Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +10 -0
- README.md +57 -0
- colbert_linear.pt +3 -0
- config.json +28 -0
- config_sentence_transformers.json +9 -0
- latest +1 -0
- model.safetensors +3 -0
- modules.json +20 -0
- rng_state.pth +3 -0
- sentence_bert_config.json +4 -0
- sentencepiece.bpe.model +3 -0
- sparse_linear.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +55 -0
- trainer_state.json +3010 -0
- training_args.bin +3 -0
- zero_to_fp32.py +592 -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
|
1_Pooling/config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 1024,
|
3 |
+
"pooling_mode_cls_token": true,
|
4 |
+
"pooling_mode_mean_tokens": false,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
+
"pooling_mode_weightedmean_tokens": false,
|
8 |
+
"pooling_mode_lasttoken": false,
|
9 |
+
"include_prompt": true
|
10 |
+
}
|
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: sentence-transformers
|
3 |
+
pipeline_tag: sentence-similarity
|
4 |
+
tags:
|
5 |
+
- sentence-transformers
|
6 |
+
- feature-extraction
|
7 |
+
- sentence-similarity
|
8 |
+
|
9 |
+
---
|
10 |
+
|
11 |
+
# {MODEL_NAME}
|
12 |
+
|
13 |
+
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
14 |
+
|
15 |
+
<!--- Describe your model here -->
|
16 |
+
|
17 |
+
## Usage (Sentence-Transformers)
|
18 |
+
|
19 |
+
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
20 |
+
|
21 |
+
```
|
22 |
+
pip install -U sentence-transformers
|
23 |
+
```
|
24 |
+
|
25 |
+
Then you can use the model like this:
|
26 |
+
|
27 |
+
```python
|
28 |
+
from sentence_transformers import SentenceTransformer
|
29 |
+
sentences = ["This is an example sentence", "Each sentence is converted"]
|
30 |
+
|
31 |
+
model = SentenceTransformer('{MODEL_NAME}')
|
32 |
+
embeddings = model.encode(sentences)
|
33 |
+
print(embeddings)
|
34 |
+
```
|
35 |
+
|
36 |
+
|
37 |
+
|
38 |
+
## Evaluation Results
|
39 |
+
|
40 |
+
<!--- Describe how your model was evaluated -->
|
41 |
+
|
42 |
+
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
|
43 |
+
|
44 |
+
|
45 |
+
|
46 |
+
## Full Model Architecture
|
47 |
+
```
|
48 |
+
SentenceTransformer(
|
49 |
+
(0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
|
50 |
+
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
51 |
+
(2): Normalize()
|
52 |
+
)
|
53 |
+
```
|
54 |
+
|
55 |
+
## Citing & Authors
|
56 |
+
|
57 |
+
<!--- Describe where people can find more information -->
|
colbert_linear.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:206fa2734e5d626bbb1cfe48b795e4495d2a238c66e095c6c2d5c47c6e46e8d7
|
3 |
+
size 2100674
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "saved_models/cross_lingual/bgem3_crosslingual_20240613/tmp-checkpoint-8546",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 8194,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 24,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.38.2",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250002
|
28 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.5.1",
|
4 |
+
"transformers": "4.38.2",
|
5 |
+
"pytorch": "2.1.0+cu121"
|
6 |
+
},
|
7 |
+
"prompts": {},
|
8 |
+
"default_prompt_name": null
|
9 |
+
}
|
latest
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
global_step8546
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0675f12f6c670bc0a8a880ec04dd4ab371f5c775da0cf0e897a709cbf4992e9a
|
3 |
+
size 2271064456
|
modules.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[
|
2 |
+
{
|
3 |
+
"idx": 0,
|
4 |
+
"name": "0",
|
5 |
+
"path": "",
|
6 |
+
"type": "sentence_transformers.models.Transformer"
|
7 |
+
},
|
8 |
+
{
|
9 |
+
"idx": 1,
|
10 |
+
"name": "1",
|
11 |
+
"path": "1_Pooling",
|
12 |
+
"type": "sentence_transformers.models.Pooling"
|
13 |
+
},
|
14 |
+
{
|
15 |
+
"idx": 2,
|
16 |
+
"name": "2",
|
17 |
+
"path": "2_Normalize",
|
18 |
+
"type": "sentence_transformers.models.Normalize"
|
19 |
+
}
|
20 |
+
]
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e99e78c0db6807a7dcb6ba51f06893fe45acc3007468ac54e3d9e5c7a5accd0
|
3 |
+
size 14244
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 8192,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
sparse_linear.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b753b82fa558b68bd5b49f9bee80eef9b60df0690648e4734970033a9c0d606
|
3 |
+
size 3516
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69564b696052886ed0ac63fa393e928384e0f8caada38c1f4864a9bfbf379c15
|
3 |
+
size 17098273
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"250001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"bos_token": "<s>",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<s>",
|
47 |
+
"eos_token": "</s>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 8192,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"sp_model_kwargs": {},
|
53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
54 |
+
"unk_token": "<unk>"
|
55 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3010 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 8546,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"grad_norm": 11.189342496234838,
|
14 |
+
"learning_rate": 4.2000000000000006e-07,
|
15 |
+
"loss": 0.6334,
|
16 |
+
"step": 20
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0,
|
20 |
+
"grad_norm": 12.102946252189938,
|
21 |
+
"learning_rate": 6.515789473684211e-07,
|
22 |
+
"loss": 0.6334,
|
23 |
+
"step": 40
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.01,
|
27 |
+
"grad_norm": 9.23868714422811,
|
28 |
+
"learning_rate": 8.831578947368421e-07,
|
29 |
+
"loss": 0.5919,
|
30 |
+
"step": 60
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.01,
|
34 |
+
"grad_norm": 10.163427827153294,
|
35 |
+
"learning_rate": 1.1147368421052632e-06,
|
36 |
+
"loss": 0.591,
|
37 |
+
"step": 80
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.01,
|
41 |
+
"grad_norm": 7.703301789458378,
|
42 |
+
"learning_rate": 1.3463157894736842e-06,
|
43 |
+
"loss": 0.5663,
|
44 |
+
"step": 100
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.01,
|
48 |
+
"grad_norm": 10.292384648986614,
|
49 |
+
"learning_rate": 1.5778947368421053e-06,
|
50 |
+
"loss": 0.5649,
|
51 |
+
"step": 120
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02,
|
55 |
+
"grad_norm": 9.622475032798782,
|
56 |
+
"learning_rate": 1.8094736842105263e-06,
|
57 |
+
"loss": 0.5215,
|
58 |
+
"step": 140
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.02,
|
62 |
+
"grad_norm": 12.80974448742081,
|
63 |
+
"learning_rate": 2.0410526315789475e-06,
|
64 |
+
"loss": 0.5166,
|
65 |
+
"step": 160
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.02,
|
69 |
+
"grad_norm": 7.2494201428270495,
|
70 |
+
"learning_rate": 2.2726315789473687e-06,
|
71 |
+
"loss": 0.4708,
|
72 |
+
"step": 180
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.02,
|
76 |
+
"grad_norm": 7.525527996410342,
|
77 |
+
"learning_rate": 2.5042105263157895e-06,
|
78 |
+
"loss": 0.4809,
|
79 |
+
"step": 200
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.03,
|
83 |
+
"grad_norm": 9.553244905277726,
|
84 |
+
"learning_rate": 2.735789473684211e-06,
|
85 |
+
"loss": 0.4149,
|
86 |
+
"step": 220
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.03,
|
90 |
+
"grad_norm": 10.08934392514418,
|
91 |
+
"learning_rate": 2.967368421052632e-06,
|
92 |
+
"loss": 0.4709,
|
93 |
+
"step": 240
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.03,
|
97 |
+
"grad_norm": 8.77781615537256,
|
98 |
+
"learning_rate": 3.198947368421053e-06,
|
99 |
+
"loss": 0.4706,
|
100 |
+
"step": 260
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.03,
|
104 |
+
"grad_norm": 8.842231539252408,
|
105 |
+
"learning_rate": 3.430526315789474e-06,
|
106 |
+
"loss": 0.4033,
|
107 |
+
"step": 280
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.04,
|
111 |
+
"grad_norm": 10.007575408247385,
|
112 |
+
"learning_rate": 3.662105263157895e-06,
|
113 |
+
"loss": 0.4411,
|
114 |
+
"step": 300
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.04,
|
118 |
+
"grad_norm": 8.652379461692668,
|
119 |
+
"learning_rate": 3.893684210526316e-06,
|
120 |
+
"loss": 0.4011,
|
121 |
+
"step": 320
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.04,
|
125 |
+
"grad_norm": 9.03023367578369,
|
126 |
+
"learning_rate": 4.125263157894737e-06,
|
127 |
+
"loss": 0.4252,
|
128 |
+
"step": 340
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.04,
|
132 |
+
"grad_norm": 8.141636176102654,
|
133 |
+
"learning_rate": 4.356842105263159e-06,
|
134 |
+
"loss": 0.4364,
|
135 |
+
"step": 360
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.04,
|
139 |
+
"grad_norm": 8.361423248626743,
|
140 |
+
"learning_rate": 4.58842105263158e-06,
|
141 |
+
"loss": 0.4193,
|
142 |
+
"step": 380
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.05,
|
146 |
+
"grad_norm": 9.373028764113052,
|
147 |
+
"learning_rate": 4.8200000000000004e-06,
|
148 |
+
"loss": 0.4078,
|
149 |
+
"step": 400
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.05,
|
153 |
+
"grad_norm": 8.799844515033747,
|
154 |
+
"learning_rate": 5.051578947368422e-06,
|
155 |
+
"loss": 0.4291,
|
156 |
+
"step": 420
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.05,
|
160 |
+
"grad_norm": 8.642174028335415,
|
161 |
+
"learning_rate": 5.283157894736842e-06,
|
162 |
+
"loss": 0.382,
|
163 |
+
"step": 440
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.05,
|
167 |
+
"grad_norm": 9.451813409785364,
|
168 |
+
"learning_rate": 5.514736842105264e-06,
|
169 |
+
"loss": 0.4089,
|
170 |
+
"step": 460
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.06,
|
174 |
+
"grad_norm": 11.329024075313082,
|
175 |
+
"learning_rate": 5.7463157894736845e-06,
|
176 |
+
"loss": 0.4015,
|
177 |
+
"step": 480
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.06,
|
181 |
+
"grad_norm": 7.271736970582471,
|
182 |
+
"learning_rate": 5.977894736842106e-06,
|
183 |
+
"loss": 0.4028,
|
184 |
+
"step": 500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.06,
|
188 |
+
"grad_norm": 10.856360235187129,
|
189 |
+
"learning_rate": 6.209473684210528e-06,
|
190 |
+
"loss": 0.3814,
|
191 |
+
"step": 520
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.06,
|
195 |
+
"grad_norm": 10.40735773829138,
|
196 |
+
"learning_rate": 6.441052631578948e-06,
|
197 |
+
"loss": 0.3868,
|
198 |
+
"step": 540
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.07,
|
202 |
+
"grad_norm": 7.176143531188922,
|
203 |
+
"learning_rate": 6.672631578947369e-06,
|
204 |
+
"loss": 0.4089,
|
205 |
+
"step": 560
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.07,
|
209 |
+
"grad_norm": 9.628282656024224,
|
210 |
+
"learning_rate": 6.90421052631579e-06,
|
211 |
+
"loss": 0.3771,
|
212 |
+
"step": 580
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.07,
|
216 |
+
"grad_norm": 11.199839686200068,
|
217 |
+
"learning_rate": 7.135789473684212e-06,
|
218 |
+
"loss": 0.383,
|
219 |
+
"step": 600
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.07,
|
223 |
+
"grad_norm": 8.042449860326105,
|
224 |
+
"learning_rate": 7.367368421052632e-06,
|
225 |
+
"loss": 0.3875,
|
226 |
+
"step": 620
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.07,
|
230 |
+
"grad_norm": 6.256777636127039,
|
231 |
+
"learning_rate": 7.598947368421053e-06,
|
232 |
+
"loss": 0.399,
|
233 |
+
"step": 640
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.08,
|
237 |
+
"grad_norm": 12.140400652487944,
|
238 |
+
"learning_rate": 7.830526315789473e-06,
|
239 |
+
"loss": 0.399,
|
240 |
+
"step": 660
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.08,
|
244 |
+
"grad_norm": 9.31740323216306,
|
245 |
+
"learning_rate": 8.062105263157896e-06,
|
246 |
+
"loss": 0.383,
|
247 |
+
"step": 680
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.08,
|
251 |
+
"grad_norm": 11.518507949844242,
|
252 |
+
"learning_rate": 8.293684210526317e-06,
|
253 |
+
"loss": 0.3673,
|
254 |
+
"step": 700
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.08,
|
258 |
+
"grad_norm": 12.23485079993539,
|
259 |
+
"learning_rate": 8.525263157894737e-06,
|
260 |
+
"loss": 0.4105,
|
261 |
+
"step": 720
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.09,
|
265 |
+
"grad_norm": 7.506176757455166,
|
266 |
+
"learning_rate": 8.756842105263158e-06,
|
267 |
+
"loss": 0.425,
|
268 |
+
"step": 740
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.09,
|
272 |
+
"grad_norm": 28.3327677352401,
|
273 |
+
"learning_rate": 8.988421052631579e-06,
|
274 |
+
"loss": 0.3874,
|
275 |
+
"step": 760
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.09,
|
279 |
+
"grad_norm": 10.006030362522525,
|
280 |
+
"learning_rate": 9.220000000000002e-06,
|
281 |
+
"loss": 0.4055,
|
282 |
+
"step": 780
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.09,
|
286 |
+
"grad_norm": 10.010446813711976,
|
287 |
+
"learning_rate": 9.451578947368422e-06,
|
288 |
+
"loss": 0.3599,
|
289 |
+
"step": 800
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.1,
|
293 |
+
"grad_norm": 7.043688000572858,
|
294 |
+
"learning_rate": 9.683157894736843e-06,
|
295 |
+
"loss": 0.3624,
|
296 |
+
"step": 820
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.1,
|
300 |
+
"grad_norm": 9.607021831412599,
|
301 |
+
"learning_rate": 9.914736842105264e-06,
|
302 |
+
"loss": 0.3952,
|
303 |
+
"step": 840
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.1,
|
307 |
+
"grad_norm": 9.147395412600936,
|
308 |
+
"learning_rate": 1.0146315789473686e-05,
|
309 |
+
"loss": 0.3819,
|
310 |
+
"step": 860
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.1,
|
314 |
+
"grad_norm": 7.993375419567414,
|
315 |
+
"learning_rate": 1.0377894736842107e-05,
|
316 |
+
"loss": 0.3678,
|
317 |
+
"step": 880
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.11,
|
321 |
+
"grad_norm": 7.52609874523302,
|
322 |
+
"learning_rate": 1.0609473684210528e-05,
|
323 |
+
"loss": 0.375,
|
324 |
+
"step": 900
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.11,
|
328 |
+
"grad_norm": 9.52738539095041,
|
329 |
+
"learning_rate": 1.084105263157895e-05,
|
330 |
+
"loss": 0.3681,
|
331 |
+
"step": 920
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.11,
|
335 |
+
"grad_norm": 11.370588516129013,
|
336 |
+
"learning_rate": 1.107263157894737e-05,
|
337 |
+
"loss": 0.3911,
|
338 |
+
"step": 940
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.11,
|
342 |
+
"grad_norm": 9.391054368953709,
|
343 |
+
"learning_rate": 1.130421052631579e-05,
|
344 |
+
"loss": 0.329,
|
345 |
+
"step": 960
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.11,
|
349 |
+
"grad_norm": 7.997549873904863,
|
350 |
+
"learning_rate": 1.1535789473684211e-05,
|
351 |
+
"loss": 0.359,
|
352 |
+
"step": 980
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.12,
|
356 |
+
"grad_norm": 10.755576173466588,
|
357 |
+
"learning_rate": 1.1767368421052634e-05,
|
358 |
+
"loss": 0.393,
|
359 |
+
"step": 1000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.12,
|
363 |
+
"grad_norm": 6.458117606549104,
|
364 |
+
"learning_rate": 1.1998947368421054e-05,
|
365 |
+
"loss": 0.363,
|
366 |
+
"step": 1020
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.12,
|
370 |
+
"grad_norm": 9.937055469862932,
|
371 |
+
"learning_rate": 1.2230526315789475e-05,
|
372 |
+
"loss": 0.3766,
|
373 |
+
"step": 1040
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.12,
|
377 |
+
"grad_norm": 7.485816768913991,
|
378 |
+
"learning_rate": 1.2462105263157898e-05,
|
379 |
+
"loss": 0.3845,
|
380 |
+
"step": 1060
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.13,
|
384 |
+
"grad_norm": 8.01333127284645,
|
385 |
+
"learning_rate": 1.2693684210526319e-05,
|
386 |
+
"loss": 0.3617,
|
387 |
+
"step": 1080
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.13,
|
391 |
+
"grad_norm": 8.911089094498925,
|
392 |
+
"learning_rate": 1.292526315789474e-05,
|
393 |
+
"loss": 0.3599,
|
394 |
+
"step": 1100
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.13,
|
398 |
+
"grad_norm": 8.32079434857686,
|
399 |
+
"learning_rate": 1.3156842105263158e-05,
|
400 |
+
"loss": 0.3722,
|
401 |
+
"step": 1120
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.13,
|
405 |
+
"grad_norm": 9.806231592184165,
|
406 |
+
"learning_rate": 1.3388421052631581e-05,
|
407 |
+
"loss": 0.3755,
|
408 |
+
"step": 1140
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.14,
|
412 |
+
"grad_norm": 8.798076540805445,
|
413 |
+
"learning_rate": 1.3620000000000002e-05,
|
414 |
+
"loss": 0.3616,
|
415 |
+
"step": 1160
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.14,
|
419 |
+
"grad_norm": 8.343613755617508,
|
420 |
+
"learning_rate": 1.3851578947368423e-05,
|
421 |
+
"loss": 0.3631,
|
422 |
+
"step": 1180
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.14,
|
426 |
+
"grad_norm": 8.35814690526204,
|
427 |
+
"learning_rate": 1.4083157894736843e-05,
|
428 |
+
"loss": 0.3638,
|
429 |
+
"step": 1200
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.14,
|
433 |
+
"grad_norm": 7.706542458286787,
|
434 |
+
"learning_rate": 1.4314736842105266e-05,
|
435 |
+
"loss": 0.375,
|
436 |
+
"step": 1220
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.15,
|
440 |
+
"grad_norm": 10.89212756963322,
|
441 |
+
"learning_rate": 1.4546315789473687e-05,
|
442 |
+
"loss": 0.4049,
|
443 |
+
"step": 1240
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.15,
|
447 |
+
"grad_norm": 11.46198790559678,
|
448 |
+
"learning_rate": 1.4777894736842107e-05,
|
449 |
+
"loss": 0.332,
|
450 |
+
"step": 1260
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.15,
|
454 |
+
"grad_norm": 8.365156167551179,
|
455 |
+
"learning_rate": 1.500947368421053e-05,
|
456 |
+
"loss": 0.3586,
|
457 |
+
"step": 1280
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.15,
|
461 |
+
"grad_norm": 7.841036992292662,
|
462 |
+
"learning_rate": 1.5241052631578949e-05,
|
463 |
+
"loss": 0.368,
|
464 |
+
"step": 1300
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.15,
|
468 |
+
"grad_norm": 9.84275168548854,
|
469 |
+
"learning_rate": 1.547263157894737e-05,
|
470 |
+
"loss": 0.3767,
|
471 |
+
"step": 1320
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.16,
|
475 |
+
"grad_norm": 10.506254240871392,
|
476 |
+
"learning_rate": 1.5704210526315792e-05,
|
477 |
+
"loss": 0.378,
|
478 |
+
"step": 1340
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.16,
|
482 |
+
"grad_norm": 7.844581104033147,
|
483 |
+
"learning_rate": 1.5935789473684213e-05,
|
484 |
+
"loss": 0.3453,
|
485 |
+
"step": 1360
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.16,
|
489 |
+
"grad_norm": 8.193758138016792,
|
490 |
+
"learning_rate": 1.6167368421052634e-05,
|
491 |
+
"loss": 0.3752,
|
492 |
+
"step": 1380
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.16,
|
496 |
+
"grad_norm": 7.475620318034102,
|
497 |
+
"learning_rate": 1.6398947368421055e-05,
|
498 |
+
"loss": 0.3642,
|
499 |
+
"step": 1400
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.17,
|
503 |
+
"grad_norm": 7.4964850772334355,
|
504 |
+
"learning_rate": 1.6630526315789475e-05,
|
505 |
+
"loss": 0.3377,
|
506 |
+
"step": 1420
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.17,
|
510 |
+
"grad_norm": 7.903753436810423,
|
511 |
+
"learning_rate": 1.6862105263157896e-05,
|
512 |
+
"loss": 0.3586,
|
513 |
+
"step": 1440
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.17,
|
517 |
+
"grad_norm": 10.49594728277505,
|
518 |
+
"learning_rate": 1.7093684210526317e-05,
|
519 |
+
"loss": 0.3468,
|
520 |
+
"step": 1460
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.17,
|
524 |
+
"grad_norm": 8.027713457118994,
|
525 |
+
"learning_rate": 1.7325263157894738e-05,
|
526 |
+
"loss": 0.3491,
|
527 |
+
"step": 1480
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.18,
|
531 |
+
"grad_norm": 7.2748681125287415,
|
532 |
+
"learning_rate": 1.755684210526316e-05,
|
533 |
+
"loss": 0.3581,
|
534 |
+
"step": 1500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.18,
|
538 |
+
"grad_norm": 6.077326940397276,
|
539 |
+
"learning_rate": 1.7788421052631583e-05,
|
540 |
+
"loss": 0.3356,
|
541 |
+
"step": 1520
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.18,
|
545 |
+
"grad_norm": 6.724980645701413,
|
546 |
+
"learning_rate": 1.802e-05,
|
547 |
+
"loss": 0.3656,
|
548 |
+
"step": 1540
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.18,
|
552 |
+
"grad_norm": 8.592315221136559,
|
553 |
+
"learning_rate": 1.825157894736842e-05,
|
554 |
+
"loss": 0.3467,
|
555 |
+
"step": 1560
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.18,
|
559 |
+
"grad_norm": 9.036253074638084,
|
560 |
+
"learning_rate": 1.8483157894736845e-05,
|
561 |
+
"loss": 0.3414,
|
562 |
+
"step": 1580
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.19,
|
566 |
+
"grad_norm": 11.349080832480995,
|
567 |
+
"learning_rate": 1.8714736842105266e-05,
|
568 |
+
"loss": 0.3655,
|
569 |
+
"step": 1600
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.19,
|
573 |
+
"grad_norm": 9.361475025905081,
|
574 |
+
"learning_rate": 1.8946315789473687e-05,
|
575 |
+
"loss": 0.3564,
|
576 |
+
"step": 1620
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.19,
|
580 |
+
"grad_norm": 6.53643855564322,
|
581 |
+
"learning_rate": 1.9177894736842108e-05,
|
582 |
+
"loss": 0.3714,
|
583 |
+
"step": 1640
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.19,
|
587 |
+
"grad_norm": 6.65699298275954,
|
588 |
+
"learning_rate": 1.940947368421053e-05,
|
589 |
+
"loss": 0.3546,
|
590 |
+
"step": 1660
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.2,
|
594 |
+
"grad_norm": 9.856127510930383,
|
595 |
+
"learning_rate": 1.964105263157895e-05,
|
596 |
+
"loss": 0.3308,
|
597 |
+
"step": 1680
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.2,
|
601 |
+
"grad_norm": 8.532146476622113,
|
602 |
+
"learning_rate": 1.987263157894737e-05,
|
603 |
+
"loss": 0.366,
|
604 |
+
"step": 1700
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.2,
|
608 |
+
"grad_norm": 8.327666937449752,
|
609 |
+
"learning_rate": 1.999999532098205e-05,
|
610 |
+
"loss": 0.3247,
|
611 |
+
"step": 1720
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.2,
|
615 |
+
"grad_norm": 10.876035443701728,
|
616 |
+
"learning_rate": 1.99999578888647e-05,
|
617 |
+
"loss": 0.3543,
|
618 |
+
"step": 1740
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.21,
|
622 |
+
"grad_norm": 8.263711805253918,
|
623 |
+
"learning_rate": 1.999988302477013e-05,
|
624 |
+
"loss": 0.3664,
|
625 |
+
"step": 1760
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.21,
|
629 |
+
"grad_norm": 7.575419338189409,
|
630 |
+
"learning_rate": 1.9999770728978607e-05,
|
631 |
+
"loss": 0.345,
|
632 |
+
"step": 1780
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.21,
|
636 |
+
"grad_norm": 7.814279338388738,
|
637 |
+
"learning_rate": 1.9999621001910508e-05,
|
638 |
+
"loss": 0.3573,
|
639 |
+
"step": 1800
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.21,
|
643 |
+
"grad_norm": 13.040107479471628,
|
644 |
+
"learning_rate": 1.999943384412636e-05,
|
645 |
+
"loss": 0.3344,
|
646 |
+
"step": 1820
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.22,
|
650 |
+
"grad_norm": 7.535441012066771,
|
651 |
+
"learning_rate": 1.99992092563268e-05,
|
652 |
+
"loss": 0.3552,
|
653 |
+
"step": 1840
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.22,
|
657 |
+
"grad_norm": 8.059491683038381,
|
658 |
+
"learning_rate": 1.9998947239352593e-05,
|
659 |
+
"loss": 0.3442,
|
660 |
+
"step": 1860
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.22,
|
664 |
+
"grad_norm": 6.700609139607897,
|
665 |
+
"learning_rate": 1.999864779418462e-05,
|
666 |
+
"loss": 0.3584,
|
667 |
+
"step": 1880
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.22,
|
671 |
+
"grad_norm": 6.831136707088909,
|
672 |
+
"learning_rate": 1.999831092194389e-05,
|
673 |
+
"loss": 0.3341,
|
674 |
+
"step": 1900
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.22,
|
678 |
+
"grad_norm": 10.30262237054047,
|
679 |
+
"learning_rate": 1.9997936623891498e-05,
|
680 |
+
"loss": 0.3704,
|
681 |
+
"step": 1920
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.23,
|
685 |
+
"grad_norm": 6.703691792033561,
|
686 |
+
"learning_rate": 1.9997524901428677e-05,
|
687 |
+
"loss": 0.3769,
|
688 |
+
"step": 1940
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.23,
|
692 |
+
"grad_norm": 7.251026212477321,
|
693 |
+
"learning_rate": 1.9997075756096734e-05,
|
694 |
+
"loss": 0.3234,
|
695 |
+
"step": 1960
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.23,
|
699 |
+
"grad_norm": 6.14471190830255,
|
700 |
+
"learning_rate": 1.9996589189577094e-05,
|
701 |
+
"loss": 0.3443,
|
702 |
+
"step": 1980
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.23,
|
706 |
+
"grad_norm": 7.254885638733633,
|
707 |
+
"learning_rate": 1.999606520369125e-05,
|
708 |
+
"loss": 0.3178,
|
709 |
+
"step": 2000
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.24,
|
713 |
+
"grad_norm": 7.330977870771951,
|
714 |
+
"learning_rate": 1.9995503800400805e-05,
|
715 |
+
"loss": 0.3309,
|
716 |
+
"step": 2020
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.24,
|
720 |
+
"grad_norm": 7.291895603037368,
|
721 |
+
"learning_rate": 1.9994904981807407e-05,
|
722 |
+
"loss": 0.3372,
|
723 |
+
"step": 2040
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.24,
|
727 |
+
"grad_norm": 12.772894555548028,
|
728 |
+
"learning_rate": 1.9994268750152793e-05,
|
729 |
+
"loss": 0.3747,
|
730 |
+
"step": 2060
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.24,
|
734 |
+
"grad_norm": 9.497788021161657,
|
735 |
+
"learning_rate": 1.999359510781875e-05,
|
736 |
+
"loss": 0.3529,
|
737 |
+
"step": 2080
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.25,
|
741 |
+
"grad_norm": 6.581748417513793,
|
742 |
+
"learning_rate": 1.9992884057327118e-05,
|
743 |
+
"loss": 0.3395,
|
744 |
+
"step": 2100
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.25,
|
748 |
+
"grad_norm": 9.523030924078585,
|
749 |
+
"learning_rate": 1.9992135601339776e-05,
|
750 |
+
"loss": 0.3469,
|
751 |
+
"step": 2120
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.25,
|
755 |
+
"grad_norm": 17.640537636796516,
|
756 |
+
"learning_rate": 1.999134974265864e-05,
|
757 |
+
"loss": 0.3365,
|
758 |
+
"step": 2140
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.25,
|
762 |
+
"grad_norm": 5.4385511763432985,
|
763 |
+
"learning_rate": 1.999052648422563e-05,
|
764 |
+
"loss": 0.3845,
|
765 |
+
"step": 2160
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.26,
|
769 |
+
"grad_norm": 7.585921156892153,
|
770 |
+
"learning_rate": 1.9989665829122704e-05,
|
771 |
+
"loss": 0.3464,
|
772 |
+
"step": 2180
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.26,
|
776 |
+
"grad_norm": 12.163408304702841,
|
777 |
+
"learning_rate": 1.9988767780571778e-05,
|
778 |
+
"loss": 0.3127,
|
779 |
+
"step": 2200
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.26,
|
783 |
+
"grad_norm": 8.246994395835456,
|
784 |
+
"learning_rate": 1.9987832341934793e-05,
|
785 |
+
"loss": 0.3424,
|
786 |
+
"step": 2220
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.26,
|
790 |
+
"grad_norm": 9.628684787640838,
|
791 |
+
"learning_rate": 1.9986859516713636e-05,
|
792 |
+
"loss": 0.3472,
|
793 |
+
"step": 2240
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.26,
|
797 |
+
"grad_norm": 10.912326639203211,
|
798 |
+
"learning_rate": 1.9985849308550167e-05,
|
799 |
+
"loss": 0.3326,
|
800 |
+
"step": 2260
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.27,
|
804 |
+
"grad_norm": 6.419410251137725,
|
805 |
+
"learning_rate": 1.9984801721226188e-05,
|
806 |
+
"loss": 0.3297,
|
807 |
+
"step": 2280
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.27,
|
811 |
+
"grad_norm": 7.798212276898864,
|
812 |
+
"learning_rate": 1.998371675866344e-05,
|
813 |
+
"loss": 0.3389,
|
814 |
+
"step": 2300
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.27,
|
818 |
+
"grad_norm": 7.811483576458649,
|
819 |
+
"learning_rate": 1.9982594424923566e-05,
|
820 |
+
"loss": 0.332,
|
821 |
+
"step": 2320
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.27,
|
825 |
+
"grad_norm": 6.967736687994363,
|
826 |
+
"learning_rate": 1.9981434724208126e-05,
|
827 |
+
"loss": 0.3099,
|
828 |
+
"step": 2340
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.28,
|
832 |
+
"grad_norm": 9.635115819134949,
|
833 |
+
"learning_rate": 1.9980237660858565e-05,
|
834 |
+
"loss": 0.3285,
|
835 |
+
"step": 2360
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.28,
|
839 |
+
"grad_norm": 6.720069081541748,
|
840 |
+
"learning_rate": 1.997900323935619e-05,
|
841 |
+
"loss": 0.343,
|
842 |
+
"step": 2380
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.28,
|
846 |
+
"grad_norm": 10.300889386045979,
|
847 |
+
"learning_rate": 1.9977731464322162e-05,
|
848 |
+
"loss": 0.3667,
|
849 |
+
"step": 2400
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.28,
|
853 |
+
"grad_norm": 7.888854177455323,
|
854 |
+
"learning_rate": 1.9976422340517495e-05,
|
855 |
+
"loss": 0.3397,
|
856 |
+
"step": 2420
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.29,
|
860 |
+
"grad_norm": 9.643051064776678,
|
861 |
+
"learning_rate": 1.9975075872843e-05,
|
862 |
+
"loss": 0.3371,
|
863 |
+
"step": 2440
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.29,
|
867 |
+
"grad_norm": 6.166262467342929,
|
868 |
+
"learning_rate": 1.9973692066339298e-05,
|
869 |
+
"loss": 0.3424,
|
870 |
+
"step": 2460
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.29,
|
874 |
+
"grad_norm": 7.520601841401043,
|
875 |
+
"learning_rate": 1.9972270926186794e-05,
|
876 |
+
"loss": 0.3083,
|
877 |
+
"step": 2480
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.29,
|
881 |
+
"grad_norm": 6.095472200047568,
|
882 |
+
"learning_rate": 1.9970812457705642e-05,
|
883 |
+
"loss": 0.3512,
|
884 |
+
"step": 2500
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.29,
|
888 |
+
"grad_norm": 7.259492119293066,
|
889 |
+
"learning_rate": 1.9969316666355757e-05,
|
890 |
+
"loss": 0.3309,
|
891 |
+
"step": 2520
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.3,
|
895 |
+
"grad_norm": 8.355978245335697,
|
896 |
+
"learning_rate": 1.996778355773676e-05,
|
897 |
+
"loss": 0.3296,
|
898 |
+
"step": 2540
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.3,
|
902 |
+
"grad_norm": 9.612502269967832,
|
903 |
+
"learning_rate": 1.996621313758798e-05,
|
904 |
+
"loss": 0.3391,
|
905 |
+
"step": 2560
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.3,
|
909 |
+
"grad_norm": 8.148285817739712,
|
910 |
+
"learning_rate": 1.9964605411788424e-05,
|
911 |
+
"loss": 0.3416,
|
912 |
+
"step": 2580
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.3,
|
916 |
+
"grad_norm": 7.645206131186397,
|
917 |
+
"learning_rate": 1.9962960386356748e-05,
|
918 |
+
"loss": 0.352,
|
919 |
+
"step": 2600
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.31,
|
923 |
+
"grad_norm": 5.406075006199623,
|
924 |
+
"learning_rate": 1.9961278067451258e-05,
|
925 |
+
"loss": 0.3194,
|
926 |
+
"step": 2620
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.31,
|
930 |
+
"grad_norm": 7.23674984010716,
|
931 |
+
"learning_rate": 1.995955846136986e-05,
|
932 |
+
"loss": 0.3216,
|
933 |
+
"step": 2640
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.31,
|
937 |
+
"grad_norm": 8.044071872202302,
|
938 |
+
"learning_rate": 1.9957801574550044e-05,
|
939 |
+
"loss": 0.321,
|
940 |
+
"step": 2660
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.31,
|
944 |
+
"grad_norm": 7.2624583573058485,
|
945 |
+
"learning_rate": 1.9956007413568874e-05,
|
946 |
+
"loss": 0.3352,
|
947 |
+
"step": 2680
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.32,
|
951 |
+
"grad_norm": 9.277277549105909,
|
952 |
+
"learning_rate": 1.9954175985142955e-05,
|
953 |
+
"loss": 0.3391,
|
954 |
+
"step": 2700
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.32,
|
958 |
+
"grad_norm": 10.975275864316648,
|
959 |
+
"learning_rate": 1.9952307296128395e-05,
|
960 |
+
"loss": 0.3298,
|
961 |
+
"step": 2720
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.32,
|
965 |
+
"grad_norm": 11.416959735607907,
|
966 |
+
"learning_rate": 1.9950401353520795e-05,
|
967 |
+
"loss": 0.3382,
|
968 |
+
"step": 2740
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.32,
|
972 |
+
"grad_norm": 7.384993942351236,
|
973 |
+
"learning_rate": 1.994845816445522e-05,
|
974 |
+
"loss": 0.3422,
|
975 |
+
"step": 2760
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.33,
|
979 |
+
"grad_norm": 6.775839902047113,
|
980 |
+
"learning_rate": 1.9946477736206167e-05,
|
981 |
+
"loss": 0.3694,
|
982 |
+
"step": 2780
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.33,
|
986 |
+
"grad_norm": 8.246414330131564,
|
987 |
+
"learning_rate": 1.9944460076187546e-05,
|
988 |
+
"loss": 0.3458,
|
989 |
+
"step": 2800
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.33,
|
993 |
+
"grad_norm": 7.152660285783071,
|
994 |
+
"learning_rate": 1.9942405191952646e-05,
|
995 |
+
"loss": 0.3426,
|
996 |
+
"step": 2820
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.33,
|
1000 |
+
"grad_norm": 6.9408668390055315,
|
1001 |
+
"learning_rate": 1.9940313091194096e-05,
|
1002 |
+
"loss": 0.3097,
|
1003 |
+
"step": 2840
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.33,
|
1007 |
+
"grad_norm": 5.797513942002627,
|
1008 |
+
"learning_rate": 1.9938183781743873e-05,
|
1009 |
+
"loss": 0.3102,
|
1010 |
+
"step": 2860
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.34,
|
1014 |
+
"grad_norm": 7.361935180345544,
|
1015 |
+
"learning_rate": 1.9936017271573223e-05,
|
1016 |
+
"loss": 0.3102,
|
1017 |
+
"step": 2880
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.34,
|
1021 |
+
"grad_norm": 7.4796257480282,
|
1022 |
+
"learning_rate": 1.9933813568792678e-05,
|
1023 |
+
"loss": 0.3256,
|
1024 |
+
"step": 2900
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.34,
|
1028 |
+
"grad_norm": 5.500192812227557,
|
1029 |
+
"learning_rate": 1.9931572681651984e-05,
|
1030 |
+
"loss": 0.3107,
|
1031 |
+
"step": 2920
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.34,
|
1035 |
+
"grad_norm": 13.84776864376109,
|
1036 |
+
"learning_rate": 1.9929294618540103e-05,
|
1037 |
+
"loss": 0.3062,
|
1038 |
+
"step": 2940
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.35,
|
1042 |
+
"grad_norm": 7.937410128828084,
|
1043 |
+
"learning_rate": 1.992697938798516e-05,
|
1044 |
+
"loss": 0.3293,
|
1045 |
+
"step": 2960
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.35,
|
1049 |
+
"grad_norm": 5.447364190742796,
|
1050 |
+
"learning_rate": 1.9924626998654433e-05,
|
1051 |
+
"loss": 0.3318,
|
1052 |
+
"step": 2980
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.35,
|
1056 |
+
"grad_norm": 7.825239369201605,
|
1057 |
+
"learning_rate": 1.9922237459354287e-05,
|
1058 |
+
"loss": 0.3238,
|
1059 |
+
"step": 3000
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.35,
|
1063 |
+
"grad_norm": 6.466926354506395,
|
1064 |
+
"learning_rate": 1.9919810779030177e-05,
|
1065 |
+
"loss": 0.3136,
|
1066 |
+
"step": 3020
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.36,
|
1070 |
+
"grad_norm": 10.115420483963225,
|
1071 |
+
"learning_rate": 1.9917346966766596e-05,
|
1072 |
+
"loss": 0.3329,
|
1073 |
+
"step": 3040
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.36,
|
1077 |
+
"grad_norm": 6.08100630613984,
|
1078 |
+
"learning_rate": 1.991484603178704e-05,
|
1079 |
+
"loss": 0.2999,
|
1080 |
+
"step": 3060
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.36,
|
1084 |
+
"grad_norm": 6.153474908414458,
|
1085 |
+
"learning_rate": 1.991230798345398e-05,
|
1086 |
+
"loss": 0.3344,
|
1087 |
+
"step": 3080
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.36,
|
1091 |
+
"grad_norm": 6.956842076140817,
|
1092 |
+
"learning_rate": 1.990973283126882e-05,
|
1093 |
+
"loss": 0.3356,
|
1094 |
+
"step": 3100
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.37,
|
1098 |
+
"grad_norm": 7.977473013654998,
|
1099 |
+
"learning_rate": 1.990712058487187e-05,
|
1100 |
+
"loss": 0.2984,
|
1101 |
+
"step": 3120
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.37,
|
1105 |
+
"grad_norm": 7.472067890046691,
|
1106 |
+
"learning_rate": 1.9904471254042304e-05,
|
1107 |
+
"loss": 0.308,
|
1108 |
+
"step": 3140
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.37,
|
1112 |
+
"grad_norm": 6.98090482864238,
|
1113 |
+
"learning_rate": 1.9901784848698125e-05,
|
1114 |
+
"loss": 0.3036,
|
1115 |
+
"step": 3160
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.37,
|
1119 |
+
"grad_norm": 7.229553593404789,
|
1120 |
+
"learning_rate": 1.989906137889613e-05,
|
1121 |
+
"loss": 0.3027,
|
1122 |
+
"step": 3180
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.37,
|
1126 |
+
"grad_norm": 5.9700766482137295,
|
1127 |
+
"learning_rate": 1.9896300854831862e-05,
|
1128 |
+
"loss": 0.3329,
|
1129 |
+
"step": 3200
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.38,
|
1133 |
+
"grad_norm": 7.864131148182889,
|
1134 |
+
"learning_rate": 1.989350328683959e-05,
|
1135 |
+
"loss": 0.308,
|
1136 |
+
"step": 3220
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.38,
|
1140 |
+
"grad_norm": 20.04577205534678,
|
1141 |
+
"learning_rate": 1.989066868539225e-05,
|
1142 |
+
"loss": 0.3217,
|
1143 |
+
"step": 3240
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.38,
|
1147 |
+
"grad_norm": 8.46751929768339,
|
1148 |
+
"learning_rate": 1.9887797061101424e-05,
|
1149 |
+
"loss": 0.3036,
|
1150 |
+
"step": 3260
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.38,
|
1154 |
+
"grad_norm": 7.667111535917501,
|
1155 |
+
"learning_rate": 1.9884888424717296e-05,
|
1156 |
+
"loss": 0.3084,
|
1157 |
+
"step": 3280
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.39,
|
1161 |
+
"grad_norm": 6.615069450077278,
|
1162 |
+
"learning_rate": 1.9881942787128594e-05,
|
1163 |
+
"loss": 0.3177,
|
1164 |
+
"step": 3300
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.39,
|
1168 |
+
"grad_norm": 9.324876177990959,
|
1169 |
+
"learning_rate": 1.9878960159362572e-05,
|
1170 |
+
"loss": 0.3496,
|
1171 |
+
"step": 3320
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.39,
|
1175 |
+
"grad_norm": 7.1979554134343635,
|
1176 |
+
"learning_rate": 1.987594055258496e-05,
|
1177 |
+
"loss": 0.3167,
|
1178 |
+
"step": 3340
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.39,
|
1182 |
+
"grad_norm": 29.076306154493622,
|
1183 |
+
"learning_rate": 1.987288397809993e-05,
|
1184 |
+
"loss": 0.34,
|
1185 |
+
"step": 3360
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.4,
|
1189 |
+
"grad_norm": 7.861933206527291,
|
1190 |
+
"learning_rate": 1.986979044735002e-05,
|
1191 |
+
"loss": 0.3424,
|
1192 |
+
"step": 3380
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.4,
|
1196 |
+
"grad_norm": 5.7878723156599445,
|
1197 |
+
"learning_rate": 1.9866659971916146e-05,
|
1198 |
+
"loss": 0.3157,
|
1199 |
+
"step": 3400
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.4,
|
1203 |
+
"grad_norm": 8.470531768859948,
|
1204 |
+
"learning_rate": 1.9863492563517513e-05,
|
1205 |
+
"loss": 0.3201,
|
1206 |
+
"step": 3420
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.4,
|
1210 |
+
"grad_norm": 8.104846079245535,
|
1211 |
+
"learning_rate": 1.98602882340116e-05,
|
1212 |
+
"loss": 0.322,
|
1213 |
+
"step": 3440
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.4,
|
1217 |
+
"grad_norm": 6.180289951670451,
|
1218 |
+
"learning_rate": 1.9857046995394084e-05,
|
1219 |
+
"loss": 0.2991,
|
1220 |
+
"step": 3460
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.41,
|
1224 |
+
"grad_norm": 4.962160167060266,
|
1225 |
+
"learning_rate": 1.985376885979884e-05,
|
1226 |
+
"loss": 0.3097,
|
1227 |
+
"step": 3480
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.41,
|
1231 |
+
"grad_norm": 6.813966925636774,
|
1232 |
+
"learning_rate": 1.9850453839497844e-05,
|
1233 |
+
"loss": 0.3294,
|
1234 |
+
"step": 3500
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.41,
|
1238 |
+
"grad_norm": 5.902763508299491,
|
1239 |
+
"learning_rate": 1.9847101946901172e-05,
|
1240 |
+
"loss": 0.2967,
|
1241 |
+
"step": 3520
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.41,
|
1245 |
+
"grad_norm": 7.359798475906595,
|
1246 |
+
"learning_rate": 1.984371319455693e-05,
|
1247 |
+
"loss": 0.3268,
|
1248 |
+
"step": 3540
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.42,
|
1252 |
+
"grad_norm": 7.377881796357637,
|
1253 |
+
"learning_rate": 1.9840287595151205e-05,
|
1254 |
+
"loss": 0.3251,
|
1255 |
+
"step": 3560
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.42,
|
1259 |
+
"grad_norm": 7.261601866242624,
|
1260 |
+
"learning_rate": 1.9836825161508032e-05,
|
1261 |
+
"loss": 0.284,
|
1262 |
+
"step": 3580
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.42,
|
1266 |
+
"grad_norm": 6.123609423918951,
|
1267 |
+
"learning_rate": 1.983332590658934e-05,
|
1268 |
+
"loss": 0.3137,
|
1269 |
+
"step": 3600
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.42,
|
1273 |
+
"grad_norm": 7.205290164862431,
|
1274 |
+
"learning_rate": 1.9829789843494885e-05,
|
1275 |
+
"loss": 0.3,
|
1276 |
+
"step": 3620
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.43,
|
1280 |
+
"grad_norm": 6.0471563544848035,
|
1281 |
+
"learning_rate": 1.9826216985462245e-05,
|
1282 |
+
"loss": 0.2991,
|
1283 |
+
"step": 3640
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 0.43,
|
1287 |
+
"grad_norm": 7.436589545934819,
|
1288 |
+
"learning_rate": 1.9822607345866715e-05,
|
1289 |
+
"loss": 0.3299,
|
1290 |
+
"step": 3660
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.43,
|
1294 |
+
"grad_norm": 8.240853065109379,
|
1295 |
+
"learning_rate": 1.9818960938221308e-05,
|
1296 |
+
"loss": 0.2886,
|
1297 |
+
"step": 3680
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.43,
|
1301 |
+
"grad_norm": 5.451034188795461,
|
1302 |
+
"learning_rate": 1.9815277776176663e-05,
|
1303 |
+
"loss": 0.3138,
|
1304 |
+
"step": 3700
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 0.44,
|
1308 |
+
"grad_norm": 7.874196329434049,
|
1309 |
+
"learning_rate": 1.9811557873521027e-05,
|
1310 |
+
"loss": 0.2946,
|
1311 |
+
"step": 3720
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.44,
|
1315 |
+
"grad_norm": 6.547528436867746,
|
1316 |
+
"learning_rate": 1.9807801244180174e-05,
|
1317 |
+
"loss": 0.2978,
|
1318 |
+
"step": 3740
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 0.44,
|
1322 |
+
"grad_norm": 5.816214082411462,
|
1323 |
+
"learning_rate": 1.980400790221739e-05,
|
1324 |
+
"loss": 0.3067,
|
1325 |
+
"step": 3760
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 0.44,
|
1329 |
+
"grad_norm": 6.245697982302123,
|
1330 |
+
"learning_rate": 1.9800177861833372e-05,
|
1331 |
+
"loss": 0.3191,
|
1332 |
+
"step": 3780
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 0.44,
|
1336 |
+
"grad_norm": 7.932045331416635,
|
1337 |
+
"learning_rate": 1.9796311137366212e-05,
|
1338 |
+
"loss": 0.3439,
|
1339 |
+
"step": 3800
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 0.45,
|
1343 |
+
"grad_norm": 6.088006858952151,
|
1344 |
+
"learning_rate": 1.9792407743291343e-05,
|
1345 |
+
"loss": 0.33,
|
1346 |
+
"step": 3820
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.45,
|
1350 |
+
"grad_norm": 5.770262468473867,
|
1351 |
+
"learning_rate": 1.9788467694221453e-05,
|
1352 |
+
"loss": 0.2897,
|
1353 |
+
"step": 3840
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.45,
|
1357 |
+
"grad_norm": 7.978864884873927,
|
1358 |
+
"learning_rate": 1.9784491004906468e-05,
|
1359 |
+
"loss": 0.3118,
|
1360 |
+
"step": 3860
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 0.45,
|
1364 |
+
"grad_norm": 6.631368778757732,
|
1365 |
+
"learning_rate": 1.9780477690233476e-05,
|
1366 |
+
"loss": 0.3165,
|
1367 |
+
"step": 3880
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 0.46,
|
1371 |
+
"grad_norm": 6.541290304773085,
|
1372 |
+
"learning_rate": 1.9776427765226664e-05,
|
1373 |
+
"loss": 0.3379,
|
1374 |
+
"step": 3900
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.46,
|
1378 |
+
"grad_norm": 6.42886929503141,
|
1379 |
+
"learning_rate": 1.9772341245047285e-05,
|
1380 |
+
"loss": 0.3136,
|
1381 |
+
"step": 3920
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.46,
|
1385 |
+
"grad_norm": 9.004651033459043,
|
1386 |
+
"learning_rate": 1.9768218144993593e-05,
|
1387 |
+
"loss": 0.311,
|
1388 |
+
"step": 3940
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 0.46,
|
1392 |
+
"grad_norm": 6.241942743461084,
|
1393 |
+
"learning_rate": 1.976405848050077e-05,
|
1394 |
+
"loss": 0.3224,
|
1395 |
+
"step": 3960
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.47,
|
1399 |
+
"grad_norm": 7.030346892956473,
|
1400 |
+
"learning_rate": 1.975986226714089e-05,
|
1401 |
+
"loss": 0.3513,
|
1402 |
+
"step": 3980
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.47,
|
1406 |
+
"grad_norm": 6.984184655106913,
|
1407 |
+
"learning_rate": 1.9755629520622835e-05,
|
1408 |
+
"loss": 0.3031,
|
1409 |
+
"step": 4000
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 0.47,
|
1413 |
+
"grad_norm": 3.6594620639728253,
|
1414 |
+
"learning_rate": 1.9751360256792274e-05,
|
1415 |
+
"loss": 0.2819,
|
1416 |
+
"step": 4020
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 0.47,
|
1420 |
+
"grad_norm": 3.9453364305431418,
|
1421 |
+
"learning_rate": 1.9747054491631567e-05,
|
1422 |
+
"loss": 0.2806,
|
1423 |
+
"step": 4040
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 0.48,
|
1427 |
+
"grad_norm": 3.8004852838340475,
|
1428 |
+
"learning_rate": 1.9742712241259726e-05,
|
1429 |
+
"loss": 0.2712,
|
1430 |
+
"step": 4060
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 0.48,
|
1434 |
+
"grad_norm": 4.671864793440983,
|
1435 |
+
"learning_rate": 1.9738333521932348e-05,
|
1436 |
+
"loss": 0.264,
|
1437 |
+
"step": 4080
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.48,
|
1441 |
+
"grad_norm": 3.9158215253486452,
|
1442 |
+
"learning_rate": 1.9733918350041546e-05,
|
1443 |
+
"loss": 0.2466,
|
1444 |
+
"step": 4100
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 0.48,
|
1448 |
+
"grad_norm": 3.232730170815344,
|
1449 |
+
"learning_rate": 1.972946674211591e-05,
|
1450 |
+
"loss": 0.28,
|
1451 |
+
"step": 4120
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 0.48,
|
1455 |
+
"grad_norm": 5.26102706338969,
|
1456 |
+
"learning_rate": 1.972497871482043e-05,
|
1457 |
+
"loss": 0.2793,
|
1458 |
+
"step": 4140
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 0.49,
|
1462 |
+
"grad_norm": 6.036896745386087,
|
1463 |
+
"learning_rate": 1.972045428495642e-05,
|
1464 |
+
"loss": 0.2551,
|
1465 |
+
"step": 4160
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.49,
|
1469 |
+
"grad_norm": 3.4899809349872823,
|
1470 |
+
"learning_rate": 1.971589346946149e-05,
|
1471 |
+
"loss": 0.2746,
|
1472 |
+
"step": 4180
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 0.49,
|
1476 |
+
"grad_norm": 4.003065603442425,
|
1477 |
+
"learning_rate": 1.9711296285409443e-05,
|
1478 |
+
"loss": 0.2639,
|
1479 |
+
"step": 4200
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.49,
|
1483 |
+
"grad_norm": 2.8477299266017626,
|
1484 |
+
"learning_rate": 1.9706662750010255e-05,
|
1485 |
+
"loss": 0.2689,
|
1486 |
+
"step": 4220
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 0.5,
|
1490 |
+
"grad_norm": 3.5491058459283837,
|
1491 |
+
"learning_rate": 1.970199288060996e-05,
|
1492 |
+
"loss": 0.2642,
|
1493 |
+
"step": 4240
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 0.5,
|
1497 |
+
"grad_norm": 3.658049963633355,
|
1498 |
+
"learning_rate": 1.969728669469063e-05,
|
1499 |
+
"loss": 0.2699,
|
1500 |
+
"step": 4260
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 0.5,
|
1504 |
+
"grad_norm": 3.7093939532444127,
|
1505 |
+
"learning_rate": 1.9692544209870287e-05,
|
1506 |
+
"loss": 0.2697,
|
1507 |
+
"step": 4280
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 0.5,
|
1511 |
+
"grad_norm": 3.0342042036143444,
|
1512 |
+
"learning_rate": 1.968776544390283e-05,
|
1513 |
+
"loss": 0.2654,
|
1514 |
+
"step": 4300
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 0.51,
|
1518 |
+
"grad_norm": 3.8174199112021174,
|
1519 |
+
"learning_rate": 1.9682950414678004e-05,
|
1520 |
+
"loss": 0.2525,
|
1521 |
+
"step": 4320
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.51,
|
1525 |
+
"grad_norm": 5.35961771156863,
|
1526 |
+
"learning_rate": 1.9678099140221284e-05,
|
1527 |
+
"loss": 0.2464,
|
1528 |
+
"step": 4340
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.51,
|
1532 |
+
"grad_norm": 5.063501894675061,
|
1533 |
+
"learning_rate": 1.9673211638693844e-05,
|
1534 |
+
"loss": 0.2788,
|
1535 |
+
"step": 4360
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 0.51,
|
1539 |
+
"grad_norm": 3.8581072620927723,
|
1540 |
+
"learning_rate": 1.9668287928392478e-05,
|
1541 |
+
"loss": 0.2743,
|
1542 |
+
"step": 4380
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 0.51,
|
1546 |
+
"grad_norm": 3.386524586463125,
|
1547 |
+
"learning_rate": 1.9663328027749523e-05,
|
1548 |
+
"loss": 0.2547,
|
1549 |
+
"step": 4400
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 0.52,
|
1553 |
+
"grad_norm": 4.049063661443696,
|
1554 |
+
"learning_rate": 1.9658331955332807e-05,
|
1555 |
+
"loss": 0.2787,
|
1556 |
+
"step": 4420
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 0.52,
|
1560 |
+
"grad_norm": 5.12761026294579,
|
1561 |
+
"learning_rate": 1.9653299729845564e-05,
|
1562 |
+
"loss": 0.2577,
|
1563 |
+
"step": 4440
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.52,
|
1567 |
+
"grad_norm": 3.808933278135121,
|
1568 |
+
"learning_rate": 1.9648231370126375e-05,
|
1569 |
+
"loss": 0.2654,
|
1570 |
+
"step": 4460
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 0.52,
|
1574 |
+
"grad_norm": 4.402659150192465,
|
1575 |
+
"learning_rate": 1.9643126895149087e-05,
|
1576 |
+
"loss": 0.2603,
|
1577 |
+
"step": 4480
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 0.53,
|
1581 |
+
"grad_norm": 8.492295307503369,
|
1582 |
+
"learning_rate": 1.963798632402275e-05,
|
1583 |
+
"loss": 0.2691,
|
1584 |
+
"step": 4500
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 0.53,
|
1588 |
+
"grad_norm": 3.628014593555578,
|
1589 |
+
"learning_rate": 1.9632809675991544e-05,
|
1590 |
+
"loss": 0.2711,
|
1591 |
+
"step": 4520
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.53,
|
1595 |
+
"grad_norm": 5.207256154885955,
|
1596 |
+
"learning_rate": 1.9627596970434708e-05,
|
1597 |
+
"loss": 0.2604,
|
1598 |
+
"step": 4540
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 0.53,
|
1602 |
+
"grad_norm": 3.892539047603965,
|
1603 |
+
"learning_rate": 1.962234822686646e-05,
|
1604 |
+
"loss": 0.2693,
|
1605 |
+
"step": 4560
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.54,
|
1609 |
+
"grad_norm": 4.005334872796194,
|
1610 |
+
"learning_rate": 1.961706346493594e-05,
|
1611 |
+
"loss": 0.2774,
|
1612 |
+
"step": 4580
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 0.54,
|
1616 |
+
"grad_norm": 4.456881895914548,
|
1617 |
+
"learning_rate": 1.9611742704427106e-05,
|
1618 |
+
"loss": 0.2531,
|
1619 |
+
"step": 4600
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 0.54,
|
1623 |
+
"grad_norm": 3.925512807597538,
|
1624 |
+
"learning_rate": 1.9606385965258697e-05,
|
1625 |
+
"loss": 0.2507,
|
1626 |
+
"step": 4620
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 0.54,
|
1630 |
+
"grad_norm": 4.401211069070843,
|
1631 |
+
"learning_rate": 1.9600993267484147e-05,
|
1632 |
+
"loss": 0.262,
|
1633 |
+
"step": 4640
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 0.55,
|
1637 |
+
"grad_norm": 5.3437799820979075,
|
1638 |
+
"learning_rate": 1.9595564631291478e-05,
|
1639 |
+
"loss": 0.2516,
|
1640 |
+
"step": 4660
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 0.55,
|
1644 |
+
"grad_norm": 4.553539308066039,
|
1645 |
+
"learning_rate": 1.9590100077003278e-05,
|
1646 |
+
"loss": 0.2603,
|
1647 |
+
"step": 4680
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.55,
|
1651 |
+
"grad_norm": 3.169670353545694,
|
1652 |
+
"learning_rate": 1.958459962507658e-05,
|
1653 |
+
"loss": 0.2875,
|
1654 |
+
"step": 4700
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 0.55,
|
1658 |
+
"grad_norm": 3.572973282405317,
|
1659 |
+
"learning_rate": 1.9579063296102812e-05,
|
1660 |
+
"loss": 0.2671,
|
1661 |
+
"step": 4720
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 0.55,
|
1665 |
+
"grad_norm": 3.59782258517998,
|
1666 |
+
"learning_rate": 1.957349111080771e-05,
|
1667 |
+
"loss": 0.2837,
|
1668 |
+
"step": 4740
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 0.56,
|
1672 |
+
"grad_norm": 5.199297439358037,
|
1673 |
+
"learning_rate": 1.956788309005123e-05,
|
1674 |
+
"loss": 0.2753,
|
1675 |
+
"step": 4760
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 0.56,
|
1679 |
+
"grad_norm": 4.993257936146954,
|
1680 |
+
"learning_rate": 1.95622392548275e-05,
|
1681 |
+
"loss": 0.2714,
|
1682 |
+
"step": 4780
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.56,
|
1686 |
+
"grad_norm": 3.7288744650364642,
|
1687 |
+
"learning_rate": 1.955655962626471e-05,
|
1688 |
+
"loss": 0.2609,
|
1689 |
+
"step": 4800
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.56,
|
1693 |
+
"grad_norm": 5.377784540016259,
|
1694 |
+
"learning_rate": 1.9550844225625043e-05,
|
1695 |
+
"loss": 0.2605,
|
1696 |
+
"step": 4820
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 0.57,
|
1700 |
+
"grad_norm": 3.1237811954279353,
|
1701 |
+
"learning_rate": 1.954509307430461e-05,
|
1702 |
+
"loss": 0.2569,
|
1703 |
+
"step": 4840
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 0.57,
|
1707 |
+
"grad_norm": 4.101705029145583,
|
1708 |
+
"learning_rate": 1.953930619383335e-05,
|
1709 |
+
"loss": 0.2719,
|
1710 |
+
"step": 4860
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 0.57,
|
1714 |
+
"grad_norm": 2.734092828632754,
|
1715 |
+
"learning_rate": 1.953348360587496e-05,
|
1716 |
+
"loss": 0.2503,
|
1717 |
+
"step": 4880
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 0.57,
|
1721 |
+
"grad_norm": 3.4516150854343604,
|
1722 |
+
"learning_rate": 1.9527625332226804e-05,
|
1723 |
+
"loss": 0.2588,
|
1724 |
+
"step": 4900
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 0.58,
|
1728 |
+
"grad_norm": 3.0561153265178085,
|
1729 |
+
"learning_rate": 1.952173139481985e-05,
|
1730 |
+
"loss": 0.2779,
|
1731 |
+
"step": 4920
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.58,
|
1735 |
+
"grad_norm": 3.5096519082422986,
|
1736 |
+
"learning_rate": 1.9515801815718566e-05,
|
1737 |
+
"loss": 0.2567,
|
1738 |
+
"step": 4940
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 0.58,
|
1742 |
+
"grad_norm": 3.1690240083159993,
|
1743 |
+
"learning_rate": 1.9509836617120856e-05,
|
1744 |
+
"loss": 0.2466,
|
1745 |
+
"step": 4960
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.58,
|
1749 |
+
"grad_norm": 3.2970371296868484,
|
1750 |
+
"learning_rate": 1.950383582135796e-05,
|
1751 |
+
"loss": 0.2762,
|
1752 |
+
"step": 4980
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 0.59,
|
1756 |
+
"grad_norm": 4.326207366177782,
|
1757 |
+
"learning_rate": 1.9497799450894387e-05,
|
1758 |
+
"loss": 0.2681,
|
1759 |
+
"step": 5000
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 0.59,
|
1763 |
+
"grad_norm": 3.977255410491104,
|
1764 |
+
"learning_rate": 1.949172752832782e-05,
|
1765 |
+
"loss": 0.235,
|
1766 |
+
"step": 5020
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 0.59,
|
1770 |
+
"grad_norm": 3.5634772315616665,
|
1771 |
+
"learning_rate": 1.9485620076389036e-05,
|
1772 |
+
"loss": 0.254,
|
1773 |
+
"step": 5040
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.59,
|
1777 |
+
"grad_norm": 2.9667663371741377,
|
1778 |
+
"learning_rate": 1.9479477117941815e-05,
|
1779 |
+
"loss": 0.2582,
|
1780 |
+
"step": 5060
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 0.59,
|
1784 |
+
"grad_norm": 3.628580495546253,
|
1785 |
+
"learning_rate": 1.9473298675982863e-05,
|
1786 |
+
"loss": 0.2526,
|
1787 |
+
"step": 5080
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 0.6,
|
1791 |
+
"grad_norm": 7.393689026504584,
|
1792 |
+
"learning_rate": 1.946708477364172e-05,
|
1793 |
+
"loss": 0.2587,
|
1794 |
+
"step": 5100
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 0.6,
|
1798 |
+
"grad_norm": 3.1975448011133407,
|
1799 |
+
"learning_rate": 1.9460835434180677e-05,
|
1800 |
+
"loss": 0.2679,
|
1801 |
+
"step": 5120
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 0.6,
|
1805 |
+
"grad_norm": 3.231683615655966,
|
1806 |
+
"learning_rate": 1.9454550680994684e-05,
|
1807 |
+
"loss": 0.2589,
|
1808 |
+
"step": 5140
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 0.6,
|
1812 |
+
"grad_norm": 2.956736460495959,
|
1813 |
+
"learning_rate": 1.9448230537611266e-05,
|
1814 |
+
"loss": 0.2594,
|
1815 |
+
"step": 5160
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.61,
|
1819 |
+
"grad_norm": 3.326543297808526,
|
1820 |
+
"learning_rate": 1.9441875027690435e-05,
|
1821 |
+
"loss": 0.2556,
|
1822 |
+
"step": 5180
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 0.61,
|
1826 |
+
"grad_norm": 3.635188025395725,
|
1827 |
+
"learning_rate": 1.94354841750246e-05,
|
1828 |
+
"loss": 0.2391,
|
1829 |
+
"step": 5200
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 0.61,
|
1833 |
+
"grad_norm": 4.934642109517512,
|
1834 |
+
"learning_rate": 1.942905800353848e-05,
|
1835 |
+
"loss": 0.2576,
|
1836 |
+
"step": 5220
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 0.61,
|
1840 |
+
"grad_norm": 3.8685357103793767,
|
1841 |
+
"learning_rate": 1.9422596537289016e-05,
|
1842 |
+
"loss": 0.2735,
|
1843 |
+
"step": 5240
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 0.62,
|
1847 |
+
"grad_norm": 4.387694986472,
|
1848 |
+
"learning_rate": 1.941609980046527e-05,
|
1849 |
+
"loss": 0.2584,
|
1850 |
+
"step": 5260
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 0.62,
|
1854 |
+
"grad_norm": 2.8046325848231977,
|
1855 |
+
"learning_rate": 1.9409567817388347e-05,
|
1856 |
+
"loss": 0.2527,
|
1857 |
+
"step": 5280
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.62,
|
1861 |
+
"grad_norm": 3.4012361074638466,
|
1862 |
+
"learning_rate": 1.94030006125113e-05,
|
1863 |
+
"loss": 0.2566,
|
1864 |
+
"step": 5300
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 0.62,
|
1868 |
+
"grad_norm": 5.450089536158873,
|
1869 |
+
"learning_rate": 1.9396398210419038e-05,
|
1870 |
+
"loss": 0.2667,
|
1871 |
+
"step": 5320
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 0.62,
|
1875 |
+
"grad_norm": 3.7967573233998677,
|
1876 |
+
"learning_rate": 1.938976063582824e-05,
|
1877 |
+
"loss": 0.2536,
|
1878 |
+
"step": 5340
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 0.63,
|
1882 |
+
"grad_norm": 3.0487888683110866,
|
1883 |
+
"learning_rate": 1.938308791358723e-05,
|
1884 |
+
"loss": 0.2673,
|
1885 |
+
"step": 5360
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 0.63,
|
1889 |
+
"grad_norm": 3.2736066169116285,
|
1890 |
+
"learning_rate": 1.9376380068675956e-05,
|
1891 |
+
"loss": 0.2592,
|
1892 |
+
"step": 5380
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 0.63,
|
1896 |
+
"grad_norm": 9.727952335441667,
|
1897 |
+
"learning_rate": 1.93696371262058e-05,
|
1898 |
+
"loss": 0.273,
|
1899 |
+
"step": 5400
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.63,
|
1903 |
+
"grad_norm": 3.3824664284674686,
|
1904 |
+
"learning_rate": 1.936285911141958e-05,
|
1905 |
+
"loss": 0.2787,
|
1906 |
+
"step": 5420
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 0.64,
|
1910 |
+
"grad_norm": 6.879080376487243,
|
1911 |
+
"learning_rate": 1.935604604969138e-05,
|
1912 |
+
"loss": 0.2698,
|
1913 |
+
"step": 5440
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 0.64,
|
1917 |
+
"grad_norm": 4.579168728014292,
|
1918 |
+
"learning_rate": 1.934919796652649e-05,
|
1919 |
+
"loss": 0.2589,
|
1920 |
+
"step": 5460
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 0.64,
|
1924 |
+
"grad_norm": 4.6776324362587784,
|
1925 |
+
"learning_rate": 1.9342314887561323e-05,
|
1926 |
+
"loss": 0.2544,
|
1927 |
+
"step": 5480
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 0.64,
|
1931 |
+
"grad_norm": 3.693997622998789,
|
1932 |
+
"learning_rate": 1.9335396838563282e-05,
|
1933 |
+
"loss": 0.2446,
|
1934 |
+
"step": 5500
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 0.65,
|
1938 |
+
"grad_norm": 5.06873813162095,
|
1939 |
+
"learning_rate": 1.932844384543069e-05,
|
1940 |
+
"loss": 0.2618,
|
1941 |
+
"step": 5520
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 0.65,
|
1945 |
+
"grad_norm": 6.816411566527297,
|
1946 |
+
"learning_rate": 1.9321455934192693e-05,
|
1947 |
+
"loss": 0.2614,
|
1948 |
+
"step": 5540
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 0.65,
|
1952 |
+
"grad_norm": 3.5475232040366853,
|
1953 |
+
"learning_rate": 1.9314433131009146e-05,
|
1954 |
+
"loss": 0.2942,
|
1955 |
+
"step": 5560
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 0.65,
|
1959 |
+
"grad_norm": 5.287550198652632,
|
1960 |
+
"learning_rate": 1.9307375462170527e-05,
|
1961 |
+
"loss": 0.2482,
|
1962 |
+
"step": 5580
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 0.66,
|
1966 |
+
"grad_norm": 11.389854038766874,
|
1967 |
+
"learning_rate": 1.9300282954097847e-05,
|
1968 |
+
"loss": 0.245,
|
1969 |
+
"step": 5600
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 0.66,
|
1973 |
+
"grad_norm": 4.178435806663215,
|
1974 |
+
"learning_rate": 1.9293155633342534e-05,
|
1975 |
+
"loss": 0.2534,
|
1976 |
+
"step": 5620
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 0.66,
|
1980 |
+
"grad_norm": 3.1710922703595035,
|
1981 |
+
"learning_rate": 1.928599352658633e-05,
|
1982 |
+
"loss": 0.2622,
|
1983 |
+
"step": 5640
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 0.66,
|
1987 |
+
"grad_norm": 2.6946627953356996,
|
1988 |
+
"learning_rate": 1.927879666064122e-05,
|
1989 |
+
"loss": 0.2626,
|
1990 |
+
"step": 5660
|
1991 |
+
},
|
1992 |
+
{
|
1993 |
+
"epoch": 0.66,
|
1994 |
+
"grad_norm": 4.8581812333670955,
|
1995 |
+
"learning_rate": 1.92715650624493e-05,
|
1996 |
+
"loss": 0.2346,
|
1997 |
+
"step": 5680
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 0.67,
|
2001 |
+
"grad_norm": 3.092927765677092,
|
2002 |
+
"learning_rate": 1.926429875908269e-05,
|
2003 |
+
"loss": 0.2585,
|
2004 |
+
"step": 5700
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 0.67,
|
2008 |
+
"grad_norm": 4.029661826813332,
|
2009 |
+
"learning_rate": 1.9256997777743437e-05,
|
2010 |
+
"loss": 0.2467,
|
2011 |
+
"step": 5720
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 0.67,
|
2015 |
+
"grad_norm": 4.642691104141709,
|
2016 |
+
"learning_rate": 1.924966214576341e-05,
|
2017 |
+
"loss": 0.2681,
|
2018 |
+
"step": 5740
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 0.67,
|
2022 |
+
"grad_norm": 7.315047122076067,
|
2023 |
+
"learning_rate": 1.9242291890604186e-05,
|
2024 |
+
"loss": 0.2508,
|
2025 |
+
"step": 5760
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 0.68,
|
2029 |
+
"grad_norm": 3.540549397482083,
|
2030 |
+
"learning_rate": 1.923488703985696e-05,
|
2031 |
+
"loss": 0.2592,
|
2032 |
+
"step": 5780
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 0.68,
|
2036 |
+
"grad_norm": 3.475018859373003,
|
2037 |
+
"learning_rate": 1.9227447621242458e-05,
|
2038 |
+
"loss": 0.2422,
|
2039 |
+
"step": 5800
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 0.68,
|
2043 |
+
"grad_norm": 3.8676644079356355,
|
2044 |
+
"learning_rate": 1.921997366261078e-05,
|
2045 |
+
"loss": 0.2603,
|
2046 |
+
"step": 5820
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 0.68,
|
2050 |
+
"grad_norm": 3.5885966628483,
|
2051 |
+
"learning_rate": 1.9212465191941346e-05,
|
2052 |
+
"loss": 0.2542,
|
2053 |
+
"step": 5840
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 0.69,
|
2057 |
+
"grad_norm": 3.6495890137770886,
|
2058 |
+
"learning_rate": 1.920492223734279e-05,
|
2059 |
+
"loss": 0.2374,
|
2060 |
+
"step": 5860
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 0.69,
|
2064 |
+
"grad_norm": 4.323488251305847,
|
2065 |
+
"learning_rate": 1.9197344827052813e-05,
|
2066 |
+
"loss": 0.2687,
|
2067 |
+
"step": 5880
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 0.69,
|
2071 |
+
"grad_norm": 5.051497760408599,
|
2072 |
+
"learning_rate": 1.9189732989438123e-05,
|
2073 |
+
"loss": 0.2678,
|
2074 |
+
"step": 5900
|
2075 |
+
},
|
2076 |
+
{
|
2077 |
+
"epoch": 0.69,
|
2078 |
+
"grad_norm": 3.5559342765441495,
|
2079 |
+
"learning_rate": 1.9182086752994295e-05,
|
2080 |
+
"loss": 0.2726,
|
2081 |
+
"step": 5920
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 0.7,
|
2085 |
+
"grad_norm": 3.029184640641301,
|
2086 |
+
"learning_rate": 1.9174406146345694e-05,
|
2087 |
+
"loss": 0.246,
|
2088 |
+
"step": 5940
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 0.7,
|
2092 |
+
"grad_norm": 3.4792605785250994,
|
2093 |
+
"learning_rate": 1.9166691198245343e-05,
|
2094 |
+
"loss": 0.2843,
|
2095 |
+
"step": 5960
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 0.7,
|
2099 |
+
"grad_norm": 3.0247490770922,
|
2100 |
+
"learning_rate": 1.915894193757483e-05,
|
2101 |
+
"loss": 0.2528,
|
2102 |
+
"step": 5980
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 0.7,
|
2106 |
+
"grad_norm": 3.7727567007247855,
|
2107 |
+
"learning_rate": 1.915115839334419e-05,
|
2108 |
+
"loss": 0.2442,
|
2109 |
+
"step": 6000
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 0.7,
|
2113 |
+
"grad_norm": 2.31881357193246,
|
2114 |
+
"learning_rate": 1.9143340594691806e-05,
|
2115 |
+
"loss": 0.2561,
|
2116 |
+
"step": 6020
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 0.71,
|
2120 |
+
"grad_norm": 3.138315746753083,
|
2121 |
+
"learning_rate": 1.913548857088429e-05,
|
2122 |
+
"loss": 0.2636,
|
2123 |
+
"step": 6040
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 0.71,
|
2127 |
+
"grad_norm": 8.010145906221986,
|
2128 |
+
"learning_rate": 1.9127602351316393e-05,
|
2129 |
+
"loss": 0.2876,
|
2130 |
+
"step": 6060
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 0.71,
|
2134 |
+
"grad_norm": 3.867596475572881,
|
2135 |
+
"learning_rate": 1.9119681965510858e-05,
|
2136 |
+
"loss": 0.2659,
|
2137 |
+
"step": 6080
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 0.71,
|
2141 |
+
"grad_norm": 3.3587166074477777,
|
2142 |
+
"learning_rate": 1.9111727443118357e-05,
|
2143 |
+
"loss": 0.2634,
|
2144 |
+
"step": 6100
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 0.72,
|
2148 |
+
"grad_norm": 2.89895288044486,
|
2149 |
+
"learning_rate": 1.9103738813917336e-05,
|
2150 |
+
"loss": 0.2533,
|
2151 |
+
"step": 6120
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 0.72,
|
2155 |
+
"grad_norm": 4.037752097559083,
|
2156 |
+
"learning_rate": 1.909571610781393e-05,
|
2157 |
+
"loss": 0.2485,
|
2158 |
+
"step": 6140
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 0.72,
|
2162 |
+
"grad_norm": 3.763608653829743,
|
2163 |
+
"learning_rate": 1.908765935484185e-05,
|
2164 |
+
"loss": 0.259,
|
2165 |
+
"step": 6160
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 0.72,
|
2169 |
+
"grad_norm": 3.161229351032073,
|
2170 |
+
"learning_rate": 1.9079568585162248e-05,
|
2171 |
+
"loss": 0.2508,
|
2172 |
+
"step": 6180
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"epoch": 0.73,
|
2176 |
+
"grad_norm": 2.725004696623228,
|
2177 |
+
"learning_rate": 1.9071443829063644e-05,
|
2178 |
+
"loss": 0.2524,
|
2179 |
+
"step": 6200
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 0.73,
|
2183 |
+
"grad_norm": 3.7116897623627985,
|
2184 |
+
"learning_rate": 1.906328511696177e-05,
|
2185 |
+
"loss": 0.2598,
|
2186 |
+
"step": 6220
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 0.73,
|
2190 |
+
"grad_norm": 2.9004110110815544,
|
2191 |
+
"learning_rate": 1.9055092479399474e-05,
|
2192 |
+
"loss": 0.2553,
|
2193 |
+
"step": 6240
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 0.73,
|
2197 |
+
"grad_norm": 4.311030925472568,
|
2198 |
+
"learning_rate": 1.9046865947046627e-05,
|
2199 |
+
"loss": 0.2678,
|
2200 |
+
"step": 6260
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 0.73,
|
2204 |
+
"grad_norm": 3.5377476420175977,
|
2205 |
+
"learning_rate": 1.903860555069997e-05,
|
2206 |
+
"loss": 0.2379,
|
2207 |
+
"step": 6280
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 0.74,
|
2211 |
+
"grad_norm": 3.58934533910836,
|
2212 |
+
"learning_rate": 1.9030311321283022e-05,
|
2213 |
+
"loss": 0.2608,
|
2214 |
+
"step": 6300
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 0.74,
|
2218 |
+
"grad_norm": 3.4612535457241624,
|
2219 |
+
"learning_rate": 1.9021983289845956e-05,
|
2220 |
+
"loss": 0.246,
|
2221 |
+
"step": 6320
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 0.74,
|
2225 |
+
"grad_norm": 3.9763337015158258,
|
2226 |
+
"learning_rate": 1.9013621487565498e-05,
|
2227 |
+
"loss": 0.238,
|
2228 |
+
"step": 6340
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 0.74,
|
2232 |
+
"grad_norm": 3.05488683337997,
|
2233 |
+
"learning_rate": 1.9005225945744782e-05,
|
2234 |
+
"loss": 0.2472,
|
2235 |
+
"step": 6360
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.75,
|
2239 |
+
"grad_norm": 3.2350295137123313,
|
2240 |
+
"learning_rate": 1.8996796695813256e-05,
|
2241 |
+
"loss": 0.261,
|
2242 |
+
"step": 6380
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 0.75,
|
2246 |
+
"grad_norm": 3.2500906711548123,
|
2247 |
+
"learning_rate": 1.8988333769326564e-05,
|
2248 |
+
"loss": 0.2641,
|
2249 |
+
"step": 6400
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 0.75,
|
2253 |
+
"grad_norm": 2.815087548041305,
|
2254 |
+
"learning_rate": 1.8979837197966415e-05,
|
2255 |
+
"loss": 0.2583,
|
2256 |
+
"step": 6420
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 0.75,
|
2260 |
+
"grad_norm": 3.7397965536014257,
|
2261 |
+
"learning_rate": 1.8971307013540464e-05,
|
2262 |
+
"loss": 0.2485,
|
2263 |
+
"step": 6440
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 0.76,
|
2267 |
+
"grad_norm": 2.7592373806083423,
|
2268 |
+
"learning_rate": 1.8962743247982205e-05,
|
2269 |
+
"loss": 0.2641,
|
2270 |
+
"step": 6460
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 0.76,
|
2274 |
+
"grad_norm": 2.818080452105616,
|
2275 |
+
"learning_rate": 1.895414593335085e-05,
|
2276 |
+
"loss": 0.2554,
|
2277 |
+
"step": 6480
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 0.76,
|
2281 |
+
"grad_norm": 3.627385505536174,
|
2282 |
+
"learning_rate": 1.8945515101831203e-05,
|
2283 |
+
"loss": 0.2693,
|
2284 |
+
"step": 6500
|
2285 |
+
},
|
2286 |
+
{
|
2287 |
+
"epoch": 0.76,
|
2288 |
+
"grad_norm": 3.255509767944512,
|
2289 |
+
"learning_rate": 1.893685078573354e-05,
|
2290 |
+
"loss": 0.2459,
|
2291 |
+
"step": 6520
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 0.77,
|
2295 |
+
"grad_norm": 4.135182845698409,
|
2296 |
+
"learning_rate": 1.8928153017493488e-05,
|
2297 |
+
"loss": 0.2499,
|
2298 |
+
"step": 6540
|
2299 |
+
},
|
2300 |
+
{
|
2301 |
+
"epoch": 0.77,
|
2302 |
+
"grad_norm": 5.892816677202276,
|
2303 |
+
"learning_rate": 1.8919421829671904e-05,
|
2304 |
+
"loss": 0.2786,
|
2305 |
+
"step": 6560
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 0.77,
|
2309 |
+
"grad_norm": 3.479892875732629,
|
2310 |
+
"learning_rate": 1.891065725495476e-05,
|
2311 |
+
"loss": 0.265,
|
2312 |
+
"step": 6580
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 0.77,
|
2316 |
+
"grad_norm": 3.8343809741781216,
|
2317 |
+
"learning_rate": 1.890185932615301e-05,
|
2318 |
+
"loss": 0.2527,
|
2319 |
+
"step": 6600
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 0.77,
|
2323 |
+
"grad_norm": 3.1643033159708107,
|
2324 |
+
"learning_rate": 1.8893028076202472e-05,
|
2325 |
+
"loss": 0.2741,
|
2326 |
+
"step": 6620
|
2327 |
+
},
|
2328 |
+
{
|
2329 |
+
"epoch": 0.78,
|
2330 |
+
"grad_norm": 4.477352585232187,
|
2331 |
+
"learning_rate": 1.8884163538163708e-05,
|
2332 |
+
"loss": 0.2525,
|
2333 |
+
"step": 6640
|
2334 |
+
},
|
2335 |
+
{
|
2336 |
+
"epoch": 0.78,
|
2337 |
+
"grad_norm": 3.529760400999529,
|
2338 |
+
"learning_rate": 1.8875265745221894e-05,
|
2339 |
+
"loss": 0.2643,
|
2340 |
+
"step": 6660
|
2341 |
+
},
|
2342 |
+
{
|
2343 |
+
"epoch": 0.78,
|
2344 |
+
"grad_norm": 2.3110189076619525,
|
2345 |
+
"learning_rate": 1.8866334730686703e-05,
|
2346 |
+
"loss": 0.2721,
|
2347 |
+
"step": 6680
|
2348 |
+
},
|
2349 |
+
{
|
2350 |
+
"epoch": 0.78,
|
2351 |
+
"grad_norm": 3.685226774238388,
|
2352 |
+
"learning_rate": 1.8857370527992165e-05,
|
2353 |
+
"loss": 0.2549,
|
2354 |
+
"step": 6700
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 0.79,
|
2358 |
+
"grad_norm": 3.8074891978039864,
|
2359 |
+
"learning_rate": 1.8848373170696567e-05,
|
2360 |
+
"loss": 0.2418,
|
2361 |
+
"step": 6720
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 0.79,
|
2365 |
+
"grad_norm": 7.507877790185021,
|
2366 |
+
"learning_rate": 1.8839342692482302e-05,
|
2367 |
+
"loss": 0.2451,
|
2368 |
+
"step": 6740
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 0.79,
|
2372 |
+
"grad_norm": 2.7359733051983186,
|
2373 |
+
"learning_rate": 1.8830279127155764e-05,
|
2374 |
+
"loss": 0.2484,
|
2375 |
+
"step": 6760
|
2376 |
+
},
|
2377 |
+
{
|
2378 |
+
"epoch": 0.79,
|
2379 |
+
"grad_norm": 2.4635290638854657,
|
2380 |
+
"learning_rate": 1.88211825086472e-05,
|
2381 |
+
"loss": 0.2407,
|
2382 |
+
"step": 6780
|
2383 |
+
},
|
2384 |
+
{
|
2385 |
+
"epoch": 0.8,
|
2386 |
+
"grad_norm": 3.040130192327906,
|
2387 |
+
"learning_rate": 1.8812052871010605e-05,
|
2388 |
+
"loss": 0.2544,
|
2389 |
+
"step": 6800
|
2390 |
+
},
|
2391 |
+
{
|
2392 |
+
"epoch": 0.8,
|
2393 |
+
"grad_norm": 5.610778632978326,
|
2394 |
+
"learning_rate": 1.8802890248423574e-05,
|
2395 |
+
"loss": 0.2397,
|
2396 |
+
"step": 6820
|
2397 |
+
},
|
2398 |
+
{
|
2399 |
+
"epoch": 0.8,
|
2400 |
+
"grad_norm": 4.156547822535594,
|
2401 |
+
"learning_rate": 1.8793694675187197e-05,
|
2402 |
+
"loss": 0.2635,
|
2403 |
+
"step": 6840
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 0.8,
|
2407 |
+
"grad_norm": 4.057314806159278,
|
2408 |
+
"learning_rate": 1.8784466185725902e-05,
|
2409 |
+
"loss": 0.2598,
|
2410 |
+
"step": 6860
|
2411 |
+
},
|
2412 |
+
{
|
2413 |
+
"epoch": 0.81,
|
2414 |
+
"grad_norm": 8.314874066232434,
|
2415 |
+
"learning_rate": 1.877520481458736e-05,
|
2416 |
+
"loss": 0.2706,
|
2417 |
+
"step": 6880
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 0.81,
|
2421 |
+
"grad_norm": 3.7767818313058195,
|
2422 |
+
"learning_rate": 1.8765910596442316e-05,
|
2423 |
+
"loss": 0.2483,
|
2424 |
+
"step": 6900
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 0.81,
|
2428 |
+
"grad_norm": 3.53905010431742,
|
2429 |
+
"learning_rate": 1.8756583566084502e-05,
|
2430 |
+
"loss": 0.2683,
|
2431 |
+
"step": 6920
|
2432 |
+
},
|
2433 |
+
{
|
2434 |
+
"epoch": 0.81,
|
2435 |
+
"grad_norm": 3.2053331160944625,
|
2436 |
+
"learning_rate": 1.8747223758430467e-05,
|
2437 |
+
"loss": 0.2567,
|
2438 |
+
"step": 6940
|
2439 |
+
},
|
2440 |
+
{
|
2441 |
+
"epoch": 0.81,
|
2442 |
+
"grad_norm": 3.655977418308093,
|
2443 |
+
"learning_rate": 1.8737831208519478e-05,
|
2444 |
+
"loss": 0.2433,
|
2445 |
+
"step": 6960
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 0.82,
|
2449 |
+
"grad_norm": 3.334646935711793,
|
2450 |
+
"learning_rate": 1.8728405951513376e-05,
|
2451 |
+
"loss": 0.2442,
|
2452 |
+
"step": 6980
|
2453 |
+
},
|
2454 |
+
{
|
2455 |
+
"epoch": 0.82,
|
2456 |
+
"grad_norm": 3.3678493336120505,
|
2457 |
+
"learning_rate": 1.8718948022696427e-05,
|
2458 |
+
"loss": 0.2634,
|
2459 |
+
"step": 7000
|
2460 |
+
},
|
2461 |
+
{
|
2462 |
+
"epoch": 0.82,
|
2463 |
+
"grad_norm": 2.9941614875638956,
|
2464 |
+
"learning_rate": 1.8709457457475224e-05,
|
2465 |
+
"loss": 0.2719,
|
2466 |
+
"step": 7020
|
2467 |
+
},
|
2468 |
+
{
|
2469 |
+
"epoch": 0.82,
|
2470 |
+
"grad_norm": 3.3212764283242495,
|
2471 |
+
"learning_rate": 1.8699934291378534e-05,
|
2472 |
+
"loss": 0.2616,
|
2473 |
+
"step": 7040
|
2474 |
+
},
|
2475 |
+
{
|
2476 |
+
"epoch": 0.83,
|
2477 |
+
"grad_norm": 3.7449113015848963,
|
2478 |
+
"learning_rate": 1.8690378560057165e-05,
|
2479 |
+
"loss": 0.251,
|
2480 |
+
"step": 7060
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 0.83,
|
2484 |
+
"grad_norm": 2.588981565454773,
|
2485 |
+
"learning_rate": 1.868079029928383e-05,
|
2486 |
+
"loss": 0.2345,
|
2487 |
+
"step": 7080
|
2488 |
+
},
|
2489 |
+
{
|
2490 |
+
"epoch": 0.83,
|
2491 |
+
"grad_norm": 4.188807496871825,
|
2492 |
+
"learning_rate": 1.8671169544953033e-05,
|
2493 |
+
"loss": 0.2537,
|
2494 |
+
"step": 7100
|
2495 |
+
},
|
2496 |
+
{
|
2497 |
+
"epoch": 0.83,
|
2498 |
+
"grad_norm": 4.66518430781191,
|
2499 |
+
"learning_rate": 1.866151633308091e-05,
|
2500 |
+
"loss": 0.2397,
|
2501 |
+
"step": 7120
|
2502 |
+
},
|
2503 |
+
{
|
2504 |
+
"epoch": 0.84,
|
2505 |
+
"grad_norm": 4.197676860816234,
|
2506 |
+
"learning_rate": 1.8651830699805108e-05,
|
2507 |
+
"loss": 0.2446,
|
2508 |
+
"step": 7140
|
2509 |
+
},
|
2510 |
+
{
|
2511 |
+
"epoch": 0.84,
|
2512 |
+
"grad_norm": 3.6434672643458543,
|
2513 |
+
"learning_rate": 1.8642112681384645e-05,
|
2514 |
+
"loss": 0.2402,
|
2515 |
+
"step": 7160
|
2516 |
+
},
|
2517 |
+
{
|
2518 |
+
"epoch": 0.84,
|
2519 |
+
"grad_norm": 3.950387723218738,
|
2520 |
+
"learning_rate": 1.8632362314199778e-05,
|
2521 |
+
"loss": 0.2536,
|
2522 |
+
"step": 7180
|
2523 |
+
},
|
2524 |
+
{
|
2525 |
+
"epoch": 0.84,
|
2526 |
+
"grad_norm": 9.658211616844094,
|
2527 |
+
"learning_rate": 1.8622579634751864e-05,
|
2528 |
+
"loss": 0.2541,
|
2529 |
+
"step": 7200
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 0.84,
|
2533 |
+
"grad_norm": 3.799337836345952,
|
2534 |
+
"learning_rate": 1.8612764679663222e-05,
|
2535 |
+
"loss": 0.2586,
|
2536 |
+
"step": 7220
|
2537 |
+
},
|
2538 |
+
{
|
2539 |
+
"epoch": 0.85,
|
2540 |
+
"grad_norm": 3.737906856782671,
|
2541 |
+
"learning_rate": 1.8602917485677e-05,
|
2542 |
+
"loss": 0.2539,
|
2543 |
+
"step": 7240
|
2544 |
+
},
|
2545 |
+
{
|
2546 |
+
"epoch": 0.85,
|
2547 |
+
"grad_norm": 3.2570157254536016,
|
2548 |
+
"learning_rate": 1.859303808965703e-05,
|
2549 |
+
"loss": 0.2533,
|
2550 |
+
"step": 7260
|
2551 |
+
},
|
2552 |
+
{
|
2553 |
+
"epoch": 0.85,
|
2554 |
+
"grad_norm": 2.8736525985585226,
|
2555 |
+
"learning_rate": 1.85831265285877e-05,
|
2556 |
+
"loss": 0.2532,
|
2557 |
+
"step": 7280
|
2558 |
+
},
|
2559 |
+
{
|
2560 |
+
"epoch": 0.85,
|
2561 |
+
"grad_norm": 3.5447389329516503,
|
2562 |
+
"learning_rate": 1.857318283957381e-05,
|
2563 |
+
"loss": 0.2387,
|
2564 |
+
"step": 7300
|
2565 |
+
},
|
2566 |
+
{
|
2567 |
+
"epoch": 0.86,
|
2568 |
+
"grad_norm": 2.7468496831393403,
|
2569 |
+
"learning_rate": 1.8563207059840436e-05,
|
2570 |
+
"loss": 0.2455,
|
2571 |
+
"step": 7320
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 0.86,
|
2575 |
+
"grad_norm": 3.483830293921577,
|
2576 |
+
"learning_rate": 1.8553199226732784e-05,
|
2577 |
+
"loss": 0.2456,
|
2578 |
+
"step": 7340
|
2579 |
+
},
|
2580 |
+
{
|
2581 |
+
"epoch": 0.86,
|
2582 |
+
"grad_norm": 3.3132796899404635,
|
2583 |
+
"learning_rate": 1.8543159377716054e-05,
|
2584 |
+
"loss": 0.2564,
|
2585 |
+
"step": 7360
|
2586 |
+
},
|
2587 |
+
{
|
2588 |
+
"epoch": 0.86,
|
2589 |
+
"grad_norm": 3.3795508326649575,
|
2590 |
+
"learning_rate": 1.8533087550375302e-05,
|
2591 |
+
"loss": 0.2527,
|
2592 |
+
"step": 7380
|
2593 |
+
},
|
2594 |
+
{
|
2595 |
+
"epoch": 0.87,
|
2596 |
+
"grad_norm": 4.001941448174156,
|
2597 |
+
"learning_rate": 1.8522983782415306e-05,
|
2598 |
+
"loss": 0.2433,
|
2599 |
+
"step": 7400
|
2600 |
+
},
|
2601 |
+
{
|
2602 |
+
"epoch": 0.87,
|
2603 |
+
"grad_norm": 3.4205382361927117,
|
2604 |
+
"learning_rate": 1.85128481116604e-05,
|
2605 |
+
"loss": 0.2538,
|
2606 |
+
"step": 7420
|
2607 |
+
},
|
2608 |
+
{
|
2609 |
+
"epoch": 0.87,
|
2610 |
+
"grad_norm": 3.896330422632185,
|
2611 |
+
"learning_rate": 1.8502680576054365e-05,
|
2612 |
+
"loss": 0.2478,
|
2613 |
+
"step": 7440
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 0.87,
|
2617 |
+
"grad_norm": 5.020228094868969,
|
2618 |
+
"learning_rate": 1.849248121366026e-05,
|
2619 |
+
"loss": 0.2427,
|
2620 |
+
"step": 7460
|
2621 |
+
},
|
2622 |
+
{
|
2623 |
+
"epoch": 0.88,
|
2624 |
+
"grad_norm": 3.574276782956127,
|
2625 |
+
"learning_rate": 1.8482250062660293e-05,
|
2626 |
+
"loss": 0.2389,
|
2627 |
+
"step": 7480
|
2628 |
+
},
|
2629 |
+
{
|
2630 |
+
"epoch": 0.88,
|
2631 |
+
"grad_norm": 3.5309579103911184,
|
2632 |
+
"learning_rate": 1.847198716135568e-05,
|
2633 |
+
"loss": 0.2567,
|
2634 |
+
"step": 7500
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 0.88,
|
2638 |
+
"grad_norm": 3.1760414458004,
|
2639 |
+
"learning_rate": 1.846169254816649e-05,
|
2640 |
+
"loss": 0.2291,
|
2641 |
+
"step": 7520
|
2642 |
+
},
|
2643 |
+
{
|
2644 |
+
"epoch": 0.88,
|
2645 |
+
"grad_norm": 4.214334621561301,
|
2646 |
+
"learning_rate": 1.8451366261631514e-05,
|
2647 |
+
"loss": 0.2624,
|
2648 |
+
"step": 7540
|
2649 |
+
},
|
2650 |
+
{
|
2651 |
+
"epoch": 0.88,
|
2652 |
+
"grad_norm": 2.977221959069712,
|
2653 |
+
"learning_rate": 1.8441008340408115e-05,
|
2654 |
+
"loss": 0.2425,
|
2655 |
+
"step": 7560
|
2656 |
+
},
|
2657 |
+
{
|
2658 |
+
"epoch": 0.89,
|
2659 |
+
"grad_norm": 3.78383188925913,
|
2660 |
+
"learning_rate": 1.8430618823272076e-05,
|
2661 |
+
"loss": 0.2437,
|
2662 |
+
"step": 7580
|
2663 |
+
},
|
2664 |
+
{
|
2665 |
+
"epoch": 0.89,
|
2666 |
+
"grad_norm": 3.2432934448936224,
|
2667 |
+
"learning_rate": 1.842019774911747e-05,
|
2668 |
+
"loss": 0.2628,
|
2669 |
+
"step": 7600
|
2670 |
+
},
|
2671 |
+
{
|
2672 |
+
"epoch": 0.89,
|
2673 |
+
"grad_norm": 3.05382414419798,
|
2674 |
+
"learning_rate": 1.8409745156956503e-05,
|
2675 |
+
"loss": 0.2332,
|
2676 |
+
"step": 7620
|
2677 |
+
},
|
2678 |
+
{
|
2679 |
+
"epoch": 0.89,
|
2680 |
+
"grad_norm": 3.098744070302099,
|
2681 |
+
"learning_rate": 1.839926108591937e-05,
|
2682 |
+
"loss": 0.2359,
|
2683 |
+
"step": 7640
|
2684 |
+
},
|
2685 |
+
{
|
2686 |
+
"epoch": 0.9,
|
2687 |
+
"grad_norm": 3.427098715766002,
|
2688 |
+
"learning_rate": 1.8388745575254117e-05,
|
2689 |
+
"loss": 0.2429,
|
2690 |
+
"step": 7660
|
2691 |
+
},
|
2692 |
+
{
|
2693 |
+
"epoch": 0.9,
|
2694 |
+
"grad_norm": 5.630711008711337,
|
2695 |
+
"learning_rate": 1.8378198664326474e-05,
|
2696 |
+
"loss": 0.2416,
|
2697 |
+
"step": 7680
|
2698 |
+
},
|
2699 |
+
{
|
2700 |
+
"epoch": 0.9,
|
2701 |
+
"grad_norm": 3.1144723181358622,
|
2702 |
+
"learning_rate": 1.836762039261974e-05,
|
2703 |
+
"loss": 0.2406,
|
2704 |
+
"step": 7700
|
2705 |
+
},
|
2706 |
+
{
|
2707 |
+
"epoch": 0.9,
|
2708 |
+
"grad_norm": 4.070301722184627,
|
2709 |
+
"learning_rate": 1.8357010799734588e-05,
|
2710 |
+
"loss": 0.234,
|
2711 |
+
"step": 7720
|
2712 |
+
},
|
2713 |
+
{
|
2714 |
+
"epoch": 0.91,
|
2715 |
+
"grad_norm": 3.255428182680105,
|
2716 |
+
"learning_rate": 1.834636992538898e-05,
|
2717 |
+
"loss": 0.2365,
|
2718 |
+
"step": 7740
|
2719 |
+
},
|
2720 |
+
{
|
2721 |
+
"epoch": 0.91,
|
2722 |
+
"grad_norm": 3.4823775104086576,
|
2723 |
+
"learning_rate": 1.8335697809417952e-05,
|
2724 |
+
"loss": 0.2376,
|
2725 |
+
"step": 7760
|
2726 |
+
},
|
2727 |
+
{
|
2728 |
+
"epoch": 0.91,
|
2729 |
+
"grad_norm": 5.528269163918348,
|
2730 |
+
"learning_rate": 1.8324994491773507e-05,
|
2731 |
+
"loss": 0.2679,
|
2732 |
+
"step": 7780
|
2733 |
+
},
|
2734 |
+
{
|
2735 |
+
"epoch": 0.91,
|
2736 |
+
"grad_norm": 2.7221100312640467,
|
2737 |
+
"learning_rate": 1.8314260012524462e-05,
|
2738 |
+
"loss": 0.2544,
|
2739 |
+
"step": 7800
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 0.92,
|
2743 |
+
"grad_norm": 3.224515621271091,
|
2744 |
+
"learning_rate": 1.8303494411856278e-05,
|
2745 |
+
"loss": 0.2586,
|
2746 |
+
"step": 7820
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 0.92,
|
2750 |
+
"grad_norm": 2.798714485709818,
|
2751 |
+
"learning_rate": 1.829269773007092e-05,
|
2752 |
+
"loss": 0.2277,
|
2753 |
+
"step": 7840
|
2754 |
+
},
|
2755 |
+
{
|
2756 |
+
"epoch": 0.92,
|
2757 |
+
"grad_norm": 3.890849401904209,
|
2758 |
+
"learning_rate": 1.8281870007586735e-05,
|
2759 |
+
"loss": 0.2565,
|
2760 |
+
"step": 7860
|
2761 |
+
},
|
2762 |
+
{
|
2763 |
+
"epoch": 0.92,
|
2764 |
+
"grad_norm": 3.701194549732654,
|
2765 |
+
"learning_rate": 1.8271011284938233e-05,
|
2766 |
+
"loss": 0.2307,
|
2767 |
+
"step": 7880
|
2768 |
+
},
|
2769 |
+
{
|
2770 |
+
"epoch": 0.92,
|
2771 |
+
"grad_norm": 3.9057568048025875,
|
2772 |
+
"learning_rate": 1.8260121602776003e-05,
|
2773 |
+
"loss": 0.2464,
|
2774 |
+
"step": 7900
|
2775 |
+
},
|
2776 |
+
{
|
2777 |
+
"epoch": 0.93,
|
2778 |
+
"grad_norm": 3.397196786583742,
|
2779 |
+
"learning_rate": 1.8249201001866533e-05,
|
2780 |
+
"loss": 0.25,
|
2781 |
+
"step": 7920
|
2782 |
+
},
|
2783 |
+
{
|
2784 |
+
"epoch": 0.93,
|
2785 |
+
"grad_norm": 3.6136942859367496,
|
2786 |
+
"learning_rate": 1.8238249523092046e-05,
|
2787 |
+
"loss": 0.2398,
|
2788 |
+
"step": 7940
|
2789 |
+
},
|
2790 |
+
{
|
2791 |
+
"epoch": 0.93,
|
2792 |
+
"grad_norm": 3.6009293204428765,
|
2793 |
+
"learning_rate": 1.8227267207450363e-05,
|
2794 |
+
"loss": 0.2356,
|
2795 |
+
"step": 7960
|
2796 |
+
},
|
2797 |
+
{
|
2798 |
+
"epoch": 0.93,
|
2799 |
+
"grad_norm": 3.1462270393488585,
|
2800 |
+
"learning_rate": 1.8216254096054747e-05,
|
2801 |
+
"loss": 0.2292,
|
2802 |
+
"step": 7980
|
2803 |
+
},
|
2804 |
+
{
|
2805 |
+
"epoch": 0.94,
|
2806 |
+
"grad_norm": 3.453766085807792,
|
2807 |
+
"learning_rate": 1.8205210230133756e-05,
|
2808 |
+
"loss": 0.2532,
|
2809 |
+
"step": 8000
|
2810 |
+
},
|
2811 |
+
{
|
2812 |
+
"epoch": 0.94,
|
2813 |
+
"grad_norm": 4.718419953986993,
|
2814 |
+
"learning_rate": 1.8194135651031063e-05,
|
2815 |
+
"loss": 0.2379,
|
2816 |
+
"step": 8020
|
2817 |
+
},
|
2818 |
+
{
|
2819 |
+
"epoch": 0.94,
|
2820 |
+
"grad_norm": 4.074122309800583,
|
2821 |
+
"learning_rate": 1.8183030400205335e-05,
|
2822 |
+
"loss": 0.247,
|
2823 |
+
"step": 8040
|
2824 |
+
},
|
2825 |
+
{
|
2826 |
+
"epoch": 0.94,
|
2827 |
+
"grad_norm": 3.597629476607082,
|
2828 |
+
"learning_rate": 1.817189451923005e-05,
|
2829 |
+
"loss": 0.2563,
|
2830 |
+
"step": 8060
|
2831 |
+
},
|
2832 |
+
{
|
2833 |
+
"epoch": 0.95,
|
2834 |
+
"grad_norm": 3.2550443969136436,
|
2835 |
+
"learning_rate": 1.8160728049793357e-05,
|
2836 |
+
"loss": 0.2425,
|
2837 |
+
"step": 8080
|
2838 |
+
},
|
2839 |
+
{
|
2840 |
+
"epoch": 0.95,
|
2841 |
+
"grad_norm": 2.6027515890006505,
|
2842 |
+
"learning_rate": 1.8149531033697913e-05,
|
2843 |
+
"loss": 0.2329,
|
2844 |
+
"step": 8100
|
2845 |
+
},
|
2846 |
+
{
|
2847 |
+
"epoch": 0.95,
|
2848 |
+
"grad_norm": 3.705349797095471,
|
2849 |
+
"learning_rate": 1.8138303512860737e-05,
|
2850 |
+
"loss": 0.2521,
|
2851 |
+
"step": 8120
|
2852 |
+
},
|
2853 |
+
{
|
2854 |
+
"epoch": 0.95,
|
2855 |
+
"grad_norm": 3.510055266811937,
|
2856 |
+
"learning_rate": 1.812704552931303e-05,
|
2857 |
+
"loss": 0.2413,
|
2858 |
+
"step": 8140
|
2859 |
+
},
|
2860 |
+
{
|
2861 |
+
"epoch": 0.95,
|
2862 |
+
"grad_norm": 3.2863076604207997,
|
2863 |
+
"learning_rate": 1.8115757125200054e-05,
|
2864 |
+
"loss": 0.2471,
|
2865 |
+
"step": 8160
|
2866 |
+
},
|
2867 |
+
{
|
2868 |
+
"epoch": 0.96,
|
2869 |
+
"grad_norm": 3.174018473859266,
|
2870 |
+
"learning_rate": 1.810443834278094e-05,
|
2871 |
+
"loss": 0.2429,
|
2872 |
+
"step": 8180
|
2873 |
+
},
|
2874 |
+
{
|
2875 |
+
"epoch": 0.96,
|
2876 |
+
"grad_norm": 4.78684161965386,
|
2877 |
+
"learning_rate": 1.8093089224428533e-05,
|
2878 |
+
"loss": 0.21,
|
2879 |
+
"step": 8200
|
2880 |
+
},
|
2881 |
+
{
|
2882 |
+
"epoch": 0.96,
|
2883 |
+
"grad_norm": 3.778736256263061,
|
2884 |
+
"learning_rate": 1.8081709812629265e-05,
|
2885 |
+
"loss": 0.2438,
|
2886 |
+
"step": 8220
|
2887 |
+
},
|
2888 |
+
{
|
2889 |
+
"epoch": 0.96,
|
2890 |
+
"grad_norm": 2.011964890319697,
|
2891 |
+
"learning_rate": 1.807030014998296e-05,
|
2892 |
+
"loss": 0.2235,
|
2893 |
+
"step": 8240
|
2894 |
+
},
|
2895 |
+
{
|
2896 |
+
"epoch": 0.97,
|
2897 |
+
"grad_norm": 2.469231474076661,
|
2898 |
+
"learning_rate": 1.8058860279202698e-05,
|
2899 |
+
"loss": 0.2361,
|
2900 |
+
"step": 8260
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 0.97,
|
2904 |
+
"grad_norm": 4.194473608952758,
|
2905 |
+
"learning_rate": 1.804739024311463e-05,
|
2906 |
+
"loss": 0.2485,
|
2907 |
+
"step": 8280
|
2908 |
+
},
|
2909 |
+
{
|
2910 |
+
"epoch": 0.97,
|
2911 |
+
"grad_norm": 3.648802255045255,
|
2912 |
+
"learning_rate": 1.8035890084657854e-05,
|
2913 |
+
"loss": 0.2448,
|
2914 |
+
"step": 8300
|
2915 |
+
},
|
2916 |
+
{
|
2917 |
+
"epoch": 0.97,
|
2918 |
+
"grad_norm": 2.8256525011924443,
|
2919 |
+
"learning_rate": 1.8024359846884213e-05,
|
2920 |
+
"loss": 0.2688,
|
2921 |
+
"step": 8320
|
2922 |
+
},
|
2923 |
+
{
|
2924 |
+
"epoch": 0.98,
|
2925 |
+
"grad_norm": 4.409589867929299,
|
2926 |
+
"learning_rate": 1.8012799572958173e-05,
|
2927 |
+
"loss": 0.2405,
|
2928 |
+
"step": 8340
|
2929 |
+
},
|
2930 |
+
{
|
2931 |
+
"epoch": 0.98,
|
2932 |
+
"grad_norm": 5.024619525530542,
|
2933 |
+
"learning_rate": 1.8001209306156634e-05,
|
2934 |
+
"loss": 0.2284,
|
2935 |
+
"step": 8360
|
2936 |
+
},
|
2937 |
+
{
|
2938 |
+
"epoch": 0.98,
|
2939 |
+
"grad_norm": 3.5087106485202026,
|
2940 |
+
"learning_rate": 1.7989589089868774e-05,
|
2941 |
+
"loss": 0.2298,
|
2942 |
+
"step": 8380
|
2943 |
+
},
|
2944 |
+
{
|
2945 |
+
"epoch": 0.98,
|
2946 |
+
"grad_norm": 4.40165070000877,
|
2947 |
+
"learning_rate": 1.7977938967595897e-05,
|
2948 |
+
"loss": 0.2507,
|
2949 |
+
"step": 8400
|
2950 |
+
},
|
2951 |
+
{
|
2952 |
+
"epoch": 0.99,
|
2953 |
+
"grad_norm": 3.9660729217673705,
|
2954 |
+
"learning_rate": 1.7966258982951255e-05,
|
2955 |
+
"loss": 0.2459,
|
2956 |
+
"step": 8420
|
2957 |
+
},
|
2958 |
+
{
|
2959 |
+
"epoch": 0.99,
|
2960 |
+
"grad_norm": 4.665706172372416,
|
2961 |
+
"learning_rate": 1.7954549179659903e-05,
|
2962 |
+
"loss": 0.2458,
|
2963 |
+
"step": 8440
|
2964 |
+
},
|
2965 |
+
{
|
2966 |
+
"epoch": 0.99,
|
2967 |
+
"grad_norm": 3.2908069759526333,
|
2968 |
+
"learning_rate": 1.794280960155851e-05,
|
2969 |
+
"loss": 0.2251,
|
2970 |
+
"step": 8460
|
2971 |
+
},
|
2972 |
+
{
|
2973 |
+
"epoch": 0.99,
|
2974 |
+
"grad_norm": 6.7504752662905725,
|
2975 |
+
"learning_rate": 1.7931040292595227e-05,
|
2976 |
+
"loss": 0.254,
|
2977 |
+
"step": 8480
|
2978 |
+
},
|
2979 |
+
{
|
2980 |
+
"epoch": 0.99,
|
2981 |
+
"grad_norm": 2.2047073417435787,
|
2982 |
+
"learning_rate": 1.791924129682949e-05,
|
2983 |
+
"loss": 0.2456,
|
2984 |
+
"step": 8500
|
2985 |
+
},
|
2986 |
+
{
|
2987 |
+
"epoch": 1.0,
|
2988 |
+
"grad_norm": 3.9048911210632236,
|
2989 |
+
"learning_rate": 1.7907412658431877e-05,
|
2990 |
+
"loss": 0.2307,
|
2991 |
+
"step": 8520
|
2992 |
+
},
|
2993 |
+
{
|
2994 |
+
"epoch": 1.0,
|
2995 |
+
"grad_norm": 3.33290909610624,
|
2996 |
+
"learning_rate": 1.7895554421683938e-05,
|
2997 |
+
"loss": 0.2514,
|
2998 |
+
"step": 8540
|
2999 |
+
}
|
3000 |
+
],
|
3001 |
+
"logging_steps": 20,
|
3002 |
+
"max_steps": 34184,
|
3003 |
+
"num_input_tokens_seen": 0,
|
3004 |
+
"num_train_epochs": 4,
|
3005 |
+
"save_steps": 500,
|
3006 |
+
"total_flos": 0.0,
|
3007 |
+
"train_batch_size": 1,
|
3008 |
+
"trial_name": null,
|
3009 |
+
"trial_params": null
|
3010 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f33bda593f07c6124a4429ccae3e94c7c86a2cfcc673b73aaba2e1ac11baeef
|
3 |
+
size 6840
|
zero_to_fp32.py
ADDED
@@ -0,0 +1,592 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#!/usr/bin/env python
|
2 |
+
|
3 |
+
# Copyright (c) Microsoft Corporation.
|
4 |
+
# SPDX-License-Identifier: Apache-2.0
|
5 |
+
|
6 |
+
# DeepSpeed Team
|
7 |
+
|
8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
11 |
+
# application.
|
12 |
+
#
|
13 |
+
# example: python zero_to_fp32.py . pytorch_model.bin
|
14 |
+
|
15 |
+
import argparse
|
16 |
+
import torch
|
17 |
+
import glob
|
18 |
+
import math
|
19 |
+
import os
|
20 |
+
import re
|
21 |
+
from collections import OrderedDict
|
22 |
+
from dataclasses import dataclass
|
23 |
+
|
24 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
25 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
26 |
+
from deepspeed.utils import logger
|
27 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
28 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
29 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
30 |
+
|
31 |
+
|
32 |
+
@dataclass
|
33 |
+
class zero_model_state:
|
34 |
+
buffers: dict()
|
35 |
+
param_shapes: dict()
|
36 |
+
shared_params: list
|
37 |
+
ds_version: int
|
38 |
+
frozen_param_shapes: dict()
|
39 |
+
frozen_param_fragments: dict()
|
40 |
+
|
41 |
+
|
42 |
+
debug = 0
|
43 |
+
|
44 |
+
# load to cpu
|
45 |
+
device = torch.device('cpu')
|
46 |
+
|
47 |
+
|
48 |
+
def atoi(text):
|
49 |
+
return int(text) if text.isdigit() else text
|
50 |
+
|
51 |
+
|
52 |
+
def natural_keys(text):
|
53 |
+
'''
|
54 |
+
alist.sort(key=natural_keys) sorts in human order
|
55 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
56 |
+
(See Toothy's implementation in the comments)
|
57 |
+
'''
|
58 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
59 |
+
|
60 |
+
|
61 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
62 |
+
if not os.path.isdir(checkpoint_dir):
|
63 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
64 |
+
|
65 |
+
# there should be only one file
|
66 |
+
if zero_stage <= 2:
|
67 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
68 |
+
elif zero_stage == 3:
|
69 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
70 |
+
|
71 |
+
if not os.path.exists(file):
|
72 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
73 |
+
|
74 |
+
return file
|
75 |
+
|
76 |
+
|
77 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
78 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
79 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
80 |
+
|
81 |
+
if len(ckpt_files) == 0:
|
82 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
83 |
+
|
84 |
+
return ckpt_files
|
85 |
+
|
86 |
+
|
87 |
+
def get_optim_files(checkpoint_dir):
|
88 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
89 |
+
|
90 |
+
|
91 |
+
def get_model_state_files(checkpoint_dir):
|
92 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
93 |
+
|
94 |
+
|
95 |
+
def parse_model_states(files):
|
96 |
+
zero_model_states = []
|
97 |
+
for file in files:
|
98 |
+
state_dict = torch.load(file, map_location=device)
|
99 |
+
|
100 |
+
if BUFFER_NAMES not in state_dict:
|
101 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
102 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
103 |
+
if debug:
|
104 |
+
print("Found buffers:", buffer_names)
|
105 |
+
|
106 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
107 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
108 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
109 |
+
|
110 |
+
# collect parameters that are included in param_shapes
|
111 |
+
param_names = []
|
112 |
+
for s in param_shapes:
|
113 |
+
for name in s.keys():
|
114 |
+
param_names.append(name)
|
115 |
+
|
116 |
+
# update with frozen parameters
|
117 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
118 |
+
if frozen_param_shapes is not None:
|
119 |
+
if debug:
|
120 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
121 |
+
param_names += list(frozen_param_shapes.keys())
|
122 |
+
|
123 |
+
# handle shared params
|
124 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
125 |
+
|
126 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
127 |
+
|
128 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
129 |
+
|
130 |
+
z_model_state = zero_model_state(buffers=buffers,
|
131 |
+
param_shapes=param_shapes,
|
132 |
+
shared_params=shared_params,
|
133 |
+
ds_version=ds_version,
|
134 |
+
frozen_param_shapes=frozen_param_shapes,
|
135 |
+
frozen_param_fragments=frozen_param_fragments)
|
136 |
+
zero_model_states.append(z_model_state)
|
137 |
+
|
138 |
+
return zero_model_states
|
139 |
+
|
140 |
+
|
141 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
142 |
+
|
143 |
+
total_files = len(files)
|
144 |
+
state_dicts = []
|
145 |
+
for f in files:
|
146 |
+
state_dict = torch.load(f, map_location=device)
|
147 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
148 |
+
# and also handle the case where it was already removed by another helper script
|
149 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
150 |
+
state_dicts.append(state_dict)
|
151 |
+
|
152 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
153 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
154 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
155 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
156 |
+
|
157 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
158 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
159 |
+
# use the max of the partition_count to get the dp world_size.
|
160 |
+
|
161 |
+
if type(world_size) is list:
|
162 |
+
world_size = max(world_size)
|
163 |
+
|
164 |
+
if world_size != total_files:
|
165 |
+
raise ValueError(
|
166 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
167 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
168 |
+
)
|
169 |
+
|
170 |
+
# the groups are named differently in each stage
|
171 |
+
if zero_stage <= 2:
|
172 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
173 |
+
elif zero_stage == 3:
|
174 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
175 |
+
else:
|
176 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
177 |
+
|
178 |
+
if zero_stage <= 2:
|
179 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
180 |
+
elif zero_stage == 3:
|
181 |
+
# if there is more than one param group, there will be multiple flattened tensors - one
|
182 |
+
# flattened tensor per group - for simplicity merge them into a single tensor
|
183 |
+
#
|
184 |
+
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
185 |
+
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
186 |
+
|
187 |
+
fp32_flat_groups = [
|
188 |
+
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
189 |
+
]
|
190 |
+
|
191 |
+
return zero_stage, world_size, fp32_flat_groups
|
192 |
+
|
193 |
+
|
194 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
|
195 |
+
"""
|
196 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
197 |
+
|
198 |
+
Args:
|
199 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
200 |
+
|
201 |
+
"""
|
202 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
203 |
+
|
204 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
205 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
206 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
207 |
+
|
208 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
209 |
+
|
210 |
+
zero_model_states = parse_model_states(model_files)
|
211 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
212 |
+
|
213 |
+
if zero_stage <= 2:
|
214 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
215 |
+
elif zero_stage == 3:
|
216 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
217 |
+
|
218 |
+
|
219 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
220 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
221 |
+
return
|
222 |
+
|
223 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
224 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
225 |
+
|
226 |
+
if debug:
|
227 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
228 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
229 |
+
|
230 |
+
wanted_params = len(frozen_param_shapes)
|
231 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
232 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
233 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
234 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
235 |
+
|
236 |
+
total_params = 0
|
237 |
+
total_numel = 0
|
238 |
+
for name, shape in frozen_param_shapes.items():
|
239 |
+
total_params += 1
|
240 |
+
unpartitioned_numel = shape.numel()
|
241 |
+
total_numel += unpartitioned_numel
|
242 |
+
|
243 |
+
state_dict[name] = frozen_param_fragments[name]
|
244 |
+
|
245 |
+
if debug:
|
246 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
247 |
+
|
248 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
249 |
+
|
250 |
+
|
251 |
+
def _has_callable(obj, fn):
|
252 |
+
attr = getattr(obj, fn, None)
|
253 |
+
return callable(attr)
|
254 |
+
|
255 |
+
|
256 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
257 |
+
param_shapes = zero_model_states[0].param_shapes
|
258 |
+
|
259 |
+
# Reconstruction protocol:
|
260 |
+
#
|
261 |
+
# XXX: document this
|
262 |
+
|
263 |
+
if debug:
|
264 |
+
for i in range(world_size):
|
265 |
+
for j in range(len(fp32_flat_groups[0])):
|
266 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
267 |
+
|
268 |
+
# XXX: memory usage doubles here (zero2)
|
269 |
+
num_param_groups = len(fp32_flat_groups[0])
|
270 |
+
merged_single_partition_of_fp32_groups = []
|
271 |
+
for i in range(num_param_groups):
|
272 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
273 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
274 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
275 |
+
avail_numel = sum(
|
276 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
277 |
+
|
278 |
+
if debug:
|
279 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
280 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
281 |
+
# not asserting if there is a mismatch due to possible padding
|
282 |
+
print(f"Have {avail_numel} numels to process.")
|
283 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
284 |
+
|
285 |
+
# params
|
286 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
287 |
+
# out-of-core computing solution
|
288 |
+
total_numel = 0
|
289 |
+
total_params = 0
|
290 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
291 |
+
offset = 0
|
292 |
+
avail_numel = full_single_fp32_vector.numel()
|
293 |
+
for name, shape in shapes.items():
|
294 |
+
|
295 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
296 |
+
total_numel += unpartitioned_numel
|
297 |
+
total_params += 1
|
298 |
+
|
299 |
+
if debug:
|
300 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
301 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
302 |
+
offset += unpartitioned_numel
|
303 |
+
|
304 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
305 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
306 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
307 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
308 |
+
align_to = 2 * world_size
|
309 |
+
|
310 |
+
def zero2_align(x):
|
311 |
+
return align_to * math.ceil(x / align_to)
|
312 |
+
|
313 |
+
if debug:
|
314 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
315 |
+
|
316 |
+
offset = zero2_align(offset)
|
317 |
+
avail_numel = zero2_align(avail_numel)
|
318 |
+
|
319 |
+
if debug:
|
320 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
321 |
+
|
322 |
+
# Sanity check
|
323 |
+
if offset != avail_numel:
|
324 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
325 |
+
|
326 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
327 |
+
|
328 |
+
|
329 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
330 |
+
state_dict = OrderedDict()
|
331 |
+
|
332 |
+
# buffers
|
333 |
+
buffers = zero_model_states[0].buffers
|
334 |
+
state_dict.update(buffers)
|
335 |
+
if debug:
|
336 |
+
print(f"added {len(buffers)} buffers")
|
337 |
+
|
338 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
339 |
+
|
340 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
341 |
+
|
342 |
+
# recover shared parameters
|
343 |
+
for pair in zero_model_states[0].shared_params:
|
344 |
+
if pair[1] in state_dict:
|
345 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
346 |
+
|
347 |
+
return state_dict
|
348 |
+
|
349 |
+
|
350 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
351 |
+
remainder = unpartitioned_numel % world_size
|
352 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
353 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
354 |
+
return partitioned_numel, padding_numel
|
355 |
+
|
356 |
+
|
357 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
358 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
359 |
+
return
|
360 |
+
|
361 |
+
if debug:
|
362 |
+
for i in range(world_size):
|
363 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
364 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
365 |
+
|
366 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
367 |
+
wanted_params = len(frozen_param_shapes)
|
368 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
369 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
370 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
371 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
372 |
+
|
373 |
+
total_params = 0
|
374 |
+
total_numel = 0
|
375 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
376 |
+
total_params += 1
|
377 |
+
unpartitioned_numel = shape.numel()
|
378 |
+
total_numel += unpartitioned_numel
|
379 |
+
|
380 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
381 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
382 |
+
|
383 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
384 |
+
|
385 |
+
if debug:
|
386 |
+
print(
|
387 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
388 |
+
)
|
389 |
+
|
390 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
391 |
+
|
392 |
+
|
393 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
394 |
+
param_shapes = zero_model_states[0].param_shapes
|
395 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
396 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
397 |
+
# param, re-consolidating each param, while dealing with padding if any
|
398 |
+
|
399 |
+
# merge list of dicts, preserving order
|
400 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
401 |
+
|
402 |
+
if debug:
|
403 |
+
for i in range(world_size):
|
404 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
405 |
+
|
406 |
+
wanted_params = len(param_shapes)
|
407 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
408 |
+
# not asserting if there is a mismatch due to possible padding
|
409 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
410 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
411 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
412 |
+
|
413 |
+
# params
|
414 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
415 |
+
# out-of-core computing solution
|
416 |
+
offset = 0
|
417 |
+
total_numel = 0
|
418 |
+
total_params = 0
|
419 |
+
for name, shape in param_shapes.items():
|
420 |
+
|
421 |
+
unpartitioned_numel = shape.numel()
|
422 |
+
total_numel += unpartitioned_numel
|
423 |
+
total_params += 1
|
424 |
+
|
425 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
426 |
+
|
427 |
+
if debug:
|
428 |
+
print(
|
429 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
430 |
+
)
|
431 |
+
|
432 |
+
# XXX: memory usage doubles here
|
433 |
+
state_dict[name] = torch.cat(
|
434 |
+
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
435 |
+
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
436 |
+
offset += partitioned_numel
|
437 |
+
|
438 |
+
offset *= world_size
|
439 |
+
|
440 |
+
# Sanity check
|
441 |
+
if offset != avail_numel:
|
442 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
443 |
+
|
444 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
445 |
+
|
446 |
+
|
447 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
448 |
+
state_dict = OrderedDict()
|
449 |
+
|
450 |
+
# buffers
|
451 |
+
buffers = zero_model_states[0].buffers
|
452 |
+
state_dict.update(buffers)
|
453 |
+
if debug:
|
454 |
+
print(f"added {len(buffers)} buffers")
|
455 |
+
|
456 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
457 |
+
|
458 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
459 |
+
|
460 |
+
# recover shared parameters
|
461 |
+
for pair in zero_model_states[0].shared_params:
|
462 |
+
if pair[1] in state_dict:
|
463 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
464 |
+
|
465 |
+
return state_dict
|
466 |
+
|
467 |
+
|
468 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
|
469 |
+
"""
|
470 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
471 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
472 |
+
via a model hub.
|
473 |
+
|
474 |
+
Args:
|
475 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
476 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
477 |
+
|
478 |
+
Returns:
|
479 |
+
- pytorch ``state_dict``
|
480 |
+
|
481 |
+
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
482 |
+
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
483 |
+
the checkpoint.
|
484 |
+
|
485 |
+
A typical usage might be ::
|
486 |
+
|
487 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
488 |
+
# do the training and checkpoint saving
|
489 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
490 |
+
model = model.cpu() # move to cpu
|
491 |
+
model.load_state_dict(state_dict)
|
492 |
+
# submit to model hub or save the model to share with others
|
493 |
+
|
494 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
495 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
496 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
497 |
+
|
498 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
499 |
+
|
500 |
+
"""
|
501 |
+
if tag is None:
|
502 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
503 |
+
if os.path.isfile(latest_path):
|
504 |
+
with open(latest_path, 'r') as fd:
|
505 |
+
tag = fd.read().strip()
|
506 |
+
else:
|
507 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
508 |
+
|
509 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
510 |
+
|
511 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
512 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
513 |
+
|
514 |
+
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
|
515 |
+
|
516 |
+
|
517 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
|
518 |
+
"""
|
519 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
520 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
521 |
+
|
522 |
+
Args:
|
523 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
524 |
+
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
|
525 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
526 |
+
"""
|
527 |
+
|
528 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
529 |
+
print(f"Saving fp32 state dict to {output_file}")
|
530 |
+
torch.save(state_dict, output_file)
|
531 |
+
|
532 |
+
|
533 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
534 |
+
"""
|
535 |
+
1. Put the provided model to cpu
|
536 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
537 |
+
3. Load it into the provided model
|
538 |
+
|
539 |
+
Args:
|
540 |
+
- ``model``: the model object to update
|
541 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
542 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
543 |
+
|
544 |
+
Returns:
|
545 |
+
- ``model`: modified model
|
546 |
+
|
547 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
548 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
549 |
+
conveniently placed for you in the checkpoint folder.
|
550 |
+
|
551 |
+
A typical usage might be ::
|
552 |
+
|
553 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
554 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
555 |
+
# submit to model hub or save the model to share with others
|
556 |
+
|
557 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
558 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
559 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
560 |
+
|
561 |
+
"""
|
562 |
+
logger.info(f"Extracting fp32 weights")
|
563 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
564 |
+
|
565 |
+
logger.info(f"Overwriting model with fp32 weights")
|
566 |
+
model = model.cpu()
|
567 |
+
model.load_state_dict(state_dict, strict=False)
|
568 |
+
|
569 |
+
return model
|
570 |
+
|
571 |
+
|
572 |
+
if __name__ == "__main__":
|
573 |
+
|
574 |
+
parser = argparse.ArgumentParser()
|
575 |
+
parser.add_argument("checkpoint_dir",
|
576 |
+
type=str,
|
577 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
578 |
+
parser.add_argument(
|
579 |
+
"output_file",
|
580 |
+
type=str,
|
581 |
+
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
|
582 |
+
parser.add_argument("-t",
|
583 |
+
"--tag",
|
584 |
+
type=str,
|
585 |
+
default=None,
|
586 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
587 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
588 |
+
args = parser.parse_args()
|
589 |
+
|
590 |
+
debug = args.debug
|
591 |
+
|
592 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)
|