214,
|
1018 |
+
"step": 720
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.40409670452170277,
|
1022 |
+
"grad_norm": 0.8770014643669128,
|
1023 |
+
"learning_rate": 7.452117519152542e-05,
|
1024 |
+
"loss": 1.2389,
|
1025 |
+
"step": 725
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 0.40688357834599037,
|
1029 |
+
"grad_norm": 0.9898686408996582,
|
1030 |
+
"learning_rate": 7.409620646485685e-05,
|
1031 |
+
"loss": 1.2573,
|
1032 |
+
"step": 730
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 0.409670452170278,
|
1036 |
+
"grad_norm": 0.8657426834106445,
|
1037 |
+
"learning_rate": 7.36689582363187e-05,
|
1038 |
+
"loss": 1.2907,
|
1039 |
+
"step": 735
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 0.4124573259945656,
|
1043 |
+
"grad_norm": 0.8856871128082275,
|
1044 |
+
"learning_rate": 7.323947092360649e-05,
|
1045 |
+
"loss": 1.2291,
|
1046 |
+
"step": 740
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.4152441998188532,
|
1050 |
+
"grad_norm": 0.9170464277267456,
|
1051 |
+
"learning_rate": 7.280778515623314e-05,
|
1052 |
+
"loss": 1.3413,
|
1053 |
+
"step": 745
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.4180310736431408,
|
1057 |
+
"grad_norm": 1.0060070753097534,
|
1058 |
+
"learning_rate": 7.237394177168548e-05,
|
1059 |
+
"loss": 1.3131,
|
1060 |
+
"step": 750
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.4208179474674284,
|
1064 |
+
"grad_norm": 0.9314805269241333,
|
1065 |
+
"learning_rate": 7.193798181156095e-05,
|
1066 |
+
"loss": 1.3345,
|
1067 |
+
"step": 755
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 0.423604821291716,
|
1071 |
+
"grad_norm": 0.8973556160926819,
|
1072 |
+
"learning_rate": 7.149994651768514e-05,
|
1073 |
+
"loss": 1.165,
|
1074 |
+
"step": 760
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.4263916951160036,
|
1078 |
+
"grad_norm": 0.961757481098175,
|
1079 |
+
"learning_rate": 7.10598773282103e-05,
|
1080 |
+
"loss": 1.2835,
|
1081 |
+
"step": 765
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 0.4291785689402912,
|
1085 |
+
"grad_norm": 0.9814241528511047,
|
1086 |
+
"learning_rate": 7.061781587369519e-05,
|
1087 |
+
"loss": 1.3459,
|
1088 |
+
"step": 770
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.4319654427645788,
|
1092 |
+
"grad_norm": 0.906623363494873,
|
1093 |
+
"learning_rate": 7.017380397316695e-05,
|
1094 |
+
"loss": 1.2327,
|
1095 |
+
"step": 775
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.4347523165888664,
|
1099 |
+
"grad_norm": 0.855728268623352,
|
1100 |
+
"learning_rate": 6.972788363016497e-05,
|
1101 |
+
"loss": 1.1951,
|
1102 |
+
"step": 780
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 0.43753919041315403,
|
1106 |
+
"grad_norm": 0.8998392820358276,
|
1107 |
+
"learning_rate": 6.92800970287674e-05,
|
1108 |
+
"loss": 1.2595,
|
1109 |
+
"step": 785
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 0.44032606423744164,
|
1113 |
+
"grad_norm": 0.8634393215179443,
|
1114 |
+
"learning_rate": 6.883048652960038e-05,
|
1115 |
+
"loss": 1.261,
|
1116 |
+
"step": 790
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 0.44311293806172924,
|
1120 |
+
"grad_norm": 0.9386719465255737,
|
1121 |
+
"learning_rate": 6.837909466583095e-05,
|
1122 |
+
"loss": 1.3039,
|
1123 |
+
"step": 795
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 0.44589981188601685,
|
1127 |
+
"grad_norm": 0.8203379511833191,
|
1128 |
+
"learning_rate": 6.792596413914324e-05,
|
1129 |
+
"loss": 1.1734,
|
1130 |
+
"step": 800
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.44868668571030446,
|
1134 |
+
"grad_norm": 0.9148008823394775,
|
1135 |
+
"learning_rate": 6.747113781569892e-05,
|
1136 |
+
"loss": 1.3215,
|
1137 |
+
"step": 805
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.45147355953459206,
|
1141 |
+
"grad_norm": 0.9338198304176331,
|
1142 |
+
"learning_rate": 6.701465872208216e-05,
|
1143 |
+
"loss": 1.3128,
|
1144 |
+
"step": 810
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 0.45426043335887967,
|
1148 |
+
"grad_norm": 0.9510387778282166,
|
1149 |
+
"learning_rate": 6.655657004122916e-05,
|
1150 |
+
"loss": 1.3056,
|
1151 |
+
"step": 815
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 0.4570473071831673,
|
1155 |
+
"grad_norm": 0.9619747996330261,
|
1156 |
+
"learning_rate": 6.60969151083432e-05,
|
1157 |
+
"loss": 1.2678,
|
1158 |
+
"step": 820
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 0.4598341810074549,
|
1162 |
+
"grad_norm": 0.8645920753479004,
|
1163 |
+
"learning_rate": 6.563573740679496e-05,
|
1164 |
+
"loss": 1.2585,
|
1165 |
+
"step": 825
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 0.4626210548317425,
|
1169 |
+
"grad_norm": 0.9401421546936035,
|
1170 |
+
"learning_rate": 6.517308056400917e-05,
|
1171 |
+
"loss": 1.2844,
|
1172 |
+
"step": 830
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.4654079286560301,
|
1176 |
+
"grad_norm": 0.8988810181617737,
|
1177 |
+
"learning_rate": 6.470898834733731e-05,
|
1178 |
+
"loss": 1.2556,
|
1179 |
+
"step": 835
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.4681948024803177,
|
1183 |
+
"grad_norm": 0.9045888781547546,
|
1184 |
+
"learning_rate": 6.42435046599173e-05,
|
1185 |
+
"loss": 1.2669,
|
1186 |
+
"step": 840
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 0.4709816763046053,
|
1190 |
+
"grad_norm": 0.9363210797309875,
|
1191 |
+
"learning_rate": 6.377667353652022e-05,
|
1192 |
+
"loss": 1.3025,
|
1193 |
+
"step": 845
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 0.4737685501288929,
|
1197 |
+
"grad_norm": 0.8949057459831238,
|
1198 |
+
"learning_rate": 6.330853913938466e-05,
|
1199 |
+
"loss": 1.2632,
|
1200 |
+
"step": 850
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.4765554239531805,
|
1204 |
+
"grad_norm": 0.8873914480209351,
|
1205 |
+
"learning_rate": 6.283914575403888e-05,
|
1206 |
+
"loss": 1.322,
|
1207 |
+
"step": 855
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 0.4793422977774681,
|
1211 |
+
"grad_norm": 0.9296184778213501,
|
1212 |
+
"learning_rate": 6.236853778511156e-05,
|
1213 |
+
"loss": 1.2484,
|
1214 |
+
"step": 860
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.4821291716017557,
|
1218 |
+
"grad_norm": 0.9600350260734558,
|
1219 |
+
"learning_rate": 6.189675975213094e-05,
|
1220 |
+
"loss": 1.2925,
|
1221 |
+
"step": 865
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.48491604542604333,
|
1225 |
+
"grad_norm": 0.9283687472343445,
|
1226 |
+
"learning_rate": 6.142385628531342e-05,
|
1227 |
+
"loss": 1.2948,
|
1228 |
+
"step": 870
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 0.48770291925033094,
|
1232 |
+
"grad_norm": 0.9505272507667542,
|
1233 |
+
"learning_rate": 6.09498721213414e-05,
|
1234 |
+
"loss": 1.2185,
|
1235 |
+
"step": 875
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 0.49048979307461854,
|
1239 |
+
"grad_norm": 0.9199963808059692,
|
1240 |
+
"learning_rate": 6.047485209913137e-05,
|
1241 |
+
"loss": 1.3212,
|
1242 |
+
"step": 880
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 0.49327666689890615,
|
1246 |
+
"grad_norm": 0.8689345717430115,
|
1247 |
+
"learning_rate": 5.999884115559192e-05,
|
1248 |
+
"loss": 1.2593,
|
1249 |
+
"step": 885
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 0.49606354072319375,
|
1253 |
+
"grad_norm": 0.8260021805763245,
|
1254 |
+
"learning_rate": 5.952188432137293e-05,
|
1255 |
+
"loss": 1.2825,
|
1256 |
+
"step": 890
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.49885041454748136,
|
1260 |
+
"grad_norm": 0.7934656143188477,
|
1261 |
+
"learning_rate": 5.90440267166055e-05,
|
1262 |
+
"loss": 1.2512,
|
1263 |
+
"step": 895
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.501637288371769,
|
1267 |
+
"grad_norm": 0.9623500108718872,
|
1268 |
+
"learning_rate": 5.8565313546633684e-05,
|
1269 |
+
"loss": 1.2891,
|
1270 |
+
"step": 900
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 0.5044241621960566,
|
1274 |
+
"grad_norm": 0.8901398777961731,
|
1275 |
+
"learning_rate": 5.8085790097738025e-05,
|
1276 |
+
"loss": 1.273,
|
1277 |
+
"step": 905
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 0.5072110360203442,
|
1281 |
+
"grad_norm": 0.9480902552604675,
|
1282 |
+
"learning_rate": 5.7605501732851475e-05,
|
1283 |
+
"loss": 1.3143,
|
1284 |
+
"step": 910
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.5099979098446318,
|
1288 |
+
"grad_norm": 0.8739180564880371,
|
1289 |
+
"learning_rate": 5.712449388726807e-05,
|
1290 |
+
"loss": 1.3233,
|
1291 |
+
"step": 915
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 0.5127847836689194,
|
1295 |
+
"grad_norm": 0.8921142220497131,
|
1296 |
+
"learning_rate": 5.664281206434472e-05,
|
1297 |
+
"loss": 1.2178,
|
1298 |
+
"step": 920
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 0.515571657493207,
|
1302 |
+
"grad_norm": 0.8952714204788208,
|
1303 |
+
"learning_rate": 5.616050183119663e-05,
|
1304 |
+
"loss": 1.3035,
|
1305 |
+
"step": 925
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.5183585313174947,
|
1309 |
+
"grad_norm": 0.8778610825538635,
|
1310 |
+
"learning_rate": 5.5677608814386616e-05,
|
1311 |
+
"loss": 1.1698,
|
1312 |
+
"step": 930
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 0.5211454051417822,
|
1316 |
+
"grad_norm": 0.9074441194534302,
|
1317 |
+
"learning_rate": 5.519417869560889e-05,
|
1318 |
+
"loss": 1.2659,
|
1319 |
+
"step": 935
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 0.5239322789660699,
|
1323 |
+
"grad_norm": 1.0030386447906494,
|
1324 |
+
"learning_rate": 5.471025720736747e-05,
|
1325 |
+
"loss": 1.3052,
|
1326 |
+
"step": 940
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 0.5267191527903574,
|
1330 |
+
"grad_norm": 0.8883451223373413,
|
1331 |
+
"learning_rate": 5.422589012864996e-05,
|
1332 |
+
"loss": 1.2955,
|
1333 |
+
"step": 945
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 0.5295060266146451,
|
1337 |
+
"grad_norm": 0.9527599215507507,
|
1338 |
+
"learning_rate": 5.3741123280596864e-05,
|
1339 |
+
"loss": 1.2489,
|
1340 |
+
"step": 950
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 0.5322929004389326,
|
1344 |
+
"grad_norm": 0.9727275967597961,
|
1345 |
+
"learning_rate": 5.325600252216685e-05,
|
1346 |
+
"loss": 1.2669,
|
1347 |
+
"step": 955
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.5350797742632203,
|
1351 |
+
"grad_norm": 0.9047435522079468,
|
1352 |
+
"learning_rate": 5.27705737457985e-05,
|
1353 |
+
"loss": 1.1822,
|
1354 |
+
"step": 960
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.5378666480875078,
|
1358 |
+
"grad_norm": 0.929094135761261,
|
1359 |
+
"learning_rate": 5.228488287306896e-05,
|
1360 |
+
"loss": 1.2304,
|
1361 |
+
"step": 965
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 0.5406535219117955,
|
1365 |
+
"grad_norm": 0.8297614455223083,
|
1366 |
+
"learning_rate": 5.179897585034963e-05,
|
1367 |
+
"loss": 1.2458,
|
1368 |
+
"step": 970
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 0.543440395736083,
|
1372 |
+
"grad_norm": 0.8769505023956299,
|
1373 |
+
"learning_rate": 5.1312898644459776e-05,
|
1374 |
+
"loss": 1.1869,
|
1375 |
+
"step": 975
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 0.5462272695603707,
|
1379 |
+
"grad_norm": 0.9683988690376282,
|
1380 |
+
"learning_rate": 5.0826697238317935e-05,
|
1381 |
+
"loss": 1.2764,
|
1382 |
+
"step": 980
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 0.5490141433846583,
|
1386 |
+
"grad_norm": 0.886499285697937,
|
1387 |
+
"learning_rate": 5.0340417626592016e-05,
|
1388 |
+
"loss": 1.2708,
|
1389 |
+
"step": 985
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.5518010172089458,
|
1393 |
+
"grad_norm": 0.9555862545967102,
|
1394 |
+
"learning_rate": 4.9854105811348216e-05,
|
1395 |
+
"loss": 1.2959,
|
1396 |
+
"step": 990
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 0.5545878910332335,
|
1400 |
+
"grad_norm": 0.9976694583892822,
|
1401 |
+
"learning_rate": 4.936780779769913e-05,
|
1402 |
+
"loss": 1.2704,
|
1403 |
+
"step": 995
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 0.557374764857521,
|
1407 |
+
"grad_norm": 0.9540396928787231,
|
1408 |
+
"learning_rate": 4.888156958945174e-05,
|
1409 |
+
"loss": 1.2399,
|
1410 |
+
"step": 1000
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.5601616386818087,
|
1414 |
+
"grad_norm": 0.9087413549423218,
|
1415 |
+
"learning_rate": 4.839543718475543e-05,
|
1416 |
+
"loss": 1.2465,
|
1417 |
+
"step": 1005
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 0.5629485125060962,
|
1421 |
+
"grad_norm": 0.8988016247749329,
|
1422 |
+
"learning_rate": 4.790945657175061e-05,
|
1423 |
+
"loss": 1.2452,
|
1424 |
+
"step": 1010
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 0.5657353863303839,
|
1428 |
+
"grad_norm": 0.9223970174789429,
|
1429 |
+
"learning_rate": 4.742367372421811e-05,
|
1430 |
+
"loss": 1.2782,
|
1431 |
+
"step": 1015
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 0.5685222601546714,
|
1435 |
+
"grad_norm": 0.9696489572525024,
|
1436 |
+
"learning_rate": 4.69381345972302e-05,
|
1437 |
+
"loss": 1.217,
|
1438 |
+
"step": 1020
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 0.5713091339789591,
|
1442 |
+
"grad_norm": 0.8725862503051758,
|
1443 |
+
"learning_rate": 4.6452885122803205e-05,
|
1444 |
+
"loss": 1.2164,
|
1445 |
+
"step": 1025
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 0.5740960078032467,
|
1449 |
+
"grad_norm": 0.9017091989517212,
|
1450 |
+
"learning_rate": 4.5967971205552194e-05,
|
1451 |
+
"loss": 1.262,
|
1452 |
+
"step": 1030
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 0.5768828816275343,
|
1456 |
+
"grad_norm": 0.8934043049812317,
|
1457 |
+
"learning_rate": 4.548343871834864e-05,
|
1458 |
+
"loss": 1.2592,
|
1459 |
+
"step": 1035
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 0.5796697554518219,
|
1463 |
+
"grad_norm": 0.962250292301178,
|
1464 |
+
"learning_rate": 4.499933349798067e-05,
|
1465 |
+
"loss": 1.2987,
|
1466 |
+
"step": 1040
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 0.5824566292761095,
|
1470 |
+
"grad_norm": 0.9082201719284058,
|
1471 |
+
"learning_rate": 4.451570134081694e-05,
|
1472 |
+
"loss": 1.3104,
|
1473 |
+
"step": 1045
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 0.5852435031003971,
|
1477 |
+
"grad_norm": 0.8380867838859558,
|
1478 |
+
"learning_rate": 4.403258799847433e-05,
|
1479 |
+
"loss": 1.2397,
|
1480 |
+
"step": 1050
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 0.5880303769246847,
|
1484 |
+
"grad_norm": 1.0069491863250732,
|
1485 |
+
"learning_rate": 4.3550039173489845e-05,
|
1486 |
+
"loss": 1.2416,
|
1487 |
+
"step": 1055
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 0.5908172507489723,
|
1491 |
+
"grad_norm": 0.901740550994873,
|
1492 |
+
"learning_rate": 4.306810051499708e-05,
|
1493 |
+
"loss": 1.2247,
|
1494 |
+
"step": 1060
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 0.59360412457326,
|
1498 |
+
"grad_norm": 1.0371346473693848,
|
1499 |
+
"learning_rate": 4.2586817614407895e-05,
|
1500 |
+
"loss": 1.2432,
|
1501 |
+
"step": 1065
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 0.5963909983975475,
|
1505 |
+
"grad_norm": 0.8401350975036621,
|
1506 |
+
"learning_rate": 4.210623600109946e-05,
|
1507 |
+
"loss": 1.1691,
|
1508 |
+
"step": 1070
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 0.5991778722218352,
|
1512 |
+
"grad_norm": 0.924321711063385,
|
1513 |
+
"learning_rate": 4.162640113810706e-05,
|
1514 |
+
"loss": 1.2647,
|
1515 |
+
"step": 1075
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 0.6019647460461227,
|
1519 |
+
"grad_norm": 0.9289098381996155,
|
1520 |
+
"learning_rate": 4.114735841782347e-05,
|
1521 |
+
"loss": 1.2958,
|
1522 |
+
"step": 1080
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 0.6047516198704104,
|
1526 |
+
"grad_norm": 0.9739760756492615,
|
1527 |
+
"learning_rate": 4.06691531577047e-05,
|
1528 |
+
"loss": 1.2703,
|
1529 |
+
"step": 1085
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 0.6075384936946979,
|
1533 |
+
"grad_norm": 0.8968196511268616,
|
1534 |
+
"learning_rate": 4.019183059598296e-05,
|
1535 |
+
"loss": 1.2312,
|
1536 |
+
"step": 1090
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 0.6103253675189856,
|
1540 |
+
"grad_norm": 0.8930853605270386,
|
1541 |
+
"learning_rate": 3.971543588738724e-05,
|
1542 |
+
"loss": 1.2612,
|
1543 |
+
"step": 1095
|
1544 |
+
},
|
1545 |
+
{
|
1546 |
+
"epoch": 0.6131122413432731,
|
1547 |
+
"grad_norm": 0.8859248757362366,
|
1548 |
+
"learning_rate": 3.924001409887158e-05,
|
1549 |
+
"loss": 1.1742,
|
1550 |
+
"step": 1100
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 0.6158991151675608,
|
1554 |
+
"grad_norm": 0.9286195635795593,
|
1555 |
+
"learning_rate": 3.87656102053517e-05,
|
1556 |
+
"loss": 1.2483,
|
1557 |
+
"step": 1105
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 0.6186859889918483,
|
1561 |
+
"grad_norm": 0.895728349685669,
|
1562 |
+
"learning_rate": 3.8292269085450474e-05,
|
1563 |
+
"loss": 1.2157,
|
1564 |
+
"step": 1110
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 0.621472862816136,
|
1568 |
+
"grad_norm": 0.879304826259613,
|
1569 |
+
"learning_rate": 3.782003551725236e-05,
|
1570 |
+
"loss": 1.3032,
|
1571 |
+
"step": 1115
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 0.6242597366404236,
|
1575 |
+
"grad_norm": 0.893455982208252,
|
1576 |
+
"learning_rate": 3.734895417406734e-05,
|
1577 |
+
"loss": 1.2443,
|
1578 |
+
"step": 1120
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 0.6270466104647112,
|
1582 |
+
"grad_norm": 0.924315869808197,
|
1583 |
+
"learning_rate": 3.687906962020491e-05,
|
1584 |
+
"loss": 1.2759,
|
1585 |
+
"step": 1125
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 0.6298334842889988,
|
1589 |
+
"grad_norm": 1.0192773342132568,
|
1590 |
+
"learning_rate": 3.641042630675829e-05,
|
1591 |
+
"loss": 1.2816,
|
1592 |
+
"step": 1130
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 0.6326203581132864,
|
1596 |
+
"grad_norm": 0.9503198266029358,
|
1597 |
+
"learning_rate": 3.594306856739924e-05,
|
1598 |
+
"loss": 1.2173,
|
1599 |
+
"step": 1135
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.635407231937574,
|
1603 |
+
"grad_norm": 0.9149984121322632,
|
1604 |
+
"learning_rate": 3.547704061418424e-05,
|
1605 |
+
"loss": 1.2245,
|
1606 |
+
"step": 1140
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"epoch": 0.6381941057618616,
|
1610 |
+
"grad_norm": 0.9525075554847717,
|
1611 |
+
"learning_rate": 3.501238653337194e-05,
|
1612 |
+
"loss": 1.2298,
|
1613 |
+
"step": 1145
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 0.6409809795861492,
|
1617 |
+
"grad_norm": 0.9972552061080933,
|
1618 |
+
"learning_rate": 3.4549150281252636e-05,
|
1619 |
+
"loss": 1.3021,
|
1620 |
+
"step": 1150
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 0.6437678534104369,
|
1624 |
+
"grad_norm": 0.8908212184906006,
|
1625 |
+
"learning_rate": 3.408737567998993e-05,
|
1626 |
+
"loss": 1.191,
|
1627 |
+
"step": 1155
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 0.6465547272347244,
|
1631 |
+
"grad_norm": 0.9422298669815063,
|
1632 |
+
"learning_rate": 3.362710641347524e-05,
|
1633 |
+
"loss": 1.2812,
|
1634 |
+
"step": 1160
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 0.6493416010590121,
|
1638 |
+
"grad_norm": 0.8892982006072998,
|
1639 |
+
"learning_rate": 3.316838602319532e-05,
|
1640 |
+
"loss": 1.2787,
|
1641 |
+
"step": 1165
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 0.6521284748832996,
|
1645 |
+
"grad_norm": 0.9730682373046875,
|
1646 |
+
"learning_rate": 3.271125790411309e-05,
|
1647 |
+
"loss": 1.1704,
|
1648 |
+
"step": 1170
|
1649 |
+
},
|
1650 |
+
{
|
1651 |
+
"epoch": 0.6549153487075873,
|
1652 |
+
"grad_norm": 1.0745271444320679,
|
1653 |
+
"learning_rate": 3.225576530056264e-05,
|
1654 |
+
"loss": 1.3028,
|
1655 |
+
"step": 1175
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 0.6577022225318748,
|
1659 |
+
"grad_norm": 0.9123522043228149,
|
1660 |
+
"learning_rate": 3.180195130215824e-05,
|
1661 |
+
"loss": 1.262,
|
1662 |
+
"step": 1180
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 0.6604890963561625,
|
1666 |
+
"grad_norm": 0.9651986360549927,
|
1667 |
+
"learning_rate": 3.1349858839717986e-05,
|
1668 |
+
"loss": 1.1867,
|
1669 |
+
"step": 1185
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 0.66327597018045,
|
1673 |
+
"grad_norm": 0.9499524831771851,
|
1674 |
+
"learning_rate": 3.089953068120271e-05,
|
1675 |
+
"loss": 1.1766,
|
1676 |
+
"step": 1190
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 0.6660628440047377,
|
1680 |
+
"grad_norm": 0.9542708396911621,
|
1681 |
+
"learning_rate": 3.0451009427669986e-05,
|
1682 |
+
"loss": 1.2212,
|
1683 |
+
"step": 1195
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 0.6688497178290252,
|
1687 |
+
"grad_norm": 0.9473170042037964,
|
1688 |
+
"learning_rate": 3.000433750924414e-05,
|
1689 |
+
"loss": 1.2332,
|
1690 |
+
"step": 1200
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 0.6716365916533129,
|
1694 |
+
"grad_norm": 0.8507165312767029,
|
1695 |
+
"learning_rate": 2.9559557181102315e-05,
|
1696 |
+
"loss": 1.245,
|
1697 |
+
"step": 1205
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 0.6744234654776005,
|
1701 |
+
"grad_norm": 0.9855820536613464,
|
1702 |
+
"learning_rate": 2.911671051947722e-05,
|
1703 |
+
"loss": 1.1962,
|
1704 |
+
"step": 1210
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 0.6772103393018881,
|
1708 |
+
"grad_norm": 0.970454752445221,
|
1709 |
+
"learning_rate": 2.867583941767657e-05,
|
1710 |
+
"loss": 1.1937,
|
1711 |
+
"step": 1215
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 0.6799972131261757,
|
1715 |
+
"grad_norm": 0.9287285804748535,
|
1716 |
+
"learning_rate": 2.823698558212009e-05,
|
1717 |
+
"loss": 1.2562,
|
1718 |
+
"step": 1220
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 0.6827840869504633,
|
1722 |
+
"grad_norm": 0.9838190078735352,
|
1723 |
+
"learning_rate": 2.7800190528394122e-05,
|
1724 |
+
"loss": 1.2125,
|
1725 |
+
"step": 1225
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 0.6855709607747509,
|
1729 |
+
"grad_norm": 0.8512199521064758,
|
1730 |
+
"learning_rate": 2.736549557732405e-05,
|
1731 |
+
"loss": 1.1991,
|
1732 |
+
"step": 1230
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 0.6883578345990385,
|
1736 |
+
"grad_norm": 0.8986166715621948,
|
1737 |
+
"learning_rate": 2.693294185106562e-05,
|
1738 |
+
"loss": 1.3633,
|
1739 |
+
"step": 1235
|
1740 |
+
},
|
1741 |
+
{
|
1742 |
+
"epoch": 0.6911447084233261,
|
1743 |
+
"grad_norm": 0.9696632027626038,
|
1744 |
+
"learning_rate": 2.650257026921455e-05,
|
1745 |
+
"loss": 1.2675,
|
1746 |
+
"step": 1240
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 0.6939315822476138,
|
1750 |
+
"grad_norm": 1.0738840103149414,
|
1751 |
+
"learning_rate": 2.607442154493568e-05,
|
1752 |
+
"loss": 1.2917,
|
1753 |
+
"step": 1245
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 0.6967184560719013,
|
1757 |
+
"grad_norm": 0.9573596715927124,
|
1758 |
+
"learning_rate": 2.5648536181111438e-05,
|
1759 |
+
"loss": 1.2427,
|
1760 |
+
"step": 1250
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 0.699505329896189,
|
1764 |
+
"grad_norm": 0.9653842449188232,
|
1765 |
+
"learning_rate": 2.5224954466510274e-05,
|
1766 |
+
"loss": 1.2188,
|
1767 |
+
"step": 1255
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 0.7022922037204765,
|
1771 |
+
"grad_norm": 0.9326026439666748,
|
1772 |
+
"learning_rate": 2.480371647197538e-05,
|
1773 |
+
"loss": 1.2812,
|
1774 |
+
"step": 1260
|
1775 |
+
},
|
1776 |
+
{
|
1777 |
+
"epoch": 0.7050790775447642,
|
1778 |
+
"grad_norm": 0.9213048219680786,
|
1779 |
+
"learning_rate": 2.438486204663391e-05,
|
1780 |
+
"loss": 1.2512,
|
1781 |
+
"step": 1265
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 0.7078659513690517,
|
1785 |
+
"grad_norm": 0.9547055959701538,
|
1786 |
+
"learning_rate": 2.3968430814127385e-05,
|
1787 |
+
"loss": 1.2657,
|
1788 |
+
"step": 1270
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 0.7106528251933394,
|
1792 |
+
"grad_norm": 0.9416990280151367,
|
1793 |
+
"learning_rate": 2.3554462168863085e-05,
|
1794 |
+
"loss": 1.2631,
|
1795 |
+
"step": 1275
|
1796 |
+
},
|
1797 |
+
{
|
1798 |
+
"epoch": 0.7134396990176269,
|
1799 |
+
"grad_norm": 0.9471155405044556,
|
1800 |
+
"learning_rate": 2.314299527228759e-05,
|
1801 |
+
"loss": 1.2631,
|
1802 |
+
"step": 1280
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 0.7162265728419146,
|
1806 |
+
"grad_norm": 0.9220243096351624,
|
1807 |
+
"learning_rate": 2.2734069049181882e-05,
|
1808 |
+
"loss": 1.2288,
|
1809 |
+
"step": 1285
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.7190134466662021,
|
1813 |
+
"grad_norm": 0.9854679107666016,
|
1814 |
+
"learning_rate": 2.2327722183979212e-05,
|
1815 |
+
"loss": 1.261,
|
1816 |
+
"step": 1290
|
1817 |
+
},
|
1818 |
+
{
|
1819 |
+
"epoch": 0.7218003204904898,
|
1820 |
+
"grad_norm": 0.898456335067749,
|
1821 |
+
"learning_rate": 2.1923993117105462e-05,
|
1822 |
+
"loss": 1.2037,
|
1823 |
+
"step": 1295
|
1824 |
+
},
|
1825 |
+
{
|
1826 |
+
"epoch": 0.7245871943147774,
|
1827 |
+
"grad_norm": 1.0650768280029297,
|
1828 |
+
"learning_rate": 2.1522920041342704e-05,
|
1829 |
+
"loss": 1.214,
|
1830 |
+
"step": 1300
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 0.727374068139065,
|
1834 |
+
"grad_norm": 1.02187979221344,
|
1835 |
+
"learning_rate": 2.1124540898216248e-05,
|
1836 |
+
"loss": 1.2634,
|
1837 |
+
"step": 1305
|
1838 |
+
},
|
1839 |
+
{
|
1840 |
+
"epoch": 0.7301609419633526,
|
1841 |
+
"grad_norm": 0.9087027311325073,
|
1842 |
+
"learning_rate": 2.0728893374405166e-05,
|
1843 |
+
"loss": 1.1596,
|
1844 |
+
"step": 1310
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 0.7329478157876402,
|
1848 |
+
"grad_norm": 1.0457086563110352,
|
1849 |
+
"learning_rate": 2.033601489817738e-05,
|
1850 |
+
"loss": 1.3245,
|
1851 |
+
"step": 1315
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 0.7357346896119278,
|
1855 |
+
"grad_norm": 1.012440800666809,
|
1856 |
+
"learning_rate": 1.9945942635848748e-05,
|
1857 |
+
"loss": 1.2658,
|
1858 |
+
"step": 1320
|
1859 |
+
},
|
1860 |
+
{
|
1861 |
+
"epoch": 0.7385215634362154,
|
1862 |
+
"grad_norm": 0.9544854164123535,
|
1863 |
+
"learning_rate": 1.9558713488267238e-05,
|
1864 |
+
"loss": 1.2584,
|
1865 |
+
"step": 1325
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 0.741308437260503,
|
1869 |
+
"grad_norm": 0.9268321394920349,
|
1870 |
+
"learning_rate": 1.917436408732208e-05,
|
1871 |
+
"loss": 1.2337,
|
1872 |
+
"step": 1330
|
1873 |
+
},
|
1874 |
+
{
|
1875 |
+
"epoch": 0.7440953110847907,
|
1876 |
+
"grad_norm": 1.108223557472229,
|
1877 |
+
"learning_rate": 1.8792930792478357e-05,
|
1878 |
+
"loss": 1.2228,
|
1879 |
+
"step": 1335
|
1880 |
+
},
|
1881 |
+
{
|
1882 |
+
"epoch": 0.7468821849090782,
|
1883 |
+
"grad_norm": 1.0709432363510132,
|
1884 |
+
"learning_rate": 1.8414449687337464e-05,
|
1885 |
+
"loss": 1.183,
|
1886 |
+
"step": 1340
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 0.7496690587333659,
|
1890 |
+
"grad_norm": 0.9613754153251648,
|
1891 |
+
"learning_rate": 1.8038956576223504e-05,
|
1892 |
+
"loss": 1.1697,
|
1893 |
+
"step": 1345
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 0.7524559325576534,
|
1897 |
+
"grad_norm": 0.865163266658783,
|
1898 |
+
"learning_rate": 1.766648698079635e-05,
|
1899 |
+
"loss": 1.2347,
|
1900 |
+
"step": 1350
|
1901 |
+
},
|
1902 |
+
{
|
1903 |
+
"epoch": 0.7552428063819411,
|
1904 |
+
"grad_norm": 0.9915691614151001,
|
1905 |
+
"learning_rate": 1.7297076136691072e-05,
|
1906 |
+
"loss": 1.3237,
|
1907 |
+
"step": 1355
|
1908 |
+
},
|
1909 |
+
{
|
1910 |
+
"epoch": 0.7580296802062286,
|
1911 |
+
"grad_norm": 1.0180468559265137,
|
1912 |
+
"learning_rate": 1.6930758990184875e-05,
|
1913 |
+
"loss": 1.2416,
|
1914 |
+
"step": 1360
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 0.7608165540305163,
|
1918 |
+
"grad_norm": 1.0427292585372925,
|
1919 |
+
"learning_rate": 1.6567570194891024e-05,
|
1920 |
+
"loss": 1.225,
|
1921 |
+
"step": 1365
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 0.7636034278548038,
|
1925 |
+
"grad_norm": 1.0692229270935059,
|
1926 |
+
"learning_rate": 1.620754410848069e-05,
|
1927 |
+
"loss": 1.2287,
|
1928 |
+
"step": 1370
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 0.7663903016790915,
|
1932 |
+
"grad_norm": 0.9599437713623047,
|
1933 |
+
"learning_rate": 1.5850714789432663e-05,
|
1934 |
+
"loss": 1.2652,
|
1935 |
+
"step": 1375
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 0.769177175503379,
|
1939 |
+
"grad_norm": 0.9924296140670776,
|
1940 |
+
"learning_rate": 1.549711599381145e-05,
|
1941 |
+
"loss": 1.2543,
|
1942 |
+
"step": 1380
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 0.7719640493276667,
|
1946 |
+
"grad_norm": 0.8805568218231201,
|
1947 |
+
"learning_rate": 1.5146781172073959e-05,
|
1948 |
+
"loss": 1.2086,
|
1949 |
+
"step": 1385
|
1950 |
+
},
|
1951 |
+
{
|
1952 |
+
"epoch": 0.7747509231519543,
|
1953 |
+
"grad_norm": 0.9607245922088623,
|
1954 |
+
"learning_rate": 1.479974346590503e-05,
|
1955 |
+
"loss": 1.2543,
|
1956 |
+
"step": 1390
|
1957 |
+
},
|
1958 |
+
{
|
1959 |
+
"epoch": 0.7775377969762419,
|
1960 |
+
"grad_norm": 0.9395803213119507,
|
1961 |
+
"learning_rate": 1.4456035705082349e-05,
|
1962 |
+
"loss": 1.2146,
|
1963 |
+
"step": 1395
|
1964 |
+
},
|
1965 |
+
{
|
1966 |
+
"epoch": 0.7803246708005295,
|
1967 |
+
"grad_norm": 0.9911707043647766,
|
1968 |
+
"learning_rate": 1.4115690404370551e-05,
|
1969 |
+
"loss": 1.2256,
|
1970 |
+
"step": 1400
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 0.7831115446248171,
|
1974 |
+
"grad_norm": 0.9199152588844299,
|
1975 |
+
"learning_rate": 1.3778739760445552e-05,
|
1976 |
+
"loss": 1.2138,
|
1977 |
+
"step": 1405
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 0.7858984184491047,
|
1981 |
+
"grad_norm": 0.9677468538284302,
|
1982 |
+
"learning_rate": 1.344521564884858e-05,
|
1983 |
+
"loss": 1.2739,
|
1984 |
+
"step": 1410
|
1985 |
+
},
|
1986 |
+
{
|
1987 |
+
"epoch": 0.7886852922733923,
|
1988 |
+
"grad_norm": 0.9051083326339722,
|
1989 |
+
"learning_rate": 1.3115149620970795e-05,
|
1990 |
+
"loss": 1.278,
|
1991 |
+
"step": 1415
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"epoch": 0.7914721660976799,
|
1995 |
+
"grad_norm": 1.0139137506484985,
|
1996 |
+
"learning_rate": 1.2788572901068552e-05,
|
1997 |
+
"loss": 1.2309,
|
1998 |
+
"step": 1420
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 0.7942590399219676,
|
2002 |
+
"grad_norm": 1.022859811782837,
|
2003 |
+
"learning_rate": 1.2465516383309551e-05,
|
2004 |
+
"loss": 1.2423,
|
2005 |
+
"step": 1425
|
2006 |
+
},
|
2007 |
+
{
|
2008 |
+
"epoch": 0.7970459137462551,
|
2009 |
+
"grad_norm": 0.9269377589225769,
|
2010 |
+
"learning_rate": 1.2146010628850268e-05,
|
2011 |
+
"loss": 1.2685,
|
2012 |
+
"step": 1430
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 0.7998327875705428,
|
2016 |
+
"grad_norm": 0.9552863836288452,
|
2017 |
+
"learning_rate": 1.183008586294485e-05,
|
2018 |
+
"loss": 1.2021,
|
2019 |
+
"step": 1435
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 0.8026196613948303,
|
2023 |
+
"grad_norm": 0.9597859382629395,
|
2024 |
+
"learning_rate": 1.151777197208585e-05,
|
2025 |
+
"loss": 1.215,
|
2026 |
+
"step": 1440
|
2027 |
+
},
|
2028 |
+
{
|
2029 |
+
"epoch": 0.805406535219118,
|
2030 |
+
"grad_norm": 0.9569510817527771,
|
2031 |
+
"learning_rate": 1.1209098501176896e-05,
|
2032 |
+
"loss": 1.2153,
|
2033 |
+
"step": 1445
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 0.8081934090434055,
|
2037 |
+
"grad_norm": 0.9744769334793091,
|
2038 |
+
"learning_rate": 1.0904094650737795e-05,
|
2039 |
+
"loss": 1.2153,
|
2040 |
+
"step": 1450
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 0.8109802828676932,
|
2044 |
+
"grad_norm": 1.118589997291565,
|
2045 |
+
"learning_rate": 1.0602789274142133e-05,
|
2046 |
+
"loss": 1.2763,
|
2047 |
+
"step": 1455
|
2048 |
+
},
|
2049 |
+
{
|
2050 |
+
"epoch": 0.8137671566919807,
|
2051 |
+
"grad_norm": 0.9778153300285339,
|
2052 |
+
"learning_rate": 1.0305210874887766e-05,
|
2053 |
+
"loss": 1.1713,
|
2054 |
+
"step": 1460
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 0.8165540305162684,
|
2058 |
+
"grad_norm": 0.9907205700874329,
|
2059 |
+
"learning_rate": 1.0011387603900385e-05,
|
2060 |
+
"loss": 1.2282,
|
2061 |
+
"step": 1465
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 0.819340904340556,
|
2065 |
+
"grad_norm": 0.9918599128723145,
|
2066 |
+
"learning_rate": 9.7213472568704e-06,
|
2067 |
+
"loss": 1.2396,
|
2068 |
+
"step": 1470
|
2069 |
+
},
|
2070 |
+
{
|
2071 |
+
"epoch": 0.8221277781648436,
|
2072 |
+
"grad_norm": 0.9913582801818848,
|
2073 |
+
"learning_rate": 9.435117271623566e-06,
|
2074 |
+
"loss": 1.1384,
|
2075 |
+
"step": 1475
|
2076 |
+
},
|
2077 |
+
{
|
2078 |
+
"epoch": 0.8249146519891312,
|
2079 |
+
"grad_norm": 0.9848992228507996,
|
2080 |
+
"learning_rate": 9.152724725525202e-06,
|
2081 |
+
"loss": 1.2261,
|
2082 |
+
"step": 1480
|
2083 |
+
},
|
2084 |
+
{
|
2085 |
+
"epoch": 0.8277015258134188,
|
2086 |
+
"grad_norm": 0.8803195953369141,
|
2087 |
+
"learning_rate": 8.87419633291886e-06,
|
2088 |
+
"loss": 1.265,
|
2089 |
+
"step": 1485
|
2090 |
+
},
|
2091 |
+
{
|
2092 |
+
"epoch": 0.8304883996377064,
|
2093 |
+
"grad_norm": 1.0013386011123657,
|
2094 |
+
"learning_rate": 8.599558442598998e-06,
|
2095 |
+
"loss": 1.1752,
|
2096 |
+
"step": 1490
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 0.833275273461994,
|
2100 |
+
"grad_norm": 1.0229575634002686,
|
2101 |
+
"learning_rate": 8.328837035318448e-06,
|
2102 |
+
"loss": 1.2616,
|
2103 |
+
"step": 1495
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 0.8360621472862816,
|
2107 |
+
"grad_norm": 0.93488609790802,
|
2108 |
+
"learning_rate": 8.06205772133063e-06,
|
2109 |
+
"loss": 1.1683,
|
2110 |
+
"step": 1500
|
2111 |
+
},
|
2112 |
+
{
|
2113 |
+
"epoch": 0.8388490211105692,
|
2114 |
+
"grad_norm": 1.0417516231536865,
|
2115 |
+
"learning_rate": 7.799245737966821e-06,
|
2116 |
+
"loss": 1.218,
|
2117 |
+
"step": 1505
|
2118 |
+
},
|
2119 |
+
{
|
2120 |
+
"epoch": 0.8416358949348568,
|
2121 |
+
"grad_norm": 0.9976839423179626,
|
2122 |
+
"learning_rate": 7.540425947248697e-06,
|
2123 |
+
"loss": 1.2297,
|
2124 |
+
"step": 1510
|
2125 |
+
},
|
2126 |
+
{
|
2127 |
+
"epoch": 0.8444227687591445,
|
2128 |
+
"grad_norm": 0.9360842108726501,
|
2129 |
+
"learning_rate": 7.28562283353637e-06,
|
2130 |
+
"loss": 1.2272,
|
2131 |
+
"step": 1515
|
2132 |
+
},
|
2133 |
+
{
|
2134 |
+
"epoch": 0.847209642583432,
|
2135 |
+
"grad_norm": 0.9308948516845703,
|
2136 |
+
"learning_rate": 7.034860501212243e-06,
|
2137 |
+
"loss": 1.228,
|
2138 |
+
"step": 1520
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 0.8499965164077197,
|
2142 |
+
"grad_norm": 0.9917842149734497,
|
2143 |
+
"learning_rate": 6.788162672400583e-06,
|
2144 |
+
"loss": 1.307,
|
2145 |
+
"step": 1525
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 0.8527833902320072,
|
2149 |
+
"grad_norm": 0.9004817605018616,
|
2150 |
+
"learning_rate": 6.5455526847235825e-06,
|
2151 |
+
"loss": 1.236,
|
2152 |
+
"step": 1530
|
2153 |
+
},
|
2154 |
+
{
|
2155 |
+
"epoch": 0.8555702640562949,
|
2156 |
+
"grad_norm": 0.9853699803352356,
|
2157 |
+
"learning_rate": 6.307053489093506e-06,
|
2158 |
+
"loss": 1.2217,
|
2159 |
+
"step": 1535
|
2160 |
+
},
|
2161 |
+
{
|
2162 |
+
"epoch": 0.8583571378805824,
|
2163 |
+
"grad_norm": 0.9549526572227478,
|
2164 |
+
"learning_rate": 6.072687647541553e-06,
|
2165 |
+
"loss": 1.2435,
|
2166 |
+
"step": 1540
|
2167 |
+
},
|
2168 |
+
{
|
2169 |
+
"epoch": 0.8611440117048701,
|
2170 |
+
"grad_norm": 0.9663627743721008,
|
2171 |
+
"learning_rate": 5.842477331083518e-06,
|
2172 |
+
"loss": 1.2514,
|
2173 |
+
"step": 1545
|
2174 |
+
},
|
2175 |
+
{
|
2176 |
+
"epoch": 0.8639308855291576,
|
2177 |
+
"grad_norm": 0.9174144864082336,
|
2178 |
+
"learning_rate": 5.616444317622388e-06,
|
2179 |
+
"loss": 1.1749,
|
2180 |
+
"step": 1550
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 0.8667177593534453,
|
2184 |
+
"grad_norm": 0.9564938545227051,
|
2185 |
+
"learning_rate": 5.394609989888161e-06,
|
2186 |
+
"loss": 1.2476,
|
2187 |
+
"step": 1555
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 0.8695046331777329,
|
2191 |
+
"grad_norm": 1.1256656646728516,
|
2192 |
+
"learning_rate": 5.176995333415019e-06,
|
2193 |
+
"loss": 1.2506,
|
2194 |
+
"step": 1560
|
2195 |
+
},
|
2196 |
+
{
|
2197 |
+
"epoch": 0.8722915070020205,
|
2198 |
+
"grad_norm": 1.0491883754730225,
|
2199 |
+
"learning_rate": 4.963620934556168e-06,
|
2200 |
+
"loss": 1.2388,
|
2201 |
+
"step": 1565
|
2202 |
+
},
|
2203 |
+
{
|
2204 |
+
"epoch": 0.8750783808263081,
|
2205 |
+
"grad_norm": 0.9458408951759338,
|
2206 |
+
"learning_rate": 4.754506978536227e-06,
|
2207 |
+
"loss": 1.2388,
|
2208 |
+
"step": 1570
|
2209 |
+
},
|
2210 |
+
{
|
2211 |
+
"epoch": 0.8778652546505957,
|
2212 |
+
"grad_norm": 0.932964563369751,
|
2213 |
+
"learning_rate": 4.549673247541875e-06,
|
2214 |
+
"loss": 1.2333,
|
2215 |
+
"step": 1575
|
2216 |
+
},
|
2217 |
+
{
|
2218 |
+
"epoch": 0.8806521284748833,
|
2219 |
+
"grad_norm": 0.8364896178245544,
|
2220 |
+
"learning_rate": 4.3491391188503264e-06,
|
2221 |
+
"loss": 1.2139,
|
2222 |
+
"step": 1580
|
2223 |
+
},
|
2224 |
+
{
|
2225 |
+
"epoch": 0.8834390022991709,
|
2226 |
+
"grad_norm": 1.0495798587799072,
|
2227 |
+
"learning_rate": 4.152923562996297e-06,
|
2228 |
+
"loss": 1.1667,
|
2229 |
+
"step": 1585
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 0.8862258761234585,
|
2233 |
+
"grad_norm": 0.9140335321426392,
|
2234 |
+
"learning_rate": 3.961045141977376e-06,
|
2235 |
+
"loss": 1.2402,
|
2236 |
+
"step": 1590
|
2237 |
+
},
|
2238 |
+
{
|
2239 |
+
"epoch": 0.8890127499477462,
|
2240 |
+
"grad_norm": 0.9842175245285034,
|
2241 |
+
"learning_rate": 3.773522007498065e-06,
|
2242 |
+
"loss": 1.2425,
|
2243 |
+
"step": 1595
|
2244 |
+
},
|
2245 |
+
{
|
2246 |
+
"epoch": 0.8917996237720337,
|
2247 |
+
"grad_norm": 0.9036964178085327,
|
2248 |
+
"learning_rate": 3.590371899252659e-06,
|
2249 |
+
"loss": 1.2087,
|
2250 |
+
"step": 1600
|
2251 |
+
},
|
2252 |
+
{
|
2253 |
+
"epoch": 0.8945864975963214,
|
2254 |
+
"grad_norm": 0.9229257106781006,
|
2255 |
+
"learning_rate": 3.4116121432469615e-06,
|
2256 |
+
"loss": 1.2167,
|
2257 |
+
"step": 1605
|
2258 |
+
},
|
2259 |
+
{
|
2260 |
+
"epoch": 0.8973733714206089,
|
2261 |
+
"grad_norm": 0.9462814331054688,
|
2262 |
+
"learning_rate": 3.237259650159402e-06,
|
2263 |
+
"loss": 1.2211,
|
2264 |
+
"step": 1610
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 0.9001602452448966,
|
2268 |
+
"grad_norm": 0.9471161961555481,
|
2269 |
+
"learning_rate": 3.0673309137411564e-06,
|
2270 |
+
"loss": 1.2463,
|
2271 |
+
"step": 1615
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 0.9029471190691841,
|
2275 |
+
"grad_norm": 0.9873669147491455,
|
2276 |
+
"learning_rate": 2.9018420092558786e-06,
|
2277 |
+
"loss": 1.207,
|
2278 |
+
"step": 1620
|
2279 |
+
},
|
2280 |
+
{
|
2281 |
+
"epoch": 0.9057339928934718,
|
2282 |
+
"grad_norm": 1.0254420042037964,
|
2283 |
+
"learning_rate": 2.7408085919590264e-06,
|
2284 |
+
"loss": 1.2891,
|
2285 |
+
"step": 1625
|
2286 |
+
},
|
2287 |
+
{
|
2288 |
+
"epoch": 0.9085208667177593,
|
2289 |
+
"grad_norm": 0.9538567662239075,
|
2290 |
+
"learning_rate": 2.584245895616788e-06,
|
2291 |
+
"loss": 1.2533,
|
2292 |
+
"step": 1630
|
2293 |
+
},
|
2294 |
+
{
|
2295 |
+
"epoch": 0.911307740542047,
|
2296 |
+
"grad_norm": 1.055637240409851,
|
2297 |
+
"learning_rate": 2.4321687310650487e-06,
|
2298 |
+
"loss": 1.2598,
|
2299 |
+
"step": 1635
|
2300 |
+
},
|
2301 |
+
{
|
2302 |
+
"epoch": 0.9140946143663345,
|
2303 |
+
"grad_norm": 0.9872303009033203,
|
2304 |
+
"learning_rate": 2.2845914848082127e-06,
|
2305 |
+
"loss": 1.2765,
|
2306 |
+
"step": 1640
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 0.9168814881906222,
|
2310 |
+
"grad_norm": 1.0598726272583008,
|
2311 |
+
"learning_rate": 2.1415281176583203e-06,
|
2312 |
+
"loss": 1.2305,
|
2313 |
+
"step": 1645
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 0.9196683620149098,
|
2317 |
+
"grad_norm": 0.9400553703308105,
|
2318 |
+
"learning_rate": 2.0029921634142632e-06,
|
2319 |
+
"loss": 1.3019,
|
2320 |
+
"step": 1650
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 0.9224552358391974,
|
2324 |
+
"grad_norm": 0.9695894122123718,
|
2325 |
+
"learning_rate": 1.8689967275815679e-06,
|
2326 |
+
"loss": 1.2685,
|
2327 |
+
"step": 1655
|
2328 |
+
},
|
2329 |
+
{
|
2330 |
+
"epoch": 0.925242109663485,
|
2331 |
+
"grad_norm": 0.9889479875564575,
|
2332 |
+
"learning_rate": 1.7395544861325718e-06,
|
2333 |
+
"loss": 1.2702,
|
2334 |
+
"step": 1660
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 0.9280289834877726,
|
2338 |
+
"grad_norm": 0.9385488033294678,
|
2339 |
+
"learning_rate": 1.614677684307264e-06,
|
2340 |
+
"loss": 1.2255,
|
2341 |
+
"step": 1665
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"epoch": 0.9308158573120602,
|
2345 |
+
"grad_norm": 0.9816272258758545,
|
2346 |
+
"learning_rate": 1.494378135454938e-06,
|
2347 |
+
"loss": 1.2531,
|
2348 |
+
"step": 1670
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 0.9336027311363478,
|
2352 |
+
"grad_norm": 0.9538016319274902,
|
2353 |
+
"learning_rate": 1.3786672199165962e-06,
|
2354 |
+
"loss": 1.2487,
|
2355 |
+
"step": 1675
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 0.9363896049606354,
|
2359 |
+
"grad_norm": 0.95050448179245,
|
2360 |
+
"learning_rate": 1.2675558839483848e-06,
|
2361 |
+
"loss": 1.1962,
|
2362 |
+
"step": 1680
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"epoch": 0.939176478784923,
|
2366 |
+
"grad_norm": 0.98070228099823,
|
2367 |
+
"learning_rate": 1.1610546386860988e-06,
|
2368 |
+
"loss": 1.2306,
|
2369 |
+
"step": 1685
|
2370 |
+
},
|
2371 |
+
{
|
2372 |
+
"epoch": 0.9419633526092106,
|
2373 |
+
"grad_norm": 1.0162360668182373,
|
2374 |
+
"learning_rate": 1.0591735591507946e-06,
|
2375 |
+
"loss": 1.2259,
|
2376 |
+
"step": 1690
|
2377 |
+
},
|
2378 |
+
{
|
2379 |
+
"epoch": 0.9447502264334983,
|
2380 |
+
"grad_norm": 0.997144341468811,
|
2381 |
+
"learning_rate": 9.619222832957243e-07,
|
2382 |
+
"loss": 1.2142,
|
2383 |
+
"step": 1695
|
2384 |
+
},
|
2385 |
+
{
|
2386 |
+
"epoch": 0.9475371002577858,
|
2387 |
+
"grad_norm": 0.9727258086204529,
|
2388 |
+
"learning_rate": 8.693100110945484e-07,
|
2389 |
+
"loss": 1.2123,
|
2390 |
+
"step": 1700
|
2391 |
+
},
|
2392 |
+
{
|
2393 |
+
"epoch": 0.9503239740820735,
|
2394 |
+
"grad_norm": 0.8900772929191589,
|
2395 |
+
"learning_rate": 7.813455036710715e-07,
|
2396 |
+
"loss": 1.1853,
|
2397 |
+
"step": 1705
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 0.953110847906361,
|
2401 |
+
"grad_norm": 0.9536607265472412,
|
2402 |
+
"learning_rate": 6.980370824703763e-07,
|
2403 |
+
"loss": 1.2617,
|
2404 |
+
"step": 1710
|
2405 |
+
},
|
2406 |
+
{
|
2407 |
+
"epoch": 0.9558977217306487,
|
2408 |
+
"grad_norm": 1.0575697422027588,
|
2409 |
+
"learning_rate": 6.193926284716711e-07,
|
2410 |
+
"loss": 1.1969,
|
2411 |
+
"step": 1715
|
2412 |
+
},
|
2413 |
+
{
|
2414 |
+
"epoch": 0.9586845955549362,
|
2415 |
+
"grad_norm": 0.9426103234291077,
|
2416 |
+
"learning_rate": 5.454195814427021e-07,
|
2417 |
+
"loss": 1.3009,
|
2418 |
+
"step": 1720
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"epoch": 0.9614714693792239,
|
2422 |
+
"grad_norm": 1.020992636680603,
|
2423 |
+
"learning_rate": 4.76124939235989e-07,
|
2424 |
+
"loss": 1.2011,
|
2425 |
+
"step": 1725
|
2426 |
+
},
|
2427 |
+
{
|
2428 |
+
"epoch": 0.9642583432035114,
|
2429 |
+
"grad_norm": 0.9522945284843445,
|
2430 |
+
"learning_rate": 4.1151525712680996e-07,
|
2431 |
+
"loss": 1.1584,
|
2432 |
+
"step": 1730
|
2433 |
+
},
|
2434 |
+
{
|
2435 |
+
"epoch": 0.9670452170277991,
|
2436 |
+
"grad_norm": 1.105689525604248,
|
2437 |
+
"learning_rate": 3.515966471930643e-07,
|
2438 |
+
"loss": 1.2898,
|
2439 |
+
"step": 1735
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 0.9698320908520867,
|
2443 |
+
"grad_norm": 1.0255939960479736,
|
2444 |
+
"learning_rate": 2.963747777370907e-07,
|
2445 |
+
"loss": 1.2634,
|
2446 |
+
"step": 1740
|
2447 |
+
},
|
2448 |
+
{
|
2449 |
+
"epoch": 0.9726189646763743,
|
2450 |
+
"grad_norm": 1.0123835802078247,
|
2451 |
+
"learning_rate": 2.458548727494292e-07,
|
2452 |
+
"loss": 1.1778,
|
2453 |
+
"step": 1745
|
2454 |
+
},
|
2455 |
+
{
|
2456 |
+
"epoch": 0.9754058385006619,
|
2457 |
+
"grad_norm": 0.9710216522216797,
|
2458 |
+
"learning_rate": 2.0004171141464467e-07,
|
2459 |
+
"loss": 1.2408,
|
2460 |
+
"step": 1750
|
2461 |
+
},
|
2462 |
+
{
|
2463 |
+
"epoch": 0.9781927123249495,
|
2464 |
+
"grad_norm": 1.0030288696289062,
|
2465 |
+
"learning_rate": 1.589396276591937e-07,
|
2466 |
+
"loss": 1.2336,
|
2467 |
+
"step": 1755
|
2468 |
+
},
|
2469 |
+
{
|
2470 |
+
"epoch": 0.9809795861492371,
|
2471 |
+
"grad_norm": 0.9503644108772278,
|
2472 |
+
"learning_rate": 1.225525097414637e-07,
|
2473 |
+
"loss": 1.1797,
|
2474 |
+
"step": 1760
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 0.9837664599735247,
|
2478 |
+
"grad_norm": 1.007887840270996,
|
2479 |
+
"learning_rate": 9.088379988392848e-08,
|
2480 |
+
"loss": 1.2185,
|
2481 |
+
"step": 1765
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 0.9865533337978123,
|
2485 |
+
"grad_norm": 1.062198281288147,
|
2486 |
+
"learning_rate": 6.393649394749734e-08,
|
2487 |
+
"loss": 1.2139,
|
2488 |
+
"step": 1770
|
2489 |
+
},
|
2490 |
+
{
|
2491 |
+
"epoch": 0.9893402076221,
|
2492 |
+
"grad_norm": 1.0820635557174683,
|
2493 |
+
"learning_rate": 4.171314114815306e-08,
|
2494 |
+
"loss": 1.2726,
|
2495 |
+
"step": 1775
|
2496 |
+
},
|
2497 |
+
{
|
2498 |
+
"epoch": 0.9921270814463875,
|
2499 |
+
"grad_norm": 0.97090744972229,
|
2500 |
+
"learning_rate": 2.4215843815733607e-08,
|
2501 |
+
"loss": 1.1734,
|
2502 |
+
"step": 1780
|
2503 |
+
},
|
2504 |
+
{
|
2505 |
+
"epoch": 0.9949139552706752,
|
2506 |
+
"grad_norm": 0.9105931520462036,
|
2507 |
+
"learning_rate": 1.1446257195119048e-08,
|
2508 |
+
"loss": 1.2729,
|
2509 |
+
"step": 1785
|
2510 |
+
},
|
2511 |
+
{
|
2512 |
+
"epoch": 0.9977008290949627,
|
2513 |
+
"grad_norm": 0.9542015790939331,
|
2514 |
+
"learning_rate": 3.4055892895901167e-09,
|
2515 |
+
"loss": 1.2552,
|
2516 |
+
"step": 1790
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 1.0,
|
2520 |
+
"grad_norm": 3.9945850372314453,
|
2521 |
+
"learning_rate": 9.460074656963969e-11,
|
2522 |
+
"loss": 1.3228,
|
2523 |
+
"step": 1795
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 1.0,
|
2527 |
+
"step": 1795,
|
2528 |
+
"total_flos": 1.3861725429517517e+17,
|
2529 |
+
"train_loss": 0.0,
|
2530 |
+
"train_runtime": 0.8982,
|
2531 |
+
"train_samples_per_second": 15978.88,
|
2532 |
+
"train_steps_per_second": 1998.334
|
2533 |
+
}
|
2534 |
+
],
|
2535 |
+
"logging_steps": 5,
|
2536 |
+
"max_steps": 1795,
|
2537 |
+
"num_input_tokens_seen": 0,
|
2538 |
+
"num_train_epochs": 1,
|
2539 |
+
"save_steps": 500,
|
2540 |
+
"stateful_callbacks": {
|
2541 |
+
"TrainerControl": {
|
2542 |
+
"args": {
|
2543 |
+
"should_epoch_stop": false,
|
2544 |
+
"should_evaluate": false,
|
2545 |
+
"should_log": false,
|
2546 |
+
"should_save": true,
|
2547 |
+
"should_training_stop": true
|
2548 |
+
},
|
2549 |
+
"attributes": {}
|
2550 |
+
}
|
2551 |
+
},
|
2552 |
+
"total_flos": 1.3861725429517517e+17,
|
2553 |
+
"train_batch_size": 1,
|
2554 |
+
"trial_name": null,
|
2555 |
+
"trial_params": null
|
2556 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f01c03272f24702ca866c8ac0dbad570816d304cbcffb07cb327b683b92f05a
|
3 |
+
size 6225
|
training_loss.png
ADDED
![]() |