End of training
Browse files- .gitattributes +1 -0
- README.md +59 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- generation_config.json +11 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2066 -0
- trainer_state.json +3381 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: unsloth/llama-3.2-3b-bnb-4bit
|
3 |
+
library_name: transformers
|
4 |
+
model_name: LoL_Build-Llama3B
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
- unsloth
|
8 |
+
- trl
|
9 |
+
- sft
|
10 |
+
licence: license
|
11 |
+
---
|
12 |
+
|
13 |
+
# Model Card for LoL_Build-Llama3B
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [unsloth/llama-3.2-3b-bnb-4bit](https://huggingface.co/unsloth/llama-3.2-3b-bnb-4bit).
|
16 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
17 |
+
|
18 |
+
## Quick start
|
19 |
+
|
20 |
+
```python
|
21 |
+
from transformers import pipeline
|
22 |
+
|
23 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
24 |
+
generator = pipeline("text-generation", model="HatimF/LoL_Build-Llama3B", device="cuda")
|
25 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
26 |
+
print(output["generated_text"])
|
27 |
+
```
|
28 |
+
|
29 |
+
## Training procedure
|
30 |
+
|
31 |
+
|
32 |
+
|
33 |
+
|
34 |
+
This model was trained with SFT.
|
35 |
+
|
36 |
+
### Framework versions
|
37 |
+
|
38 |
+
- TRL: 0.15.2
|
39 |
+
- Transformers: 4.51.3
|
40 |
+
- Pytorch: 2.6.0
|
41 |
+
- Datasets: 3.5.0
|
42 |
+
- Tokenizers: 0.21.1
|
43 |
+
|
44 |
+
## Citations
|
45 |
+
|
46 |
+
|
47 |
+
|
48 |
+
Cite TRL as:
|
49 |
+
|
50 |
+
```bibtex
|
51 |
+
@misc{vonwerra2022trl,
|
52 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
53 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
54 |
+
year = 2020,
|
55 |
+
journal = {GitHub repository},
|
56 |
+
publisher = {GitHub},
|
57 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
58 |
+
}
|
59 |
+
```
|
adapter_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/llama-3.2-3b-bnb-4bit",
|
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": 32,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0.05,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": null,
|
22 |
+
"peft_type": "LORA",
|
23 |
+
"r": 16,
|
24 |
+
"rank_pattern": {},
|
25 |
+
"revision": null,
|
26 |
+
"target_modules": [
|
27 |
+
"o_proj",
|
28 |
+
"v_proj",
|
29 |
+
"down_proj",
|
30 |
+
"q_proj",
|
31 |
+
"up_proj",
|
32 |
+
"gate_proj",
|
33 |
+
"k_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:fb860557877b89ec4a77e2080ddfb5ea42f36bbb2d7b3272348bf6c21ba3e0a3
|
3 |
+
size 48680136
|
generation_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 128000,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 128001,
|
6 |
+
"max_length": 131072,
|
7 |
+
"pad_token_id": 128004,
|
8 |
+
"temperature": 0.6,
|
9 |
+
"top_p": 0.9,
|
10 |
+
"transformers_version": "4.51.3"
|
11 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end_of_text|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|finetune_right_pad_id|>",
|
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 sha256:9c85066e7642934ed09b44155e6566b0b5dab2637fb9433439ba5c9c7f8b50d3
|
3 |
+
size 17210018
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2066 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"128000": {
|
5 |
+
"content": "<|begin_of_text|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"128001": {
|
13 |
+
"content": "<|end_of_text|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"128002": {
|
21 |
+
"content": "<|reserved_special_token_0|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"128003": {
|
29 |
+
"content": "<|reserved_special_token_1|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"128004": {
|
37 |
+
"content": "<|finetune_right_pad_id|>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"128005": {
|
45 |
+
"content": "<|reserved_special_token_2|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"128006": {
|
53 |
+
"content": "<|start_header_id|>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"128007": {
|
61 |
+
"content": "<|end_header_id|>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"128008": {
|
69 |
+
"content": "<|eom_id|>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"128009": {
|
77 |
+
"content": "<|eot_id|>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"128010": {
|
85 |
+
"content": "<|python_tag|>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"128011": {
|
93 |
+
"content": "<|reserved_special_token_3|>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"128012": {
|
101 |
+
"content": "<|reserved_special_token_4|>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"128013": {
|
109 |
+
"content": "<|reserved_special_token_5|>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"128014": {
|
117 |
+
"content": "<|reserved_special_token_6|>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"128015": {
|
125 |
+
"content": "<|reserved_special_token_7|>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"128016": {
|
133 |
+
"content": "<|reserved_special_token_8|>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"128017": {
|
141 |
+
"content": "<|reserved_special_token_9|>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"128018": {
|
149 |
+
"content": "<|reserved_special_token_10|>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
},
|
156 |
+
"128019": {
|
157 |
+
"content": "<|reserved_special_token_11|>",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
"128020": {
|
165 |
+
"content": "<|reserved_special_token_12|>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": true
|
171 |
+
},
|
172 |
+
"128021": {
|
173 |
+
"content": "<|reserved_special_token_13|>",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": true
|
179 |
+
},
|
180 |
+
"128022": {
|
181 |
+
"content": "<|reserved_special_token_14|>",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": true
|
187 |
+
},
|
188 |
+
"128023": {
|
189 |
+
"content": "<|reserved_special_token_15|>",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": true
|
195 |
+
},
|
196 |
+
"128024": {
|
197 |
+
"content": "<|reserved_special_token_16|>",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
"128025": {
|
205 |
+
"content": "<|reserved_special_token_17|>",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
},
|
212 |
+
"128026": {
|
213 |
+
"content": "<|reserved_special_token_18|>",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": true
|
219 |
+
},
|
220 |
+
"128027": {
|
221 |
+
"content": "<|reserved_special_token_19|>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
+
},
|
228 |
+
"128028": {
|
229 |
+
"content": "<|reserved_special_token_20|>",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": true
|
235 |
+
},
|
236 |
+
"128029": {
|
237 |
+
"content": "<|reserved_special_token_21|>",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": true
|
243 |
+
},
|
244 |
+
"128030": {
|
245 |
+
"content": "<|reserved_special_token_22|>",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": true
|
251 |
+
},
|
252 |
+
"128031": {
|
253 |
+
"content": "<|reserved_special_token_23|>",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": true
|
259 |
+
},
|
260 |
+
"128032": {
|
261 |
+
"content": "<|reserved_special_token_24|>",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": true
|
267 |
+
},
|
268 |
+
"128033": {
|
269 |
+
"content": "<|reserved_special_token_25|>",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": false,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": true
|
275 |
+
},
|
276 |
+
"128034": {
|
277 |
+
"content": "<|reserved_special_token_26|>",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": true
|
283 |
+
},
|
284 |
+
"128035": {
|
285 |
+
"content": "<|reserved_special_token_27|>",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": false,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": true
|
291 |
+
},
|
292 |
+
"128036": {
|
293 |
+
"content": "<|reserved_special_token_28|>",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": false,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": true
|
299 |
+
},
|
300 |
+
"128037": {
|
301 |
+
"content": "<|reserved_special_token_29|>",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": false,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": true
|
307 |
+
},
|
308 |
+
"128038": {
|
309 |
+
"content": "<|reserved_special_token_30|>",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": false,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": true
|
315 |
+
},
|
316 |
+
"128039": {
|
317 |
+
"content": "<|reserved_special_token_31|>",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": true
|
323 |
+
},
|
324 |
+
"128040": {
|
325 |
+
"content": "<|reserved_special_token_32|>",
|
326 |
+
"lstrip": false,
|
327 |
+
"normalized": false,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": true
|
331 |
+
},
|
332 |
+
"128041": {
|
333 |
+
"content": "<|reserved_special_token_33|>",
|
334 |
+
"lstrip": false,
|
335 |
+
"normalized": false,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false,
|
338 |
+
"special": true
|
339 |
+
},
|
340 |
+
"128042": {
|
341 |
+
"content": "<|reserved_special_token_34|>",
|
342 |
+
"lstrip": false,
|
343 |
+
"normalized": false,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false,
|
346 |
+
"special": true
|
347 |
+
},
|
348 |
+
"128043": {
|
349 |
+
"content": "<|reserved_special_token_35|>",
|
350 |
+
"lstrip": false,
|
351 |
+
"normalized": false,
|
352 |
+
"rstrip": false,
|
353 |
+
"single_word": false,
|
354 |
+
"special": true
|
355 |
+
},
|
356 |
+
"128044": {
|
357 |
+
"content": "<|reserved_special_token_36|>",
|
358 |
+
"lstrip": false,
|
359 |
+
"normalized": false,
|
360 |
+
"rstrip": false,
|
361 |
+
"single_word": false,
|
362 |
+
"special": true
|
363 |
+
},
|
364 |
+
"128045": {
|
365 |
+
"content": "<|reserved_special_token_37|>",
|
366 |
+
"lstrip": false,
|
367 |
+
"normalized": false,
|
368 |
+
"rstrip": false,
|
369 |
+
"single_word": false,
|
370 |
+
"special": true
|
371 |
+
},
|
372 |
+
"128046": {
|
373 |
+
"content": "<|reserved_special_token_38|>",
|
374 |
+
"lstrip": false,
|
375 |
+
"normalized": false,
|
376 |
+
"rstrip": false,
|
377 |
+
"single_word": false,
|
378 |
+
"special": true
|
379 |
+
},
|
380 |
+
"128047": {
|
381 |
+
"content": "<|reserved_special_token_39|>",
|
382 |
+
"lstrip": false,
|
383 |
+
"normalized": false,
|
384 |
+
"rstrip": false,
|
385 |
+
"single_word": false,
|
386 |
+
"special": true
|
387 |
+
},
|
388 |
+
"128048": {
|
389 |
+
"content": "<|reserved_special_token_40|>",
|
390 |
+
"lstrip": false,
|
391 |
+
"normalized": false,
|
392 |
+
"rstrip": false,
|
393 |
+
"single_word": false,
|
394 |
+
"special": true
|
395 |
+
},
|
396 |
+
"128049": {
|
397 |
+
"content": "<|reserved_special_token_41|>",
|
398 |
+
"lstrip": false,
|
399 |
+
"normalized": false,
|
400 |
+
"rstrip": false,
|
401 |
+
"single_word": false,
|
402 |
+
"special": true
|
403 |
+
},
|
404 |
+
"128050": {
|
405 |
+
"content": "<|reserved_special_token_42|>",
|
406 |
+
"lstrip": false,
|
407 |
+
"normalized": false,
|
408 |
+
"rstrip": false,
|
409 |
+
"single_word": false,
|
410 |
+
"special": true
|
411 |
+
},
|
412 |
+
"128051": {
|
413 |
+
"content": "<|reserved_special_token_43|>",
|
414 |
+
"lstrip": false,
|
415 |
+
"normalized": false,
|
416 |
+
"rstrip": false,
|
417 |
+
"single_word": false,
|
418 |
+
"special": true
|
419 |
+
},
|
420 |
+
"128052": {
|
421 |
+
"content": "<|reserved_special_token_44|>",
|
422 |
+
"lstrip": false,
|
423 |
+
"normalized": false,
|
424 |
+
"rstrip": false,
|
425 |
+
"single_word": false,
|
426 |
+
"special": true
|
427 |
+
},
|
428 |
+
"128053": {
|
429 |
+
"content": "<|reserved_special_token_45|>",
|
430 |
+
"lstrip": false,
|
431 |
+
"normalized": false,
|
432 |
+
"rstrip": false,
|
433 |
+
"single_word": false,
|
434 |
+
"special": true
|
435 |
+
},
|
436 |
+
"128054": {
|
437 |
+
"content": "<|reserved_special_token_46|>",
|
438 |
+
"lstrip": false,
|
439 |
+
"normalized": false,
|
440 |
+
"rstrip": false,
|
441 |
+
"single_word": false,
|
442 |
+
"special": true
|
443 |
+
},
|
444 |
+
"128055": {
|
445 |
+
"content": "<|reserved_special_token_47|>",
|
446 |
+
"lstrip": false,
|
447 |
+
"normalized": false,
|
448 |
+
"rstrip": false,
|
449 |
+
"single_word": false,
|
450 |
+
"special": true
|
451 |
+
},
|
452 |
+
"128056": {
|
453 |
+
"content": "<|reserved_special_token_48|>",
|
454 |
+
"lstrip": false,
|
455 |
+
"normalized": false,
|
456 |
+
"rstrip": false,
|
457 |
+
"single_word": false,
|
458 |
+
"special": true
|
459 |
+
},
|
460 |
+
"128057": {
|
461 |
+
"content": "<|reserved_special_token_49|>",
|
462 |
+
"lstrip": false,
|
463 |
+
"normalized": false,
|
464 |
+
"rstrip": false,
|
465 |
+
"single_word": false,
|
466 |
+
"special": true
|
467 |
+
},
|
468 |
+
"128058": {
|
469 |
+
"content": "<|reserved_special_token_50|>",
|
470 |
+
"lstrip": false,
|
471 |
+
"normalized": false,
|
472 |
+
"rstrip": false,
|
473 |
+
"single_word": false,
|
474 |
+
"special": true
|
475 |
+
},
|
476 |
+
"128059": {
|
477 |
+
"content": "<|reserved_special_token_51|>",
|
478 |
+
"lstrip": false,
|
479 |
+
"normalized": false,
|
480 |
+
"rstrip": false,
|
481 |
+
"single_word": false,
|
482 |
+
"special": true
|
483 |
+
},
|
484 |
+
"128060": {
|
485 |
+
"content": "<|reserved_special_token_52|>",
|
486 |
+
"lstrip": false,
|
487 |
+
"normalized": false,
|
488 |
+
"rstrip": false,
|
489 |
+
"single_word": false,
|
490 |
+
"special": true
|
491 |
+
},
|
492 |
+
"128061": {
|
493 |
+
"content": "<|reserved_special_token_53|>",
|
494 |
+
"lstrip": false,
|
495 |
+
"normalized": false,
|
496 |
+
"rstrip": false,
|
497 |
+
"single_word": false,
|
498 |
+
"special": true
|
499 |
+
},
|
500 |
+
"128062": {
|
501 |
+
"content": "<|reserved_special_token_54|>",
|
502 |
+
"lstrip": false,
|
503 |
+
"normalized": false,
|
504 |
+
"rstrip": false,
|
505 |
+
"single_word": false,
|
506 |
+
"special": true
|
507 |
+
},
|
508 |
+
"128063": {
|
509 |
+
"content": "<|reserved_special_token_55|>",
|
510 |
+
"lstrip": false,
|
511 |
+
"normalized": false,
|
512 |
+
"rstrip": false,
|
513 |
+
"single_word": false,
|
514 |
+
"special": true
|
515 |
+
},
|
516 |
+
"128064": {
|
517 |
+
"content": "<|reserved_special_token_56|>",
|
518 |
+
"lstrip": false,
|
519 |
+
"normalized": false,
|
520 |
+
"rstrip": false,
|
521 |
+
"single_word": false,
|
522 |
+
"special": true
|
523 |
+
},
|
524 |
+
"128065": {
|
525 |
+
"content": "<|reserved_special_token_57|>",
|
526 |
+
"lstrip": false,
|
527 |
+
"normalized": false,
|
528 |
+
"rstrip": false,
|
529 |
+
"single_word": false,
|
530 |
+
"special": true
|
531 |
+
},
|
532 |
+
"128066": {
|
533 |
+
"content": "<|reserved_special_token_58|>",
|
534 |
+
"lstrip": false,
|
535 |
+
"normalized": false,
|
536 |
+
"rstrip": false,
|
537 |
+
"single_word": false,
|
538 |
+
"special": true
|
539 |
+
},
|
540 |
+
"128067": {
|
541 |
+
"content": "<|reserved_special_token_59|>",
|
542 |
+
"lstrip": false,
|
543 |
+
"normalized": false,
|
544 |
+
"rstrip": false,
|
545 |
+
"single_word": false,
|
546 |
+
"special": true
|
547 |
+
},
|
548 |
+
"128068": {
|
549 |
+
"content": "<|reserved_special_token_60|>",
|
550 |
+
"lstrip": false,
|
551 |
+
"normalized": false,
|
552 |
+
"rstrip": false,
|
553 |
+
"single_word": false,
|
554 |
+
"special": true
|
555 |
+
},
|
556 |
+
"128069": {
|
557 |
+
"content": "<|reserved_special_token_61|>",
|
558 |
+
"lstrip": false,
|
559 |
+
"normalized": false,
|
560 |
+
"rstrip": false,
|
561 |
+
"single_word": false,
|
562 |
+
"special": true
|
563 |
+
},
|
564 |
+
"128070": {
|
565 |
+
"content": "<|reserved_special_token_62|>",
|
566 |
+
"lstrip": false,
|
567 |
+
"normalized": false,
|
568 |
+
"rstrip": false,
|
569 |
+
"single_word": false,
|
570 |
+
"special": true
|
571 |
+
},
|
572 |
+
"128071": {
|
573 |
+
"content": "<|reserved_special_token_63|>",
|
574 |
+
"lstrip": false,
|
575 |
+
"normalized": false,
|
576 |
+
"rstrip": false,
|
577 |
+
"single_word": false,
|
578 |
+
"special": true
|
579 |
+
},
|
580 |
+
"128072": {
|
581 |
+
"content": "<|reserved_special_token_64|>",
|
582 |
+
"lstrip": false,
|
583 |
+
"normalized": false,
|
584 |
+
"rstrip": false,
|
585 |
+
"single_word": false,
|
586 |
+
"special": true
|
587 |
+
},
|
588 |
+
"128073": {
|
589 |
+
"content": "<|reserved_special_token_65|>",
|
590 |
+
"lstrip": false,
|
591 |
+
"normalized": false,
|
592 |
+
"rstrip": false,
|
593 |
+
"single_word": false,
|
594 |
+
"special": true
|
595 |
+
},
|
596 |
+
"128074": {
|
597 |
+
"content": "<|reserved_special_token_66|>",
|
598 |
+
"lstrip": false,
|
599 |
+
"normalized": false,
|
600 |
+
"rstrip": false,
|
601 |
+
"single_word": false,
|
602 |
+
"special": true
|
603 |
+
},
|
604 |
+
"128075": {
|
605 |
+
"content": "<|reserved_special_token_67|>",
|
606 |
+
"lstrip": false,
|
607 |
+
"normalized": false,
|
608 |
+
"rstrip": false,
|
609 |
+
"single_word": false,
|
610 |
+
"special": true
|
611 |
+
},
|
612 |
+
"128076": {
|
613 |
+
"content": "<|reserved_special_token_68|>",
|
614 |
+
"lstrip": false,
|
615 |
+
"normalized": false,
|
616 |
+
"rstrip": false,
|
617 |
+
"single_word": false,
|
618 |
+
"special": true
|
619 |
+
},
|
620 |
+
"128077": {
|
621 |
+
"content": "<|reserved_special_token_69|>",
|
622 |
+
"lstrip": false,
|
623 |
+
"normalized": false,
|
624 |
+
"rstrip": false,
|
625 |
+
"single_word": false,
|
626 |
+
"special": true
|
627 |
+
},
|
628 |
+
"128078": {
|
629 |
+
"content": "<|reserved_special_token_70|>",
|
630 |
+
"lstrip": false,
|
631 |
+
"normalized": false,
|
632 |
+
"rstrip": false,
|
633 |
+
"single_word": false,
|
634 |
+
"special": true
|
635 |
+
},
|
636 |
+
"128079": {
|
637 |
+
"content": "<|reserved_special_token_71|>",
|
638 |
+
"lstrip": false,
|
639 |
+
"normalized": false,
|
640 |
+
"rstrip": false,
|
641 |
+
"single_word": false,
|
642 |
+
"special": true
|
643 |
+
},
|
644 |
+
"128080": {
|
645 |
+
"content": "<|reserved_special_token_72|>",
|
646 |
+
"lstrip": false,
|
647 |
+
"normalized": false,
|
648 |
+
"rstrip": false,
|
649 |
+
"single_word": false,
|
650 |
+
"special": true
|
651 |
+
},
|
652 |
+
"128081": {
|
653 |
+
"content": "<|reserved_special_token_73|>",
|
654 |
+
"lstrip": false,
|
655 |
+
"normalized": false,
|
656 |
+
"rstrip": false,
|
657 |
+
"single_word": false,
|
658 |
+
"special": true
|
659 |
+
},
|
660 |
+
"128082": {
|
661 |
+
"content": "<|reserved_special_token_74|>",
|
662 |
+
"lstrip": false,
|
663 |
+
"normalized": false,
|
664 |
+
"rstrip": false,
|
665 |
+
"single_word": false,
|
666 |
+
"special": true
|
667 |
+
},
|
668 |
+
"128083": {
|
669 |
+
"content": "<|reserved_special_token_75|>",
|
670 |
+
"lstrip": false,
|
671 |
+
"normalized": false,
|
672 |
+
"rstrip": false,
|
673 |
+
"single_word": false,
|
674 |
+
"special": true
|
675 |
+
},
|
676 |
+
"128084": {
|
677 |
+
"content": "<|reserved_special_token_76|>",
|
678 |
+
"lstrip": false,
|
679 |
+
"normalized": false,
|
680 |
+
"rstrip": false,
|
681 |
+
"single_word": false,
|
682 |
+
"special": true
|
683 |
+
},
|
684 |
+
"128085": {
|
685 |
+
"content": "<|reserved_special_token_77|>",
|
686 |
+
"lstrip": false,
|
687 |
+
"normalized": false,
|
688 |
+
"rstrip": false,
|
689 |
+
"single_word": false,
|
690 |
+
"special": true
|
691 |
+
},
|
692 |
+
"128086": {
|
693 |
+
"content": "<|reserved_special_token_78|>",
|
694 |
+
"lstrip": false,
|
695 |
+
"normalized": false,
|
696 |
+
"rstrip": false,
|
697 |
+
"single_word": false,
|
698 |
+
"special": true
|
699 |
+
},
|
700 |
+
"128087": {
|
701 |
+
"content": "<|reserved_special_token_79|>",
|
702 |
+
"lstrip": false,
|
703 |
+
"normalized": false,
|
704 |
+
"rstrip": false,
|
705 |
+
"single_word": false,
|
706 |
+
"special": true
|
707 |
+
},
|
708 |
+
"128088": {
|
709 |
+
"content": "<|reserved_special_token_80|>",
|
710 |
+
"lstrip": false,
|
711 |
+
"normalized": false,
|
712 |
+
"rstrip": false,
|
713 |
+
"single_word": false,
|
714 |
+
"special": true
|
715 |
+
},
|
716 |
+
"128089": {
|
717 |
+
"content": "<|reserved_special_token_81|>",
|
718 |
+
"lstrip": false,
|
719 |
+
"normalized": false,
|
720 |
+
"rstrip": false,
|
721 |
+
"single_word": false,
|
722 |
+
"special": true
|
723 |
+
},
|
724 |
+
"128090": {
|
725 |
+
"content": "<|reserved_special_token_82|>",
|
726 |
+
"lstrip": false,
|
727 |
+
"normalized": false,
|
728 |
+
"rstrip": false,
|
729 |
+
"single_word": false,
|
730 |
+
"special": true
|
731 |
+
},
|
732 |
+
"128091": {
|
733 |
+
"content": "<|reserved_special_token_83|>",
|
734 |
+
"lstrip": false,
|
735 |
+
"normalized": false,
|
736 |
+
"rstrip": false,
|
737 |
+
"single_word": false,
|
738 |
+
"special": true
|
739 |
+
},
|
740 |
+
"128092": {
|
741 |
+
"content": "<|reserved_special_token_84|>",
|
742 |
+
"lstrip": false,
|
743 |
+
"normalized": false,
|
744 |
+
"rstrip": false,
|
745 |
+
"single_word": false,
|
746 |
+
"special": true
|
747 |
+
},
|
748 |
+
"128093": {
|
749 |
+
"content": "<|reserved_special_token_85|>",
|
750 |
+
"lstrip": false,
|
751 |
+
"normalized": false,
|
752 |
+
"rstrip": false,
|
753 |
+
"single_word": false,
|
754 |
+
"special": true
|
755 |
+
},
|
756 |
+
"128094": {
|
757 |
+
"content": "<|reserved_special_token_86|>",
|
758 |
+
"lstrip": false,
|
759 |
+
"normalized": false,
|
760 |
+
"rstrip": false,
|
761 |
+
"single_word": false,
|
762 |
+
"special": true
|
763 |
+
},
|
764 |
+
"128095": {
|
765 |
+
"content": "<|reserved_special_token_87|>",
|
766 |
+
"lstrip": false,
|
767 |
+
"normalized": false,
|
768 |
+
"rstrip": false,
|
769 |
+
"single_word": false,
|
770 |
+
"special": true
|
771 |
+
},
|
772 |
+
"128096": {
|
773 |
+
"content": "<|reserved_special_token_88|>",
|
774 |
+
"lstrip": false,
|
775 |
+
"normalized": false,
|
776 |
+
"rstrip": false,
|
777 |
+
"single_word": false,
|
778 |
+
"special": true
|
779 |
+
},
|
780 |
+
"128097": {
|
781 |
+
"content": "<|reserved_special_token_89|>",
|
782 |
+
"lstrip": false,
|
783 |
+
"normalized": false,
|
784 |
+
"rstrip": false,
|
785 |
+
"single_word": false,
|
786 |
+
"special": true
|
787 |
+
},
|
788 |
+
"128098": {
|
789 |
+
"content": "<|reserved_special_token_90|>",
|
790 |
+
"lstrip": false,
|
791 |
+
"normalized": false,
|
792 |
+
"rstrip": false,
|
793 |
+
"single_word": false,
|
794 |
+
"special": true
|
795 |
+
},
|
796 |
+
"128099": {
|
797 |
+
"content": "<|reserved_special_token_91|>",
|
798 |
+
"lstrip": false,
|
799 |
+
"normalized": false,
|
800 |
+
"rstrip": false,
|
801 |
+
"single_word": false,
|
802 |
+
"special": true
|
803 |
+
},
|
804 |
+
"128100": {
|
805 |
+
"content": "<|reserved_special_token_92|>",
|
806 |
+
"lstrip": false,
|
807 |
+
"normalized": false,
|
808 |
+
"rstrip": false,
|
809 |
+
"single_word": false,
|
810 |
+
"special": true
|
811 |
+
},
|
812 |
+
"128101": {
|
813 |
+
"content": "<|reserved_special_token_93|>",
|
814 |
+
"lstrip": false,
|
815 |
+
"normalized": false,
|
816 |
+
"rstrip": false,
|
817 |
+
"single_word": false,
|
818 |
+
"special": true
|
819 |
+
},
|
820 |
+
"128102": {
|
821 |
+
"content": "<|reserved_special_token_94|>",
|
822 |
+
"lstrip": false,
|
823 |
+
"normalized": false,
|
824 |
+
"rstrip": false,
|
825 |
+
"single_word": false,
|
826 |
+
"special": true
|
827 |
+
},
|
828 |
+
"128103": {
|
829 |
+
"content": "<|reserved_special_token_95|>",
|
830 |
+
"lstrip": false,
|
831 |
+
"normalized": false,
|
832 |
+
"rstrip": false,
|
833 |
+
"single_word": false,
|
834 |
+
"special": true
|
835 |
+
},
|
836 |
+
"128104": {
|
837 |
+
"content": "<|reserved_special_token_96|>",
|
838 |
+
"lstrip": false,
|
839 |
+
"normalized": false,
|
840 |
+
"rstrip": false,
|
841 |
+
"single_word": false,
|
842 |
+
"special": true
|
843 |
+
},
|
844 |
+
"128105": {
|
845 |
+
"content": "<|reserved_special_token_97|>",
|
846 |
+
"lstrip": false,
|
847 |
+
"normalized": false,
|
848 |
+
"rstrip": false,
|
849 |
+
"single_word": false,
|
850 |
+
"special": true
|
851 |
+
},
|
852 |
+
"128106": {
|
853 |
+
"content": "<|reserved_special_token_98|>",
|
854 |
+
"lstrip": false,
|
855 |
+
"normalized": false,
|
856 |
+
"rstrip": false,
|
857 |
+
"single_word": false,
|
858 |
+
"special": true
|
859 |
+
},
|
860 |
+
"128107": {
|
861 |
+
"content": "<|reserved_special_token_99|>",
|
862 |
+
"lstrip": false,
|
863 |
+
"normalized": false,
|
864 |
+
"rstrip": false,
|
865 |
+
"single_word": false,
|
866 |
+
"special": true
|
867 |
+
},
|
868 |
+
"128108": {
|
869 |
+
"content": "<|reserved_special_token_100|>",
|
870 |
+
"lstrip": false,
|
871 |
+
"normalized": false,
|
872 |
+
"rstrip": false,
|
873 |
+
"single_word": false,
|
874 |
+
"special": true
|
875 |
+
},
|
876 |
+
"128109": {
|
877 |
+
"content": "<|reserved_special_token_101|>",
|
878 |
+
"lstrip": false,
|
879 |
+
"normalized": false,
|
880 |
+
"rstrip": false,
|
881 |
+
"single_word": false,
|
882 |
+
"special": true
|
883 |
+
},
|
884 |
+
"128110": {
|
885 |
+
"content": "<|reserved_special_token_102|>",
|
886 |
+
"lstrip": false,
|
887 |
+
"normalized": false,
|
888 |
+
"rstrip": false,
|
889 |
+
"single_word": false,
|
890 |
+
"special": true
|
891 |
+
},
|
892 |
+
"128111": {
|
893 |
+
"content": "<|reserved_special_token_103|>",
|
894 |
+
"lstrip": false,
|
895 |
+
"normalized": false,
|
896 |
+
"rstrip": false,
|
897 |
+
"single_word": false,
|
898 |
+
"special": true
|
899 |
+
},
|
900 |
+
"128112": {
|
901 |
+
"content": "<|reserved_special_token_104|>",
|
902 |
+
"lstrip": false,
|
903 |
+
"normalized": false,
|
904 |
+
"rstrip": false,
|
905 |
+
"single_word": false,
|
906 |
+
"special": true
|
907 |
+
},
|
908 |
+
"128113": {
|
909 |
+
"content": "<|reserved_special_token_105|>",
|
910 |
+
"lstrip": false,
|
911 |
+
"normalized": false,
|
912 |
+
"rstrip": false,
|
913 |
+
"single_word": false,
|
914 |
+
"special": true
|
915 |
+
},
|
916 |
+
"128114": {
|
917 |
+
"content": "<|reserved_special_token_106|>",
|
918 |
+
"lstrip": false,
|
919 |
+
"normalized": false,
|
920 |
+
"rstrip": false,
|
921 |
+
"single_word": false,
|
922 |
+
"special": true
|
923 |
+
},
|
924 |
+
"128115": {
|
925 |
+
"content": "<|reserved_special_token_107|>",
|
926 |
+
"lstrip": false,
|
927 |
+
"normalized": false,
|
928 |
+
"rstrip": false,
|
929 |
+
"single_word": false,
|
930 |
+
"special": true
|
931 |
+
},
|
932 |
+
"128116": {
|
933 |
+
"content": "<|reserved_special_token_108|>",
|
934 |
+
"lstrip": false,
|
935 |
+
"normalized": false,
|
936 |
+
"rstrip": false,
|
937 |
+
"single_word": false,
|
938 |
+
"special": true
|
939 |
+
},
|
940 |
+
"128117": {
|
941 |
+
"content": "<|reserved_special_token_109|>",
|
942 |
+
"lstrip": false,
|
943 |
+
"normalized": false,
|
944 |
+
"rstrip": false,
|
945 |
+
"single_word": false,
|
946 |
+
"special": true
|
947 |
+
},
|
948 |
+
"128118": {
|
949 |
+
"content": "<|reserved_special_token_110|>",
|
950 |
+
"lstrip": false,
|
951 |
+
"normalized": false,
|
952 |
+
"rstrip": false,
|
953 |
+
"single_word": false,
|
954 |
+
"special": true
|
955 |
+
},
|
956 |
+
"128119": {
|
957 |
+
"content": "<|reserved_special_token_111|>",
|
958 |
+
"lstrip": false,
|
959 |
+
"normalized": false,
|
960 |
+
"rstrip": false,
|
961 |
+
"single_word": false,
|
962 |
+
"special": true
|
963 |
+
},
|
964 |
+
"128120": {
|
965 |
+
"content": "<|reserved_special_token_112|>",
|
966 |
+
"lstrip": false,
|
967 |
+
"normalized": false,
|
968 |
+
"rstrip": false,
|
969 |
+
"single_word": false,
|
970 |
+
"special": true
|
971 |
+
},
|
972 |
+
"128121": {
|
973 |
+
"content": "<|reserved_special_token_113|>",
|
974 |
+
"lstrip": false,
|
975 |
+
"normalized": false,
|
976 |
+
"rstrip": false,
|
977 |
+
"single_word": false,
|
978 |
+
"special": true
|
979 |
+
},
|
980 |
+
"128122": {
|
981 |
+
"content": "<|reserved_special_token_114|>",
|
982 |
+
"lstrip": false,
|
983 |
+
"normalized": false,
|
984 |
+
"rstrip": false,
|
985 |
+
"single_word": false,
|
986 |
+
"special": true
|
987 |
+
},
|
988 |
+
"128123": {
|
989 |
+
"content": "<|reserved_special_token_115|>",
|
990 |
+
"lstrip": false,
|
991 |
+
"normalized": false,
|
992 |
+
"rstrip": false,
|
993 |
+
"single_word": false,
|
994 |
+
"special": true
|
995 |
+
},
|
996 |
+
"128124": {
|
997 |
+
"content": "<|reserved_special_token_116|>",
|
998 |
+
"lstrip": false,
|
999 |
+
"normalized": false,
|
1000 |
+
"rstrip": false,
|
1001 |
+
"single_word": false,
|
1002 |
+
"special": true
|
1003 |
+
},
|
1004 |
+
"128125": {
|
1005 |
+
"content": "<|reserved_special_token_117|>",
|
1006 |
+
"lstrip": false,
|
1007 |
+
"normalized": false,
|
1008 |
+
"rstrip": false,
|
1009 |
+
"single_word": false,
|
1010 |
+
"special": true
|
1011 |
+
},
|
1012 |
+
"128126": {
|
1013 |
+
"content": "<|reserved_special_token_118|>",
|
1014 |
+
"lstrip": false,
|
1015 |
+
"normalized": false,
|
1016 |
+
"rstrip": false,
|
1017 |
+
"single_word": false,
|
1018 |
+
"special": true
|
1019 |
+
},
|
1020 |
+
"128127": {
|
1021 |
+
"content": "<|reserved_special_token_119|>",
|
1022 |
+
"lstrip": false,
|
1023 |
+
"normalized": false,
|
1024 |
+
"rstrip": false,
|
1025 |
+
"single_word": false,
|
1026 |
+
"special": true
|
1027 |
+
},
|
1028 |
+
"128128": {
|
1029 |
+
"content": "<|reserved_special_token_120|>",
|
1030 |
+
"lstrip": false,
|
1031 |
+
"normalized": false,
|
1032 |
+
"rstrip": false,
|
1033 |
+
"single_word": false,
|
1034 |
+
"special": true
|
1035 |
+
},
|
1036 |
+
"128129": {
|
1037 |
+
"content": "<|reserved_special_token_121|>",
|
1038 |
+
"lstrip": false,
|
1039 |
+
"normalized": false,
|
1040 |
+
"rstrip": false,
|
1041 |
+
"single_word": false,
|
1042 |
+
"special": true
|
1043 |
+
},
|
1044 |
+
"128130": {
|
1045 |
+
"content": "<|reserved_special_token_122|>",
|
1046 |
+
"lstrip": false,
|
1047 |
+
"normalized": false,
|
1048 |
+
"rstrip": false,
|
1049 |
+
"single_word": false,
|
1050 |
+
"special": true
|
1051 |
+
},
|
1052 |
+
"128131": {
|
1053 |
+
"content": "<|reserved_special_token_123|>",
|
1054 |
+
"lstrip": false,
|
1055 |
+
"normalized": false,
|
1056 |
+
"rstrip": false,
|
1057 |
+
"single_word": false,
|
1058 |
+
"special": true
|
1059 |
+
},
|
1060 |
+
"128132": {
|
1061 |
+
"content": "<|reserved_special_token_124|>",
|
1062 |
+
"lstrip": false,
|
1063 |
+
"normalized": false,
|
1064 |
+
"rstrip": false,
|
1065 |
+
"single_word": false,
|
1066 |
+
"special": true
|
1067 |
+
},
|
1068 |
+
"128133": {
|
1069 |
+
"content": "<|reserved_special_token_125|>",
|
1070 |
+
"lstrip": false,
|
1071 |
+
"normalized": false,
|
1072 |
+
"rstrip": false,
|
1073 |
+
"single_word": false,
|
1074 |
+
"special": true
|
1075 |
+
},
|
1076 |
+
"128134": {
|
1077 |
+
"content": "<|reserved_special_token_126|>",
|
1078 |
+
"lstrip": false,
|
1079 |
+
"normalized": false,
|
1080 |
+
"rstrip": false,
|
1081 |
+
"single_word": false,
|
1082 |
+
"special": true
|
1083 |
+
},
|
1084 |
+
"128135": {
|
1085 |
+
"content": "<|reserved_special_token_127|>",
|
1086 |
+
"lstrip": false,
|
1087 |
+
"normalized": false,
|
1088 |
+
"rstrip": false,
|
1089 |
+
"single_word": false,
|
1090 |
+
"special": true
|
1091 |
+
},
|
1092 |
+
"128136": {
|
1093 |
+
"content": "<|reserved_special_token_128|>",
|
1094 |
+
"lstrip": false,
|
1095 |
+
"normalized": false,
|
1096 |
+
"rstrip": false,
|
1097 |
+
"single_word": false,
|
1098 |
+
"special": true
|
1099 |
+
},
|
1100 |
+
"128137": {
|
1101 |
+
"content": "<|reserved_special_token_129|>",
|
1102 |
+
"lstrip": false,
|
1103 |
+
"normalized": false,
|
1104 |
+
"rstrip": false,
|
1105 |
+
"single_word": false,
|
1106 |
+
"special": true
|
1107 |
+
},
|
1108 |
+
"128138": {
|
1109 |
+
"content": "<|reserved_special_token_130|>",
|
1110 |
+
"lstrip": false,
|
1111 |
+
"normalized": false,
|
1112 |
+
"rstrip": false,
|
1113 |
+
"single_word": false,
|
1114 |
+
"special": true
|
1115 |
+
},
|
1116 |
+
"128139": {
|
1117 |
+
"content": "<|reserved_special_token_131|>",
|
1118 |
+
"lstrip": false,
|
1119 |
+
"normalized": false,
|
1120 |
+
"rstrip": false,
|
1121 |
+
"single_word": false,
|
1122 |
+
"special": true
|
1123 |
+
},
|
1124 |
+
"128140": {
|
1125 |
+
"content": "<|reserved_special_token_132|>",
|
1126 |
+
"lstrip": false,
|
1127 |
+
"normalized": false,
|
1128 |
+
"rstrip": false,
|
1129 |
+
"single_word": false,
|
1130 |
+
"special": true
|
1131 |
+
},
|
1132 |
+
"128141": {
|
1133 |
+
"content": "<|reserved_special_token_133|>",
|
1134 |
+
"lstrip": false,
|
1135 |
+
"normalized": false,
|
1136 |
+
"rstrip": false,
|
1137 |
+
"single_word": false,
|
1138 |
+
"special": true
|
1139 |
+
},
|
1140 |
+
"128142": {
|
1141 |
+
"content": "<|reserved_special_token_134|>",
|
1142 |
+
"lstrip": false,
|
1143 |
+
"normalized": false,
|
1144 |
+
"rstrip": false,
|
1145 |
+
"single_word": false,
|
1146 |
+
"special": true
|
1147 |
+
},
|
1148 |
+
"128143": {
|
1149 |
+
"content": "<|reserved_special_token_135|>",
|
1150 |
+
"lstrip": false,
|
1151 |
+
"normalized": false,
|
1152 |
+
"rstrip": false,
|
1153 |
+
"single_word": false,
|
1154 |
+
"special": true
|
1155 |
+
},
|
1156 |
+
"128144": {
|
1157 |
+
"content": "<|reserved_special_token_136|>",
|
1158 |
+
"lstrip": false,
|
1159 |
+
"normalized": false,
|
1160 |
+
"rstrip": false,
|
1161 |
+
"single_word": false,
|
1162 |
+
"special": true
|
1163 |
+
},
|
1164 |
+
"128145": {
|
1165 |
+
"content": "<|reserved_special_token_137|>",
|
1166 |
+
"lstrip": false,
|
1167 |
+
"normalized": false,
|
1168 |
+
"rstrip": false,
|
1169 |
+
"single_word": false,
|
1170 |
+
"special": true
|
1171 |
+
},
|
1172 |
+
"128146": {
|
1173 |
+
"content": "<|reserved_special_token_138|>",
|
1174 |
+
"lstrip": false,
|
1175 |
+
"normalized": false,
|
1176 |
+
"rstrip": false,
|
1177 |
+
"single_word": false,
|
1178 |
+
"special": true
|
1179 |
+
},
|
1180 |
+
"128147": {
|
1181 |
+
"content": "<|reserved_special_token_139|>",
|
1182 |
+
"lstrip": false,
|
1183 |
+
"normalized": false,
|
1184 |
+
"rstrip": false,
|
1185 |
+
"single_word": false,
|
1186 |
+
"special": true
|
1187 |
+
},
|
1188 |
+
"128148": {
|
1189 |
+
"content": "<|reserved_special_token_140|>",
|
1190 |
+
"lstrip": false,
|
1191 |
+
"normalized": false,
|
1192 |
+
"rstrip": false,
|
1193 |
+
"single_word": false,
|
1194 |
+
"special": true
|
1195 |
+
},
|
1196 |
+
"128149": {
|
1197 |
+
"content": "<|reserved_special_token_141|>",
|
1198 |
+
"lstrip": false,
|
1199 |
+
"normalized": false,
|
1200 |
+
"rstrip": false,
|
1201 |
+
"single_word": false,
|
1202 |
+
"special": true
|
1203 |
+
},
|
1204 |
+
"128150": {
|
1205 |
+
"content": "<|reserved_special_token_142|>",
|
1206 |
+
"lstrip": false,
|
1207 |
+
"normalized": false,
|
1208 |
+
"rstrip": false,
|
1209 |
+
"single_word": false,
|
1210 |
+
"special": true
|
1211 |
+
},
|
1212 |
+
"128151": {
|
1213 |
+
"content": "<|reserved_special_token_143|>",
|
1214 |
+
"lstrip": false,
|
1215 |
+
"normalized": false,
|
1216 |
+
"rstrip": false,
|
1217 |
+
"single_word": false,
|
1218 |
+
"special": true
|
1219 |
+
},
|
1220 |
+
"128152": {
|
1221 |
+
"content": "<|reserved_special_token_144|>",
|
1222 |
+
"lstrip": false,
|
1223 |
+
"normalized": false,
|
1224 |
+
"rstrip": false,
|
1225 |
+
"single_word": false,
|
1226 |
+
"special": true
|
1227 |
+
},
|
1228 |
+
"128153": {
|
1229 |
+
"content": "<|reserved_special_token_145|>",
|
1230 |
+
"lstrip": false,
|
1231 |
+
"normalized": false,
|
1232 |
+
"rstrip": false,
|
1233 |
+
"single_word": false,
|
1234 |
+
"special": true
|
1235 |
+
},
|
1236 |
+
"128154": {
|
1237 |
+
"content": "<|reserved_special_token_146|>",
|
1238 |
+
"lstrip": false,
|
1239 |
+
"normalized": false,
|
1240 |
+
"rstrip": false,
|
1241 |
+
"single_word": false,
|
1242 |
+
"special": true
|
1243 |
+
},
|
1244 |
+
"128155": {
|
1245 |
+
"content": "<|reserved_special_token_147|>",
|
1246 |
+
"lstrip": false,
|
1247 |
+
"normalized": false,
|
1248 |
+
"rstrip": false,
|
1249 |
+
"single_word": false,
|
1250 |
+
"special": true
|
1251 |
+
},
|
1252 |
+
"128156": {
|
1253 |
+
"content": "<|reserved_special_token_148|>",
|
1254 |
+
"lstrip": false,
|
1255 |
+
"normalized": false,
|
1256 |
+
"rstrip": false,
|
1257 |
+
"single_word": false,
|
1258 |
+
"special": true
|
1259 |
+
},
|
1260 |
+
"128157": {
|
1261 |
+
"content": "<|reserved_special_token_149|>",
|
1262 |
+
"lstrip": false,
|
1263 |
+
"normalized": false,
|
1264 |
+
"rstrip": false,
|
1265 |
+
"single_word": false,
|
1266 |
+
"special": true
|
1267 |
+
},
|
1268 |
+
"128158": {
|
1269 |
+
"content": "<|reserved_special_token_150|>",
|
1270 |
+
"lstrip": false,
|
1271 |
+
"normalized": false,
|
1272 |
+
"rstrip": false,
|
1273 |
+
"single_word": false,
|
1274 |
+
"special": true
|
1275 |
+
},
|
1276 |
+
"128159": {
|
1277 |
+
"content": "<|reserved_special_token_151|>",
|
1278 |
+
"lstrip": false,
|
1279 |
+
"normalized": false,
|
1280 |
+
"rstrip": false,
|
1281 |
+
"single_word": false,
|
1282 |
+
"special": true
|
1283 |
+
},
|
1284 |
+
"128160": {
|
1285 |
+
"content": "<|reserved_special_token_152|>",
|
1286 |
+
"lstrip": false,
|
1287 |
+
"normalized": false,
|
1288 |
+
"rstrip": false,
|
1289 |
+
"single_word": false,
|
1290 |
+
"special": true
|
1291 |
+
},
|
1292 |
+
"128161": {
|
1293 |
+
"content": "<|reserved_special_token_153|>",
|
1294 |
+
"lstrip": false,
|
1295 |
+
"normalized": false,
|
1296 |
+
"rstrip": false,
|
1297 |
+
"single_word": false,
|
1298 |
+
"special": true
|
1299 |
+
},
|
1300 |
+
"128162": {
|
1301 |
+
"content": "<|reserved_special_token_154|>",
|
1302 |
+
"lstrip": false,
|
1303 |
+
"normalized": false,
|
1304 |
+
"rstrip": false,
|
1305 |
+
"single_word": false,
|
1306 |
+
"special": true
|
1307 |
+
},
|
1308 |
+
"128163": {
|
1309 |
+
"content": "<|reserved_special_token_155|>",
|
1310 |
+
"lstrip": false,
|
1311 |
+
"normalized": false,
|
1312 |
+
"rstrip": false,
|
1313 |
+
"single_word": false,
|
1314 |
+
"special": true
|
1315 |
+
},
|
1316 |
+
"128164": {
|
1317 |
+
"content": "<|reserved_special_token_156|>",
|
1318 |
+
"lstrip": false,
|
1319 |
+
"normalized": false,
|
1320 |
+
"rstrip": false,
|
1321 |
+
"single_word": false,
|
1322 |
+
"special": true
|
1323 |
+
},
|
1324 |
+
"128165": {
|
1325 |
+
"content": "<|reserved_special_token_157|>",
|
1326 |
+
"lstrip": false,
|
1327 |
+
"normalized": false,
|
1328 |
+
"rstrip": false,
|
1329 |
+
"single_word": false,
|
1330 |
+
"special": true
|
1331 |
+
},
|
1332 |
+
"128166": {
|
1333 |
+
"content": "<|reserved_special_token_158|>",
|
1334 |
+
"lstrip": false,
|
1335 |
+
"normalized": false,
|
1336 |
+
"rstrip": false,
|
1337 |
+
"single_word": false,
|
1338 |
+
"special": true
|
1339 |
+
},
|
1340 |
+
"128167": {
|
1341 |
+
"content": "<|reserved_special_token_159|>",
|
1342 |
+
"lstrip": false,
|
1343 |
+
"normalized": false,
|
1344 |
+
"rstrip": false,
|
1345 |
+
"single_word": false,
|
1346 |
+
"special": true
|
1347 |
+
},
|
1348 |
+
"128168": {
|
1349 |
+
"content": "<|reserved_special_token_160|>",
|
1350 |
+
"lstrip": false,
|
1351 |
+
"normalized": false,
|
1352 |
+
"rstrip": false,
|
1353 |
+
"single_word": false,
|
1354 |
+
"special": true
|
1355 |
+
},
|
1356 |
+
"128169": {
|
1357 |
+
"content": "<|reserved_special_token_161|>",
|
1358 |
+
"lstrip": false,
|
1359 |
+
"normalized": false,
|
1360 |
+
"rstrip": false,
|
1361 |
+
"single_word": false,
|
1362 |
+
"special": true
|
1363 |
+
},
|
1364 |
+
"128170": {
|
1365 |
+
"content": "<|reserved_special_token_162|>",
|
1366 |
+
"lstrip": false,
|
1367 |
+
"normalized": false,
|
1368 |
+
"rstrip": false,
|
1369 |
+
"single_word": false,
|
1370 |
+
"special": true
|
1371 |
+
},
|
1372 |
+
"128171": {
|
1373 |
+
"content": "<|reserved_special_token_163|>",
|
1374 |
+
"lstrip": false,
|
1375 |
+
"normalized": false,
|
1376 |
+
"rstrip": false,
|
1377 |
+
"single_word": false,
|
1378 |
+
"special": true
|
1379 |
+
},
|
1380 |
+
"128172": {
|
1381 |
+
"content": "<|reserved_special_token_164|>",
|
1382 |
+
"lstrip": false,
|
1383 |
+
"normalized": false,
|
1384 |
+
"rstrip": false,
|
1385 |
+
"single_word": false,
|
1386 |
+
"special": true
|
1387 |
+
},
|
1388 |
+
"128173": {
|
1389 |
+
"content": "<|reserved_special_token_165|>",
|
1390 |
+
"lstrip": false,
|
1391 |
+
"normalized": false,
|
1392 |
+
"rstrip": false,
|
1393 |
+
"single_word": false,
|
1394 |
+
"special": true
|
1395 |
+
},
|
1396 |
+
"128174": {
|
1397 |
+
"content": "<|reserved_special_token_166|>",
|
1398 |
+
"lstrip": false,
|
1399 |
+
"normalized": false,
|
1400 |
+
"rstrip": false,
|
1401 |
+
"single_word": false,
|
1402 |
+
"special": true
|
1403 |
+
},
|
1404 |
+
"128175": {
|
1405 |
+
"content": "<|reserved_special_token_167|>",
|
1406 |
+
"lstrip": false,
|
1407 |
+
"normalized": false,
|
1408 |
+
"rstrip": false,
|
1409 |
+
"single_word": false,
|
1410 |
+
"special": true
|
1411 |
+
},
|
1412 |
+
"128176": {
|
1413 |
+
"content": "<|reserved_special_token_168|>",
|
1414 |
+
"lstrip": false,
|
1415 |
+
"normalized": false,
|
1416 |
+
"rstrip": false,
|
1417 |
+
"single_word": false,
|
1418 |
+
"special": true
|
1419 |
+
},
|
1420 |
+
"128177": {
|
1421 |
+
"content": "<|reserved_special_token_169|>",
|
1422 |
+
"lstrip": false,
|
1423 |
+
"normalized": false,
|
1424 |
+
"rstrip": false,
|
1425 |
+
"single_word": false,
|
1426 |
+
"special": true
|
1427 |
+
},
|
1428 |
+
"128178": {
|
1429 |
+
"content": "<|reserved_special_token_170|>",
|
1430 |
+
"lstrip": false,
|
1431 |
+
"normalized": false,
|
1432 |
+
"rstrip": false,
|
1433 |
+
"single_word": false,
|
1434 |
+
"special": true
|
1435 |
+
},
|
1436 |
+
"128179": {
|
1437 |
+
"content": "<|reserved_special_token_171|>",
|
1438 |
+
"lstrip": false,
|
1439 |
+
"normalized": false,
|
1440 |
+
"rstrip": false,
|
1441 |
+
"single_word": false,
|
1442 |
+
"special": true
|
1443 |
+
},
|
1444 |
+
"128180": {
|
1445 |
+
"content": "<|reserved_special_token_172|>",
|
1446 |
+
"lstrip": false,
|
1447 |
+
"normalized": false,
|
1448 |
+
"rstrip": false,
|
1449 |
+
"single_word": false,
|
1450 |
+
"special": true
|
1451 |
+
},
|
1452 |
+
"128181": {
|
1453 |
+
"content": "<|reserved_special_token_173|>",
|
1454 |
+
"lstrip": false,
|
1455 |
+
"normalized": false,
|
1456 |
+
"rstrip": false,
|
1457 |
+
"single_word": false,
|
1458 |
+
"special": true
|
1459 |
+
},
|
1460 |
+
"128182": {
|
1461 |
+
"content": "<|reserved_special_token_174|>",
|
1462 |
+
"lstrip": false,
|
1463 |
+
"normalized": false,
|
1464 |
+
"rstrip": false,
|
1465 |
+
"single_word": false,
|
1466 |
+
"special": true
|
1467 |
+
},
|
1468 |
+
"128183": {
|
1469 |
+
"content": "<|reserved_special_token_175|>",
|
1470 |
+
"lstrip": false,
|
1471 |
+
"normalized": false,
|
1472 |
+
"rstrip": false,
|
1473 |
+
"single_word": false,
|
1474 |
+
"special": true
|
1475 |
+
},
|
1476 |
+
"128184": {
|
1477 |
+
"content": "<|reserved_special_token_176|>",
|
1478 |
+
"lstrip": false,
|
1479 |
+
"normalized": false,
|
1480 |
+
"rstrip": false,
|
1481 |
+
"single_word": false,
|
1482 |
+
"special": true
|
1483 |
+
},
|
1484 |
+
"128185": {
|
1485 |
+
"content": "<|reserved_special_token_177|>",
|
1486 |
+
"lstrip": false,
|
1487 |
+
"normalized": false,
|
1488 |
+
"rstrip": false,
|
1489 |
+
"single_word": false,
|
1490 |
+
"special": true
|
1491 |
+
},
|
1492 |
+
"128186": {
|
1493 |
+
"content": "<|reserved_special_token_178|>",
|
1494 |
+
"lstrip": false,
|
1495 |
+
"normalized": false,
|
1496 |
+
"rstrip": false,
|
1497 |
+
"single_word": false,
|
1498 |
+
"special": true
|
1499 |
+
},
|
1500 |
+
"128187": {
|
1501 |
+
"content": "<|reserved_special_token_179|>",
|
1502 |
+
"lstrip": false,
|
1503 |
+
"normalized": false,
|
1504 |
+
"rstrip": false,
|
1505 |
+
"single_word": false,
|
1506 |
+
"special": true
|
1507 |
+
},
|
1508 |
+
"128188": {
|
1509 |
+
"content": "<|reserved_special_token_180|>",
|
1510 |
+
"lstrip": false,
|
1511 |
+
"normalized": false,
|
1512 |
+
"rstrip": false,
|
1513 |
+
"single_word": false,
|
1514 |
+
"special": true
|
1515 |
+
},
|
1516 |
+
"128189": {
|
1517 |
+
"content": "<|reserved_special_token_181|>",
|
1518 |
+
"lstrip": false,
|
1519 |
+
"normalized": false,
|
1520 |
+
"rstrip": false,
|
1521 |
+
"single_word": false,
|
1522 |
+
"special": true
|
1523 |
+
},
|
1524 |
+
"128190": {
|
1525 |
+
"content": "<|reserved_special_token_182|>",
|
1526 |
+
"lstrip": false,
|
1527 |
+
"normalized": false,
|
1528 |
+
"rstrip": false,
|
1529 |
+
"single_word": false,
|
1530 |
+
"special": true
|
1531 |
+
},
|
1532 |
+
"128191": {
|
1533 |
+
"content": "<|reserved_special_token_183|>",
|
1534 |
+
"lstrip": false,
|
1535 |
+
"normalized": false,
|
1536 |
+
"rstrip": false,
|
1537 |
+
"single_word": false,
|
1538 |
+
"special": true
|
1539 |
+
},
|
1540 |
+
"128192": {
|
1541 |
+
"content": "<|reserved_special_token_184|>",
|
1542 |
+
"lstrip": false,
|
1543 |
+
"normalized": false,
|
1544 |
+
"rstrip": false,
|
1545 |
+
"single_word": false,
|
1546 |
+
"special": true
|
1547 |
+
},
|
1548 |
+
"128193": {
|
1549 |
+
"content": "<|reserved_special_token_185|>",
|
1550 |
+
"lstrip": false,
|
1551 |
+
"normalized": false,
|
1552 |
+
"rstrip": false,
|
1553 |
+
"single_word": false,
|
1554 |
+
"special": true
|
1555 |
+
},
|
1556 |
+
"128194": {
|
1557 |
+
"content": "<|reserved_special_token_186|>",
|
1558 |
+
"lstrip": false,
|
1559 |
+
"normalized": false,
|
1560 |
+
"rstrip": false,
|
1561 |
+
"single_word": false,
|
1562 |
+
"special": true
|
1563 |
+
},
|
1564 |
+
"128195": {
|
1565 |
+
"content": "<|reserved_special_token_187|>",
|
1566 |
+
"lstrip": false,
|
1567 |
+
"normalized": false,
|
1568 |
+
"rstrip": false,
|
1569 |
+
"single_word": false,
|
1570 |
+
"special": true
|
1571 |
+
},
|
1572 |
+
"128196": {
|
1573 |
+
"content": "<|reserved_special_token_188|>",
|
1574 |
+
"lstrip": false,
|
1575 |
+
"normalized": false,
|
1576 |
+
"rstrip": false,
|
1577 |
+
"single_word": false,
|
1578 |
+
"special": true
|
1579 |
+
},
|
1580 |
+
"128197": {
|
1581 |
+
"content": "<|reserved_special_token_189|>",
|
1582 |
+
"lstrip": false,
|
1583 |
+
"normalized": false,
|
1584 |
+
"rstrip": false,
|
1585 |
+
"single_word": false,
|
1586 |
+
"special": true
|
1587 |
+
},
|
1588 |
+
"128198": {
|
1589 |
+
"content": "<|reserved_special_token_190|>",
|
1590 |
+
"lstrip": false,
|
1591 |
+
"normalized": false,
|
1592 |
+
"rstrip": false,
|
1593 |
+
"single_word": false,
|
1594 |
+
"special": true
|
1595 |
+
},
|
1596 |
+
"128199": {
|
1597 |
+
"content": "<|reserved_special_token_191|>",
|
1598 |
+
"lstrip": false,
|
1599 |
+
"normalized": false,
|
1600 |
+
"rstrip": false,
|
1601 |
+
"single_word": false,
|
1602 |
+
"special": true
|
1603 |
+
},
|
1604 |
+
"128200": {
|
1605 |
+
"content": "<|reserved_special_token_192|>",
|
1606 |
+
"lstrip": false,
|
1607 |
+
"normalized": false,
|
1608 |
+
"rstrip": false,
|
1609 |
+
"single_word": false,
|
1610 |
+
"special": true
|
1611 |
+
},
|
1612 |
+
"128201": {
|
1613 |
+
"content": "<|reserved_special_token_193|>",
|
1614 |
+
"lstrip": false,
|
1615 |
+
"normalized": false,
|
1616 |
+
"rstrip": false,
|
1617 |
+
"single_word": false,
|
1618 |
+
"special": true
|
1619 |
+
},
|
1620 |
+
"128202": {
|
1621 |
+
"content": "<|reserved_special_token_194|>",
|
1622 |
+
"lstrip": false,
|
1623 |
+
"normalized": false,
|
1624 |
+
"rstrip": false,
|
1625 |
+
"single_word": false,
|
1626 |
+
"special": true
|
1627 |
+
},
|
1628 |
+
"128203": {
|
1629 |
+
"content": "<|reserved_special_token_195|>",
|
1630 |
+
"lstrip": false,
|
1631 |
+
"normalized": false,
|
1632 |
+
"rstrip": false,
|
1633 |
+
"single_word": false,
|
1634 |
+
"special": true
|
1635 |
+
},
|
1636 |
+
"128204": {
|
1637 |
+
"content": "<|reserved_special_token_196|>",
|
1638 |
+
"lstrip": false,
|
1639 |
+
"normalized": false,
|
1640 |
+
"rstrip": false,
|
1641 |
+
"single_word": false,
|
1642 |
+
"special": true
|
1643 |
+
},
|
1644 |
+
"128205": {
|
1645 |
+
"content": "<|reserved_special_token_197|>",
|
1646 |
+
"lstrip": false,
|
1647 |
+
"normalized": false,
|
1648 |
+
"rstrip": false,
|
1649 |
+
"single_word": false,
|
1650 |
+
"special": true
|
1651 |
+
},
|
1652 |
+
"128206": {
|
1653 |
+
"content": "<|reserved_special_token_198|>",
|
1654 |
+
"lstrip": false,
|
1655 |
+
"normalized": false,
|
1656 |
+
"rstrip": false,
|
1657 |
+
"single_word": false,
|
1658 |
+
"special": true
|
1659 |
+
},
|
1660 |
+
"128207": {
|
1661 |
+
"content": "<|reserved_special_token_199|>",
|
1662 |
+
"lstrip": false,
|
1663 |
+
"normalized": false,
|
1664 |
+
"rstrip": false,
|
1665 |
+
"single_word": false,
|
1666 |
+
"special": true
|
1667 |
+
},
|
1668 |
+
"128208": {
|
1669 |
+
"content": "<|reserved_special_token_200|>",
|
1670 |
+
"lstrip": false,
|
1671 |
+
"normalized": false,
|
1672 |
+
"rstrip": false,
|
1673 |
+
"single_word": false,
|
1674 |
+
"special": true
|
1675 |
+
},
|
1676 |
+
"128209": {
|
1677 |
+
"content": "<|reserved_special_token_201|>",
|
1678 |
+
"lstrip": false,
|
1679 |
+
"normalized": false,
|
1680 |
+
"rstrip": false,
|
1681 |
+
"single_word": false,
|
1682 |
+
"special": true
|
1683 |
+
},
|
1684 |
+
"128210": {
|
1685 |
+
"content": "<|reserved_special_token_202|>",
|
1686 |
+
"lstrip": false,
|
1687 |
+
"normalized": false,
|
1688 |
+
"rstrip": false,
|
1689 |
+
"single_word": false,
|
1690 |
+
"special": true
|
1691 |
+
},
|
1692 |
+
"128211": {
|
1693 |
+
"content": "<|reserved_special_token_203|>",
|
1694 |
+
"lstrip": false,
|
1695 |
+
"normalized": false,
|
1696 |
+
"rstrip": false,
|
1697 |
+
"single_word": false,
|
1698 |
+
"special": true
|
1699 |
+
},
|
1700 |
+
"128212": {
|
1701 |
+
"content": "<|reserved_special_token_204|>",
|
1702 |
+
"lstrip": false,
|
1703 |
+
"normalized": false,
|
1704 |
+
"rstrip": false,
|
1705 |
+
"single_word": false,
|
1706 |
+
"special": true
|
1707 |
+
},
|
1708 |
+
"128213": {
|
1709 |
+
"content": "<|reserved_special_token_205|>",
|
1710 |
+
"lstrip": false,
|
1711 |
+
"normalized": false,
|
1712 |
+
"rstrip": false,
|
1713 |
+
"single_word": false,
|
1714 |
+
"special": true
|
1715 |
+
},
|
1716 |
+
"128214": {
|
1717 |
+
"content": "<|reserved_special_token_206|>",
|
1718 |
+
"lstrip": false,
|
1719 |
+
"normalized": false,
|
1720 |
+
"rstrip": false,
|
1721 |
+
"single_word": false,
|
1722 |
+
"special": true
|
1723 |
+
},
|
1724 |
+
"128215": {
|
1725 |
+
"content": "<|reserved_special_token_207|>",
|
1726 |
+
"lstrip": false,
|
1727 |
+
"normalized": false,
|
1728 |
+
"rstrip": false,
|
1729 |
+
"single_word": false,
|
1730 |
+
"special": true
|
1731 |
+
},
|
1732 |
+
"128216": {
|
1733 |
+
"content": "<|reserved_special_token_208|>",
|
1734 |
+
"lstrip": false,
|
1735 |
+
"normalized": false,
|
1736 |
+
"rstrip": false,
|
1737 |
+
"single_word": false,
|
1738 |
+
"special": true
|
1739 |
+
},
|
1740 |
+
"128217": {
|
1741 |
+
"content": "<|reserved_special_token_209|>",
|
1742 |
+
"lstrip": false,
|
1743 |
+
"normalized": false,
|
1744 |
+
"rstrip": false,
|
1745 |
+
"single_word": false,
|
1746 |
+
"special": true
|
1747 |
+
},
|
1748 |
+
"128218": {
|
1749 |
+
"content": "<|reserved_special_token_210|>",
|
1750 |
+
"lstrip": false,
|
1751 |
+
"normalized": false,
|
1752 |
+
"rstrip": false,
|
1753 |
+
"single_word": false,
|
1754 |
+
"special": true
|
1755 |
+
},
|
1756 |
+
"128219": {
|
1757 |
+
"content": "<|reserved_special_token_211|>",
|
1758 |
+
"lstrip": false,
|
1759 |
+
"normalized": false,
|
1760 |
+
"rstrip": false,
|
1761 |
+
"single_word": false,
|
1762 |
+
"special": true
|
1763 |
+
},
|
1764 |
+
"128220": {
|
1765 |
+
"content": "<|reserved_special_token_212|>",
|
1766 |
+
"lstrip": false,
|
1767 |
+
"normalized": false,
|
1768 |
+
"rstrip": false,
|
1769 |
+
"single_word": false,
|
1770 |
+
"special": true
|
1771 |
+
},
|
1772 |
+
"128221": {
|
1773 |
+
"content": "<|reserved_special_token_213|>",
|
1774 |
+
"lstrip": false,
|
1775 |
+
"normalized": false,
|
1776 |
+
"rstrip": false,
|
1777 |
+
"single_word": false,
|
1778 |
+
"special": true
|
1779 |
+
},
|
1780 |
+
"128222": {
|
1781 |
+
"content": "<|reserved_special_token_214|>",
|
1782 |
+
"lstrip": false,
|
1783 |
+
"normalized": false,
|
1784 |
+
"rstrip": false,
|
1785 |
+
"single_word": false,
|
1786 |
+
"special": true
|
1787 |
+
},
|
1788 |
+
"128223": {
|
1789 |
+
"content": "<|reserved_special_token_215|>",
|
1790 |
+
"lstrip": false,
|
1791 |
+
"normalized": false,
|
1792 |
+
"rstrip": false,
|
1793 |
+
"single_word": false,
|
1794 |
+
"special": true
|
1795 |
+
},
|
1796 |
+
"128224": {
|
1797 |
+
"content": "<|reserved_special_token_216|>",
|
1798 |
+
"lstrip": false,
|
1799 |
+
"normalized": false,
|
1800 |
+
"rstrip": false,
|
1801 |
+
"single_word": false,
|
1802 |
+
"special": true
|
1803 |
+
},
|
1804 |
+
"128225": {
|
1805 |
+
"content": "<|reserved_special_token_217|>",
|
1806 |
+
"lstrip": false,
|
1807 |
+
"normalized": false,
|
1808 |
+
"rstrip": false,
|
1809 |
+
"single_word": false,
|
1810 |
+
"special": true
|
1811 |
+
},
|
1812 |
+
"128226": {
|
1813 |
+
"content": "<|reserved_special_token_218|>",
|
1814 |
+
"lstrip": false,
|
1815 |
+
"normalized": false,
|
1816 |
+
"rstrip": false,
|
1817 |
+
"single_word": false,
|
1818 |
+
"special": true
|
1819 |
+
},
|
1820 |
+
"128227": {
|
1821 |
+
"content": "<|reserved_special_token_219|>",
|
1822 |
+
"lstrip": false,
|
1823 |
+
"normalized": false,
|
1824 |
+
"rstrip": false,
|
1825 |
+
"single_word": false,
|
1826 |
+
"special": true
|
1827 |
+
},
|
1828 |
+
"128228": {
|
1829 |
+
"content": "<|reserved_special_token_220|>",
|
1830 |
+
"lstrip": false,
|
1831 |
+
"normalized": false,
|
1832 |
+
"rstrip": false,
|
1833 |
+
"single_word": false,
|
1834 |
+
"special": true
|
1835 |
+
},
|
1836 |
+
"128229": {
|
1837 |
+
"content": "<|reserved_special_token_221|>",
|
1838 |
+
"lstrip": false,
|
1839 |
+
"normalized": false,
|
1840 |
+
"rstrip": false,
|
1841 |
+
"single_word": false,
|
1842 |
+
"special": true
|
1843 |
+
},
|
1844 |
+
"128230": {
|
1845 |
+
"content": "<|reserved_special_token_222|>",
|
1846 |
+
"lstrip": false,
|
1847 |
+
"normalized": false,
|
1848 |
+
"rstrip": false,
|
1849 |
+
"single_word": false,
|
1850 |
+
"special": true
|
1851 |
+
},
|
1852 |
+
"128231": {
|
1853 |
+
"content": "<|reserved_special_token_223|>",
|
1854 |
+
"lstrip": false,
|
1855 |
+
"normalized": false,
|
1856 |
+
"rstrip": false,
|
1857 |
+
"single_word": false,
|
1858 |
+
"special": true
|
1859 |
+
},
|
1860 |
+
"128232": {
|
1861 |
+
"content": "<|reserved_special_token_224|>",
|
1862 |
+
"lstrip": false,
|
1863 |
+
"normalized": false,
|
1864 |
+
"rstrip": false,
|
1865 |
+
"single_word": false,
|
1866 |
+
"special": true
|
1867 |
+
},
|
1868 |
+
"128233": {
|
1869 |
+
"content": "<|reserved_special_token_225|>",
|
1870 |
+
"lstrip": false,
|
1871 |
+
"normalized": false,
|
1872 |
+
"rstrip": false,
|
1873 |
+
"single_word": false,
|
1874 |
+
"special": true
|
1875 |
+
},
|
1876 |
+
"128234": {
|
1877 |
+
"content": "<|reserved_special_token_226|>",
|
1878 |
+
"lstrip": false,
|
1879 |
+
"normalized": false,
|
1880 |
+
"rstrip": false,
|
1881 |
+
"single_word": false,
|
1882 |
+
"special": true
|
1883 |
+
},
|
1884 |
+
"128235": {
|
1885 |
+
"content": "<|reserved_special_token_227|>",
|
1886 |
+
"lstrip": false,
|
1887 |
+
"normalized": false,
|
1888 |
+
"rstrip": false,
|
1889 |
+
"single_word": false,
|
1890 |
+
"special": true
|
1891 |
+
},
|
1892 |
+
"128236": {
|
1893 |
+
"content": "<|reserved_special_token_228|>",
|
1894 |
+
"lstrip": false,
|
1895 |
+
"normalized": false,
|
1896 |
+
"rstrip": false,
|
1897 |
+
"single_word": false,
|
1898 |
+
"special": true
|
1899 |
+
},
|
1900 |
+
"128237": {
|
1901 |
+
"content": "<|reserved_special_token_229|>",
|
1902 |
+
"lstrip": false,
|
1903 |
+
"normalized": false,
|
1904 |
+
"rstrip": false,
|
1905 |
+
"single_word": false,
|
1906 |
+
"special": true
|
1907 |
+
},
|
1908 |
+
"128238": {
|
1909 |
+
"content": "<|reserved_special_token_230|>",
|
1910 |
+
"lstrip": false,
|
1911 |
+
"normalized": false,
|
1912 |
+
"rstrip": false,
|
1913 |
+
"single_word": false,
|
1914 |
+
"special": true
|
1915 |
+
},
|
1916 |
+
"128239": {
|
1917 |
+
"content": "<|reserved_special_token_231|>",
|
1918 |
+
"lstrip": false,
|
1919 |
+
"normalized": false,
|
1920 |
+
"rstrip": false,
|
1921 |
+
"single_word": false,
|
1922 |
+
"special": true
|
1923 |
+
},
|
1924 |
+
"128240": {
|
1925 |
+
"content": "<|reserved_special_token_232|>",
|
1926 |
+
"lstrip": false,
|
1927 |
+
"normalized": false,
|
1928 |
+
"rstrip": false,
|
1929 |
+
"single_word": false,
|
1930 |
+
"special": true
|
1931 |
+
},
|
1932 |
+
"128241": {
|
1933 |
+
"content": "<|reserved_special_token_233|>",
|
1934 |
+
"lstrip": false,
|
1935 |
+
"normalized": false,
|
1936 |
+
"rstrip": false,
|
1937 |
+
"single_word": false,
|
1938 |
+
"special": true
|
1939 |
+
},
|
1940 |
+
"128242": {
|
1941 |
+
"content": "<|reserved_special_token_234|>",
|
1942 |
+
"lstrip": false,
|
1943 |
+
"normalized": false,
|
1944 |
+
"rstrip": false,
|
1945 |
+
"single_word": false,
|
1946 |
+
"special": true
|
1947 |
+
},
|
1948 |
+
"128243": {
|
1949 |
+
"content": "<|reserved_special_token_235|>",
|
1950 |
+
"lstrip": false,
|
1951 |
+
"normalized": false,
|
1952 |
+
"rstrip": false,
|
1953 |
+
"single_word": false,
|
1954 |
+
"special": true
|
1955 |
+
},
|
1956 |
+
"128244": {
|
1957 |
+
"content": "<|reserved_special_token_236|>",
|
1958 |
+
"lstrip": false,
|
1959 |
+
"normalized": false,
|
1960 |
+
"rstrip": false,
|
1961 |
+
"single_word": false,
|
1962 |
+
"special": true
|
1963 |
+
},
|
1964 |
+
"128245": {
|
1965 |
+
"content": "<|reserved_special_token_237|>",
|
1966 |
+
"lstrip": false,
|
1967 |
+
"normalized": false,
|
1968 |
+
"rstrip": false,
|
1969 |
+
"single_word": false,
|
1970 |
+
"special": true
|
1971 |
+
},
|
1972 |
+
"128246": {
|
1973 |
+
"content": "<|reserved_special_token_238|>",
|
1974 |
+
"lstrip": false,
|
1975 |
+
"normalized": false,
|
1976 |
+
"rstrip": false,
|
1977 |
+
"single_word": false,
|
1978 |
+
"special": true
|
1979 |
+
},
|
1980 |
+
"128247": {
|
1981 |
+
"content": "<|reserved_special_token_239|>",
|
1982 |
+
"lstrip": false,
|
1983 |
+
"normalized": false,
|
1984 |
+
"rstrip": false,
|
1985 |
+
"single_word": false,
|
1986 |
+
"special": true
|
1987 |
+
},
|
1988 |
+
"128248": {
|
1989 |
+
"content": "<|reserved_special_token_240|>",
|
1990 |
+
"lstrip": false,
|
1991 |
+
"normalized": false,
|
1992 |
+
"rstrip": false,
|
1993 |
+
"single_word": false,
|
1994 |
+
"special": true
|
1995 |
+
},
|
1996 |
+
"128249": {
|
1997 |
+
"content": "<|reserved_special_token_241|>",
|
1998 |
+
"lstrip": false,
|
1999 |
+
"normalized": false,
|
2000 |
+
"rstrip": false,
|
2001 |
+
"single_word": false,
|
2002 |
+
"special": true
|
2003 |
+
},
|
2004 |
+
"128250": {
|
2005 |
+
"content": "<|reserved_special_token_242|>",
|
2006 |
+
"lstrip": false,
|
2007 |
+
"normalized": false,
|
2008 |
+
"rstrip": false,
|
2009 |
+
"single_word": false,
|
2010 |
+
"special": true
|
2011 |
+
},
|
2012 |
+
"128251": {
|
2013 |
+
"content": "<|reserved_special_token_243|>",
|
2014 |
+
"lstrip": false,
|
2015 |
+
"normalized": false,
|
2016 |
+
"rstrip": false,
|
2017 |
+
"single_word": false,
|
2018 |
+
"special": true
|
2019 |
+
},
|
2020 |
+
"128252": {
|
2021 |
+
"content": "<|reserved_special_token_244|>",
|
2022 |
+
"lstrip": false,
|
2023 |
+
"normalized": false,
|
2024 |
+
"rstrip": false,
|
2025 |
+
"single_word": false,
|
2026 |
+
"special": true
|
2027 |
+
},
|
2028 |
+
"128253": {
|
2029 |
+
"content": "<|reserved_special_token_245|>",
|
2030 |
+
"lstrip": false,
|
2031 |
+
"normalized": false,
|
2032 |
+
"rstrip": false,
|
2033 |
+
"single_word": false,
|
2034 |
+
"special": true
|
2035 |
+
},
|
2036 |
+
"128254": {
|
2037 |
+
"content": "<|reserved_special_token_246|>",
|
2038 |
+
"lstrip": false,
|
2039 |
+
"normalized": false,
|
2040 |
+
"rstrip": false,
|
2041 |
+
"single_word": false,
|
2042 |
+
"special": true
|
2043 |
+
},
|
2044 |
+
"128255": {
|
2045 |
+
"content": "<|reserved_special_token_247|>",
|
2046 |
+
"lstrip": false,
|
2047 |
+
"normalized": false,
|
2048 |
+
"rstrip": false,
|
2049 |
+
"single_word": false,
|
2050 |
+
"special": true
|
2051 |
+
}
|
2052 |
+
},
|
2053 |
+
"bos_token": "<|begin_of_text|>",
|
2054 |
+
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|end_of_text|>",
|
2056 |
+
"extra_special_tokens": {},
|
2057 |
+
"model_input_names": [
|
2058 |
+
"input_ids",
|
2059 |
+
"attention_mask"
|
2060 |
+
],
|
2061 |
+
"model_max_length": 131072,
|
2062 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
2063 |
+
"padding_side": "right",
|
2064 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
2065 |
+
"unk_token": null
|
2066 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3381 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 2386,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 0.0020955574182732607,
|
14 |
+
"grad_norm": 0.5915184020996094,
|
15 |
+
"learning_rate": 0.0001996647108130763,
|
16 |
+
"loss": 1.2488,
|
17 |
+
"step": 5
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.004191114836546521,
|
21 |
+
"grad_norm": 0.6416106224060059,
|
22 |
+
"learning_rate": 0.00019924559932942164,
|
23 |
+
"loss": 0.8074,
|
24 |
+
"step": 10
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.006286672254819782,
|
28 |
+
"grad_norm": 0.47403833270072937,
|
29 |
+
"learning_rate": 0.000198826487845767,
|
30 |
+
"loss": 0.5298,
|
31 |
+
"step": 15
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.008382229673093043,
|
35 |
+
"grad_norm": 0.49060583114624023,
|
36 |
+
"learning_rate": 0.00019840737636211232,
|
37 |
+
"loss": 0.4396,
|
38 |
+
"step": 20
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.010477787091366304,
|
42 |
+
"grad_norm": 0.3994845449924469,
|
43 |
+
"learning_rate": 0.00019798826487845767,
|
44 |
+
"loss": 0.3997,
|
45 |
+
"step": 25
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.012573344509639563,
|
49 |
+
"grad_norm": 5.743133068084717,
|
50 |
+
"learning_rate": 0.00019756915339480302,
|
51 |
+
"loss": 0.3571,
|
52 |
+
"step": 30
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.014668901927912825,
|
56 |
+
"grad_norm": 0.4928306043148041,
|
57 |
+
"learning_rate": 0.00019715004191114837,
|
58 |
+
"loss": 0.3467,
|
59 |
+
"step": 35
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.016764459346186086,
|
63 |
+
"grad_norm": 333.243896484375,
|
64 |
+
"learning_rate": 0.00019673093042749373,
|
65 |
+
"loss": 0.3173,
|
66 |
+
"step": 40
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.018860016764459347,
|
70 |
+
"grad_norm": 0.5272846817970276,
|
71 |
+
"learning_rate": 0.00019631181894383908,
|
72 |
+
"loss": 0.2952,
|
73 |
+
"step": 45
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.020955574182732608,
|
77 |
+
"grad_norm": 3.5901286602020264,
|
78 |
+
"learning_rate": 0.00019589270746018443,
|
79 |
+
"loss": 0.2935,
|
80 |
+
"step": 50
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.02305113160100587,
|
84 |
+
"grad_norm": 0.5013518929481506,
|
85 |
+
"learning_rate": 0.00019547359597652975,
|
86 |
+
"loss": 0.3024,
|
87 |
+
"step": 55
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.025146689019279127,
|
91 |
+
"grad_norm": 16.086902618408203,
|
92 |
+
"learning_rate": 0.0001950544844928751,
|
93 |
+
"loss": 0.2683,
|
94 |
+
"step": 60
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.027242246437552388,
|
98 |
+
"grad_norm": 0.30715975165367126,
|
99 |
+
"learning_rate": 0.00019463537300922046,
|
100 |
+
"loss": 0.2653,
|
101 |
+
"step": 65
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.02933780385582565,
|
105 |
+
"grad_norm": 0.33719402551651,
|
106 |
+
"learning_rate": 0.0001942162615255658,
|
107 |
+
"loss": 0.2575,
|
108 |
+
"step": 70
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.03143336127409891,
|
112 |
+
"grad_norm": 0.3756738305091858,
|
113 |
+
"learning_rate": 0.00019379715004191116,
|
114 |
+
"loss": 0.2449,
|
115 |
+
"step": 75
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.03352891869237217,
|
119 |
+
"grad_norm": 0.3635186553001404,
|
120 |
+
"learning_rate": 0.0001933780385582565,
|
121 |
+
"loss": 0.2538,
|
122 |
+
"step": 80
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.03562447611064543,
|
126 |
+
"grad_norm": 0.3560231328010559,
|
127 |
+
"learning_rate": 0.00019295892707460186,
|
128 |
+
"loss": 0.2435,
|
129 |
+
"step": 85
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.037720033528918694,
|
133 |
+
"grad_norm": 0.371216356754303,
|
134 |
+
"learning_rate": 0.00019253981559094722,
|
135 |
+
"loss": 0.2329,
|
136 |
+
"step": 90
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.039815590947191955,
|
140 |
+
"grad_norm": 0.45535510778427124,
|
141 |
+
"learning_rate": 0.00019212070410729254,
|
142 |
+
"loss": 0.2338,
|
143 |
+
"step": 95
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.041911148365465216,
|
147 |
+
"grad_norm": 15.063165664672852,
|
148 |
+
"learning_rate": 0.0001917015926236379,
|
149 |
+
"loss": 0.2353,
|
150 |
+
"step": 100
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.04400670578373848,
|
154 |
+
"grad_norm": 0.308463454246521,
|
155 |
+
"learning_rate": 0.00019128248113998324,
|
156 |
+
"loss": 0.2323,
|
157 |
+
"step": 105
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.04610226320201174,
|
161 |
+
"grad_norm": 0.29910165071487427,
|
162 |
+
"learning_rate": 0.0001908633696563286,
|
163 |
+
"loss": 0.2222,
|
164 |
+
"step": 110
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.04819782062028499,
|
168 |
+
"grad_norm": 0.3254060745239258,
|
169 |
+
"learning_rate": 0.00019044425817267395,
|
170 |
+
"loss": 0.216,
|
171 |
+
"step": 115
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.050293378038558254,
|
175 |
+
"grad_norm": 0.2623255252838135,
|
176 |
+
"learning_rate": 0.0001900251466890193,
|
177 |
+
"loss": 0.2136,
|
178 |
+
"step": 120
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.052388935456831515,
|
182 |
+
"grad_norm": 0.2627584636211395,
|
183 |
+
"learning_rate": 0.00018960603520536465,
|
184 |
+
"loss": 0.2118,
|
185 |
+
"step": 125
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.054484492875104776,
|
189 |
+
"grad_norm": 0.28595617413520813,
|
190 |
+
"learning_rate": 0.00018918692372170998,
|
191 |
+
"loss": 0.2088,
|
192 |
+
"step": 130
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.05658005029337804,
|
196 |
+
"grad_norm": 0.550282895565033,
|
197 |
+
"learning_rate": 0.00018876781223805533,
|
198 |
+
"loss": 0.2198,
|
199 |
+
"step": 135
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.0586756077116513,
|
203 |
+
"grad_norm": 0.296385258436203,
|
204 |
+
"learning_rate": 0.00018834870075440068,
|
205 |
+
"loss": 0.2219,
|
206 |
+
"step": 140
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.06077116512992456,
|
210 |
+
"grad_norm": 0.3291824460029602,
|
211 |
+
"learning_rate": 0.00018792958927074603,
|
212 |
+
"loss": 0.2059,
|
213 |
+
"step": 145
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.06286672254819782,
|
217 |
+
"grad_norm": 0.27933308482170105,
|
218 |
+
"learning_rate": 0.00018751047778709136,
|
219 |
+
"loss": 0.2001,
|
220 |
+
"step": 150
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.06496227996647108,
|
224 |
+
"grad_norm": 0.2848331332206726,
|
225 |
+
"learning_rate": 0.00018709136630343674,
|
226 |
+
"loss": 0.1999,
|
227 |
+
"step": 155
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.06705783738474434,
|
231 |
+
"grad_norm": 0.25534388422966003,
|
232 |
+
"learning_rate": 0.0001866722548197821,
|
233 |
+
"loss": 0.1977,
|
234 |
+
"step": 160
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.0691533948030176,
|
238 |
+
"grad_norm": 2.9550936222076416,
|
239 |
+
"learning_rate": 0.0001862531433361274,
|
240 |
+
"loss": 0.2004,
|
241 |
+
"step": 165
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.07124895222129086,
|
245 |
+
"grad_norm": 0.35537609457969666,
|
246 |
+
"learning_rate": 0.00018583403185247276,
|
247 |
+
"loss": 0.2131,
|
248 |
+
"step": 170
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.07334450963956413,
|
252 |
+
"grad_norm": 47.72193908691406,
|
253 |
+
"learning_rate": 0.00018541492036881812,
|
254 |
+
"loss": 0.2016,
|
255 |
+
"step": 175
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.07544006705783739,
|
259 |
+
"grad_norm": 0.3546775281429291,
|
260 |
+
"learning_rate": 0.00018499580888516347,
|
261 |
+
"loss": 0.1998,
|
262 |
+
"step": 180
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.07753562447611065,
|
266 |
+
"grad_norm": 0.2701320946216583,
|
267 |
+
"learning_rate": 0.0001845766974015088,
|
268 |
+
"loss": 0.1948,
|
269 |
+
"step": 185
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.07963118189438391,
|
273 |
+
"grad_norm": 0.2246120572090149,
|
274 |
+
"learning_rate": 0.00018415758591785414,
|
275 |
+
"loss": 0.1882,
|
276 |
+
"step": 190
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.08172673931265717,
|
280 |
+
"grad_norm": 0.27891814708709717,
|
281 |
+
"learning_rate": 0.00018373847443419952,
|
282 |
+
"loss": 0.1879,
|
283 |
+
"step": 195
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.08382229673093043,
|
287 |
+
"grad_norm": 0.4772103428840637,
|
288 |
+
"learning_rate": 0.00018331936295054485,
|
289 |
+
"loss": 0.2069,
|
290 |
+
"step": 200
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.08591785414920369,
|
294 |
+
"grad_norm": 2.367286205291748,
|
295 |
+
"learning_rate": 0.0001829002514668902,
|
296 |
+
"loss": 0.2043,
|
297 |
+
"step": 205
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.08801341156747695,
|
301 |
+
"grad_norm": 0.30191686749458313,
|
302 |
+
"learning_rate": 0.00018248113998323555,
|
303 |
+
"loss": 0.1978,
|
304 |
+
"step": 210
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.09010896898575022,
|
308 |
+
"grad_norm": 0.22913698852062225,
|
309 |
+
"learning_rate": 0.0001820620284995809,
|
310 |
+
"loss": 0.1937,
|
311 |
+
"step": 215
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.09220452640402348,
|
315 |
+
"grad_norm": 0.26689326763153076,
|
316 |
+
"learning_rate": 0.00018164291701592623,
|
317 |
+
"loss": 0.1892,
|
318 |
+
"step": 220
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.09430008382229674,
|
322 |
+
"grad_norm": 0.26441484689712524,
|
323 |
+
"learning_rate": 0.00018122380553227158,
|
324 |
+
"loss": 0.1924,
|
325 |
+
"step": 225
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.09639564124056998,
|
329 |
+
"grad_norm": 0.2602805197238922,
|
330 |
+
"learning_rate": 0.00018080469404861696,
|
331 |
+
"loss": 0.1856,
|
332 |
+
"step": 230
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.09849119865884325,
|
336 |
+
"grad_norm": 0.21042250096797943,
|
337 |
+
"learning_rate": 0.0001803855825649623,
|
338 |
+
"loss": 0.1848,
|
339 |
+
"step": 235
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.10058675607711651,
|
343 |
+
"grad_norm": 1.8752623796463013,
|
344 |
+
"learning_rate": 0.00017996647108130763,
|
345 |
+
"loss": 0.1822,
|
346 |
+
"step": 240
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.10268231349538977,
|
350 |
+
"grad_norm": 0.3879601061344147,
|
351 |
+
"learning_rate": 0.00017954735959765299,
|
352 |
+
"loss": 0.1979,
|
353 |
+
"step": 245
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.10477787091366303,
|
357 |
+
"grad_norm": 0.27347472310066223,
|
358 |
+
"learning_rate": 0.00017912824811399834,
|
359 |
+
"loss": 0.1903,
|
360 |
+
"step": 250
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.10687342833193629,
|
364 |
+
"grad_norm": 0.24279960989952087,
|
365 |
+
"learning_rate": 0.0001787091366303437,
|
366 |
+
"loss": 0.1848,
|
367 |
+
"step": 255
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.10896898575020955,
|
371 |
+
"grad_norm": 0.275285005569458,
|
372 |
+
"learning_rate": 0.00017829002514668901,
|
373 |
+
"loss": 0.1848,
|
374 |
+
"step": 260
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.11106454316848281,
|
378 |
+
"grad_norm": 0.33457309007644653,
|
379 |
+
"learning_rate": 0.00017787091366303437,
|
380 |
+
"loss": 0.1851,
|
381 |
+
"step": 265
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.11316010058675607,
|
385 |
+
"grad_norm": 0.5345426797866821,
|
386 |
+
"learning_rate": 0.00017745180217937974,
|
387 |
+
"loss": 0.189,
|
388 |
+
"step": 270
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.11525565800502934,
|
392 |
+
"grad_norm": 0.3533399701118469,
|
393 |
+
"learning_rate": 0.00017703269069572507,
|
394 |
+
"loss": 0.1835,
|
395 |
+
"step": 275
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.1173512154233026,
|
399 |
+
"grad_norm": 0.3257920742034912,
|
400 |
+
"learning_rate": 0.00017661357921207042,
|
401 |
+
"loss": 0.1892,
|
402 |
+
"step": 280
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.11944677284157586,
|
406 |
+
"grad_norm": 0.21177901327610016,
|
407 |
+
"learning_rate": 0.00017619446772841577,
|
408 |
+
"loss": 0.1818,
|
409 |
+
"step": 285
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.12154233025984912,
|
413 |
+
"grad_norm": 0.20798452198505402,
|
414 |
+
"learning_rate": 0.00017577535624476112,
|
415 |
+
"loss": 0.1792,
|
416 |
+
"step": 290
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.12363788767812238,
|
420 |
+
"grad_norm": 0.21963848173618317,
|
421 |
+
"learning_rate": 0.00017535624476110645,
|
422 |
+
"loss": 0.1776,
|
423 |
+
"step": 295
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.12573344509639564,
|
427 |
+
"grad_norm": 0.22277575731277466,
|
428 |
+
"learning_rate": 0.0001749371332774518,
|
429 |
+
"loss": 0.178,
|
430 |
+
"step": 300
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.12782900251466892,
|
434 |
+
"grad_norm": 0.22803856432437897,
|
435 |
+
"learning_rate": 0.00017451802179379715,
|
436 |
+
"loss": 0.1732,
|
437 |
+
"step": 305
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.12992455993294216,
|
441 |
+
"grad_norm": 0.20474207401275635,
|
442 |
+
"learning_rate": 0.0001740989103101425,
|
443 |
+
"loss": 0.173,
|
444 |
+
"step": 310
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.1320201173512154,
|
448 |
+
"grad_norm": 0.23283089697360992,
|
449 |
+
"learning_rate": 0.00017367979882648786,
|
450 |
+
"loss": 0.1752,
|
451 |
+
"step": 315
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.13411567476948869,
|
455 |
+
"grad_norm": 0.24834850430488586,
|
456 |
+
"learning_rate": 0.0001732606873428332,
|
457 |
+
"loss": 0.1727,
|
458 |
+
"step": 320
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.13621123218776193,
|
462 |
+
"grad_norm": 0.2943226993083954,
|
463 |
+
"learning_rate": 0.00017284157585917856,
|
464 |
+
"loss": 0.1758,
|
465 |
+
"step": 325
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.1383067896060352,
|
469 |
+
"grad_norm": 0.28577786684036255,
|
470 |
+
"learning_rate": 0.00017242246437552388,
|
471 |
+
"loss": 0.1835,
|
472 |
+
"step": 330
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.14040234702430845,
|
476 |
+
"grad_norm": 0.22449374198913574,
|
477 |
+
"learning_rate": 0.00017200335289186924,
|
478 |
+
"loss": 0.1795,
|
479 |
+
"step": 335
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.14249790444258173,
|
483 |
+
"grad_norm": 0.3676876425743103,
|
484 |
+
"learning_rate": 0.0001715842414082146,
|
485 |
+
"loss": 0.1771,
|
486 |
+
"step": 340
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.14459346186085498,
|
490 |
+
"grad_norm": 0.4172014594078064,
|
491 |
+
"learning_rate": 0.00017116512992455994,
|
492 |
+
"loss": 0.197,
|
493 |
+
"step": 345
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.14668901927912825,
|
497 |
+
"grad_norm": 0.26507022976875305,
|
498 |
+
"learning_rate": 0.0001707460184409053,
|
499 |
+
"loss": 0.181,
|
500 |
+
"step": 350
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.1487845766974015,
|
504 |
+
"grad_norm": 0.2308947890996933,
|
505 |
+
"learning_rate": 0.00017032690695725064,
|
506 |
+
"loss": 0.1767,
|
507 |
+
"step": 355
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.15088013411567477,
|
511 |
+
"grad_norm": 0.30771297216415405,
|
512 |
+
"learning_rate": 0.000169907795473596,
|
513 |
+
"loss": 0.1832,
|
514 |
+
"step": 360
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.15297569153394802,
|
518 |
+
"grad_norm": 0.23101018369197845,
|
519 |
+
"learning_rate": 0.00016948868398994132,
|
520 |
+
"loss": 0.1811,
|
521 |
+
"step": 365
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.1550712489522213,
|
525 |
+
"grad_norm": 0.20816421508789062,
|
526 |
+
"learning_rate": 0.00016906957250628667,
|
527 |
+
"loss": 0.1755,
|
528 |
+
"step": 370
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.15716680637049454,
|
532 |
+
"grad_norm": 0.2107459455728531,
|
533 |
+
"learning_rate": 0.00016865046102263202,
|
534 |
+
"loss": 0.1726,
|
535 |
+
"step": 375
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.15926236378876782,
|
539 |
+
"grad_norm": 2.224956750869751,
|
540 |
+
"learning_rate": 0.00016823134953897737,
|
541 |
+
"loss": 0.1718,
|
542 |
+
"step": 380
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.16135792120704107,
|
546 |
+
"grad_norm": 0.22022977471351624,
|
547 |
+
"learning_rate": 0.00016781223805532273,
|
548 |
+
"loss": 0.1725,
|
549 |
+
"step": 385
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.16345347862531434,
|
553 |
+
"grad_norm": 0.1845213919878006,
|
554 |
+
"learning_rate": 0.00016739312657166808,
|
555 |
+
"loss": 0.1677,
|
556 |
+
"step": 390
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.1655490360435876,
|
560 |
+
"grad_norm": 0.21298770606517792,
|
561 |
+
"learning_rate": 0.00016697401508801343,
|
562 |
+
"loss": 0.1734,
|
563 |
+
"step": 395
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.16764459346186086,
|
567 |
+
"grad_norm": 0.20876356959342957,
|
568 |
+
"learning_rate": 0.00016655490360435878,
|
569 |
+
"loss": 0.1761,
|
570 |
+
"step": 400
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.1697401508801341,
|
574 |
+
"grad_norm": 0.21667592227458954,
|
575 |
+
"learning_rate": 0.0001661357921207041,
|
576 |
+
"loss": 0.1668,
|
577 |
+
"step": 405
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.17183570829840739,
|
581 |
+
"grad_norm": 2.4301416873931885,
|
582 |
+
"learning_rate": 0.00016571668063704946,
|
583 |
+
"loss": 0.1697,
|
584 |
+
"step": 410
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.17393126571668063,
|
588 |
+
"grad_norm": 0.43861570954322815,
|
589 |
+
"learning_rate": 0.0001652975691533948,
|
590 |
+
"loss": 0.1804,
|
591 |
+
"step": 415
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.1760268231349539,
|
595 |
+
"grad_norm": 0.2521713078022003,
|
596 |
+
"learning_rate": 0.00016487845766974016,
|
597 |
+
"loss": 0.1762,
|
598 |
+
"step": 420
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.17812238055322716,
|
602 |
+
"grad_norm": 0.20923659205436707,
|
603 |
+
"learning_rate": 0.00016445934618608551,
|
604 |
+
"loss": 0.1695,
|
605 |
+
"step": 425
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.18021793797150043,
|
609 |
+
"grad_norm": 0.20591603219509125,
|
610 |
+
"learning_rate": 0.00016404023470243087,
|
611 |
+
"loss": 0.1729,
|
612 |
+
"step": 430
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.18231349538977368,
|
616 |
+
"grad_norm": 2.5188469886779785,
|
617 |
+
"learning_rate": 0.00016362112321877622,
|
618 |
+
"loss": 0.1723,
|
619 |
+
"step": 435
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.18440905280804695,
|
623 |
+
"grad_norm": 0.2523597478866577,
|
624 |
+
"learning_rate": 0.00016320201173512154,
|
625 |
+
"loss": 0.174,
|
626 |
+
"step": 440
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.1865046102263202,
|
630 |
+
"grad_norm": 0.23274292051792145,
|
631 |
+
"learning_rate": 0.0001627829002514669,
|
632 |
+
"loss": 0.1707,
|
633 |
+
"step": 445
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.18860016764459347,
|
637 |
+
"grad_norm": 0.26748543977737427,
|
638 |
+
"learning_rate": 0.00016236378876781225,
|
639 |
+
"loss": 0.1686,
|
640 |
+
"step": 450
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.19069572506286672,
|
644 |
+
"grad_norm": 0.2876422107219696,
|
645 |
+
"learning_rate": 0.0001619446772841576,
|
646 |
+
"loss": 0.1723,
|
647 |
+
"step": 455
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.19279128248113997,
|
651 |
+
"grad_norm": 0.5347093939781189,
|
652 |
+
"learning_rate": 0.00016152556580050292,
|
653 |
+
"loss": 0.1873,
|
654 |
+
"step": 460
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.19488683989941324,
|
658 |
+
"grad_norm": 0.2463475912809372,
|
659 |
+
"learning_rate": 0.0001611064543168483,
|
660 |
+
"loss": 0.1817,
|
661 |
+
"step": 465
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.1969823973176865,
|
665 |
+
"grad_norm": 0.21807396411895752,
|
666 |
+
"learning_rate": 0.00016068734283319365,
|
667 |
+
"loss": 0.1751,
|
668 |
+
"step": 470
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.19907795473595977,
|
672 |
+
"grad_norm": 0.1950008124113083,
|
673 |
+
"learning_rate": 0.00016026823134953898,
|
674 |
+
"loss": 0.1723,
|
675 |
+
"step": 475
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.20117351215423301,
|
679 |
+
"grad_norm": 0.19139733910560608,
|
680 |
+
"learning_rate": 0.00015984911986588433,
|
681 |
+
"loss": 0.168,
|
682 |
+
"step": 480
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.2032690695725063,
|
686 |
+
"grad_norm": 0.24496974050998688,
|
687 |
+
"learning_rate": 0.00015943000838222968,
|
688 |
+
"loss": 0.1713,
|
689 |
+
"step": 485
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.20536462699077954,
|
693 |
+
"grad_norm": 0.2883533239364624,
|
694 |
+
"learning_rate": 0.00015901089689857503,
|
695 |
+
"loss": 0.1758,
|
696 |
+
"step": 490
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.2074601844090528,
|
700 |
+
"grad_norm": 0.2685905694961548,
|
701 |
+
"learning_rate": 0.00015859178541492036,
|
702 |
+
"loss": 0.1789,
|
703 |
+
"step": 495
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.20955574182732606,
|
707 |
+
"grad_norm": 0.22861076891422272,
|
708 |
+
"learning_rate": 0.0001581726739312657,
|
709 |
+
"loss": 0.1751,
|
710 |
+
"step": 500
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.21165129924559933,
|
714 |
+
"grad_norm": 0.4216708242893219,
|
715 |
+
"learning_rate": 0.0001577535624476111,
|
716 |
+
"loss": 0.1765,
|
717 |
+
"step": 505
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.21374685666387258,
|
721 |
+
"grad_norm": 0.33128198981285095,
|
722 |
+
"learning_rate": 0.0001573344509639564,
|
723 |
+
"loss": 0.1908,
|
724 |
+
"step": 510
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.21584241408214586,
|
728 |
+
"grad_norm": 0.21954227983951569,
|
729 |
+
"learning_rate": 0.00015691533948030176,
|
730 |
+
"loss": 0.1707,
|
731 |
+
"step": 515
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 0.2179379715004191,
|
735 |
+
"grad_norm": 0.22218674421310425,
|
736 |
+
"learning_rate": 0.00015649622799664712,
|
737 |
+
"loss": 0.1695,
|
738 |
+
"step": 520
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.22003352891869238,
|
742 |
+
"grad_norm": 0.23518136143684387,
|
743 |
+
"learning_rate": 0.00015607711651299247,
|
744 |
+
"loss": 0.1677,
|
745 |
+
"step": 525
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.22212908633696563,
|
749 |
+
"grad_norm": 0.4071219861507416,
|
750 |
+
"learning_rate": 0.0001556580050293378,
|
751 |
+
"loss": 0.1753,
|
752 |
+
"step": 530
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.2242246437552389,
|
756 |
+
"grad_norm": 0.25883597135543823,
|
757 |
+
"learning_rate": 0.00015523889354568314,
|
758 |
+
"loss": 0.1741,
|
759 |
+
"step": 535
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.22632020117351215,
|
763 |
+
"grad_norm": 0.19170518219470978,
|
764 |
+
"learning_rate": 0.00015481978206202852,
|
765 |
+
"loss": 0.17,
|
766 |
+
"step": 540
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.22841575859178542,
|
770 |
+
"grad_norm": 0.18559418618679047,
|
771 |
+
"learning_rate": 0.00015440067057837387,
|
772 |
+
"loss": 0.1701,
|
773 |
+
"step": 545
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.23051131601005867,
|
777 |
+
"grad_norm": 0.2035888284444809,
|
778 |
+
"learning_rate": 0.0001539815590947192,
|
779 |
+
"loss": 0.1623,
|
780 |
+
"step": 550
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.23260687342833195,
|
784 |
+
"grad_norm": 7.4185709953308105,
|
785 |
+
"learning_rate": 0.00015356244761106455,
|
786 |
+
"loss": 0.1654,
|
787 |
+
"step": 555
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.2347024308466052,
|
791 |
+
"grad_norm": 0.21483619511127472,
|
792 |
+
"learning_rate": 0.0001531433361274099,
|
793 |
+
"loss": 0.1664,
|
794 |
+
"step": 560
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.23679798826487847,
|
798 |
+
"grad_norm": 0.2908990979194641,
|
799 |
+
"learning_rate": 0.00015272422464375525,
|
800 |
+
"loss": 0.1733,
|
801 |
+
"step": 565
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.23889354568315171,
|
805 |
+
"grad_norm": 0.34150460362434387,
|
806 |
+
"learning_rate": 0.00015230511316010058,
|
807 |
+
"loss": 0.1721,
|
808 |
+
"step": 570
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.240989103101425,
|
812 |
+
"grad_norm": 0.26667365431785583,
|
813 |
+
"learning_rate": 0.00015188600167644593,
|
814 |
+
"loss": 0.1778,
|
815 |
+
"step": 575
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 0.24308466051969824,
|
819 |
+
"grad_norm": 0.2024029940366745,
|
820 |
+
"learning_rate": 0.0001514668901927913,
|
821 |
+
"loss": 0.1681,
|
822 |
+
"step": 580
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.2451802179379715,
|
826 |
+
"grad_norm": 0.1918814480304718,
|
827 |
+
"learning_rate": 0.00015104777870913663,
|
828 |
+
"loss": 0.1672,
|
829 |
+
"step": 585
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.24727577535624476,
|
833 |
+
"grad_norm": 0.22173915803432465,
|
834 |
+
"learning_rate": 0.00015062866722548199,
|
835 |
+
"loss": 0.1629,
|
836 |
+
"step": 590
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.24937133277451803,
|
840 |
+
"grad_norm": 0.20861753821372986,
|
841 |
+
"learning_rate": 0.00015020955574182734,
|
842 |
+
"loss": 0.1695,
|
843 |
+
"step": 595
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.2514668901927913,
|
847 |
+
"grad_norm": 0.2476891726255417,
|
848 |
+
"learning_rate": 0.0001497904442581727,
|
849 |
+
"loss": 0.1687,
|
850 |
+
"step": 600
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 0.25356244761106456,
|
854 |
+
"grad_norm": 0.23498353362083435,
|
855 |
+
"learning_rate": 0.00014937133277451801,
|
856 |
+
"loss": 0.1721,
|
857 |
+
"step": 605
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 0.25565800502933783,
|
861 |
+
"grad_norm": 0.24014067649841309,
|
862 |
+
"learning_rate": 0.00014895222129086337,
|
863 |
+
"loss": 0.1643,
|
864 |
+
"step": 610
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.25775356244761105,
|
868 |
+
"grad_norm": 1.1056888103485107,
|
869 |
+
"learning_rate": 0.00014853310980720872,
|
870 |
+
"loss": 0.1652,
|
871 |
+
"step": 615
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.2598491198658843,
|
875 |
+
"grad_norm": 0.3467954397201538,
|
876 |
+
"learning_rate": 0.00014811399832355407,
|
877 |
+
"loss": 0.1741,
|
878 |
+
"step": 620
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.2619446772841576,
|
882 |
+
"grad_norm": 0.29533931612968445,
|
883 |
+
"learning_rate": 0.00014769488683989942,
|
884 |
+
"loss": 0.1768,
|
885 |
+
"step": 625
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.2640402347024308,
|
889 |
+
"grad_norm": 0.2000960111618042,
|
890 |
+
"learning_rate": 0.00014727577535624477,
|
891 |
+
"loss": 0.1662,
|
892 |
+
"step": 630
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.2661357921207041,
|
896 |
+
"grad_norm": 0.18396534025669098,
|
897 |
+
"learning_rate": 0.00014685666387259013,
|
898 |
+
"loss": 0.166,
|
899 |
+
"step": 635
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 0.26823134953897737,
|
903 |
+
"grad_norm": 0.18797029554843903,
|
904 |
+
"learning_rate": 0.00014643755238893545,
|
905 |
+
"loss": 0.1624,
|
906 |
+
"step": 640
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.27032690695725065,
|
910 |
+
"grad_norm": 0.1914837509393692,
|
911 |
+
"learning_rate": 0.0001460184409052808,
|
912 |
+
"loss": 0.1625,
|
913 |
+
"step": 645
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.27242246437552387,
|
917 |
+
"grad_norm": 0.18006779253482819,
|
918 |
+
"learning_rate": 0.00014559932942162615,
|
919 |
+
"loss": 0.1602,
|
920 |
+
"step": 650
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.27451802179379714,
|
924 |
+
"grad_norm": 0.19413350522518158,
|
925 |
+
"learning_rate": 0.0001451802179379715,
|
926 |
+
"loss": 0.1632,
|
927 |
+
"step": 655
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.2766135792120704,
|
931 |
+
"grad_norm": 0.19674436748027802,
|
932 |
+
"learning_rate": 0.00014476110645431686,
|
933 |
+
"loss": 0.1593,
|
934 |
+
"step": 660
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.2787091366303437,
|
938 |
+
"grad_norm": 0.16716861724853516,
|
939 |
+
"learning_rate": 0.0001443419949706622,
|
940 |
+
"loss": 0.161,
|
941 |
+
"step": 665
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.2808046940486169,
|
945 |
+
"grad_norm": 0.1591351330280304,
|
946 |
+
"learning_rate": 0.00014392288348700756,
|
947 |
+
"loss": 0.163,
|
948 |
+
"step": 670
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.2829002514668902,
|
952 |
+
"grad_norm": 0.16973218321800232,
|
953 |
+
"learning_rate": 0.0001435037720033529,
|
954 |
+
"loss": 0.1665,
|
955 |
+
"step": 675
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 0.28499580888516346,
|
959 |
+
"grad_norm": 0.16811800003051758,
|
960 |
+
"learning_rate": 0.00014308466051969824,
|
961 |
+
"loss": 0.1586,
|
962 |
+
"step": 680
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.28709136630343673,
|
966 |
+
"grad_norm": 0.21386906504631042,
|
967 |
+
"learning_rate": 0.0001426655490360436,
|
968 |
+
"loss": 0.1589,
|
969 |
+
"step": 685
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.28918692372170995,
|
973 |
+
"grad_norm": 0.17704640328884125,
|
974 |
+
"learning_rate": 0.00014224643755238894,
|
975 |
+
"loss": 0.1597,
|
976 |
+
"step": 690
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.29128248113998323,
|
980 |
+
"grad_norm": 0.1727607399225235,
|
981 |
+
"learning_rate": 0.0001418273260687343,
|
982 |
+
"loss": 0.1565,
|
983 |
+
"step": 695
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.2933780385582565,
|
987 |
+
"grad_norm": 0.18027518689632416,
|
988 |
+
"learning_rate": 0.00014140821458507964,
|
989 |
+
"loss": 0.1597,
|
990 |
+
"step": 700
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.2954735959765298,
|
994 |
+
"grad_norm": 0.18142397701740265,
|
995 |
+
"learning_rate": 0.000140989103101425,
|
996 |
+
"loss": 0.1618,
|
997 |
+
"step": 705
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 0.297569153394803,
|
1001 |
+
"grad_norm": 0.18902671337127686,
|
1002 |
+
"learning_rate": 0.00014056999161777035,
|
1003 |
+
"loss": 0.1606,
|
1004 |
+
"step": 710
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.2996647108130763,
|
1008 |
+
"grad_norm": 0.2578323185443878,
|
1009 |
+
"learning_rate": 0.00014015088013411567,
|
1010 |
+
"loss": 0.1658,
|
1011 |
+
"step": 715
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.30176026823134955,
|
1015 |
+
"grad_norm": 0.2432331144809723,
|
1016 |
+
"learning_rate": 0.00013973176865046102,
|
1017 |
+
"loss": 0.1694,
|
1018 |
+
"step": 720
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.3038558256496228,
|
1022 |
+
"grad_norm": 0.1846640259027481,
|
1023 |
+
"learning_rate": 0.00013931265716680638,
|
1024 |
+
"loss": 0.1655,
|
1025 |
+
"step": 725
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 0.30595138306789604,
|
1029 |
+
"grad_norm": 0.1582545042037964,
|
1030 |
+
"learning_rate": 0.00013889354568315173,
|
1031 |
+
"loss": 0.1639,
|
1032 |
+
"step": 730
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 0.3080469404861693,
|
1036 |
+
"grad_norm": 0.16749900579452515,
|
1037 |
+
"learning_rate": 0.00013847443419949708,
|
1038 |
+
"loss": 0.1596,
|
1039 |
+
"step": 735
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 0.3101424979044426,
|
1043 |
+
"grad_norm": 0.17118974030017853,
|
1044 |
+
"learning_rate": 0.00013805532271584243,
|
1045 |
+
"loss": 0.1569,
|
1046 |
+
"step": 740
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.31223805532271587,
|
1050 |
+
"grad_norm": 0.16258081793785095,
|
1051 |
+
"learning_rate": 0.00013763621123218778,
|
1052 |
+
"loss": 0.1599,
|
1053 |
+
"step": 745
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.3143336127409891,
|
1057 |
+
"grad_norm": 0.17213059961795807,
|
1058 |
+
"learning_rate": 0.0001372170997485331,
|
1059 |
+
"loss": 0.1588,
|
1060 |
+
"step": 750
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.31642917015926236,
|
1064 |
+
"grad_norm": 0.18207783997058868,
|
1065 |
+
"learning_rate": 0.00013679798826487846,
|
1066 |
+
"loss": 0.1571,
|
1067 |
+
"step": 755
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 0.31852472757753564,
|
1071 |
+
"grad_norm": 0.19723886251449585,
|
1072 |
+
"learning_rate": 0.0001363788767812238,
|
1073 |
+
"loss": 0.1552,
|
1074 |
+
"step": 760
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.32062028499580886,
|
1078 |
+
"grad_norm": 0.17248809337615967,
|
1079 |
+
"learning_rate": 0.00013595976529756916,
|
1080 |
+
"loss": 0.1564,
|
1081 |
+
"step": 765
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 0.32271584241408213,
|
1085 |
+
"grad_norm": 0.18213661015033722,
|
1086 |
+
"learning_rate": 0.0001355406538139145,
|
1087 |
+
"loss": 0.1597,
|
1088 |
+
"step": 770
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.3248113998323554,
|
1092 |
+
"grad_norm": 0.1856526881456375,
|
1093 |
+
"learning_rate": 0.00013512154233025987,
|
1094 |
+
"loss": 0.1609,
|
1095 |
+
"step": 775
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.3269069572506287,
|
1099 |
+
"grad_norm": 0.16957145929336548,
|
1100 |
+
"learning_rate": 0.00013470243084660522,
|
1101 |
+
"loss": 0.1595,
|
1102 |
+
"step": 780
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 0.3290025146689019,
|
1106 |
+
"grad_norm": 0.17088639736175537,
|
1107 |
+
"learning_rate": 0.00013428331936295054,
|
1108 |
+
"loss": 0.161,
|
1109 |
+
"step": 785
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 0.3310980720871752,
|
1113 |
+
"grad_norm": 1.320410132408142,
|
1114 |
+
"learning_rate": 0.0001338642078792959,
|
1115 |
+
"loss": 0.165,
|
1116 |
+
"step": 790
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 0.33319362950544845,
|
1120 |
+
"grad_norm": 0.19440437853336334,
|
1121 |
+
"learning_rate": 0.00013344509639564125,
|
1122 |
+
"loss": 0.1602,
|
1123 |
+
"step": 795
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 0.3352891869237217,
|
1127 |
+
"grad_norm": 0.19590894877910614,
|
1128 |
+
"learning_rate": 0.0001330259849119866,
|
1129 |
+
"loss": 0.1616,
|
1130 |
+
"step": 800
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.33738474434199495,
|
1134 |
+
"grad_norm": 0.19055521488189697,
|
1135 |
+
"learning_rate": 0.00013260687342833192,
|
1136 |
+
"loss": 0.1638,
|
1137 |
+
"step": 805
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.3394803017602682,
|
1141 |
+
"grad_norm": 0.1577232927083969,
|
1142 |
+
"learning_rate": 0.00013218776194467727,
|
1143 |
+
"loss": 0.1582,
|
1144 |
+
"step": 810
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 0.3415758591785415,
|
1148 |
+
"grad_norm": 0.16225744783878326,
|
1149 |
+
"learning_rate": 0.00013176865046102265,
|
1150 |
+
"loss": 0.1555,
|
1151 |
+
"step": 815
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 0.34367141659681477,
|
1155 |
+
"grad_norm": 0.1565002202987671,
|
1156 |
+
"learning_rate": 0.000131349538977368,
|
1157 |
+
"loss": 0.1567,
|
1158 |
+
"step": 820
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 0.345766974015088,
|
1162 |
+
"grad_norm": 0.18790805339813232,
|
1163 |
+
"learning_rate": 0.00013093042749371333,
|
1164 |
+
"loss": 0.1581,
|
1165 |
+
"step": 825
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 0.34786253143336127,
|
1169 |
+
"grad_norm": 0.18632063269615173,
|
1170 |
+
"learning_rate": 0.00013051131601005868,
|
1171 |
+
"loss": 0.1621,
|
1172 |
+
"step": 830
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.34995808885163454,
|
1176 |
+
"grad_norm": 0.17684835195541382,
|
1177 |
+
"learning_rate": 0.00013009220452640403,
|
1178 |
+
"loss": 0.1591,
|
1179 |
+
"step": 835
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.3520536462699078,
|
1183 |
+
"grad_norm": 0.16213147342205048,
|
1184 |
+
"learning_rate": 0.00012967309304274938,
|
1185 |
+
"loss": 0.1593,
|
1186 |
+
"step": 840
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 0.35414920368818104,
|
1190 |
+
"grad_norm": 0.1656450480222702,
|
1191 |
+
"learning_rate": 0.0001292539815590947,
|
1192 |
+
"loss": 0.1617,
|
1193 |
+
"step": 845
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 0.3562447611064543,
|
1197 |
+
"grad_norm": 0.16887331008911133,
|
1198 |
+
"learning_rate": 0.0001288348700754401,
|
1199 |
+
"loss": 0.1601,
|
1200 |
+
"step": 850
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.3583403185247276,
|
1204 |
+
"grad_norm": 0.17660242319107056,
|
1205 |
+
"learning_rate": 0.00012841575859178544,
|
1206 |
+
"loss": 0.1575,
|
1207 |
+
"step": 855
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 0.36043587594300086,
|
1211 |
+
"grad_norm": 0.17625996470451355,
|
1212 |
+
"learning_rate": 0.00012799664710813076,
|
1213 |
+
"loss": 0.1597,
|
1214 |
+
"step": 860
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.3625314333612741,
|
1218 |
+
"grad_norm": 0.15301348268985748,
|
1219 |
+
"learning_rate": 0.00012757753562447612,
|
1220 |
+
"loss": 0.1597,
|
1221 |
+
"step": 865
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.36462699077954736,
|
1225 |
+
"grad_norm": 0.15253449976444244,
|
1226 |
+
"learning_rate": 0.00012715842414082147,
|
1227 |
+
"loss": 0.157,
|
1228 |
+
"step": 870
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 0.36672254819782063,
|
1232 |
+
"grad_norm": 0.16985070705413818,
|
1233 |
+
"learning_rate": 0.00012673931265716682,
|
1234 |
+
"loss": 0.1558,
|
1235 |
+
"step": 875
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 0.3688181056160939,
|
1239 |
+
"grad_norm": 0.1545540988445282,
|
1240 |
+
"learning_rate": 0.00012632020117351214,
|
1241 |
+
"loss": 0.1596,
|
1242 |
+
"step": 880
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 0.3709136630343671,
|
1246 |
+
"grad_norm": 0.1766255795955658,
|
1247 |
+
"learning_rate": 0.0001259010896898575,
|
1248 |
+
"loss": 0.1537,
|
1249 |
+
"step": 885
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 0.3730092204526404,
|
1253 |
+
"grad_norm": 0.15094798803329468,
|
1254 |
+
"learning_rate": 0.00012548197820620288,
|
1255 |
+
"loss": 0.1562,
|
1256 |
+
"step": 890
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.3751047778709137,
|
1260 |
+
"grad_norm": 0.16060136258602142,
|
1261 |
+
"learning_rate": 0.0001250628667225482,
|
1262 |
+
"loss": 0.158,
|
1263 |
+
"step": 895
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.37720033528918695,
|
1267 |
+
"grad_norm": 0.17947901785373688,
|
1268 |
+
"learning_rate": 0.00012464375523889355,
|
1269 |
+
"loss": 0.1583,
|
1270 |
+
"step": 900
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 0.37929589270746017,
|
1274 |
+
"grad_norm": 0.15727129578590393,
|
1275 |
+
"learning_rate": 0.0001242246437552389,
|
1276 |
+
"loss": 0.1529,
|
1277 |
+
"step": 905
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 0.38139145012573344,
|
1281 |
+
"grad_norm": 0.14456555247306824,
|
1282 |
+
"learning_rate": 0.00012380553227158426,
|
1283 |
+
"loss": 0.1573,
|
1284 |
+
"step": 910
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.3834870075440067,
|
1288 |
+
"grad_norm": 0.15629969537258148,
|
1289 |
+
"learning_rate": 0.00012338642078792958,
|
1290 |
+
"loss": 0.1607,
|
1291 |
+
"step": 915
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 0.38558256496227994,
|
1295 |
+
"grad_norm": 0.1958230435848236,
|
1296 |
+
"learning_rate": 0.00012296730930427493,
|
1297 |
+
"loss": 0.1572,
|
1298 |
+
"step": 920
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 0.3876781223805532,
|
1302 |
+
"grad_norm": 0.18159349262714386,
|
1303 |
+
"learning_rate": 0.00012254819782062028,
|
1304 |
+
"loss": 0.1565,
|
1305 |
+
"step": 925
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.3897736797988265,
|
1309 |
+
"grad_norm": 0.19391848146915436,
|
1310 |
+
"learning_rate": 0.00012212908633696564,
|
1311 |
+
"loss": 0.1552,
|
1312 |
+
"step": 930
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 0.39186923721709976,
|
1316 |
+
"grad_norm": 0.18596895039081573,
|
1317 |
+
"learning_rate": 0.00012170997485331099,
|
1318 |
+
"loss": 0.1623,
|
1319 |
+
"step": 935
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 0.393964794635373,
|
1323 |
+
"grad_norm": 0.175604447722435,
|
1324 |
+
"learning_rate": 0.00012129086336965634,
|
1325 |
+
"loss": 0.1593,
|
1326 |
+
"step": 940
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 0.39606035205364626,
|
1330 |
+
"grad_norm": 0.18805819749832153,
|
1331 |
+
"learning_rate": 0.00012087175188600168,
|
1332 |
+
"loss": 0.1603,
|
1333 |
+
"step": 945
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 0.39815590947191953,
|
1337 |
+
"grad_norm": 0.15223102271556854,
|
1338 |
+
"learning_rate": 0.00012045264040234703,
|
1339 |
+
"loss": 0.1568,
|
1340 |
+
"step": 950
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 0.4002514668901928,
|
1344 |
+
"grad_norm": 0.13771827518939972,
|
1345 |
+
"learning_rate": 0.00012003352891869237,
|
1346 |
+
"loss": 0.1553,
|
1347 |
+
"step": 955
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.40234702430846603,
|
1351 |
+
"grad_norm": 0.1633366495370865,
|
1352 |
+
"learning_rate": 0.00011961441743503772,
|
1353 |
+
"loss": 0.156,
|
1354 |
+
"step": 960
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.4044425817267393,
|
1358 |
+
"grad_norm": 0.17143379151821136,
|
1359 |
+
"learning_rate": 0.00011919530595138306,
|
1360 |
+
"loss": 0.1542,
|
1361 |
+
"step": 965
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 0.4065381391450126,
|
1365 |
+
"grad_norm": 0.16767437756061554,
|
1366 |
+
"learning_rate": 0.00011877619446772844,
|
1367 |
+
"loss": 0.1572,
|
1368 |
+
"step": 970
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 0.40863369656328585,
|
1372 |
+
"grad_norm": 0.16299773752689362,
|
1373 |
+
"learning_rate": 0.00011835708298407377,
|
1374 |
+
"loss": 0.1583,
|
1375 |
+
"step": 975
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 0.4107292539815591,
|
1379 |
+
"grad_norm": 0.15164397656917572,
|
1380 |
+
"learning_rate": 0.00011793797150041913,
|
1381 |
+
"loss": 0.1526,
|
1382 |
+
"step": 980
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 0.41282481139983235,
|
1386 |
+
"grad_norm": 0.1567896157503128,
|
1387 |
+
"learning_rate": 0.00011751886001676446,
|
1388 |
+
"loss": 0.154,
|
1389 |
+
"step": 985
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.4149203688181056,
|
1393 |
+
"grad_norm": 0.15943744778633118,
|
1394 |
+
"learning_rate": 0.00011709974853310982,
|
1395 |
+
"loss": 0.1533,
|
1396 |
+
"step": 990
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 0.4170159262363789,
|
1400 |
+
"grad_norm": 0.16572755575180054,
|
1401 |
+
"learning_rate": 0.00011668063704945515,
|
1402 |
+
"loss": 0.1559,
|
1403 |
+
"step": 995
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 0.4191114836546521,
|
1407 |
+
"grad_norm": 0.15907670557498932,
|
1408 |
+
"learning_rate": 0.0001162615255658005,
|
1409 |
+
"loss": 0.1558,
|
1410 |
+
"step": 1000
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.4212070410729254,
|
1414 |
+
"grad_norm": 0.1808643937110901,
|
1415 |
+
"learning_rate": 0.00011584241408214587,
|
1416 |
+
"loss": 0.1555,
|
1417 |
+
"step": 1005
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 0.42330259849119867,
|
1421 |
+
"grad_norm": 0.23819687962532043,
|
1422 |
+
"learning_rate": 0.00011542330259849121,
|
1423 |
+
"loss": 0.1579,
|
1424 |
+
"step": 1010
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 0.42539815590947194,
|
1428 |
+
"grad_norm": 0.24894015491008759,
|
1429 |
+
"learning_rate": 0.00011500419111483656,
|
1430 |
+
"loss": 0.1637,
|
1431 |
+
"step": 1015
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 0.42749371332774516,
|
1435 |
+
"grad_norm": 0.18128713965415955,
|
1436 |
+
"learning_rate": 0.0001145850796311819,
|
1437 |
+
"loss": 0.1605,
|
1438 |
+
"step": 1020
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 0.42958927074601844,
|
1442 |
+
"grad_norm": 0.1779192090034485,
|
1443 |
+
"learning_rate": 0.00011416596814752725,
|
1444 |
+
"loss": 0.1586,
|
1445 |
+
"step": 1025
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 0.4316848281642917,
|
1449 |
+
"grad_norm": 0.1617233157157898,
|
1450 |
+
"learning_rate": 0.00011374685666387259,
|
1451 |
+
"loss": 0.1548,
|
1452 |
+
"step": 1030
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 0.433780385582565,
|
1456 |
+
"grad_norm": 0.146457701921463,
|
1457 |
+
"learning_rate": 0.00011332774518021794,
|
1458 |
+
"loss": 0.1581,
|
1459 |
+
"step": 1035
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 0.4358759430008382,
|
1463 |
+
"grad_norm": 18.378135681152344,
|
1464 |
+
"learning_rate": 0.00011290863369656328,
|
1465 |
+
"loss": 0.1546,
|
1466 |
+
"step": 1040
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 0.4379715004191115,
|
1470 |
+
"grad_norm": 0.16601739823818207,
|
1471 |
+
"learning_rate": 0.00011248952221290864,
|
1472 |
+
"loss": 0.1573,
|
1473 |
+
"step": 1045
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 0.44006705783738476,
|
1477 |
+
"grad_norm": 0.18232333660125732,
|
1478 |
+
"learning_rate": 0.000112070410729254,
|
1479 |
+
"loss": 0.1546,
|
1480 |
+
"step": 1050
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 0.44216261525565803,
|
1484 |
+
"grad_norm": 0.15297749638557434,
|
1485 |
+
"learning_rate": 0.00011165129924559933,
|
1486 |
+
"loss": 0.1561,
|
1487 |
+
"step": 1055
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 0.44425817267393125,
|
1491 |
+
"grad_norm": 7.5409440994262695,
|
1492 |
+
"learning_rate": 0.00011123218776194469,
|
1493 |
+
"loss": 0.1614,
|
1494 |
+
"step": 1060
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 0.4463537300922045,
|
1498 |
+
"grad_norm": 0.1807660162448883,
|
1499 |
+
"learning_rate": 0.00011081307627829002,
|
1500 |
+
"loss": 0.1624,
|
1501 |
+
"step": 1065
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 0.4484492875104778,
|
1505 |
+
"grad_norm": 0.18783360719680786,
|
1506 |
+
"learning_rate": 0.00011039396479463538,
|
1507 |
+
"loss": 0.1609,
|
1508 |
+
"step": 1070
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 0.450544844928751,
|
1512 |
+
"grad_norm": 0.23045672476291656,
|
1513 |
+
"learning_rate": 0.00010997485331098071,
|
1514 |
+
"loss": 0.1618,
|
1515 |
+
"step": 1075
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 0.4526404023470243,
|
1519 |
+
"grad_norm": 0.2051040381193161,
|
1520 |
+
"learning_rate": 0.00010955574182732607,
|
1521 |
+
"loss": 0.164,
|
1522 |
+
"step": 1080
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 0.45473595976529757,
|
1526 |
+
"grad_norm": 0.17596812546253204,
|
1527 |
+
"learning_rate": 0.00010913663034367143,
|
1528 |
+
"loss": 0.1578,
|
1529 |
+
"step": 1085
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 0.45683151718357085,
|
1533 |
+
"grad_norm": 0.1564697027206421,
|
1534 |
+
"learning_rate": 0.00010871751886001677,
|
1535 |
+
"loss": 0.1549,
|
1536 |
+
"step": 1090
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 0.45892707460184406,
|
1540 |
+
"grad_norm": 0.2508351802825928,
|
1541 |
+
"learning_rate": 0.00010829840737636212,
|
1542 |
+
"loss": 0.1541,
|
1543 |
+
"step": 1095
|
1544 |
+
},
|
1545 |
+
{
|
1546 |
+
"epoch": 0.46102263202011734,
|
1547 |
+
"grad_norm": 0.17002500593662262,
|
1548 |
+
"learning_rate": 0.00010787929589270746,
|
1549 |
+
"loss": 0.1606,
|
1550 |
+
"step": 1100
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 0.4631181894383906,
|
1554 |
+
"grad_norm": 0.1768285632133484,
|
1555 |
+
"learning_rate": 0.00010746018440905281,
|
1556 |
+
"loss": 0.1533,
|
1557 |
+
"step": 1105
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 0.4652137468566639,
|
1561 |
+
"grad_norm": 0.21098843216896057,
|
1562 |
+
"learning_rate": 0.00010704107292539815,
|
1563 |
+
"loss": 0.1598,
|
1564 |
+
"step": 1110
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 0.4673093042749371,
|
1568 |
+
"grad_norm": 0.1743684709072113,
|
1569 |
+
"learning_rate": 0.0001066219614417435,
|
1570 |
+
"loss": 0.1577,
|
1571 |
+
"step": 1115
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 0.4694048616932104,
|
1575 |
+
"grad_norm": 0.18270978331565857,
|
1576 |
+
"learning_rate": 0.00010620284995808884,
|
1577 |
+
"loss": 0.1533,
|
1578 |
+
"step": 1120
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 0.47150041911148366,
|
1582 |
+
"grad_norm": 0.19265097379684448,
|
1583 |
+
"learning_rate": 0.00010578373847443422,
|
1584 |
+
"loss": 0.1545,
|
1585 |
+
"step": 1125
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 0.47359597652975693,
|
1589 |
+
"grad_norm": 0.19420358538627625,
|
1590 |
+
"learning_rate": 0.00010536462699077956,
|
1591 |
+
"loss": 0.1587,
|
1592 |
+
"step": 1130
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 0.47569153394803015,
|
1596 |
+
"grad_norm": 0.1721310317516327,
|
1597 |
+
"learning_rate": 0.00010494551550712491,
|
1598 |
+
"loss": 0.1577,
|
1599 |
+
"step": 1135
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.47778709136630343,
|
1603 |
+
"grad_norm": 0.1586717814207077,
|
1604 |
+
"learning_rate": 0.00010452640402347025,
|
1605 |
+
"loss": 0.1551,
|
1606 |
+
"step": 1140
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"epoch": 0.4798826487845767,
|
1610 |
+
"grad_norm": 1.5393892526626587,
|
1611 |
+
"learning_rate": 0.0001041072925398156,
|
1612 |
+
"loss": 0.1537,
|
1613 |
+
"step": 1145
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 0.48197820620285,
|
1617 |
+
"grad_norm": 0.17265351116657257,
|
1618 |
+
"learning_rate": 0.00010368818105616094,
|
1619 |
+
"loss": 0.1514,
|
1620 |
+
"step": 1150
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 0.4840737636211232,
|
1624 |
+
"grad_norm": 0.15501521527767181,
|
1625 |
+
"learning_rate": 0.00010326906957250629,
|
1626 |
+
"loss": 0.1559,
|
1627 |
+
"step": 1155
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 0.4861693210393965,
|
1631 |
+
"grad_norm": 0.1425572782754898,
|
1632 |
+
"learning_rate": 0.00010284995808885165,
|
1633 |
+
"loss": 0.1532,
|
1634 |
+
"step": 1160
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 0.48826487845766975,
|
1638 |
+
"grad_norm": 0.1547863483428955,
|
1639 |
+
"learning_rate": 0.00010243084660519699,
|
1640 |
+
"loss": 0.1557,
|
1641 |
+
"step": 1165
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 0.490360435875943,
|
1645 |
+
"grad_norm": 0.1579703986644745,
|
1646 |
+
"learning_rate": 0.00010201173512154234,
|
1647 |
+
"loss": 0.1568,
|
1648 |
+
"step": 1170
|
1649 |
+
},
|
1650 |
+
{
|
1651 |
+
"epoch": 0.49245599329421624,
|
1652 |
+
"grad_norm": 4.8748297691345215,
|
1653 |
+
"learning_rate": 0.00010159262363788768,
|
1654 |
+
"loss": 0.1542,
|
1655 |
+
"step": 1175
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 0.4945515507124895,
|
1659 |
+
"grad_norm": 0.16955487430095673,
|
1660 |
+
"learning_rate": 0.00010117351215423303,
|
1661 |
+
"loss": 0.1573,
|
1662 |
+
"step": 1180
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 0.4966471081307628,
|
1666 |
+
"grad_norm": 0.17641142010688782,
|
1667 |
+
"learning_rate": 0.00010075440067057837,
|
1668 |
+
"loss": 0.1563,
|
1669 |
+
"step": 1185
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 0.49874266554903607,
|
1673 |
+
"grad_norm": 0.19048817455768585,
|
1674 |
+
"learning_rate": 0.00010033528918692372,
|
1675 |
+
"loss": 0.1565,
|
1676 |
+
"step": 1190
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 0.5008382229673093,
|
1680 |
+
"grad_norm": 0.1500770002603531,
|
1681 |
+
"learning_rate": 9.991617770326908e-05,
|
1682 |
+
"loss": 0.1561,
|
1683 |
+
"step": 1195
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 0.5029337803855826,
|
1687 |
+
"grad_norm": 0.1577143371105194,
|
1688 |
+
"learning_rate": 9.949706621961443e-05,
|
1689 |
+
"loss": 0.1555,
|
1690 |
+
"step": 1200
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 0.5050293378038558,
|
1694 |
+
"grad_norm": 0.14767815172672272,
|
1695 |
+
"learning_rate": 9.907795473595977e-05,
|
1696 |
+
"loss": 0.1546,
|
1697 |
+
"step": 1205
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 0.5071248952221291,
|
1701 |
+
"grad_norm": 0.1728920042514801,
|
1702 |
+
"learning_rate": 9.865884325230512e-05,
|
1703 |
+
"loss": 0.1582,
|
1704 |
+
"step": 1210
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 0.5092204526404024,
|
1708 |
+
"grad_norm": 0.13907761871814728,
|
1709 |
+
"learning_rate": 9.823973176865047e-05,
|
1710 |
+
"loss": 0.154,
|
1711 |
+
"step": 1215
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 0.5113160100586757,
|
1715 |
+
"grad_norm": 0.14644944667816162,
|
1716 |
+
"learning_rate": 9.782062028499581e-05,
|
1717 |
+
"loss": 0.151,
|
1718 |
+
"step": 1220
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 0.5134115674769488,
|
1722 |
+
"grad_norm": 0.1749754697084427,
|
1723 |
+
"learning_rate": 9.740150880134116e-05,
|
1724 |
+
"loss": 0.1558,
|
1725 |
+
"step": 1225
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 0.5155071248952221,
|
1729 |
+
"grad_norm": 1.7467832565307617,
|
1730 |
+
"learning_rate": 9.698239731768651e-05,
|
1731 |
+
"loss": 0.154,
|
1732 |
+
"step": 1230
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 0.5176026823134954,
|
1736 |
+
"grad_norm": 0.3709283471107483,
|
1737 |
+
"learning_rate": 9.656328583403186e-05,
|
1738 |
+
"loss": 0.1648,
|
1739 |
+
"step": 1235
|
1740 |
+
},
|
1741 |
+
{
|
1742 |
+
"epoch": 0.5196982397317687,
|
1743 |
+
"grad_norm": 0.28035739064216614,
|
1744 |
+
"learning_rate": 9.61441743503772e-05,
|
1745 |
+
"loss": 0.1697,
|
1746 |
+
"step": 1240
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 0.5217937971500419,
|
1750 |
+
"grad_norm": 0.1671634167432785,
|
1751 |
+
"learning_rate": 9.572506286672255e-05,
|
1752 |
+
"loss": 0.1611,
|
1753 |
+
"step": 1245
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 0.5238893545683152,
|
1757 |
+
"grad_norm": 0.15249969065189362,
|
1758 |
+
"learning_rate": 9.53059513830679e-05,
|
1759 |
+
"loss": 0.1557,
|
1760 |
+
"step": 1250
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 0.5259849119865885,
|
1764 |
+
"grad_norm": 0.14879916608333588,
|
1765 |
+
"learning_rate": 9.488683989941326e-05,
|
1766 |
+
"loss": 0.1516,
|
1767 |
+
"step": 1255
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 0.5280804694048616,
|
1771 |
+
"grad_norm": 2.7410941123962402,
|
1772 |
+
"learning_rate": 9.44677284157586e-05,
|
1773 |
+
"loss": 0.1497,
|
1774 |
+
"step": 1260
|
1775 |
+
},
|
1776 |
+
{
|
1777 |
+
"epoch": 0.5301760268231349,
|
1778 |
+
"grad_norm": 0.188863143324852,
|
1779 |
+
"learning_rate": 9.404861693210395e-05,
|
1780 |
+
"loss": 0.1567,
|
1781 |
+
"step": 1265
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 0.5322715842414082,
|
1785 |
+
"grad_norm": 0.22812993824481964,
|
1786 |
+
"learning_rate": 9.36295054484493e-05,
|
1787 |
+
"loss": 0.1586,
|
1788 |
+
"step": 1270
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 0.5343671416596815,
|
1792 |
+
"grad_norm": 0.23461438715457916,
|
1793 |
+
"learning_rate": 9.321039396479464e-05,
|
1794 |
+
"loss": 0.1593,
|
1795 |
+
"step": 1275
|
1796 |
+
},
|
1797 |
+
{
|
1798 |
+
"epoch": 0.5364626990779547,
|
1799 |
+
"grad_norm": 0.23611848056316376,
|
1800 |
+
"learning_rate": 9.279128248113999e-05,
|
1801 |
+
"loss": 0.1575,
|
1802 |
+
"step": 1280
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 0.538558256496228,
|
1806 |
+
"grad_norm": 0.20142588019371033,
|
1807 |
+
"learning_rate": 9.237217099748533e-05,
|
1808 |
+
"loss": 0.1611,
|
1809 |
+
"step": 1285
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.5406538139145013,
|
1813 |
+
"grad_norm": 0.18650312721729279,
|
1814 |
+
"learning_rate": 9.195305951383069e-05,
|
1815 |
+
"loss": 0.1585,
|
1816 |
+
"step": 1290
|
1817 |
+
},
|
1818 |
+
{
|
1819 |
+
"epoch": 0.5427493713327746,
|
1820 |
+
"grad_norm": 0.1717916578054428,
|
1821 |
+
"learning_rate": 9.153394803017603e-05,
|
1822 |
+
"loss": 0.1566,
|
1823 |
+
"step": 1295
|
1824 |
+
},
|
1825 |
+
{
|
1826 |
+
"epoch": 0.5448449287510477,
|
1827 |
+
"grad_norm": 0.154686838388443,
|
1828 |
+
"learning_rate": 9.111483654652138e-05,
|
1829 |
+
"loss": 0.154,
|
1830 |
+
"step": 1300
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 0.546940486169321,
|
1834 |
+
"grad_norm": 0.17387616634368896,
|
1835 |
+
"learning_rate": 9.069572506286673e-05,
|
1836 |
+
"loss": 0.1574,
|
1837 |
+
"step": 1305
|
1838 |
+
},
|
1839 |
+
{
|
1840 |
+
"epoch": 0.5490360435875943,
|
1841 |
+
"grad_norm": 0.1707635372877121,
|
1842 |
+
"learning_rate": 9.027661357921207e-05,
|
1843 |
+
"loss": 0.1595,
|
1844 |
+
"step": 1310
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 0.5511316010058676,
|
1848 |
+
"grad_norm": 0.1505287140607834,
|
1849 |
+
"learning_rate": 8.985750209555742e-05,
|
1850 |
+
"loss": 0.1572,
|
1851 |
+
"step": 1315
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 0.5532271584241408,
|
1855 |
+
"grad_norm": 0.17044112086296082,
|
1856 |
+
"learning_rate": 8.943839061190276e-05,
|
1857 |
+
"loss": 0.1526,
|
1858 |
+
"step": 1320
|
1859 |
+
},
|
1860 |
+
{
|
1861 |
+
"epoch": 0.5553227158424141,
|
1862 |
+
"grad_norm": 0.20292381942272186,
|
1863 |
+
"learning_rate": 8.901927912824813e-05,
|
1864 |
+
"loss": 0.157,
|
1865 |
+
"step": 1325
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 0.5574182732606874,
|
1869 |
+
"grad_norm": 0.22127684950828552,
|
1870 |
+
"learning_rate": 8.860016764459346e-05,
|
1871 |
+
"loss": 0.1569,
|
1872 |
+
"step": 1330
|
1873 |
+
},
|
1874 |
+
{
|
1875 |
+
"epoch": 0.5595138306789607,
|
1876 |
+
"grad_norm": 0.169328510761261,
|
1877 |
+
"learning_rate": 8.818105616093882e-05,
|
1878 |
+
"loss": 0.1574,
|
1879 |
+
"step": 1335
|
1880 |
+
},
|
1881 |
+
{
|
1882 |
+
"epoch": 0.5616093880972338,
|
1883 |
+
"grad_norm": 0.1888064444065094,
|
1884 |
+
"learning_rate": 8.776194467728415e-05,
|
1885 |
+
"loss": 0.152,
|
1886 |
+
"step": 1340
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 0.5637049455155071,
|
1890 |
+
"grad_norm": 2.7211835384368896,
|
1891 |
+
"learning_rate": 8.734283319362952e-05,
|
1892 |
+
"loss": 0.1557,
|
1893 |
+
"step": 1345
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 0.5658005029337804,
|
1897 |
+
"grad_norm": 0.18435344099998474,
|
1898 |
+
"learning_rate": 8.692372170997486e-05,
|
1899 |
+
"loss": 0.1527,
|
1900 |
+
"step": 1350
|
1901 |
+
},
|
1902 |
+
{
|
1903 |
+
"epoch": 0.5678960603520536,
|
1904 |
+
"grad_norm": 0.2031932920217514,
|
1905 |
+
"learning_rate": 8.650461022632021e-05,
|
1906 |
+
"loss": 0.1573,
|
1907 |
+
"step": 1355
|
1908 |
+
},
|
1909 |
+
{
|
1910 |
+
"epoch": 0.5699916177703269,
|
1911 |
+
"grad_norm": 0.1941346377134323,
|
1912 |
+
"learning_rate": 8.608549874266555e-05,
|
1913 |
+
"loss": 0.1538,
|
1914 |
+
"step": 1360
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 0.5720871751886002,
|
1918 |
+
"grad_norm": 0.18645240366458893,
|
1919 |
+
"learning_rate": 8.56663872590109e-05,
|
1920 |
+
"loss": 0.1542,
|
1921 |
+
"step": 1365
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 0.5741827326068735,
|
1925 |
+
"grad_norm": 0.1776381880044937,
|
1926 |
+
"learning_rate": 8.524727577535625e-05,
|
1927 |
+
"loss": 0.1567,
|
1928 |
+
"step": 1370
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 0.5762782900251467,
|
1932 |
+
"grad_norm": 0.17730367183685303,
|
1933 |
+
"learning_rate": 8.482816429170159e-05,
|
1934 |
+
"loss": 0.1552,
|
1935 |
+
"step": 1375
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 0.5783738474434199,
|
1939 |
+
"grad_norm": 0.1614091843366623,
|
1940 |
+
"learning_rate": 8.440905280804694e-05,
|
1941 |
+
"loss": 0.1545,
|
1942 |
+
"step": 1380
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 0.5804694048616932,
|
1946 |
+
"grad_norm": 0.2010612040758133,
|
1947 |
+
"learning_rate": 8.398994132439229e-05,
|
1948 |
+
"loss": 0.1525,
|
1949 |
+
"step": 1385
|
1950 |
+
},
|
1951 |
+
{
|
1952 |
+
"epoch": 0.5825649622799665,
|
1953 |
+
"grad_norm": 0.29623404145240784,
|
1954 |
+
"learning_rate": 8.357082984073764e-05,
|
1955 |
+
"loss": 0.1632,
|
1956 |
+
"step": 1390
|
1957 |
+
},
|
1958 |
+
{
|
1959 |
+
"epoch": 0.5846605196982397,
|
1960 |
+
"grad_norm": 0.26536107063293457,
|
1961 |
+
"learning_rate": 8.315171835708298e-05,
|
1962 |
+
"loss": 0.161,
|
1963 |
+
"step": 1395
|
1964 |
+
},
|
1965 |
+
{
|
1966 |
+
"epoch": 0.586756077116513,
|
1967 |
+
"grad_norm": 0.21128953993320465,
|
1968 |
+
"learning_rate": 8.273260687342833e-05,
|
1969 |
+
"loss": 0.1585,
|
1970 |
+
"step": 1400
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 0.5888516345347863,
|
1974 |
+
"grad_norm": 3.6902313232421875,
|
1975 |
+
"learning_rate": 8.231349538977369e-05,
|
1976 |
+
"loss": 0.153,
|
1977 |
+
"step": 1405
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 0.5909471919530596,
|
1981 |
+
"grad_norm": 0.18794021010398865,
|
1982 |
+
"learning_rate": 8.189438390611904e-05,
|
1983 |
+
"loss": 0.1585,
|
1984 |
+
"step": 1410
|
1985 |
+
},
|
1986 |
+
{
|
1987 |
+
"epoch": 0.5930427493713327,
|
1988 |
+
"grad_norm": 0.17947795987129211,
|
1989 |
+
"learning_rate": 8.147527242246438e-05,
|
1990 |
+
"loss": 0.1584,
|
1991 |
+
"step": 1415
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"epoch": 0.595138306789606,
|
1995 |
+
"grad_norm": 0.15674275159835815,
|
1996 |
+
"learning_rate": 8.105616093880973e-05,
|
1997 |
+
"loss": 0.1547,
|
1998 |
+
"step": 1420
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 0.5972338642078793,
|
2002 |
+
"grad_norm": 0.15368077158927917,
|
2003 |
+
"learning_rate": 8.063704945515508e-05,
|
2004 |
+
"loss": 0.154,
|
2005 |
+
"step": 1425
|
2006 |
+
},
|
2007 |
+
{
|
2008 |
+
"epoch": 0.5993294216261525,
|
2009 |
+
"grad_norm": 0.1675073206424713,
|
2010 |
+
"learning_rate": 8.021793797150042e-05,
|
2011 |
+
"loss": 0.1519,
|
2012 |
+
"step": 1430
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 0.6014249790444258,
|
2016 |
+
"grad_norm": 0.15424901247024536,
|
2017 |
+
"learning_rate": 7.979882648784577e-05,
|
2018 |
+
"loss": 0.1532,
|
2019 |
+
"step": 1435
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 0.6035205364626991,
|
2023 |
+
"grad_norm": 1.752557396888733,
|
2024 |
+
"learning_rate": 7.937971500419112e-05,
|
2025 |
+
"loss": 0.1521,
|
2026 |
+
"step": 1440
|
2027 |
+
},
|
2028 |
+
{
|
2029 |
+
"epoch": 0.6056160938809724,
|
2030 |
+
"grad_norm": 0.179281547665596,
|
2031 |
+
"learning_rate": 7.896060352053647e-05,
|
2032 |
+
"loss": 0.1568,
|
2033 |
+
"step": 1445
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 0.6077116512992456,
|
2037 |
+
"grad_norm": 0.18618442118167877,
|
2038 |
+
"learning_rate": 7.854149203688181e-05,
|
2039 |
+
"loss": 0.1555,
|
2040 |
+
"step": 1450
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 0.6098072087175188,
|
2044 |
+
"grad_norm": 0.1767512410879135,
|
2045 |
+
"learning_rate": 7.812238055322716e-05,
|
2046 |
+
"loss": 0.156,
|
2047 |
+
"step": 1455
|
2048 |
+
},
|
2049 |
+
{
|
2050 |
+
"epoch": 0.6119027661357921,
|
2051 |
+
"grad_norm": 0.1729685217142105,
|
2052 |
+
"learning_rate": 7.770326906957252e-05,
|
2053 |
+
"loss": 0.1521,
|
2054 |
+
"step": 1460
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 0.6139983235540654,
|
2058 |
+
"grad_norm": 0.16246432065963745,
|
2059 |
+
"learning_rate": 7.728415758591785e-05,
|
2060 |
+
"loss": 0.1541,
|
2061 |
+
"step": 1465
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 0.6160938809723386,
|
2065 |
+
"grad_norm": 0.15939489006996155,
|
2066 |
+
"learning_rate": 7.68650461022632e-05,
|
2067 |
+
"loss": 0.1551,
|
2068 |
+
"step": 1470
|
2069 |
+
},
|
2070 |
+
{
|
2071 |
+
"epoch": 0.6181894383906119,
|
2072 |
+
"grad_norm": 0.1684809774160385,
|
2073 |
+
"learning_rate": 7.644593461860854e-05,
|
2074 |
+
"loss": 0.1542,
|
2075 |
+
"step": 1475
|
2076 |
+
},
|
2077 |
+
{
|
2078 |
+
"epoch": 0.6202849958088852,
|
2079 |
+
"grad_norm": 0.18968342244625092,
|
2080 |
+
"learning_rate": 7.602682313495391e-05,
|
2081 |
+
"loss": 0.1537,
|
2082 |
+
"step": 1480
|
2083 |
+
},
|
2084 |
+
{
|
2085 |
+
"epoch": 0.6223805532271585,
|
2086 |
+
"grad_norm": 0.20144881308078766,
|
2087 |
+
"learning_rate": 7.560771165129925e-05,
|
2088 |
+
"loss": 0.158,
|
2089 |
+
"step": 1485
|
2090 |
+
},
|
2091 |
+
{
|
2092 |
+
"epoch": 0.6244761106454317,
|
2093 |
+
"grad_norm": 0.1785353720188141,
|
2094 |
+
"learning_rate": 7.51886001676446e-05,
|
2095 |
+
"loss": 0.1537,
|
2096 |
+
"step": 1490
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 0.6265716680637049,
|
2100 |
+
"grad_norm": 3.9302639961242676,
|
2101 |
+
"learning_rate": 7.476948868398994e-05,
|
2102 |
+
"loss": 0.1539,
|
2103 |
+
"step": 1495
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 0.6286672254819782,
|
2107 |
+
"grad_norm": 0.17349500954151154,
|
2108 |
+
"learning_rate": 7.43503772003353e-05,
|
2109 |
+
"loss": 0.1549,
|
2110 |
+
"step": 1500
|
2111 |
+
},
|
2112 |
+
{
|
2113 |
+
"epoch": 0.6307627829002515,
|
2114 |
+
"grad_norm": 0.181074857711792,
|
2115 |
+
"learning_rate": 7.393126571668064e-05,
|
2116 |
+
"loss": 0.1523,
|
2117 |
+
"step": 1505
|
2118 |
+
},
|
2119 |
+
{
|
2120 |
+
"epoch": 0.6328583403185247,
|
2121 |
+
"grad_norm": 0.1837494969367981,
|
2122 |
+
"learning_rate": 7.351215423302599e-05,
|
2123 |
+
"loss": 0.1543,
|
2124 |
+
"step": 1510
|
2125 |
+
},
|
2126 |
+
{
|
2127 |
+
"epoch": 0.634953897736798,
|
2128 |
+
"grad_norm": 0.17972221970558167,
|
2129 |
+
"learning_rate": 7.309304274937133e-05,
|
2130 |
+
"loss": 0.1539,
|
2131 |
+
"step": 1515
|
2132 |
+
},
|
2133 |
+
{
|
2134 |
+
"epoch": 0.6370494551550713,
|
2135 |
+
"grad_norm": 0.18084241449832916,
|
2136 |
+
"learning_rate": 7.267393126571668e-05,
|
2137 |
+
"loss": 0.1504,
|
2138 |
+
"step": 1520
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 0.6391450125733446,
|
2142 |
+
"grad_norm": 0.16487205028533936,
|
2143 |
+
"learning_rate": 7.225481978206203e-05,
|
2144 |
+
"loss": 0.1547,
|
2145 |
+
"step": 1525
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 0.6412405699916177,
|
2149 |
+
"grad_norm": 3.8815670013427734,
|
2150 |
+
"learning_rate": 7.183570829840737e-05,
|
2151 |
+
"loss": 0.1481,
|
2152 |
+
"step": 1530
|
2153 |
+
},
|
2154 |
+
{
|
2155 |
+
"epoch": 0.643336127409891,
|
2156 |
+
"grad_norm": 0.18625426292419434,
|
2157 |
+
"learning_rate": 7.141659681475272e-05,
|
2158 |
+
"loss": 0.1551,
|
2159 |
+
"step": 1535
|
2160 |
+
},
|
2161 |
+
{
|
2162 |
+
"epoch": 0.6454316848281643,
|
2163 |
+
"grad_norm": 0.2006104439496994,
|
2164 |
+
"learning_rate": 7.099748533109808e-05,
|
2165 |
+
"loss": 0.1567,
|
2166 |
+
"step": 1540
|
2167 |
+
},
|
2168 |
+
{
|
2169 |
+
"epoch": 0.6475272422464375,
|
2170 |
+
"grad_norm": 0.20722784101963043,
|
2171 |
+
"learning_rate": 7.057837384744343e-05,
|
2172 |
+
"loss": 0.1599,
|
2173 |
+
"step": 1545
|
2174 |
+
},
|
2175 |
+
{
|
2176 |
+
"epoch": 0.6496227996647108,
|
2177 |
+
"grad_norm": 0.18843336403369904,
|
2178 |
+
"learning_rate": 7.015926236378877e-05,
|
2179 |
+
"loss": 0.1568,
|
2180 |
+
"step": 1550
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 0.6517183570829841,
|
2184 |
+
"grad_norm": 0.16453127562999725,
|
2185 |
+
"learning_rate": 6.974015088013412e-05,
|
2186 |
+
"loss": 0.1564,
|
2187 |
+
"step": 1555
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 0.6538139145012574,
|
2191 |
+
"grad_norm": 0.1718008667230606,
|
2192 |
+
"learning_rate": 6.932103939647947e-05,
|
2193 |
+
"loss": 0.1507,
|
2194 |
+
"step": 1560
|
2195 |
+
},
|
2196 |
+
{
|
2197 |
+
"epoch": 0.6559094719195306,
|
2198 |
+
"grad_norm": 1.9749072790145874,
|
2199 |
+
"learning_rate": 6.890192791282482e-05,
|
2200 |
+
"loss": 0.1546,
|
2201 |
+
"step": 1565
|
2202 |
+
},
|
2203 |
+
{
|
2204 |
+
"epoch": 0.6580050293378038,
|
2205 |
+
"grad_norm": 0.846435546875,
|
2206 |
+
"learning_rate": 6.848281642917016e-05,
|
2207 |
+
"loss": 0.1553,
|
2208 |
+
"step": 1570
|
2209 |
+
},
|
2210 |
+
{
|
2211 |
+
"epoch": 0.6601005867560771,
|
2212 |
+
"grad_norm": 0.21918132901191711,
|
2213 |
+
"learning_rate": 6.806370494551551e-05,
|
2214 |
+
"loss": 0.1544,
|
2215 |
+
"step": 1575
|
2216 |
+
},
|
2217 |
+
{
|
2218 |
+
"epoch": 0.6621961441743504,
|
2219 |
+
"grad_norm": 0.20493735373020172,
|
2220 |
+
"learning_rate": 6.764459346186086e-05,
|
2221 |
+
"loss": 0.1588,
|
2222 |
+
"step": 1580
|
2223 |
+
},
|
2224 |
+
{
|
2225 |
+
"epoch": 0.6642917015926236,
|
2226 |
+
"grad_norm": 0.16465319693088531,
|
2227 |
+
"learning_rate": 6.72254819782062e-05,
|
2228 |
+
"loss": 0.1556,
|
2229 |
+
"step": 1585
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 0.6663872590108969,
|
2233 |
+
"grad_norm": 0.1511167287826538,
|
2234 |
+
"learning_rate": 6.680637049455155e-05,
|
2235 |
+
"loss": 0.1551,
|
2236 |
+
"step": 1590
|
2237 |
+
},
|
2238 |
+
{
|
2239 |
+
"epoch": 0.6684828164291702,
|
2240 |
+
"grad_norm": 0.15197286009788513,
|
2241 |
+
"learning_rate": 6.63872590108969e-05,
|
2242 |
+
"loss": 0.1513,
|
2243 |
+
"step": 1595
|
2244 |
+
},
|
2245 |
+
{
|
2246 |
+
"epoch": 0.6705783738474435,
|
2247 |
+
"grad_norm": 0.14843755960464478,
|
2248 |
+
"learning_rate": 6.596814752724226e-05,
|
2249 |
+
"loss": 0.1476,
|
2250 |
+
"step": 1600
|
2251 |
+
},
|
2252 |
+
{
|
2253 |
+
"epoch": 0.6726739312657167,
|
2254 |
+
"grad_norm": 0.14049085974693298,
|
2255 |
+
"learning_rate": 6.55490360435876e-05,
|
2256 |
+
"loss": 0.1507,
|
2257 |
+
"step": 1605
|
2258 |
+
},
|
2259 |
+
{
|
2260 |
+
"epoch": 0.6747694886839899,
|
2261 |
+
"grad_norm": 0.1492355465888977,
|
2262 |
+
"learning_rate": 6.512992455993295e-05,
|
2263 |
+
"loss": 0.1499,
|
2264 |
+
"step": 1610
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 0.6768650461022632,
|
2268 |
+
"grad_norm": 0.15042835474014282,
|
2269 |
+
"learning_rate": 6.47108130762783e-05,
|
2270 |
+
"loss": 0.15,
|
2271 |
+
"step": 1615
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 0.6789606035205364,
|
2275 |
+
"grad_norm": 0.14849700033664703,
|
2276 |
+
"learning_rate": 6.429170159262365e-05,
|
2277 |
+
"loss": 0.152,
|
2278 |
+
"step": 1620
|
2279 |
+
},
|
2280 |
+
{
|
2281 |
+
"epoch": 0.6810561609388097,
|
2282 |
+
"grad_norm": 0.15401747822761536,
|
2283 |
+
"learning_rate": 6.387259010896899e-05,
|
2284 |
+
"loss": 0.1507,
|
2285 |
+
"step": 1625
|
2286 |
+
},
|
2287 |
+
{
|
2288 |
+
"epoch": 0.683151718357083,
|
2289 |
+
"grad_norm": 0.13168840110301971,
|
2290 |
+
"learning_rate": 6.345347862531434e-05,
|
2291 |
+
"loss": 0.153,
|
2292 |
+
"step": 1630
|
2293 |
+
},
|
2294 |
+
{
|
2295 |
+
"epoch": 0.6852472757753563,
|
2296 |
+
"grad_norm": 0.1513977199792862,
|
2297 |
+
"learning_rate": 6.303436714165969e-05,
|
2298 |
+
"loss": 0.1516,
|
2299 |
+
"step": 1635
|
2300 |
+
},
|
2301 |
+
{
|
2302 |
+
"epoch": 0.6873428331936295,
|
2303 |
+
"grad_norm": 0.14483259618282318,
|
2304 |
+
"learning_rate": 6.261525565800503e-05,
|
2305 |
+
"loss": 0.15,
|
2306 |
+
"step": 1640
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 0.6894383906119028,
|
2310 |
+
"grad_norm": 0.15542860329151154,
|
2311 |
+
"learning_rate": 6.219614417435038e-05,
|
2312 |
+
"loss": 0.1493,
|
2313 |
+
"step": 1645
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 0.691533948030176,
|
2317 |
+
"grad_norm": 0.14083847403526306,
|
2318 |
+
"learning_rate": 6.177703269069572e-05,
|
2319 |
+
"loss": 0.1511,
|
2320 |
+
"step": 1650
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 0.6936295054484493,
|
2324 |
+
"grad_norm": 0.14129005372524261,
|
2325 |
+
"learning_rate": 6.135792120704108e-05,
|
2326 |
+
"loss": 0.1525,
|
2327 |
+
"step": 1655
|
2328 |
+
},
|
2329 |
+
{
|
2330 |
+
"epoch": 0.6957250628667225,
|
2331 |
+
"grad_norm": 0.14137649536132812,
|
2332 |
+
"learning_rate": 6.093880972338642e-05,
|
2333 |
+
"loss": 0.1486,
|
2334 |
+
"step": 1660
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 0.6978206202849958,
|
2338 |
+
"grad_norm": 0.163183331489563,
|
2339 |
+
"learning_rate": 6.051969823973177e-05,
|
2340 |
+
"loss": 0.1526,
|
2341 |
+
"step": 1665
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"epoch": 0.6999161777032691,
|
2345 |
+
"grad_norm": 0.15466581284999847,
|
2346 |
+
"learning_rate": 6.010058675607711e-05,
|
2347 |
+
"loss": 0.1523,
|
2348 |
+
"step": 1670
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 0.7020117351215424,
|
2352 |
+
"grad_norm": 0.1582300364971161,
|
2353 |
+
"learning_rate": 5.968147527242247e-05,
|
2354 |
+
"loss": 0.1501,
|
2355 |
+
"step": 1675
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 0.7041072925398156,
|
2359 |
+
"grad_norm": 0.15225544571876526,
|
2360 |
+
"learning_rate": 5.9262363788767817e-05,
|
2361 |
+
"loss": 0.1529,
|
2362 |
+
"step": 1680
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"epoch": 0.7062028499580888,
|
2366 |
+
"grad_norm": 0.1497444212436676,
|
2367 |
+
"learning_rate": 5.884325230511316e-05,
|
2368 |
+
"loss": 0.1504,
|
2369 |
+
"step": 1685
|
2370 |
+
},
|
2371 |
+
{
|
2372 |
+
"epoch": 0.7082984073763621,
|
2373 |
+
"grad_norm": 0.15386608242988586,
|
2374 |
+
"learning_rate": 5.8424140821458507e-05,
|
2375 |
+
"loss": 0.1507,
|
2376 |
+
"step": 1690
|
2377 |
+
},
|
2378 |
+
{
|
2379 |
+
"epoch": 0.7103939647946353,
|
2380 |
+
"grad_norm": 0.16286878287792206,
|
2381 |
+
"learning_rate": 5.8005029337803865e-05,
|
2382 |
+
"loss": 0.1483,
|
2383 |
+
"step": 1695
|
2384 |
+
},
|
2385 |
+
{
|
2386 |
+
"epoch": 0.7124895222129086,
|
2387 |
+
"grad_norm": 0.16049712896347046,
|
2388 |
+
"learning_rate": 5.758591785414921e-05,
|
2389 |
+
"loss": 0.1511,
|
2390 |
+
"step": 1700
|
2391 |
+
},
|
2392 |
+
{
|
2393 |
+
"epoch": 0.7145850796311819,
|
2394 |
+
"grad_norm": 0.16950005292892456,
|
2395 |
+
"learning_rate": 5.7166806370494555e-05,
|
2396 |
+
"loss": 0.1497,
|
2397 |
+
"step": 1705
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 0.7166806370494552,
|
2401 |
+
"grad_norm": 0.14905424416065216,
|
2402 |
+
"learning_rate": 5.67476948868399e-05,
|
2403 |
+
"loss": 0.1518,
|
2404 |
+
"step": 1710
|
2405 |
+
},
|
2406 |
+
{
|
2407 |
+
"epoch": 0.7187761944677284,
|
2408 |
+
"grad_norm": 0.16250193119049072,
|
2409 |
+
"learning_rate": 5.632858340318525e-05,
|
2410 |
+
"loss": 0.1518,
|
2411 |
+
"step": 1715
|
2412 |
+
},
|
2413 |
+
{
|
2414 |
+
"epoch": 0.7208717518860017,
|
2415 |
+
"grad_norm": 0.15719325840473175,
|
2416 |
+
"learning_rate": 5.59094719195306e-05,
|
2417 |
+
"loss": 0.1509,
|
2418 |
+
"step": 1720
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"epoch": 0.7229673093042749,
|
2422 |
+
"grad_norm": 0.13987241685390472,
|
2423 |
+
"learning_rate": 5.549036043587594e-05,
|
2424 |
+
"loss": 0.1493,
|
2425 |
+
"step": 1725
|
2426 |
+
},
|
2427 |
+
{
|
2428 |
+
"epoch": 0.7250628667225482,
|
2429 |
+
"grad_norm": 0.15766645967960358,
|
2430 |
+
"learning_rate": 5.507124895222129e-05,
|
2431 |
+
"loss": 0.151,
|
2432 |
+
"step": 1730
|
2433 |
+
},
|
2434 |
+
{
|
2435 |
+
"epoch": 0.7271584241408214,
|
2436 |
+
"grad_norm": 0.1426958292722702,
|
2437 |
+
"learning_rate": 5.4652137468566645e-05,
|
2438 |
+
"loss": 0.1477,
|
2439 |
+
"step": 1735
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 0.7292539815590947,
|
2443 |
+
"grad_norm": 0.15173014998435974,
|
2444 |
+
"learning_rate": 5.423302598491199e-05,
|
2445 |
+
"loss": 0.1498,
|
2446 |
+
"step": 1740
|
2447 |
+
},
|
2448 |
+
{
|
2449 |
+
"epoch": 0.731349538977368,
|
2450 |
+
"grad_norm": 0.13781285285949707,
|
2451 |
+
"learning_rate": 5.3813914501257335e-05,
|
2452 |
+
"loss": 0.1461,
|
2453 |
+
"step": 1745
|
2454 |
+
},
|
2455 |
+
{
|
2456 |
+
"epoch": 0.7334450963956413,
|
2457 |
+
"grad_norm": 0.15598557889461517,
|
2458 |
+
"learning_rate": 5.339480301760269e-05,
|
2459 |
+
"loss": 0.1468,
|
2460 |
+
"step": 1750
|
2461 |
+
},
|
2462 |
+
{
|
2463 |
+
"epoch": 0.7355406538139145,
|
2464 |
+
"grad_norm": 0.1487160325050354,
|
2465 |
+
"learning_rate": 5.297569153394803e-05,
|
2466 |
+
"loss": 0.1515,
|
2467 |
+
"step": 1755
|
2468 |
+
},
|
2469 |
+
{
|
2470 |
+
"epoch": 0.7376362112321878,
|
2471 |
+
"grad_norm": 0.1766008883714676,
|
2472 |
+
"learning_rate": 5.255658005029338e-05,
|
2473 |
+
"loss": 0.1496,
|
2474 |
+
"step": 1760
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 0.739731768650461,
|
2478 |
+
"grad_norm": 0.1634136140346527,
|
2479 |
+
"learning_rate": 5.213746856663872e-05,
|
2480 |
+
"loss": 0.152,
|
2481 |
+
"step": 1765
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 0.7418273260687342,
|
2485 |
+
"grad_norm": 0.16231022775173187,
|
2486 |
+
"learning_rate": 5.171835708298408e-05,
|
2487 |
+
"loss": 0.1511,
|
2488 |
+
"step": 1770
|
2489 |
+
},
|
2490 |
+
{
|
2491 |
+
"epoch": 0.7439228834870075,
|
2492 |
+
"grad_norm": 0.1736147552728653,
|
2493 |
+
"learning_rate": 5.1299245599329425e-05,
|
2494 |
+
"loss": 0.1519,
|
2495 |
+
"step": 1775
|
2496 |
+
},
|
2497 |
+
{
|
2498 |
+
"epoch": 0.7460184409052808,
|
2499 |
+
"grad_norm": 0.15696606040000916,
|
2500 |
+
"learning_rate": 5.088013411567477e-05,
|
2501 |
+
"loss": 0.1522,
|
2502 |
+
"step": 1780
|
2503 |
+
},
|
2504 |
+
{
|
2505 |
+
"epoch": 0.7481139983235541,
|
2506 |
+
"grad_norm": 0.16596518456935883,
|
2507 |
+
"learning_rate": 5.0461022632020115e-05,
|
2508 |
+
"loss": 0.1494,
|
2509 |
+
"step": 1785
|
2510 |
+
},
|
2511 |
+
{
|
2512 |
+
"epoch": 0.7502095557418273,
|
2513 |
+
"grad_norm": 0.16456949710845947,
|
2514 |
+
"learning_rate": 5.0041911148365474e-05,
|
2515 |
+
"loss": 0.1485,
|
2516 |
+
"step": 1790
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 0.7523051131601006,
|
2520 |
+
"grad_norm": 0.16951188445091248,
|
2521 |
+
"learning_rate": 4.962279966471082e-05,
|
2522 |
+
"loss": 0.1536,
|
2523 |
+
"step": 1795
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 0.7544006705783739,
|
2527 |
+
"grad_norm": 0.17507892847061157,
|
2528 |
+
"learning_rate": 4.9203688181056164e-05,
|
2529 |
+
"loss": 0.1524,
|
2530 |
+
"step": 1800
|
2531 |
+
},
|
2532 |
+
{
|
2533 |
+
"epoch": 0.7564962279966471,
|
2534 |
+
"grad_norm": 0.1613740175962448,
|
2535 |
+
"learning_rate": 4.8784576697401516e-05,
|
2536 |
+
"loss": 0.151,
|
2537 |
+
"step": 1805
|
2538 |
+
},
|
2539 |
+
{
|
2540 |
+
"epoch": 0.7585917854149203,
|
2541 |
+
"grad_norm": 0.1735554188489914,
|
2542 |
+
"learning_rate": 4.836546521374686e-05,
|
2543 |
+
"loss": 0.149,
|
2544 |
+
"step": 1810
|
2545 |
+
},
|
2546 |
+
{
|
2547 |
+
"epoch": 0.7606873428331936,
|
2548 |
+
"grad_norm": 0.15241263806819916,
|
2549 |
+
"learning_rate": 4.7946353730092206e-05,
|
2550 |
+
"loss": 0.1475,
|
2551 |
+
"step": 1815
|
2552 |
+
},
|
2553 |
+
{
|
2554 |
+
"epoch": 0.7627829002514669,
|
2555 |
+
"grad_norm": 0.15598662197589874,
|
2556 |
+
"learning_rate": 4.752724224643755e-05,
|
2557 |
+
"loss": 0.1504,
|
2558 |
+
"step": 1820
|
2559 |
+
},
|
2560 |
+
{
|
2561 |
+
"epoch": 0.7648784576697402,
|
2562 |
+
"grad_norm": 0.1638031303882599,
|
2563 |
+
"learning_rate": 4.71081307627829e-05,
|
2564 |
+
"loss": 0.1483,
|
2565 |
+
"step": 1825
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 0.7669740150880134,
|
2569 |
+
"grad_norm": 0.15647321939468384,
|
2570 |
+
"learning_rate": 4.668901927912825e-05,
|
2571 |
+
"loss": 0.1487,
|
2572 |
+
"step": 1830
|
2573 |
+
},
|
2574 |
+
{
|
2575 |
+
"epoch": 0.7690695725062867,
|
2576 |
+
"grad_norm": 0.15045635402202606,
|
2577 |
+
"learning_rate": 4.62699077954736e-05,
|
2578 |
+
"loss": 0.1489,
|
2579 |
+
"step": 1835
|
2580 |
+
},
|
2581 |
+
{
|
2582 |
+
"epoch": 0.7711651299245599,
|
2583 |
+
"grad_norm": 0.1481800377368927,
|
2584 |
+
"learning_rate": 4.5850796311818944e-05,
|
2585 |
+
"loss": 0.1498,
|
2586 |
+
"step": 1840
|
2587 |
+
},
|
2588 |
+
{
|
2589 |
+
"epoch": 0.7732606873428332,
|
2590 |
+
"grad_norm": 0.16117189824581146,
|
2591 |
+
"learning_rate": 4.5431684828164296e-05,
|
2592 |
+
"loss": 0.147,
|
2593 |
+
"step": 1845
|
2594 |
+
},
|
2595 |
+
{
|
2596 |
+
"epoch": 0.7753562447611064,
|
2597 |
+
"grad_norm": 0.15690650045871735,
|
2598 |
+
"learning_rate": 4.501257334450964e-05,
|
2599 |
+
"loss": 0.152,
|
2600 |
+
"step": 1850
|
2601 |
+
},
|
2602 |
+
{
|
2603 |
+
"epoch": 0.7774518021793797,
|
2604 |
+
"grad_norm": 0.15324068069458008,
|
2605 |
+
"learning_rate": 4.459346186085499e-05,
|
2606 |
+
"loss": 0.1509,
|
2607 |
+
"step": 1855
|
2608 |
+
},
|
2609 |
+
{
|
2610 |
+
"epoch": 0.779547359597653,
|
2611 |
+
"grad_norm": 0.1670048087835312,
|
2612 |
+
"learning_rate": 4.417435037720034e-05,
|
2613 |
+
"loss": 0.1481,
|
2614 |
+
"step": 1860
|
2615 |
+
},
|
2616 |
+
{
|
2617 |
+
"epoch": 0.7816429170159263,
|
2618 |
+
"grad_norm": 0.16738423705101013,
|
2619 |
+
"learning_rate": 4.375523889354568e-05,
|
2620 |
+
"loss": 0.1525,
|
2621 |
+
"step": 1865
|
2622 |
+
},
|
2623 |
+
{
|
2624 |
+
"epoch": 0.7837384744341995,
|
2625 |
+
"grad_norm": 0.15926587581634521,
|
2626 |
+
"learning_rate": 4.333612740989103e-05,
|
2627 |
+
"loss": 0.1499,
|
2628 |
+
"step": 1870
|
2629 |
+
},
|
2630 |
+
{
|
2631 |
+
"epoch": 0.7858340318524728,
|
2632 |
+
"grad_norm": 0.15555323660373688,
|
2633 |
+
"learning_rate": 4.291701592623638e-05,
|
2634 |
+
"loss": 0.1487,
|
2635 |
+
"step": 1875
|
2636 |
+
},
|
2637 |
+
{
|
2638 |
+
"epoch": 0.787929589270746,
|
2639 |
+
"grad_norm": 0.14897003769874573,
|
2640 |
+
"learning_rate": 4.2497904442581724e-05,
|
2641 |
+
"loss": 0.153,
|
2642 |
+
"step": 1880
|
2643 |
+
},
|
2644 |
+
{
|
2645 |
+
"epoch": 0.7900251466890192,
|
2646 |
+
"grad_norm": 0.16712865233421326,
|
2647 |
+
"learning_rate": 4.2078792958927076e-05,
|
2648 |
+
"loss": 0.1522,
|
2649 |
+
"step": 1885
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 0.7921207041072925,
|
2653 |
+
"grad_norm": 0.16521087288856506,
|
2654 |
+
"learning_rate": 4.165968147527242e-05,
|
2655 |
+
"loss": 0.1554,
|
2656 |
+
"step": 1890
|
2657 |
+
},
|
2658 |
+
{
|
2659 |
+
"epoch": 0.7942162615255658,
|
2660 |
+
"grad_norm": 0.15836192667484283,
|
2661 |
+
"learning_rate": 4.124056999161777e-05,
|
2662 |
+
"loss": 0.1515,
|
2663 |
+
"step": 1895
|
2664 |
+
},
|
2665 |
+
{
|
2666 |
+
"epoch": 0.7963118189438391,
|
2667 |
+
"grad_norm": 0.1507478654384613,
|
2668 |
+
"learning_rate": 4.0821458507963125e-05,
|
2669 |
+
"loss": 0.1525,
|
2670 |
+
"step": 1900
|
2671 |
+
},
|
2672 |
+
{
|
2673 |
+
"epoch": 0.7984073763621123,
|
2674 |
+
"grad_norm": 0.6994775533676147,
|
2675 |
+
"learning_rate": 4.040234702430847e-05,
|
2676 |
+
"loss": 0.1522,
|
2677 |
+
"step": 1905
|
2678 |
+
},
|
2679 |
+
{
|
2680 |
+
"epoch": 0.8005029337803856,
|
2681 |
+
"grad_norm": 0.1698751598596573,
|
2682 |
+
"learning_rate": 3.998323554065382e-05,
|
2683 |
+
"loss": 0.152,
|
2684 |
+
"step": 1910
|
2685 |
+
},
|
2686 |
+
{
|
2687 |
+
"epoch": 0.8025984911986589,
|
2688 |
+
"grad_norm": 0.16350072622299194,
|
2689 |
+
"learning_rate": 3.9564124056999166e-05,
|
2690 |
+
"loss": 0.1499,
|
2691 |
+
"step": 1915
|
2692 |
+
},
|
2693 |
+
{
|
2694 |
+
"epoch": 0.8046940486169321,
|
2695 |
+
"grad_norm": 0.15547800064086914,
|
2696 |
+
"learning_rate": 3.914501257334451e-05,
|
2697 |
+
"loss": 0.1496,
|
2698 |
+
"step": 1920
|
2699 |
+
},
|
2700 |
+
{
|
2701 |
+
"epoch": 0.8067896060352053,
|
2702 |
+
"grad_norm": 0.1584520936012268,
|
2703 |
+
"learning_rate": 3.8725901089689856e-05,
|
2704 |
+
"loss": 0.1521,
|
2705 |
+
"step": 1925
|
2706 |
+
},
|
2707 |
+
{
|
2708 |
+
"epoch": 0.8088851634534786,
|
2709 |
+
"grad_norm": 0.15392720699310303,
|
2710 |
+
"learning_rate": 3.830678960603521e-05,
|
2711 |
+
"loss": 0.1513,
|
2712 |
+
"step": 1930
|
2713 |
+
},
|
2714 |
+
{
|
2715 |
+
"epoch": 0.8109807208717519,
|
2716 |
+
"grad_norm": 0.15251478552818298,
|
2717 |
+
"learning_rate": 3.788767812238055e-05,
|
2718 |
+
"loss": 0.1503,
|
2719 |
+
"step": 1935
|
2720 |
+
},
|
2721 |
+
{
|
2722 |
+
"epoch": 0.8130762782900252,
|
2723 |
+
"grad_norm": 0.1555824875831604,
|
2724 |
+
"learning_rate": 3.7468566638725905e-05,
|
2725 |
+
"loss": 0.148,
|
2726 |
+
"step": 1940
|
2727 |
+
},
|
2728 |
+
{
|
2729 |
+
"epoch": 0.8151718357082984,
|
2730 |
+
"grad_norm": 1.0603052377700806,
|
2731 |
+
"learning_rate": 3.704945515507125e-05,
|
2732 |
+
"loss": 0.1511,
|
2733 |
+
"step": 1945
|
2734 |
+
},
|
2735 |
+
{
|
2736 |
+
"epoch": 0.8172673931265717,
|
2737 |
+
"grad_norm": 0.21994204819202423,
|
2738 |
+
"learning_rate": 3.66303436714166e-05,
|
2739 |
+
"loss": 0.1536,
|
2740 |
+
"step": 1950
|
2741 |
+
},
|
2742 |
+
{
|
2743 |
+
"epoch": 0.819362950544845,
|
2744 |
+
"grad_norm": 0.2238265573978424,
|
2745 |
+
"learning_rate": 3.6211232187761947e-05,
|
2746 |
+
"loss": 0.1549,
|
2747 |
+
"step": 1955
|
2748 |
+
},
|
2749 |
+
{
|
2750 |
+
"epoch": 0.8214585079631181,
|
2751 |
+
"grad_norm": 0.212602898478508,
|
2752 |
+
"learning_rate": 3.57921207041073e-05,
|
2753 |
+
"loss": 0.1567,
|
2754 |
+
"step": 1960
|
2755 |
+
},
|
2756 |
+
{
|
2757 |
+
"epoch": 0.8235540653813914,
|
2758 |
+
"grad_norm": 0.18257835507392883,
|
2759 |
+
"learning_rate": 3.537300922045264e-05,
|
2760 |
+
"loss": 0.1513,
|
2761 |
+
"step": 1965
|
2762 |
+
},
|
2763 |
+
{
|
2764 |
+
"epoch": 0.8256496227996647,
|
2765 |
+
"grad_norm": 0.17607073485851288,
|
2766 |
+
"learning_rate": 3.495389773679799e-05,
|
2767 |
+
"loss": 0.1539,
|
2768 |
+
"step": 1970
|
2769 |
+
},
|
2770 |
+
{
|
2771 |
+
"epoch": 0.827745180217938,
|
2772 |
+
"grad_norm": 0.14804469048976898,
|
2773 |
+
"learning_rate": 3.453478625314333e-05,
|
2774 |
+
"loss": 0.1502,
|
2775 |
+
"step": 1975
|
2776 |
+
},
|
2777 |
+
{
|
2778 |
+
"epoch": 0.8298407376362112,
|
2779 |
+
"grad_norm": 0.15939727425575256,
|
2780 |
+
"learning_rate": 3.4115674769488685e-05,
|
2781 |
+
"loss": 0.1482,
|
2782 |
+
"step": 1980
|
2783 |
+
},
|
2784 |
+
{
|
2785 |
+
"epoch": 0.8319362950544845,
|
2786 |
+
"grad_norm": 0.16081516444683075,
|
2787 |
+
"learning_rate": 3.369656328583403e-05,
|
2788 |
+
"loss": 0.152,
|
2789 |
+
"step": 1985
|
2790 |
+
},
|
2791 |
+
{
|
2792 |
+
"epoch": 0.8340318524727578,
|
2793 |
+
"grad_norm": 0.7829539179801941,
|
2794 |
+
"learning_rate": 3.327745180217938e-05,
|
2795 |
+
"loss": 0.1497,
|
2796 |
+
"step": 1990
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 0.836127409891031,
|
2800 |
+
"grad_norm": 0.15778230130672455,
|
2801 |
+
"learning_rate": 3.285834031852473e-05,
|
2802 |
+
"loss": 0.1485,
|
2803 |
+
"step": 1995
|
2804 |
+
},
|
2805 |
+
{
|
2806 |
+
"epoch": 0.8382229673093042,
|
2807 |
+
"grad_norm": 0.16156698763370514,
|
2808 |
+
"learning_rate": 3.243922883487008e-05,
|
2809 |
+
"loss": 0.1508,
|
2810 |
+
"step": 2000
|
2811 |
+
},
|
2812 |
+
{
|
2813 |
+
"epoch": 0.8403185247275775,
|
2814 |
+
"grad_norm": 0.15631239116191864,
|
2815 |
+
"learning_rate": 3.2020117351215424e-05,
|
2816 |
+
"loss": 0.1484,
|
2817 |
+
"step": 2005
|
2818 |
+
},
|
2819 |
+
{
|
2820 |
+
"epoch": 0.8424140821458508,
|
2821 |
+
"grad_norm": 0.1522732824087143,
|
2822 |
+
"learning_rate": 3.1601005867560775e-05,
|
2823 |
+
"loss": 0.1508,
|
2824 |
+
"step": 2010
|
2825 |
+
},
|
2826 |
+
{
|
2827 |
+
"epoch": 0.8445096395641241,
|
2828 |
+
"grad_norm": 0.1581004112958908,
|
2829 |
+
"learning_rate": 3.118189438390612e-05,
|
2830 |
+
"loss": 0.149,
|
2831 |
+
"step": 2015
|
2832 |
+
},
|
2833 |
+
{
|
2834 |
+
"epoch": 0.8466051969823973,
|
2835 |
+
"grad_norm": 0.1513088047504425,
|
2836 |
+
"learning_rate": 3.076278290025147e-05,
|
2837 |
+
"loss": 0.15,
|
2838 |
+
"step": 2020
|
2839 |
+
},
|
2840 |
+
{
|
2841 |
+
"epoch": 0.8487007544006706,
|
2842 |
+
"grad_norm": 0.1780407577753067,
|
2843 |
+
"learning_rate": 3.0343671416596814e-05,
|
2844 |
+
"loss": 0.1494,
|
2845 |
+
"step": 2025
|
2846 |
+
},
|
2847 |
+
{
|
2848 |
+
"epoch": 0.8507963118189439,
|
2849 |
+
"grad_norm": 0.16309364140033722,
|
2850 |
+
"learning_rate": 2.9924559932942165e-05,
|
2851 |
+
"loss": 0.1474,
|
2852 |
+
"step": 2030
|
2853 |
+
},
|
2854 |
+
{
|
2855 |
+
"epoch": 0.852891869237217,
|
2856 |
+
"grad_norm": 0.15739715099334717,
|
2857 |
+
"learning_rate": 2.950544844928751e-05,
|
2858 |
+
"loss": 0.1496,
|
2859 |
+
"step": 2035
|
2860 |
+
},
|
2861 |
+
{
|
2862 |
+
"epoch": 0.8549874266554903,
|
2863 |
+
"grad_norm": 0.1566157042980194,
|
2864 |
+
"learning_rate": 2.908633696563286e-05,
|
2865 |
+
"loss": 0.1482,
|
2866 |
+
"step": 2040
|
2867 |
+
},
|
2868 |
+
{
|
2869 |
+
"epoch": 0.8570829840737636,
|
2870 |
+
"grad_norm": 0.14910633862018585,
|
2871 |
+
"learning_rate": 2.8667225481978204e-05,
|
2872 |
+
"loss": 0.1493,
|
2873 |
+
"step": 2045
|
2874 |
+
},
|
2875 |
+
{
|
2876 |
+
"epoch": 0.8591785414920369,
|
2877 |
+
"grad_norm": 0.15060973167419434,
|
2878 |
+
"learning_rate": 2.8248113998323556e-05,
|
2879 |
+
"loss": 0.1462,
|
2880 |
+
"step": 2050
|
2881 |
+
},
|
2882 |
+
{
|
2883 |
+
"epoch": 0.8612740989103101,
|
2884 |
+
"grad_norm": 0.15438151359558105,
|
2885 |
+
"learning_rate": 2.7829002514668907e-05,
|
2886 |
+
"loss": 0.1509,
|
2887 |
+
"step": 2055
|
2888 |
+
},
|
2889 |
+
{
|
2890 |
+
"epoch": 0.8633696563285834,
|
2891 |
+
"grad_norm": 0.15441566705703735,
|
2892 |
+
"learning_rate": 2.7409891031014252e-05,
|
2893 |
+
"loss": 0.1481,
|
2894 |
+
"step": 2060
|
2895 |
+
},
|
2896 |
+
{
|
2897 |
+
"epoch": 0.8654652137468567,
|
2898 |
+
"grad_norm": 0.15039560198783875,
|
2899 |
+
"learning_rate": 2.69907795473596e-05,
|
2900 |
+
"loss": 0.1466,
|
2901 |
+
"step": 2065
|
2902 |
+
},
|
2903 |
+
{
|
2904 |
+
"epoch": 0.86756077116513,
|
2905 |
+
"grad_norm": 0.14182990789413452,
|
2906 |
+
"learning_rate": 2.6571668063704946e-05,
|
2907 |
+
"loss": 0.1475,
|
2908 |
+
"step": 2070
|
2909 |
+
},
|
2910 |
+
{
|
2911 |
+
"epoch": 0.8696563285834031,
|
2912 |
+
"grad_norm": 0.1383397877216339,
|
2913 |
+
"learning_rate": 2.6152556580050297e-05,
|
2914 |
+
"loss": 0.1498,
|
2915 |
+
"step": 2075
|
2916 |
+
},
|
2917 |
+
{
|
2918 |
+
"epoch": 0.8717518860016764,
|
2919 |
+
"grad_norm": 0.1353161633014679,
|
2920 |
+
"learning_rate": 2.5733445096395642e-05,
|
2921 |
+
"loss": 0.1485,
|
2922 |
+
"step": 2080
|
2923 |
+
},
|
2924 |
+
{
|
2925 |
+
"epoch": 0.8738474434199497,
|
2926 |
+
"grad_norm": 0.14230230450630188,
|
2927 |
+
"learning_rate": 2.5314333612740994e-05,
|
2928 |
+
"loss": 0.1488,
|
2929 |
+
"step": 2085
|
2930 |
+
},
|
2931 |
+
{
|
2932 |
+
"epoch": 0.875943000838223,
|
2933 |
+
"grad_norm": 0.14749757945537567,
|
2934 |
+
"learning_rate": 2.4895222129086336e-05,
|
2935 |
+
"loss": 0.1464,
|
2936 |
+
"step": 2090
|
2937 |
+
},
|
2938 |
+
{
|
2939 |
+
"epoch": 0.8780385582564962,
|
2940 |
+
"grad_norm": 0.1343354731798172,
|
2941 |
+
"learning_rate": 2.4476110645431684e-05,
|
2942 |
+
"loss": 0.1476,
|
2943 |
+
"step": 2095
|
2944 |
+
},
|
2945 |
+
{
|
2946 |
+
"epoch": 0.8801341156747695,
|
2947 |
+
"grad_norm": 0.15284012258052826,
|
2948 |
+
"learning_rate": 2.4056999161777032e-05,
|
2949 |
+
"loss": 0.1499,
|
2950 |
+
"step": 2100
|
2951 |
+
},
|
2952 |
+
{
|
2953 |
+
"epoch": 0.8822296730930428,
|
2954 |
+
"grad_norm": 0.14641784131526947,
|
2955 |
+
"learning_rate": 2.363788767812238e-05,
|
2956 |
+
"loss": 0.1473,
|
2957 |
+
"step": 2105
|
2958 |
+
},
|
2959 |
+
{
|
2960 |
+
"epoch": 0.8843252305113161,
|
2961 |
+
"grad_norm": 0.13705027103424072,
|
2962 |
+
"learning_rate": 2.321877619446773e-05,
|
2963 |
+
"loss": 0.1464,
|
2964 |
+
"step": 2110
|
2965 |
+
},
|
2966 |
+
{
|
2967 |
+
"epoch": 0.8864207879295892,
|
2968 |
+
"grad_norm": 0.15073353052139282,
|
2969 |
+
"learning_rate": 2.2799664710813078e-05,
|
2970 |
+
"loss": 0.1464,
|
2971 |
+
"step": 2115
|
2972 |
+
},
|
2973 |
+
{
|
2974 |
+
"epoch": 0.8885163453478625,
|
2975 |
+
"grad_norm": 0.14341919124126434,
|
2976 |
+
"learning_rate": 2.2380553227158423e-05,
|
2977 |
+
"loss": 0.1479,
|
2978 |
+
"step": 2120
|
2979 |
+
},
|
2980 |
+
{
|
2981 |
+
"epoch": 0.8906119027661358,
|
2982 |
+
"grad_norm": 0.14984482526779175,
|
2983 |
+
"learning_rate": 2.196144174350377e-05,
|
2984 |
+
"loss": 0.1468,
|
2985 |
+
"step": 2125
|
2986 |
+
},
|
2987 |
+
{
|
2988 |
+
"epoch": 0.892707460184409,
|
2989 |
+
"grad_norm": 0.1421850025653839,
|
2990 |
+
"learning_rate": 2.1542330259849123e-05,
|
2991 |
+
"loss": 0.1431,
|
2992 |
+
"step": 2130
|
2993 |
+
},
|
2994 |
+
{
|
2995 |
+
"epoch": 0.8948030176026823,
|
2996 |
+
"grad_norm": 0.15779058635234833,
|
2997 |
+
"learning_rate": 2.112321877619447e-05,
|
2998 |
+
"loss": 0.1484,
|
2999 |
+
"step": 2135
|
3000 |
+
},
|
3001 |
+
{
|
3002 |
+
"epoch": 0.8968985750209556,
|
3003 |
+
"grad_norm": 0.14414595067501068,
|
3004 |
+
"learning_rate": 2.0704107292539816e-05,
|
3005 |
+
"loss": 0.1477,
|
3006 |
+
"step": 2140
|
3007 |
+
},
|
3008 |
+
{
|
3009 |
+
"epoch": 0.8989941324392289,
|
3010 |
+
"grad_norm": 0.15078584849834442,
|
3011 |
+
"learning_rate": 2.0284995808885164e-05,
|
3012 |
+
"loss": 0.1471,
|
3013 |
+
"step": 2145
|
3014 |
+
},
|
3015 |
+
{
|
3016 |
+
"epoch": 0.901089689857502,
|
3017 |
+
"grad_norm": 0.6652347445487976,
|
3018 |
+
"learning_rate": 1.9865884325230513e-05,
|
3019 |
+
"loss": 0.146,
|
3020 |
+
"step": 2150
|
3021 |
+
},
|
3022 |
+
{
|
3023 |
+
"epoch": 0.9031852472757753,
|
3024 |
+
"grad_norm": 0.1553775519132614,
|
3025 |
+
"learning_rate": 1.944677284157586e-05,
|
3026 |
+
"loss": 0.1455,
|
3027 |
+
"step": 2155
|
3028 |
+
},
|
3029 |
+
{
|
3030 |
+
"epoch": 0.9052808046940486,
|
3031 |
+
"grad_norm": 0.14678525924682617,
|
3032 |
+
"learning_rate": 1.902766135792121e-05,
|
3033 |
+
"loss": 0.1469,
|
3034 |
+
"step": 2160
|
3035 |
+
},
|
3036 |
+
{
|
3037 |
+
"epoch": 0.9073763621123219,
|
3038 |
+
"grad_norm": 0.1497979462146759,
|
3039 |
+
"learning_rate": 1.8608549874266558e-05,
|
3040 |
+
"loss": 0.1488,
|
3041 |
+
"step": 2165
|
3042 |
+
},
|
3043 |
+
{
|
3044 |
+
"epoch": 0.9094719195305951,
|
3045 |
+
"grad_norm": 0.14247293770313263,
|
3046 |
+
"learning_rate": 1.8189438390611903e-05,
|
3047 |
+
"loss": 0.147,
|
3048 |
+
"step": 2170
|
3049 |
+
},
|
3050 |
+
{
|
3051 |
+
"epoch": 0.9115674769488684,
|
3052 |
+
"grad_norm": 0.1436048001050949,
|
3053 |
+
"learning_rate": 1.777032690695725e-05,
|
3054 |
+
"loss": 0.148,
|
3055 |
+
"step": 2175
|
3056 |
+
},
|
3057 |
+
{
|
3058 |
+
"epoch": 0.9136630343671417,
|
3059 |
+
"grad_norm": 0.1506524235010147,
|
3060 |
+
"learning_rate": 1.73512154233026e-05,
|
3061 |
+
"loss": 0.147,
|
3062 |
+
"step": 2180
|
3063 |
+
},
|
3064 |
+
{
|
3065 |
+
"epoch": 0.915758591785415,
|
3066 |
+
"grad_norm": 0.14503729343414307,
|
3067 |
+
"learning_rate": 1.6932103939647948e-05,
|
3068 |
+
"loss": 0.1475,
|
3069 |
+
"step": 2185
|
3070 |
+
},
|
3071 |
+
{
|
3072 |
+
"epoch": 0.9178541492036881,
|
3073 |
+
"grad_norm": 0.14085812866687775,
|
3074 |
+
"learning_rate": 1.6512992455993296e-05,
|
3075 |
+
"loss": 0.1468,
|
3076 |
+
"step": 2190
|
3077 |
+
},
|
3078 |
+
{
|
3079 |
+
"epoch": 0.9199497066219614,
|
3080 |
+
"grad_norm": 0.13786457479000092,
|
3081 |
+
"learning_rate": 1.609388097233864e-05,
|
3082 |
+
"loss": 0.1449,
|
3083 |
+
"step": 2195
|
3084 |
+
},
|
3085 |
+
{
|
3086 |
+
"epoch": 0.9220452640402347,
|
3087 |
+
"grad_norm": 0.14363813400268555,
|
3088 |
+
"learning_rate": 1.567476948868399e-05,
|
3089 |
+
"loss": 0.144,
|
3090 |
+
"step": 2200
|
3091 |
+
},
|
3092 |
+
{
|
3093 |
+
"epoch": 0.924140821458508,
|
3094 |
+
"grad_norm": 0.14791929721832275,
|
3095 |
+
"learning_rate": 1.5255658005029338e-05,
|
3096 |
+
"loss": 0.147,
|
3097 |
+
"step": 2205
|
3098 |
+
},
|
3099 |
+
{
|
3100 |
+
"epoch": 0.9262363788767812,
|
3101 |
+
"grad_norm": 0.14655451476573944,
|
3102 |
+
"learning_rate": 1.4836546521374687e-05,
|
3103 |
+
"loss": 0.1496,
|
3104 |
+
"step": 2210
|
3105 |
+
},
|
3106 |
+
{
|
3107 |
+
"epoch": 0.9283319362950545,
|
3108 |
+
"grad_norm": 0.14993825554847717,
|
3109 |
+
"learning_rate": 1.4417435037720033e-05,
|
3110 |
+
"loss": 0.1465,
|
3111 |
+
"step": 2215
|
3112 |
+
},
|
3113 |
+
{
|
3114 |
+
"epoch": 0.9304274937133278,
|
3115 |
+
"grad_norm": 0.1357424557209015,
|
3116 |
+
"learning_rate": 1.3998323554065382e-05,
|
3117 |
+
"loss": 0.1478,
|
3118 |
+
"step": 2220
|
3119 |
+
},
|
3120 |
+
{
|
3121 |
+
"epoch": 0.932523051131601,
|
3122 |
+
"grad_norm": 0.15557856857776642,
|
3123 |
+
"learning_rate": 1.357921207041073e-05,
|
3124 |
+
"loss": 0.1429,
|
3125 |
+
"step": 2225
|
3126 |
+
},
|
3127 |
+
{
|
3128 |
+
"epoch": 0.9346186085498742,
|
3129 |
+
"grad_norm": 0.16618798673152924,
|
3130 |
+
"learning_rate": 1.3160100586756077e-05,
|
3131 |
+
"loss": 0.1475,
|
3132 |
+
"step": 2230
|
3133 |
+
},
|
3134 |
+
{
|
3135 |
+
"epoch": 0.9367141659681475,
|
3136 |
+
"grad_norm": 0.14325110614299774,
|
3137 |
+
"learning_rate": 1.2740989103101425e-05,
|
3138 |
+
"loss": 0.1453,
|
3139 |
+
"step": 2235
|
3140 |
+
},
|
3141 |
+
{
|
3142 |
+
"epoch": 0.9388097233864208,
|
3143 |
+
"grad_norm": 0.15656636655330658,
|
3144 |
+
"learning_rate": 1.2321877619446773e-05,
|
3145 |
+
"loss": 0.1463,
|
3146 |
+
"step": 2240
|
3147 |
+
},
|
3148 |
+
{
|
3149 |
+
"epoch": 0.940905280804694,
|
3150 |
+
"grad_norm": 0.15591678023338318,
|
3151 |
+
"learning_rate": 1.1902766135792122e-05,
|
3152 |
+
"loss": 0.1475,
|
3153 |
+
"step": 2245
|
3154 |
+
},
|
3155 |
+
{
|
3156 |
+
"epoch": 0.9430008382229673,
|
3157 |
+
"grad_norm": 0.14923661947250366,
|
3158 |
+
"learning_rate": 1.148365465213747e-05,
|
3159 |
+
"loss": 0.1474,
|
3160 |
+
"step": 2250
|
3161 |
+
},
|
3162 |
+
{
|
3163 |
+
"epoch": 0.9450963956412406,
|
3164 |
+
"grad_norm": 1.0343477725982666,
|
3165 |
+
"learning_rate": 1.1064543168482817e-05,
|
3166 |
+
"loss": 0.1434,
|
3167 |
+
"step": 2255
|
3168 |
+
},
|
3169 |
+
{
|
3170 |
+
"epoch": 0.9471919530595139,
|
3171 |
+
"grad_norm": 0.16045677661895752,
|
3172 |
+
"learning_rate": 1.0645431684828165e-05,
|
3173 |
+
"loss": 0.1448,
|
3174 |
+
"step": 2260
|
3175 |
+
},
|
3176 |
+
{
|
3177 |
+
"epoch": 0.9492875104777871,
|
3178 |
+
"grad_norm": 0.14702020585536957,
|
3179 |
+
"learning_rate": 1.0226320201173514e-05,
|
3180 |
+
"loss": 0.1468,
|
3181 |
+
"step": 2265
|
3182 |
+
},
|
3183 |
+
{
|
3184 |
+
"epoch": 0.9513830678960603,
|
3185 |
+
"grad_norm": 0.14469429850578308,
|
3186 |
+
"learning_rate": 9.80720871751886e-06,
|
3187 |
+
"loss": 0.1434,
|
3188 |
+
"step": 2270
|
3189 |
+
},
|
3190 |
+
{
|
3191 |
+
"epoch": 0.9534786253143336,
|
3192 |
+
"grad_norm": 0.1469959169626236,
|
3193 |
+
"learning_rate": 9.388097233864209e-06,
|
3194 |
+
"loss": 0.1487,
|
3195 |
+
"step": 2275
|
3196 |
+
},
|
3197 |
+
{
|
3198 |
+
"epoch": 0.9555741827326069,
|
3199 |
+
"grad_norm": 0.13562710583209991,
|
3200 |
+
"learning_rate": 8.968985750209557e-06,
|
3201 |
+
"loss": 0.1477,
|
3202 |
+
"step": 2280
|
3203 |
+
},
|
3204 |
+
{
|
3205 |
+
"epoch": 0.9576697401508801,
|
3206 |
+
"grad_norm": 0.15792514383792877,
|
3207 |
+
"learning_rate": 8.549874266554904e-06,
|
3208 |
+
"loss": 0.149,
|
3209 |
+
"step": 2285
|
3210 |
+
},
|
3211 |
+
{
|
3212 |
+
"epoch": 0.9597652975691534,
|
3213 |
+
"grad_norm": 0.13964731991291046,
|
3214 |
+
"learning_rate": 8.130762782900252e-06,
|
3215 |
+
"loss": 0.144,
|
3216 |
+
"step": 2290
|
3217 |
+
},
|
3218 |
+
{
|
3219 |
+
"epoch": 0.9618608549874267,
|
3220 |
+
"grad_norm": 0.1598869264125824,
|
3221 |
+
"learning_rate": 7.711651299245599e-06,
|
3222 |
+
"loss": 0.1486,
|
3223 |
+
"step": 2295
|
3224 |
+
},
|
3225 |
+
{
|
3226 |
+
"epoch": 0.9639564124057,
|
3227 |
+
"grad_norm": 11.353910446166992,
|
3228 |
+
"learning_rate": 7.292539815590947e-06,
|
3229 |
+
"loss": 0.1441,
|
3230 |
+
"step": 2300
|
3231 |
+
},
|
3232 |
+
{
|
3233 |
+
"epoch": 0.9660519698239731,
|
3234 |
+
"grad_norm": 0.9498974084854126,
|
3235 |
+
"learning_rate": 6.873428331936295e-06,
|
3236 |
+
"loss": 0.149,
|
3237 |
+
"step": 2305
|
3238 |
+
},
|
3239 |
+
{
|
3240 |
+
"epoch": 0.9681475272422464,
|
3241 |
+
"grad_norm": 0.15554401278495789,
|
3242 |
+
"learning_rate": 6.454316848281643e-06,
|
3243 |
+
"loss": 0.1449,
|
3244 |
+
"step": 2310
|
3245 |
+
},
|
3246 |
+
{
|
3247 |
+
"epoch": 0.9702430846605197,
|
3248 |
+
"grad_norm": 0.16430126130580902,
|
3249 |
+
"learning_rate": 6.035205364626991e-06,
|
3250 |
+
"loss": 0.1451,
|
3251 |
+
"step": 2315
|
3252 |
+
},
|
3253 |
+
{
|
3254 |
+
"epoch": 0.972338642078793,
|
3255 |
+
"grad_norm": 0.15480098128318787,
|
3256 |
+
"learning_rate": 5.616093880972339e-06,
|
3257 |
+
"loss": 0.146,
|
3258 |
+
"step": 2320
|
3259 |
+
},
|
3260 |
+
{
|
3261 |
+
"epoch": 0.9744341994970662,
|
3262 |
+
"grad_norm": 0.15997706353664398,
|
3263 |
+
"learning_rate": 5.1969823973176864e-06,
|
3264 |
+
"loss": 0.1483,
|
3265 |
+
"step": 2325
|
3266 |
+
},
|
3267 |
+
{
|
3268 |
+
"epoch": 0.9765297569153395,
|
3269 |
+
"grad_norm": 0.15260910987854004,
|
3270 |
+
"learning_rate": 4.777870913663034e-06,
|
3271 |
+
"loss": 0.1472,
|
3272 |
+
"step": 2330
|
3273 |
+
},
|
3274 |
+
{
|
3275 |
+
"epoch": 0.9786253143336128,
|
3276 |
+
"grad_norm": 0.15502935647964478,
|
3277 |
+
"learning_rate": 4.358759430008382e-06,
|
3278 |
+
"loss": 0.1456,
|
3279 |
+
"step": 2335
|
3280 |
+
},
|
3281 |
+
{
|
3282 |
+
"epoch": 0.980720871751886,
|
3283 |
+
"grad_norm": 0.14989130198955536,
|
3284 |
+
"learning_rate": 3.939647946353731e-06,
|
3285 |
+
"loss": 0.1464,
|
3286 |
+
"step": 2340
|
3287 |
+
},
|
3288 |
+
{
|
3289 |
+
"epoch": 0.9828164291701592,
|
3290 |
+
"grad_norm": 0.1601138710975647,
|
3291 |
+
"learning_rate": 3.5205364626990782e-06,
|
3292 |
+
"loss": 0.1479,
|
3293 |
+
"step": 2345
|
3294 |
+
},
|
3295 |
+
{
|
3296 |
+
"epoch": 0.9849119865884325,
|
3297 |
+
"grad_norm": 0.15280233323574066,
|
3298 |
+
"learning_rate": 3.101424979044426e-06,
|
3299 |
+
"loss": 0.1459,
|
3300 |
+
"step": 2350
|
3301 |
+
},
|
3302 |
+
{
|
3303 |
+
"epoch": 0.9870075440067058,
|
3304 |
+
"grad_norm": 0.15722650289535522,
|
3305 |
+
"learning_rate": 2.6823134953897737e-06,
|
3306 |
+
"loss": 0.1484,
|
3307 |
+
"step": 2355
|
3308 |
+
},
|
3309 |
+
{
|
3310 |
+
"epoch": 0.989103101424979,
|
3311 |
+
"grad_norm": 0.15498095750808716,
|
3312 |
+
"learning_rate": 2.2632020117351217e-06,
|
3313 |
+
"loss": 0.1486,
|
3314 |
+
"step": 2360
|
3315 |
+
},
|
3316 |
+
{
|
3317 |
+
"epoch": 0.9911986588432523,
|
3318 |
+
"grad_norm": 0.16407634317874908,
|
3319 |
+
"learning_rate": 1.8440905280804694e-06,
|
3320 |
+
"loss": 0.1508,
|
3321 |
+
"step": 2365
|
3322 |
+
},
|
3323 |
+
{
|
3324 |
+
"epoch": 0.9932942162615256,
|
3325 |
+
"grad_norm": 0.1465112566947937,
|
3326 |
+
"learning_rate": 1.4249790444258174e-06,
|
3327 |
+
"loss": 0.1482,
|
3328 |
+
"step": 2370
|
3329 |
+
},
|
3330 |
+
{
|
3331 |
+
"epoch": 0.9953897736797989,
|
3332 |
+
"grad_norm": 0.1511894315481186,
|
3333 |
+
"learning_rate": 1.005867560771165e-06,
|
3334 |
+
"loss": 0.1458,
|
3335 |
+
"step": 2375
|
3336 |
+
},
|
3337 |
+
{
|
3338 |
+
"epoch": 0.9974853310980721,
|
3339 |
+
"grad_norm": 0.15166474878787994,
|
3340 |
+
"learning_rate": 5.86756077116513e-07,
|
3341 |
+
"loss": 0.147,
|
3342 |
+
"step": 2380
|
3343 |
+
},
|
3344 |
+
{
|
3345 |
+
"epoch": 0.9995808885163453,
|
3346 |
+
"grad_norm": 1.638846516609192,
|
3347 |
+
"learning_rate": 1.6764459346186086e-07,
|
3348 |
+
"loss": 0.1469,
|
3349 |
+
"step": 2385
|
3350 |
+
},
|
3351 |
+
{
|
3352 |
+
"epoch": 1.0,
|
3353 |
+
"eval_loss": 0.14722344279289246,
|
3354 |
+
"eval_runtime": 1611.1392,
|
3355 |
+
"eval_samples_per_second": 5.265,
|
3356 |
+
"eval_steps_per_second": 0.659,
|
3357 |
+
"step": 2386
|
3358 |
+
}
|
3359 |
+
],
|
3360 |
+
"logging_steps": 5,
|
3361 |
+
"max_steps": 2386,
|
3362 |
+
"num_input_tokens_seen": 0,
|
3363 |
+
"num_train_epochs": 1,
|
3364 |
+
"save_steps": 500,
|
3365 |
+
"stateful_callbacks": {
|
3366 |
+
"TrainerControl": {
|
3367 |
+
"args": {
|
3368 |
+
"should_epoch_stop": false,
|
3369 |
+
"should_evaluate": false,
|
3370 |
+
"should_log": false,
|
3371 |
+
"should_save": true,
|
3372 |
+
"should_training_stop": true
|
3373 |
+
},
|
3374 |
+
"attributes": {}
|
3375 |
+
}
|
3376 |
+
},
|
3377 |
+
"total_flos": 6.667359824212132e+17,
|
3378 |
+
"train_batch_size": 32,
|
3379 |
+
"trial_name": null,
|
3380 |
+
"trial_params": null
|
3381 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:013e435f2e29457d9392e4189b5bb0be9030270a541c5294766981b33966a016
|
3 |
+
size 5688
|