crown commited on
Upload 11 files
Browse files- config.json +71 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +1586 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "../../bert",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Agricultural and Biological Sciences",
|
| 14 |
+
"1": "Biochemistry, Genetics and Molecular Biology",
|
| 15 |
+
"2": "Chemical Engineering",
|
| 16 |
+
"3": "Chemistry",
|
| 17 |
+
"4": "Computer Science",
|
| 18 |
+
"5": "Earth and Planetary",
|
| 19 |
+
"6": "Economics, Econometrics and Finance",
|
| 20 |
+
"7": "Engineering",
|
| 21 |
+
"8": "Food Science",
|
| 22 |
+
"9": "Immunology and Microbiology",
|
| 23 |
+
"10": "Materials Science",
|
| 24 |
+
"11": "Mathematics",
|
| 25 |
+
"12": "Medicine and Dentistry",
|
| 26 |
+
"13": "Neuroscience",
|
| 27 |
+
"14": "Nursing and Health Professions",
|
| 28 |
+
"15": "Pharmacology, Toxicology and Pharmaceutical Science",
|
| 29 |
+
"16": "Physics and Astronomy",
|
| 30 |
+
"17": "Psychology",
|
| 31 |
+
"18": "Social Sciences",
|
| 32 |
+
"19": "Veterinary Science and Veterinary Medicine"
|
| 33 |
+
},
|
| 34 |
+
"initializer_range": 0.02,
|
| 35 |
+
"intermediate_size": 3072,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"Agricultural and Biological Sciences": 0,
|
| 38 |
+
"Biochemistry, Genetics and Molecular Biology": 1,
|
| 39 |
+
"Chemical Engineering": 2,
|
| 40 |
+
"Chemistry": 3,
|
| 41 |
+
"Computer Science": 4,
|
| 42 |
+
"Earth and Planetary": 5,
|
| 43 |
+
"Economics, Econometrics and Finance": 6,
|
| 44 |
+
"Engineering": 7,
|
| 45 |
+
"Food Science": 8,
|
| 46 |
+
"Immunology and Microbiology": 9,
|
| 47 |
+
"Materials Science": 10,
|
| 48 |
+
"Mathematics": 11,
|
| 49 |
+
"Medicine and Dentistry": 12,
|
| 50 |
+
"Neuroscience": 13,
|
| 51 |
+
"Nursing and Health Professions": 14,
|
| 52 |
+
"Pharmacology, Toxicology and Pharmaceutical Science": 15,
|
| 53 |
+
"Physics and Astronomy": 16,
|
| 54 |
+
"Psychology": 17,
|
| 55 |
+
"Social Sciences": 18,
|
| 56 |
+
"Veterinary Science and Veterinary Medicine": 19
|
| 57 |
+
},
|
| 58 |
+
"layer_norm_eps": 1e-12,
|
| 59 |
+
"max_position_embeddings": 512,
|
| 60 |
+
"model_type": "bert",
|
| 61 |
+
"num_attention_heads": 12,
|
| 62 |
+
"num_hidden_layers": 12,
|
| 63 |
+
"pad_token_id": 0,
|
| 64 |
+
"position_embedding_type": "absolute",
|
| 65 |
+
"problem_type": "multi_label_classification",
|
| 66 |
+
"torch_dtype": "float32",
|
| 67 |
+
"transformers_version": "4.42.3",
|
| 68 |
+
"type_vocab_size": 2,
|
| 69 |
+
"use_cache": true,
|
| 70 |
+
"vocab_size": 30522
|
| 71 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4e5f7e9bad60fe639dedd44471ae1cf5d97f22ebad783fe753dbc72ed593132
|
| 3 |
+
size 438014016
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bbb1ce5faf8f2cb9776c5566d987764c02e434caf69a6cbf2fa200178735f92
|
| 3 |
+
size 876149114
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72351c5ca54abf9f46ad9d15a8a913849131486ed6f9ad78ca81a1c8aac71b82
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e27a7631631d7147f4c96c542ba700cdde3381d1d59738c37fc7222b83ff3ab9
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1586 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.759579488098438,
|
| 3 |
+
"best_model_checkpoint": "bert-finetuned-sem_eval-english\\checkpoint-85976",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 107470,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.023262305759746905,
|
| 13 |
+
"grad_norm": 0.5290595293045044,
|
| 14 |
+
"learning_rate": 1.9906950776961013e-05,
|
| 15 |
+
"loss": 0.2421,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04652461151949381,
|
| 20 |
+
"grad_norm": 0.7135451436042786,
|
| 21 |
+
"learning_rate": 1.9813901553922027e-05,
|
| 22 |
+
"loss": 0.153,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.06978691727924072,
|
| 27 |
+
"grad_norm": 0.6057224869728088,
|
| 28 |
+
"learning_rate": 1.9720852330883038e-05,
|
| 29 |
+
"loss": 0.135,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09304922303898762,
|
| 34 |
+
"grad_norm": 2.033938407897949,
|
| 35 |
+
"learning_rate": 1.962780310784405e-05,
|
| 36 |
+
"loss": 0.1273,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11631152879873453,
|
| 41 |
+
"grad_norm": 1.6713635921478271,
|
| 42 |
+
"learning_rate": 1.9534753884805063e-05,
|
| 43 |
+
"loss": 0.1221,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13957383455848144,
|
| 48 |
+
"grad_norm": 0.4952755570411682,
|
| 49 |
+
"learning_rate": 1.9441704661766077e-05,
|
| 50 |
+
"loss": 0.116,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.16283614031822835,
|
| 55 |
+
"grad_norm": 0.5051670670509338,
|
| 56 |
+
"learning_rate": 1.9348655438727088e-05,
|
| 57 |
+
"loss": 0.1147,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.18609844607797524,
|
| 62 |
+
"grad_norm": 0.9887399077415466,
|
| 63 |
+
"learning_rate": 1.92556062156881e-05,
|
| 64 |
+
"loss": 0.1152,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.20936075183772215,
|
| 69 |
+
"grad_norm": 0.7931112051010132,
|
| 70 |
+
"learning_rate": 1.9162556992649114e-05,
|
| 71 |
+
"loss": 0.1138,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.23262305759746907,
|
| 76 |
+
"grad_norm": 0.7627053260803223,
|
| 77 |
+
"learning_rate": 1.9069507769610124e-05,
|
| 78 |
+
"loss": 0.113,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.25588536335721596,
|
| 83 |
+
"grad_norm": 0.6043164730072021,
|
| 84 |
+
"learning_rate": 1.897645854657114e-05,
|
| 85 |
+
"loss": 0.1119,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.27914766911696287,
|
| 90 |
+
"grad_norm": 0.5762751698493958,
|
| 91 |
+
"learning_rate": 1.888340932353215e-05,
|
| 92 |
+
"loss": 0.1107,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.3024099748767098,
|
| 97 |
+
"grad_norm": 0.6853972673416138,
|
| 98 |
+
"learning_rate": 1.8790360100493164e-05,
|
| 99 |
+
"loss": 0.1075,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.3256722806364567,
|
| 104 |
+
"grad_norm": 0.6911000609397888,
|
| 105 |
+
"learning_rate": 1.8697310877454175e-05,
|
| 106 |
+
"loss": 0.1079,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3489345863962036,
|
| 111 |
+
"grad_norm": 0.5828253626823425,
|
| 112 |
+
"learning_rate": 1.860426165441519e-05,
|
| 113 |
+
"loss": 0.1091,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.3721968921559505,
|
| 118 |
+
"grad_norm": 0.782696008682251,
|
| 119 |
+
"learning_rate": 1.85112124313762e-05,
|
| 120 |
+
"loss": 0.1084,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.3954591979156974,
|
| 125 |
+
"grad_norm": 0.8830183148384094,
|
| 126 |
+
"learning_rate": 1.841816320833721e-05,
|
| 127 |
+
"loss": 0.1059,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.4187215036754443,
|
| 132 |
+
"grad_norm": 1.4506700038909912,
|
| 133 |
+
"learning_rate": 1.8325113985298225e-05,
|
| 134 |
+
"loss": 0.1058,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4419838094351912,
|
| 139 |
+
"grad_norm": 1.0449475049972534,
|
| 140 |
+
"learning_rate": 1.8232064762259236e-05,
|
| 141 |
+
"loss": 0.1067,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.46524611519493814,
|
| 146 |
+
"grad_norm": 1.4629307985305786,
|
| 147 |
+
"learning_rate": 1.8139015539220247e-05,
|
| 148 |
+
"loss": 0.1031,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.48850842095468505,
|
| 153 |
+
"grad_norm": 0.5856618285179138,
|
| 154 |
+
"learning_rate": 1.804596631618126e-05,
|
| 155 |
+
"loss": 0.1064,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5117707267144319,
|
| 160 |
+
"grad_norm": 0.7551602125167847,
|
| 161 |
+
"learning_rate": 1.7952917093142276e-05,
|
| 162 |
+
"loss": 0.1029,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5350330324741789,
|
| 167 |
+
"grad_norm": 0.762008011341095,
|
| 168 |
+
"learning_rate": 1.7859867870103287e-05,
|
| 169 |
+
"loss": 0.1043,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.5582953382339257,
|
| 174 |
+
"grad_norm": 0.9580531716346741,
|
| 175 |
+
"learning_rate": 1.7766818647064298e-05,
|
| 176 |
+
"loss": 0.1048,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.5815576439936726,
|
| 181 |
+
"grad_norm": 1.0684598684310913,
|
| 182 |
+
"learning_rate": 1.7673769424025312e-05,
|
| 183 |
+
"loss": 0.1041,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6048199497534196,
|
| 188 |
+
"grad_norm": 1.6208114624023438,
|
| 189 |
+
"learning_rate": 1.7580720200986323e-05,
|
| 190 |
+
"loss": 0.1005,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6280822555131664,
|
| 195 |
+
"grad_norm": 1.0143775939941406,
|
| 196 |
+
"learning_rate": 1.7487670977947334e-05,
|
| 197 |
+
"loss": 0.1012,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.6513445612729134,
|
| 202 |
+
"grad_norm": 0.8733798861503601,
|
| 203 |
+
"learning_rate": 1.7394621754908348e-05,
|
| 204 |
+
"loss": 0.1009,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.6746068670326603,
|
| 209 |
+
"grad_norm": 1.1354494094848633,
|
| 210 |
+
"learning_rate": 1.730157253186936e-05,
|
| 211 |
+
"loss": 0.1012,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.6978691727924072,
|
| 216 |
+
"grad_norm": 0.852428674697876,
|
| 217 |
+
"learning_rate": 1.720852330883037e-05,
|
| 218 |
+
"loss": 0.1003,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7211314785521541,
|
| 223 |
+
"grad_norm": 0.6298101544380188,
|
| 224 |
+
"learning_rate": 1.7115474085791384e-05,
|
| 225 |
+
"loss": 0.1009,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.744393784311901,
|
| 230 |
+
"grad_norm": 0.6968585252761841,
|
| 231 |
+
"learning_rate": 1.70224248627524e-05,
|
| 232 |
+
"loss": 0.1002,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.7676560900716479,
|
| 237 |
+
"grad_norm": 0.7687616944313049,
|
| 238 |
+
"learning_rate": 1.692937563971341e-05,
|
| 239 |
+
"loss": 0.0976,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.7909183958313948,
|
| 244 |
+
"grad_norm": 0.9958521723747253,
|
| 245 |
+
"learning_rate": 1.6836326416674424e-05,
|
| 246 |
+
"loss": 0.0996,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.8141807015911418,
|
| 251 |
+
"grad_norm": 1.9353946447372437,
|
| 252 |
+
"learning_rate": 1.6743277193635435e-05,
|
| 253 |
+
"loss": 0.0982,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.8374430073508886,
|
| 258 |
+
"grad_norm": 0.4970337450504303,
|
| 259 |
+
"learning_rate": 1.6650227970596446e-05,
|
| 260 |
+
"loss": 0.1013,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.8607053131106355,
|
| 265 |
+
"grad_norm": 1.3484145402908325,
|
| 266 |
+
"learning_rate": 1.655717874755746e-05,
|
| 267 |
+
"loss": 0.1001,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.8839676188703824,
|
| 272 |
+
"grad_norm": 0.9516633749008179,
|
| 273 |
+
"learning_rate": 1.646412952451847e-05,
|
| 274 |
+
"loss": 0.0978,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.9072299246301293,
|
| 279 |
+
"grad_norm": 1.358478307723999,
|
| 280 |
+
"learning_rate": 1.6371080301479485e-05,
|
| 281 |
+
"loss": 0.1016,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9304922303898763,
|
| 286 |
+
"grad_norm": 0.5643423795700073,
|
| 287 |
+
"learning_rate": 1.6278031078440496e-05,
|
| 288 |
+
"loss": 0.0983,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.9537545361496231,
|
| 293 |
+
"grad_norm": 0.532564103603363,
|
| 294 |
+
"learning_rate": 1.618498185540151e-05,
|
| 295 |
+
"loss": 0.0972,
|
| 296 |
+
"step": 20500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.9770168419093701,
|
| 300 |
+
"grad_norm": 1.3922828435897827,
|
| 301 |
+
"learning_rate": 1.609193263236252e-05,
|
| 302 |
+
"loss": 0.0976,
|
| 303 |
+
"step": 21000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.0,
|
| 307 |
+
"eval_accuracy": 0.5307062436028659,
|
| 308 |
+
"eval_f1": 0.7361535927721048,
|
| 309 |
+
"eval_loss": 0.09595564752817154,
|
| 310 |
+
"eval_roc_auc": 0.8461935311283144,
|
| 311 |
+
"eval_runtime": 24.262,
|
| 312 |
+
"eval_samples_per_second": 885.911,
|
| 313 |
+
"eval_steps_per_second": 110.749,
|
| 314 |
+
"step": 21494
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.0002791476691169,
|
| 318 |
+
"grad_norm": 0.6412343978881836,
|
| 319 |
+
"learning_rate": 1.5998883409323532e-05,
|
| 320 |
+
"loss": 0.0986,
|
| 321 |
+
"step": 21500
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.0235414534288638,
|
| 325 |
+
"grad_norm": 0.6500938534736633,
|
| 326 |
+
"learning_rate": 1.5905834186284547e-05,
|
| 327 |
+
"loss": 0.0889,
|
| 328 |
+
"step": 22000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.0468037591886108,
|
| 332 |
+
"grad_norm": 0.49381542205810547,
|
| 333 |
+
"learning_rate": 1.5812784963245558e-05,
|
| 334 |
+
"loss": 0.0861,
|
| 335 |
+
"step": 22500
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.0700660649483578,
|
| 339 |
+
"grad_norm": 0.790490448474884,
|
| 340 |
+
"learning_rate": 1.571973574020657e-05,
|
| 341 |
+
"loss": 0.0853,
|
| 342 |
+
"step": 23000
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.0933283707081045,
|
| 346 |
+
"grad_norm": 1.0638964176177979,
|
| 347 |
+
"learning_rate": 1.5626686517167583e-05,
|
| 348 |
+
"loss": 0.0855,
|
| 349 |
+
"step": 23500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.1165906764678515,
|
| 353 |
+
"grad_norm": 0.8379644751548767,
|
| 354 |
+
"learning_rate": 1.5533637294128597e-05,
|
| 355 |
+
"loss": 0.0839,
|
| 356 |
+
"step": 24000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.1398529822275985,
|
| 360 |
+
"grad_norm": 1.5022120475769043,
|
| 361 |
+
"learning_rate": 1.5440588071089608e-05,
|
| 362 |
+
"loss": 0.0883,
|
| 363 |
+
"step": 24500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.1631152879873454,
|
| 367 |
+
"grad_norm": 0.6825814247131348,
|
| 368 |
+
"learning_rate": 1.534753884805062e-05,
|
| 369 |
+
"loss": 0.0852,
|
| 370 |
+
"step": 25000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.1863775937470922,
|
| 374 |
+
"grad_norm": 2.154118776321411,
|
| 375 |
+
"learning_rate": 1.5254489625011633e-05,
|
| 376 |
+
"loss": 0.0854,
|
| 377 |
+
"step": 25500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.2096398995068391,
|
| 381 |
+
"grad_norm": 0.8945685029029846,
|
| 382 |
+
"learning_rate": 1.5161440401972644e-05,
|
| 383 |
+
"loss": 0.0862,
|
| 384 |
+
"step": 26000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.2329022052665861,
|
| 388 |
+
"grad_norm": 1.1257520914077759,
|
| 389 |
+
"learning_rate": 1.5068391178933657e-05,
|
| 390 |
+
"loss": 0.0832,
|
| 391 |
+
"step": 26500
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.2561645110263329,
|
| 395 |
+
"grad_norm": 0.785380482673645,
|
| 396 |
+
"learning_rate": 1.497534195589467e-05,
|
| 397 |
+
"loss": 0.0842,
|
| 398 |
+
"step": 27000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.2794268167860798,
|
| 402 |
+
"grad_norm": 0.4283202290534973,
|
| 403 |
+
"learning_rate": 1.488229273285568e-05,
|
| 404 |
+
"loss": 0.0859,
|
| 405 |
+
"step": 27500
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.3026891225458268,
|
| 409 |
+
"grad_norm": 1.3082115650177002,
|
| 410 |
+
"learning_rate": 1.4789243509816695e-05,
|
| 411 |
+
"loss": 0.0824,
|
| 412 |
+
"step": 28000
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.3259514283055736,
|
| 416 |
+
"grad_norm": 0.6663931608200073,
|
| 417 |
+
"learning_rate": 1.4696194286777707e-05,
|
| 418 |
+
"loss": 0.0868,
|
| 419 |
+
"step": 28500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.3492137340653205,
|
| 423 |
+
"grad_norm": 1.093483805656433,
|
| 424 |
+
"learning_rate": 1.460314506373872e-05,
|
| 425 |
+
"loss": 0.0871,
|
| 426 |
+
"step": 29000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.3724760398250675,
|
| 430 |
+
"grad_norm": 1.7370342016220093,
|
| 431 |
+
"learning_rate": 1.4510095840699731e-05,
|
| 432 |
+
"loss": 0.0858,
|
| 433 |
+
"step": 29500
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 1.3957383455848142,
|
| 437 |
+
"grad_norm": 1.280945062637329,
|
| 438 |
+
"learning_rate": 1.4417046617660744e-05,
|
| 439 |
+
"loss": 0.0853,
|
| 440 |
+
"step": 30000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.4190006513445612,
|
| 444 |
+
"grad_norm": 0.44828563928604126,
|
| 445 |
+
"learning_rate": 1.4323997394621756e-05,
|
| 446 |
+
"loss": 0.0828,
|
| 447 |
+
"step": 30500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.4422629571043082,
|
| 451 |
+
"grad_norm": 1.0420727729797363,
|
| 452 |
+
"learning_rate": 1.4230948171582769e-05,
|
| 453 |
+
"loss": 0.0836,
|
| 454 |
+
"step": 31000
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.4655252628640552,
|
| 458 |
+
"grad_norm": 1.529417634010315,
|
| 459 |
+
"learning_rate": 1.413789894854378e-05,
|
| 460 |
+
"loss": 0.0827,
|
| 461 |
+
"step": 31500
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.4887875686238021,
|
| 465 |
+
"grad_norm": 0.8359895944595337,
|
| 466 |
+
"learning_rate": 1.4044849725504792e-05,
|
| 467 |
+
"loss": 0.0836,
|
| 468 |
+
"step": 32000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.5120498743835489,
|
| 472 |
+
"grad_norm": 0.8840139508247375,
|
| 473 |
+
"learning_rate": 1.3951800502465807e-05,
|
| 474 |
+
"loss": 0.0858,
|
| 475 |
+
"step": 32500
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.5353121801432958,
|
| 479 |
+
"grad_norm": 1.2289206981658936,
|
| 480 |
+
"learning_rate": 1.385875127942682e-05,
|
| 481 |
+
"loss": 0.0835,
|
| 482 |
+
"step": 33000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.5585744859030428,
|
| 486 |
+
"grad_norm": 1.725092887878418,
|
| 487 |
+
"learning_rate": 1.376570205638783e-05,
|
| 488 |
+
"loss": 0.0833,
|
| 489 |
+
"step": 33500
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.5818367916627896,
|
| 493 |
+
"grad_norm": 1.8183008432388306,
|
| 494 |
+
"learning_rate": 1.3672652833348843e-05,
|
| 495 |
+
"loss": 0.085,
|
| 496 |
+
"step": 34000
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.6050990974225365,
|
| 500 |
+
"grad_norm": 1.5482715368270874,
|
| 501 |
+
"learning_rate": 1.3579603610309855e-05,
|
| 502 |
+
"loss": 0.0825,
|
| 503 |
+
"step": 34500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.6283614031822835,
|
| 507 |
+
"grad_norm": 2.1967756748199463,
|
| 508 |
+
"learning_rate": 1.3486554387270866e-05,
|
| 509 |
+
"loss": 0.0857,
|
| 510 |
+
"step": 35000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.6516237089420303,
|
| 514 |
+
"grad_norm": 0.9423213005065918,
|
| 515 |
+
"learning_rate": 1.3393505164231879e-05,
|
| 516 |
+
"loss": 0.0818,
|
| 517 |
+
"step": 35500
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 1.6748860147017772,
|
| 521 |
+
"grad_norm": 0.8981990218162537,
|
| 522 |
+
"learning_rate": 1.3300455941192892e-05,
|
| 523 |
+
"loss": 0.0821,
|
| 524 |
+
"step": 36000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.6981483204615242,
|
| 528 |
+
"grad_norm": 1.125404715538025,
|
| 529 |
+
"learning_rate": 1.3207406718153904e-05,
|
| 530 |
+
"loss": 0.0849,
|
| 531 |
+
"step": 36500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.721410626221271,
|
| 535 |
+
"grad_norm": 2.038687229156494,
|
| 536 |
+
"learning_rate": 1.3114357495114918e-05,
|
| 537 |
+
"loss": 0.0847,
|
| 538 |
+
"step": 37000
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.744672931981018,
|
| 542 |
+
"grad_norm": 1.0153677463531494,
|
| 543 |
+
"learning_rate": 1.302130827207593e-05,
|
| 544 |
+
"loss": 0.084,
|
| 545 |
+
"step": 37500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.7679352377407649,
|
| 549 |
+
"grad_norm": 1.0724354982376099,
|
| 550 |
+
"learning_rate": 1.2928259049036942e-05,
|
| 551 |
+
"loss": 0.0825,
|
| 552 |
+
"step": 38000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.7911975435005116,
|
| 556 |
+
"grad_norm": 0.6580795645713806,
|
| 557 |
+
"learning_rate": 1.2835209825997955e-05,
|
| 558 |
+
"loss": 0.0843,
|
| 559 |
+
"step": 38500
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 1.8144598492602588,
|
| 563 |
+
"grad_norm": 1.5284615755081177,
|
| 564 |
+
"learning_rate": 1.2742160602958966e-05,
|
| 565 |
+
"loss": 0.0858,
|
| 566 |
+
"step": 39000
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.8377221550200056,
|
| 570 |
+
"grad_norm": 2.040937900543213,
|
| 571 |
+
"learning_rate": 1.2649111379919978e-05,
|
| 572 |
+
"loss": 0.0838,
|
| 573 |
+
"step": 39500
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.8609844607797523,
|
| 577 |
+
"grad_norm": 1.1230378150939941,
|
| 578 |
+
"learning_rate": 1.255606215688099e-05,
|
| 579 |
+
"loss": 0.0822,
|
| 580 |
+
"step": 40000
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.8842467665394995,
|
| 584 |
+
"grad_norm": 0.6881332397460938,
|
| 585 |
+
"learning_rate": 1.2463012933842002e-05,
|
| 586 |
+
"loss": 0.0827,
|
| 587 |
+
"step": 40500
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.9075090722992463,
|
| 591 |
+
"grad_norm": 1.4516489505767822,
|
| 592 |
+
"learning_rate": 1.2369963710803016e-05,
|
| 593 |
+
"loss": 0.0797,
|
| 594 |
+
"step": 41000
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.9307713780589932,
|
| 598 |
+
"grad_norm": 0.8135964870452881,
|
| 599 |
+
"learning_rate": 1.2276914487764029e-05,
|
| 600 |
+
"loss": 0.0823,
|
| 601 |
+
"step": 41500
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.9540336838187402,
|
| 605 |
+
"grad_norm": 0.51099693775177,
|
| 606 |
+
"learning_rate": 1.2183865264725041e-05,
|
| 607 |
+
"loss": 0.0819,
|
| 608 |
+
"step": 42000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.977295989578487,
|
| 612 |
+
"grad_norm": 1.2015933990478516,
|
| 613 |
+
"learning_rate": 1.2090816041686054e-05,
|
| 614 |
+
"loss": 0.0826,
|
| 615 |
+
"step": 42500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.0,
|
| 619 |
+
"eval_accuracy": 0.5615520610402903,
|
| 620 |
+
"eval_f1": 0.7499260228316903,
|
| 621 |
+
"eval_loss": 0.09278739243745804,
|
| 622 |
+
"eval_roc_auc": 0.8556249389001388,
|
| 623 |
+
"eval_runtime": 23.2564,
|
| 624 |
+
"eval_samples_per_second": 924.221,
|
| 625 |
+
"eval_steps_per_second": 115.538,
|
| 626 |
+
"step": 42988
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.0005582953382337,
|
| 630 |
+
"grad_norm": 1.1591126918792725,
|
| 631 |
+
"learning_rate": 1.1997766818647065e-05,
|
| 632 |
+
"loss": 0.0807,
|
| 633 |
+
"step": 43000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.023820601097981,
|
| 637 |
+
"grad_norm": 0.6749496459960938,
|
| 638 |
+
"learning_rate": 1.1904717595608077e-05,
|
| 639 |
+
"loss": 0.07,
|
| 640 |
+
"step": 43500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 2.0470829068577276,
|
| 644 |
+
"grad_norm": 1.0793603658676147,
|
| 645 |
+
"learning_rate": 1.181166837256909e-05,
|
| 646 |
+
"loss": 0.0682,
|
| 647 |
+
"step": 44000
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.070345212617475,
|
| 651 |
+
"grad_norm": 1.9193094968795776,
|
| 652 |
+
"learning_rate": 1.1718619149530101e-05,
|
| 653 |
+
"loss": 0.0659,
|
| 654 |
+
"step": 44500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.0936075183772216,
|
| 658 |
+
"grad_norm": 2.0090835094451904,
|
| 659 |
+
"learning_rate": 1.1625569926491114e-05,
|
| 660 |
+
"loss": 0.0661,
|
| 661 |
+
"step": 45000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.1168698241369683,
|
| 665 |
+
"grad_norm": 1.252321720123291,
|
| 666 |
+
"learning_rate": 1.1532520703452128e-05,
|
| 667 |
+
"loss": 0.0663,
|
| 668 |
+
"step": 45500
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.1401321298967155,
|
| 672 |
+
"grad_norm": 0.25603464245796204,
|
| 673 |
+
"learning_rate": 1.143947148041314e-05,
|
| 674 |
+
"loss": 0.0671,
|
| 675 |
+
"step": 46000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.1633944356564623,
|
| 679 |
+
"grad_norm": 0.9230429530143738,
|
| 680 |
+
"learning_rate": 1.1346422257374151e-05,
|
| 681 |
+
"loss": 0.0654,
|
| 682 |
+
"step": 46500
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.186656741416209,
|
| 686 |
+
"grad_norm": 0.8180581331253052,
|
| 687 |
+
"learning_rate": 1.1253373034335164e-05,
|
| 688 |
+
"loss": 0.0675,
|
| 689 |
+
"step": 47000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.209919047175956,
|
| 693 |
+
"grad_norm": 1.928276777267456,
|
| 694 |
+
"learning_rate": 1.1160323811296177e-05,
|
| 695 |
+
"loss": 0.0686,
|
| 696 |
+
"step": 47500
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.233181352935703,
|
| 700 |
+
"grad_norm": 1.222936987876892,
|
| 701 |
+
"learning_rate": 1.106727458825719e-05,
|
| 702 |
+
"loss": 0.0706,
|
| 703 |
+
"step": 48000
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.2564436586954497,
|
| 707 |
+
"grad_norm": 0.6796595454216003,
|
| 708 |
+
"learning_rate": 1.09742253652182e-05,
|
| 709 |
+
"loss": 0.0681,
|
| 710 |
+
"step": 48500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.279705964455197,
|
| 714 |
+
"grad_norm": 1.2472426891326904,
|
| 715 |
+
"learning_rate": 1.0881176142179213e-05,
|
| 716 |
+
"loss": 0.0677,
|
| 717 |
+
"step": 49000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.3029682702149437,
|
| 721 |
+
"grad_norm": 1.2157268524169922,
|
| 722 |
+
"learning_rate": 1.0788126919140227e-05,
|
| 723 |
+
"loss": 0.0688,
|
| 724 |
+
"step": 49500
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 2.326230575974691,
|
| 728 |
+
"grad_norm": 1.0946940183639526,
|
| 729 |
+
"learning_rate": 1.069507769610124e-05,
|
| 730 |
+
"loss": 0.0669,
|
| 731 |
+
"step": 50000
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 2.3494928817344376,
|
| 735 |
+
"grad_norm": 2.56750750541687,
|
| 736 |
+
"learning_rate": 1.060202847306225e-05,
|
| 737 |
+
"loss": 0.065,
|
| 738 |
+
"step": 50500
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.3727551874941843,
|
| 742 |
+
"grad_norm": 0.8625161051750183,
|
| 743 |
+
"learning_rate": 1.0508979250023263e-05,
|
| 744 |
+
"loss": 0.0676,
|
| 745 |
+
"step": 51000
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 2.3960174932539315,
|
| 749 |
+
"grad_norm": 1.6813982725143433,
|
| 750 |
+
"learning_rate": 1.0415930026984276e-05,
|
| 751 |
+
"loss": 0.0669,
|
| 752 |
+
"step": 51500
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.4192797990136783,
|
| 756 |
+
"grad_norm": 1.76870596408844,
|
| 757 |
+
"learning_rate": 1.0322880803945287e-05,
|
| 758 |
+
"loss": 0.0704,
|
| 759 |
+
"step": 52000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.442542104773425,
|
| 763 |
+
"grad_norm": 0.8901593089103699,
|
| 764 |
+
"learning_rate": 1.02298315809063e-05,
|
| 765 |
+
"loss": 0.0703,
|
| 766 |
+
"step": 52500
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.4658044105331722,
|
| 770 |
+
"grad_norm": 0.7651998400688171,
|
| 771 |
+
"learning_rate": 1.0136782357867312e-05,
|
| 772 |
+
"loss": 0.0685,
|
| 773 |
+
"step": 53000
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.489066716292919,
|
| 777 |
+
"grad_norm": 1.2652794122695923,
|
| 778 |
+
"learning_rate": 1.0043733134828325e-05,
|
| 779 |
+
"loss": 0.0653,
|
| 780 |
+
"step": 53500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.5123290220526657,
|
| 784 |
+
"grad_norm": 1.768955111503601,
|
| 785 |
+
"learning_rate": 9.950683911789337e-06,
|
| 786 |
+
"loss": 0.0686,
|
| 787 |
+
"step": 54000
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 2.535591327812413,
|
| 791 |
+
"grad_norm": 1.6044102907180786,
|
| 792 |
+
"learning_rate": 9.85763468875035e-06,
|
| 793 |
+
"loss": 0.0676,
|
| 794 |
+
"step": 54500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.5588536335721597,
|
| 798 |
+
"grad_norm": 1.808396816253662,
|
| 799 |
+
"learning_rate": 9.764585465711363e-06,
|
| 800 |
+
"loss": 0.0662,
|
| 801 |
+
"step": 55000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.5821159393319064,
|
| 805 |
+
"grad_norm": 1.0778286457061768,
|
| 806 |
+
"learning_rate": 9.671536242672375e-06,
|
| 807 |
+
"loss": 0.0689,
|
| 808 |
+
"step": 55500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.6053782450916536,
|
| 812 |
+
"grad_norm": 2.739319324493408,
|
| 813 |
+
"learning_rate": 9.578487019633386e-06,
|
| 814 |
+
"loss": 0.068,
|
| 815 |
+
"step": 56000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 2.6286405508514004,
|
| 819 |
+
"grad_norm": 1.368030071258545,
|
| 820 |
+
"learning_rate": 9.485437796594399e-06,
|
| 821 |
+
"loss": 0.0655,
|
| 822 |
+
"step": 56500
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 2.651902856611147,
|
| 826 |
+
"grad_norm": 0.30945539474487305,
|
| 827 |
+
"learning_rate": 9.392388573555411e-06,
|
| 828 |
+
"loss": 0.0649,
|
| 829 |
+
"step": 57000
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 2.6751651623708943,
|
| 833 |
+
"grad_norm": 0.8296416997909546,
|
| 834 |
+
"learning_rate": 9.299339350516424e-06,
|
| 835 |
+
"loss": 0.0677,
|
| 836 |
+
"step": 57500
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 2.698427468130641,
|
| 840 |
+
"grad_norm": 1.1620192527770996,
|
| 841 |
+
"learning_rate": 9.206290127477437e-06,
|
| 842 |
+
"loss": 0.069,
|
| 843 |
+
"step": 58000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.721689773890388,
|
| 847 |
+
"grad_norm": 0.9376591444015503,
|
| 848 |
+
"learning_rate": 9.11324090443845e-06,
|
| 849 |
+
"loss": 0.0662,
|
| 850 |
+
"step": 58500
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 2.744952079650135,
|
| 854 |
+
"grad_norm": 1.6231029033660889,
|
| 855 |
+
"learning_rate": 9.02019168139946e-06,
|
| 856 |
+
"loss": 0.0674,
|
| 857 |
+
"step": 59000
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 2.7682143854098817,
|
| 861 |
+
"grad_norm": 1.0340408086776733,
|
| 862 |
+
"learning_rate": 8.927142458360474e-06,
|
| 863 |
+
"loss": 0.0685,
|
| 864 |
+
"step": 59500
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 2.7914766911696285,
|
| 868 |
+
"grad_norm": 1.5797666311264038,
|
| 869 |
+
"learning_rate": 8.834093235321485e-06,
|
| 870 |
+
"loss": 0.065,
|
| 871 |
+
"step": 60000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 2.8147389969293757,
|
| 875 |
+
"grad_norm": 0.9955604076385498,
|
| 876 |
+
"learning_rate": 8.741044012282498e-06,
|
| 877 |
+
"loss": 0.0682,
|
| 878 |
+
"step": 60500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.8380013026891224,
|
| 882 |
+
"grad_norm": 2.2507500648498535,
|
| 883 |
+
"learning_rate": 8.64799478924351e-06,
|
| 884 |
+
"loss": 0.0651,
|
| 885 |
+
"step": 61000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.861263608448869,
|
| 889 |
+
"grad_norm": 0.9272844791412354,
|
| 890 |
+
"learning_rate": 8.554945566204523e-06,
|
| 891 |
+
"loss": 0.0651,
|
| 892 |
+
"step": 61500
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.8845259142086164,
|
| 896 |
+
"grad_norm": 1.3886868953704834,
|
| 897 |
+
"learning_rate": 8.461896343165536e-06,
|
| 898 |
+
"loss": 0.066,
|
| 899 |
+
"step": 62000
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.907788219968363,
|
| 903 |
+
"grad_norm": 0.9660001397132874,
|
| 904 |
+
"learning_rate": 8.368847120126547e-06,
|
| 905 |
+
"loss": 0.0683,
|
| 906 |
+
"step": 62500
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.9310505257281103,
|
| 910 |
+
"grad_norm": 0.8844442963600159,
|
| 911 |
+
"learning_rate": 8.27579789708756e-06,
|
| 912 |
+
"loss": 0.0671,
|
| 913 |
+
"step": 63000
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.954312831487857,
|
| 917 |
+
"grad_norm": 2.407435417175293,
|
| 918 |
+
"learning_rate": 8.182748674048572e-06,
|
| 919 |
+
"loss": 0.0664,
|
| 920 |
+
"step": 63500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.9775751372476043,
|
| 924 |
+
"grad_norm": 2.187854528427124,
|
| 925 |
+
"learning_rate": 8.089699451009585e-06,
|
| 926 |
+
"loss": 0.0666,
|
| 927 |
+
"step": 64000
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 3.0,
|
| 931 |
+
"eval_accuracy": 0.5649948822927329,
|
| 932 |
+
"eval_f1": 0.7591117292255597,
|
| 933 |
+
"eval_loss": 0.09460150450468063,
|
| 934 |
+
"eval_roc_auc": 0.8701062840131171,
|
| 935 |
+
"eval_runtime": 23.3037,
|
| 936 |
+
"eval_samples_per_second": 922.345,
|
| 937 |
+
"eval_steps_per_second": 115.304,
|
| 938 |
+
"step": 64482
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.000837443007351,
|
| 942 |
+
"grad_norm": 1.4572051763534546,
|
| 943 |
+
"learning_rate": 7.996650227970597e-06,
|
| 944 |
+
"loss": 0.0662,
|
| 945 |
+
"step": 64500
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 3.0240997487670978,
|
| 949 |
+
"grad_norm": 1.0595591068267822,
|
| 950 |
+
"learning_rate": 7.90360100493161e-06,
|
| 951 |
+
"loss": 0.0532,
|
| 952 |
+
"step": 65000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 3.0473620545268445,
|
| 956 |
+
"grad_norm": 0.7926930785179138,
|
| 957 |
+
"learning_rate": 7.81055178189262e-06,
|
| 958 |
+
"loss": 0.0513,
|
| 959 |
+
"step": 65500
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 3.0706243602865917,
|
| 963 |
+
"grad_norm": 2.0223031044006348,
|
| 964 |
+
"learning_rate": 7.717502558853635e-06,
|
| 965 |
+
"loss": 0.056,
|
| 966 |
+
"step": 66000
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 3.0938866660463384,
|
| 970 |
+
"grad_norm": 1.3608500957489014,
|
| 971 |
+
"learning_rate": 7.624453335814647e-06,
|
| 972 |
+
"loss": 0.051,
|
| 973 |
+
"step": 66500
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 3.1171489718060856,
|
| 977 |
+
"grad_norm": 1.0539377927780151,
|
| 978 |
+
"learning_rate": 7.531404112775659e-06,
|
| 979 |
+
"loss": 0.0535,
|
| 980 |
+
"step": 67000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 3.1404112775658324,
|
| 984 |
+
"grad_norm": 0.8993151187896729,
|
| 985 |
+
"learning_rate": 7.4383548897366704e-06,
|
| 986 |
+
"loss": 0.0529,
|
| 987 |
+
"step": 67500
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 3.163673583325579,
|
| 991 |
+
"grad_norm": 1.5115621089935303,
|
| 992 |
+
"learning_rate": 7.345305666697684e-06,
|
| 993 |
+
"loss": 0.0512,
|
| 994 |
+
"step": 68000
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 3.1869358890853263,
|
| 998 |
+
"grad_norm": 0.8718969225883484,
|
| 999 |
+
"learning_rate": 7.2522564436586965e-06,
|
| 1000 |
+
"loss": 0.0517,
|
| 1001 |
+
"step": 68500
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 3.210198194845073,
|
| 1005 |
+
"grad_norm": 1.0791226625442505,
|
| 1006 |
+
"learning_rate": 7.159207220619708e-06,
|
| 1007 |
+
"loss": 0.0512,
|
| 1008 |
+
"step": 69000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 3.23346050060482,
|
| 1012 |
+
"grad_norm": 1.2362322807312012,
|
| 1013 |
+
"learning_rate": 7.06615799758072e-06,
|
| 1014 |
+
"loss": 0.0505,
|
| 1015 |
+
"step": 69500
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 3.256722806364567,
|
| 1019 |
+
"grad_norm": 0.4878983497619629,
|
| 1020 |
+
"learning_rate": 6.9731087745417335e-06,
|
| 1021 |
+
"loss": 0.0523,
|
| 1022 |
+
"step": 70000
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 3.2799851121243138,
|
| 1026 |
+
"grad_norm": 0.5156907439231873,
|
| 1027 |
+
"learning_rate": 6.880059551502746e-06,
|
| 1028 |
+
"loss": 0.0522,
|
| 1029 |
+
"step": 70500
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 3.3032474178840605,
|
| 1033 |
+
"grad_norm": 1.0036829710006714,
|
| 1034 |
+
"learning_rate": 6.787010328463758e-06,
|
| 1035 |
+
"loss": 0.053,
|
| 1036 |
+
"step": 71000
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 3.3265097236438077,
|
| 1040 |
+
"grad_norm": 1.9383690357208252,
|
| 1041 |
+
"learning_rate": 6.69396110542477e-06,
|
| 1042 |
+
"loss": 0.0524,
|
| 1043 |
+
"step": 71500
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 3.3497720294035545,
|
| 1047 |
+
"grad_norm": 0.9468953609466553,
|
| 1048 |
+
"learning_rate": 6.600911882385782e-06,
|
| 1049 |
+
"loss": 0.0507,
|
| 1050 |
+
"step": 72000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 3.373034335163301,
|
| 1054 |
+
"grad_norm": 1.7953852415084839,
|
| 1055 |
+
"learning_rate": 6.507862659346795e-06,
|
| 1056 |
+
"loss": 0.0536,
|
| 1057 |
+
"step": 72500
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 3.3962966409230484,
|
| 1061 |
+
"grad_norm": 3.1470677852630615,
|
| 1062 |
+
"learning_rate": 6.4148134363078075e-06,
|
| 1063 |
+
"loss": 0.0521,
|
| 1064 |
+
"step": 73000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.419558946682795,
|
| 1068 |
+
"grad_norm": 2.5121142864227295,
|
| 1069 |
+
"learning_rate": 6.321764213268819e-06,
|
| 1070 |
+
"loss": 0.0513,
|
| 1071 |
+
"step": 73500
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 3.442821252442542,
|
| 1075 |
+
"grad_norm": 1.0771255493164062,
|
| 1076 |
+
"learning_rate": 6.228714990229832e-06,
|
| 1077 |
+
"loss": 0.0529,
|
| 1078 |
+
"step": 74000
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 3.466083558202289,
|
| 1082 |
+
"grad_norm": 1.3458467721939087,
|
| 1083 |
+
"learning_rate": 6.1356657671908446e-06,
|
| 1084 |
+
"loss": 0.053,
|
| 1085 |
+
"step": 74500
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 3.489345863962036,
|
| 1089 |
+
"grad_norm": 0.29975369572639465,
|
| 1090 |
+
"learning_rate": 6.042616544151857e-06,
|
| 1091 |
+
"loss": 0.0512,
|
| 1092 |
+
"step": 75000
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 3.5126081697217826,
|
| 1096 |
+
"grad_norm": 1.2391622066497803,
|
| 1097 |
+
"learning_rate": 5.949567321112869e-06,
|
| 1098 |
+
"loss": 0.0519,
|
| 1099 |
+
"step": 75500
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 3.5358704754815298,
|
| 1103 |
+
"grad_norm": 1.6513882875442505,
|
| 1104 |
+
"learning_rate": 5.8565180980738816e-06,
|
| 1105 |
+
"loss": 0.0529,
|
| 1106 |
+
"step": 76000
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 3.5591327812412765,
|
| 1110 |
+
"grad_norm": 1.1643694639205933,
|
| 1111 |
+
"learning_rate": 5.763468875034894e-06,
|
| 1112 |
+
"loss": 0.0537,
|
| 1113 |
+
"step": 76500
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 3.5823950870010233,
|
| 1117 |
+
"grad_norm": 1.9166603088378906,
|
| 1118 |
+
"learning_rate": 5.670419651995907e-06,
|
| 1119 |
+
"loss": 0.0508,
|
| 1120 |
+
"step": 77000
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 3.6056573927607705,
|
| 1124 |
+
"grad_norm": 1.5334446430206299,
|
| 1125 |
+
"learning_rate": 5.5773704289569186e-06,
|
| 1126 |
+
"loss": 0.0514,
|
| 1127 |
+
"step": 77500
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 3.628919698520517,
|
| 1131 |
+
"grad_norm": 2.500365972518921,
|
| 1132 |
+
"learning_rate": 5.48432120591793e-06,
|
| 1133 |
+
"loss": 0.0537,
|
| 1134 |
+
"step": 78000
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 3.6521820042802644,
|
| 1138 |
+
"grad_norm": 0.8305968046188354,
|
| 1139 |
+
"learning_rate": 5.391271982878944e-06,
|
| 1140 |
+
"loss": 0.0546,
|
| 1141 |
+
"step": 78500
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 3.675444310040011,
|
| 1145 |
+
"grad_norm": 1.3438687324523926,
|
| 1146 |
+
"learning_rate": 5.2982227598399564e-06,
|
| 1147 |
+
"loss": 0.0536,
|
| 1148 |
+
"step": 79000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 3.6987066157997583,
|
| 1152 |
+
"grad_norm": 1.1025956869125366,
|
| 1153 |
+
"learning_rate": 5.205173536800968e-06,
|
| 1154 |
+
"loss": 0.0546,
|
| 1155 |
+
"step": 79500
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 3.721968921559505,
|
| 1159 |
+
"grad_norm": 1.6700533628463745,
|
| 1160 |
+
"learning_rate": 5.11212431376198e-06,
|
| 1161 |
+
"loss": 0.0533,
|
| 1162 |
+
"step": 80000
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 3.745231227319252,
|
| 1166 |
+
"grad_norm": 0.8916147351264954,
|
| 1167 |
+
"learning_rate": 5.019075090722993e-06,
|
| 1168 |
+
"loss": 0.0516,
|
| 1169 |
+
"step": 80500
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 3.768493533078999,
|
| 1173 |
+
"grad_norm": 1.7522839307785034,
|
| 1174 |
+
"learning_rate": 4.926025867684005e-06,
|
| 1175 |
+
"loss": 0.0537,
|
| 1176 |
+
"step": 81000
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 3.791755838838746,
|
| 1180 |
+
"grad_norm": 1.4133764505386353,
|
| 1181 |
+
"learning_rate": 4.832976644645018e-06,
|
| 1182 |
+
"loss": 0.0542,
|
| 1183 |
+
"step": 81500
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 3.8150181445984925,
|
| 1187 |
+
"grad_norm": 0.9128021001815796,
|
| 1188 |
+
"learning_rate": 4.73992742160603e-06,
|
| 1189 |
+
"loss": 0.0516,
|
| 1190 |
+
"step": 82000
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 3.8382804503582397,
|
| 1194 |
+
"grad_norm": 2.4152848720550537,
|
| 1195 |
+
"learning_rate": 4.646878198567042e-06,
|
| 1196 |
+
"loss": 0.0532,
|
| 1197 |
+
"step": 82500
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 3.8615427561179865,
|
| 1201 |
+
"grad_norm": 1.5950450897216797,
|
| 1202 |
+
"learning_rate": 4.553828975528055e-06,
|
| 1203 |
+
"loss": 0.0523,
|
| 1204 |
+
"step": 83000
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 3.8848050618777332,
|
| 1208 |
+
"grad_norm": 1.5487794876098633,
|
| 1209 |
+
"learning_rate": 4.4607797524890675e-06,
|
| 1210 |
+
"loss": 0.054,
|
| 1211 |
+
"step": 83500
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 3.9080673676374804,
|
| 1215 |
+
"grad_norm": 1.6051621437072754,
|
| 1216 |
+
"learning_rate": 4.367730529450079e-06,
|
| 1217 |
+
"loss": 0.052,
|
| 1218 |
+
"step": 84000
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 3.931329673397227,
|
| 1222 |
+
"grad_norm": 1.2082515954971313,
|
| 1223 |
+
"learning_rate": 4.274681306411092e-06,
|
| 1224 |
+
"loss": 0.0512,
|
| 1225 |
+
"step": 84500
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 3.954591979156974,
|
| 1229 |
+
"grad_norm": 1.1482079029083252,
|
| 1230 |
+
"learning_rate": 4.1816320833721045e-06,
|
| 1231 |
+
"loss": 0.0514,
|
| 1232 |
+
"step": 85000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 3.977854284916721,
|
| 1236 |
+
"grad_norm": 1.919583797454834,
|
| 1237 |
+
"learning_rate": 4.088582860333117e-06,
|
| 1238 |
+
"loss": 0.0543,
|
| 1239 |
+
"step": 85500
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 4.0,
|
| 1243 |
+
"eval_accuracy": 0.5645761607890574,
|
| 1244 |
+
"eval_f1": 0.759579488098438,
|
| 1245 |
+
"eval_loss": 0.10311879962682724,
|
| 1246 |
+
"eval_roc_auc": 0.8744104988949349,
|
| 1247 |
+
"eval_runtime": 22.8736,
|
| 1248 |
+
"eval_samples_per_second": 939.686,
|
| 1249 |
+
"eval_steps_per_second": 117.472,
|
| 1250 |
+
"step": 85976
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 4.001116590676467,
|
| 1254 |
+
"grad_norm": 0.9219486713409424,
|
| 1255 |
+
"learning_rate": 3.995533637294129e-06,
|
| 1256 |
+
"loss": 0.0531,
|
| 1257 |
+
"step": 86000
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 4.024378896436215,
|
| 1261 |
+
"grad_norm": 0.5063530206680298,
|
| 1262 |
+
"learning_rate": 3.902484414255141e-06,
|
| 1263 |
+
"loss": 0.0431,
|
| 1264 |
+
"step": 86500
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 4.047641202195962,
|
| 1268 |
+
"grad_norm": 0.9435988068580627,
|
| 1269 |
+
"learning_rate": 3.8094351912161537e-06,
|
| 1270 |
+
"loss": 0.0419,
|
| 1271 |
+
"step": 87000
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 4.070903507955709,
|
| 1275 |
+
"grad_norm": 0.8546033501625061,
|
| 1276 |
+
"learning_rate": 3.716385968177166e-06,
|
| 1277 |
+
"loss": 0.0413,
|
| 1278 |
+
"step": 87500
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 4.094165813715455,
|
| 1282 |
+
"grad_norm": 1.6249778270721436,
|
| 1283 |
+
"learning_rate": 3.6233367451381785e-06,
|
| 1284 |
+
"loss": 0.0429,
|
| 1285 |
+
"step": 88000
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 4.1174281194752025,
|
| 1289 |
+
"grad_norm": 1.7502926588058472,
|
| 1290 |
+
"learning_rate": 3.5302875220991907e-06,
|
| 1291 |
+
"loss": 0.0395,
|
| 1292 |
+
"step": 88500
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 4.14069042523495,
|
| 1296 |
+
"grad_norm": 3.170189380645752,
|
| 1297 |
+
"learning_rate": 3.4372382990602033e-06,
|
| 1298 |
+
"loss": 0.0431,
|
| 1299 |
+
"step": 89000
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 4.163952730994696,
|
| 1303 |
+
"grad_norm": 1.2306873798370361,
|
| 1304 |
+
"learning_rate": 3.3441890760212155e-06,
|
| 1305 |
+
"loss": 0.0419,
|
| 1306 |
+
"step": 89500
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 4.187215036754443,
|
| 1310 |
+
"grad_norm": 2.3752849102020264,
|
| 1311 |
+
"learning_rate": 3.251139852982228e-06,
|
| 1312 |
+
"loss": 0.0426,
|
| 1313 |
+
"step": 90000
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 4.21047734251419,
|
| 1317 |
+
"grad_norm": 1.0530017614364624,
|
| 1318 |
+
"learning_rate": 3.1580906299432403e-06,
|
| 1319 |
+
"loss": 0.0406,
|
| 1320 |
+
"step": 90500
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 4.233739648273937,
|
| 1324 |
+
"grad_norm": 1.7250635623931885,
|
| 1325 |
+
"learning_rate": 3.065041406904253e-06,
|
| 1326 |
+
"loss": 0.0431,
|
| 1327 |
+
"step": 91000
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 4.257001954033684,
|
| 1331 |
+
"grad_norm": 0.6301759481430054,
|
| 1332 |
+
"learning_rate": 2.9719921838652647e-06,
|
| 1333 |
+
"loss": 0.0437,
|
| 1334 |
+
"step": 91500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 4.280264259793431,
|
| 1338 |
+
"grad_norm": 2.9674508571624756,
|
| 1339 |
+
"learning_rate": 2.8789429608262777e-06,
|
| 1340 |
+
"loss": 0.0429,
|
| 1341 |
+
"step": 92000
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 4.303526565553177,
|
| 1345 |
+
"grad_norm": 1.3684778213500977,
|
| 1346 |
+
"learning_rate": 2.7858937377872895e-06,
|
| 1347 |
+
"loss": 0.0413,
|
| 1348 |
+
"step": 92500
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 4.326788871312925,
|
| 1352 |
+
"grad_norm": 2.5620508193969727,
|
| 1353 |
+
"learning_rate": 2.692844514748302e-06,
|
| 1354 |
+
"loss": 0.0425,
|
| 1355 |
+
"step": 93000
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 4.350051177072672,
|
| 1359 |
+
"grad_norm": 2.529858350753784,
|
| 1360 |
+
"learning_rate": 2.5997952917093143e-06,
|
| 1361 |
+
"loss": 0.0432,
|
| 1362 |
+
"step": 93500
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 4.373313482832418,
|
| 1366 |
+
"grad_norm": 1.6359411478042603,
|
| 1367 |
+
"learning_rate": 2.5067460686703265e-06,
|
| 1368 |
+
"loss": 0.0437,
|
| 1369 |
+
"step": 94000
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 4.396575788592165,
|
| 1373 |
+
"grad_norm": 1.6633356809616089,
|
| 1374 |
+
"learning_rate": 2.413696845631339e-06,
|
| 1375 |
+
"loss": 0.0415,
|
| 1376 |
+
"step": 94500
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 4.419838094351912,
|
| 1380 |
+
"grad_norm": 0.9840025901794434,
|
| 1381 |
+
"learning_rate": 2.3206476225923518e-06,
|
| 1382 |
+
"loss": 0.0387,
|
| 1383 |
+
"step": 95000
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 4.443100400111659,
|
| 1387 |
+
"grad_norm": 1.1913479566574097,
|
| 1388 |
+
"learning_rate": 2.227598399553364e-06,
|
| 1389 |
+
"loss": 0.0433,
|
| 1390 |
+
"step": 95500
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 4.466362705871406,
|
| 1394 |
+
"grad_norm": 0.9769937992095947,
|
| 1395 |
+
"learning_rate": 2.1345491765143766e-06,
|
| 1396 |
+
"loss": 0.042,
|
| 1397 |
+
"step": 96000
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 4.489625011631153,
|
| 1401 |
+
"grad_norm": 0.4699022173881531,
|
| 1402 |
+
"learning_rate": 2.0414999534753888e-06,
|
| 1403 |
+
"loss": 0.0416,
|
| 1404 |
+
"step": 96500
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 4.512887317390899,
|
| 1408 |
+
"grad_norm": 1.7338500022888184,
|
| 1409 |
+
"learning_rate": 1.948450730436401e-06,
|
| 1410 |
+
"loss": 0.0422,
|
| 1411 |
+
"step": 97000
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 4.536149623150647,
|
| 1415 |
+
"grad_norm": 2.9296669960021973,
|
| 1416 |
+
"learning_rate": 1.8554015073974132e-06,
|
| 1417 |
+
"loss": 0.041,
|
| 1418 |
+
"step": 97500
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 4.559411928910394,
|
| 1422 |
+
"grad_norm": 2.108750820159912,
|
| 1423 |
+
"learning_rate": 1.7623522843584256e-06,
|
| 1424 |
+
"loss": 0.0406,
|
| 1425 |
+
"step": 98000
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 4.58267423467014,
|
| 1429 |
+
"grad_norm": 1.38349449634552,
|
| 1430 |
+
"learning_rate": 1.669303061319438e-06,
|
| 1431 |
+
"loss": 0.0403,
|
| 1432 |
+
"step": 98500
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 4.605936540429887,
|
| 1436 |
+
"grad_norm": 1.092578411102295,
|
| 1437 |
+
"learning_rate": 1.5762538382804504e-06,
|
| 1438 |
+
"loss": 0.0419,
|
| 1439 |
+
"step": 99000
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 4.6291988461896345,
|
| 1443 |
+
"grad_norm": 2.6619553565979004,
|
| 1444 |
+
"learning_rate": 1.4832046152414628e-06,
|
| 1445 |
+
"loss": 0.0394,
|
| 1446 |
+
"step": 99500
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 4.652461151949382,
|
| 1450 |
+
"grad_norm": 1.8110424280166626,
|
| 1451 |
+
"learning_rate": 1.3901553922024752e-06,
|
| 1452 |
+
"loss": 0.0407,
|
| 1453 |
+
"step": 100000
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 4.675723457709128,
|
| 1457 |
+
"grad_norm": 1.2239103317260742,
|
| 1458 |
+
"learning_rate": 1.2971061691634876e-06,
|
| 1459 |
+
"loss": 0.0415,
|
| 1460 |
+
"step": 100500
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 4.698985763468875,
|
| 1464 |
+
"grad_norm": 3.0208041667938232,
|
| 1465 |
+
"learning_rate": 1.2040569461245e-06,
|
| 1466 |
+
"loss": 0.0411,
|
| 1467 |
+
"step": 101000
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 4.7222480692286215,
|
| 1471 |
+
"grad_norm": 1.5058140754699707,
|
| 1472 |
+
"learning_rate": 1.1110077230855124e-06,
|
| 1473 |
+
"loss": 0.0431,
|
| 1474 |
+
"step": 101500
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 4.745510374988369,
|
| 1478 |
+
"grad_norm": 1.6732498407363892,
|
| 1479 |
+
"learning_rate": 1.0179585000465248e-06,
|
| 1480 |
+
"loss": 0.0408,
|
| 1481 |
+
"step": 102000
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 4.768772680748116,
|
| 1485 |
+
"grad_norm": 2.15928053855896,
|
| 1486 |
+
"learning_rate": 9.249092770075371e-07,
|
| 1487 |
+
"loss": 0.0412,
|
| 1488 |
+
"step": 102500
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 4.792034986507863,
|
| 1492 |
+
"grad_norm": 1.8211805820465088,
|
| 1493 |
+
"learning_rate": 8.318600539685494e-07,
|
| 1494 |
+
"loss": 0.0418,
|
| 1495 |
+
"step": 103000
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 4.815297292267609,
|
| 1499 |
+
"grad_norm": 1.1392755508422852,
|
| 1500 |
+
"learning_rate": 7.388108309295617e-07,
|
| 1501 |
+
"loss": 0.0395,
|
| 1502 |
+
"step": 103500
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 4.838559598027357,
|
| 1506 |
+
"grad_norm": 1.2640013694763184,
|
| 1507 |
+
"learning_rate": 6.457616078905741e-07,
|
| 1508 |
+
"loss": 0.0404,
|
| 1509 |
+
"step": 104000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 4.861821903787103,
|
| 1513 |
+
"grad_norm": 1.2413549423217773,
|
| 1514 |
+
"learning_rate": 5.527123848515865e-07,
|
| 1515 |
+
"loss": 0.0409,
|
| 1516 |
+
"step": 104500
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 4.88508420954685,
|
| 1520 |
+
"grad_norm": 0.14875428378582,
|
| 1521 |
+
"learning_rate": 4.5966316181259895e-07,
|
| 1522 |
+
"loss": 0.0405,
|
| 1523 |
+
"step": 105000
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 4.908346515306597,
|
| 1527 |
+
"grad_norm": 1.309793472290039,
|
| 1528 |
+
"learning_rate": 3.6661393877361125e-07,
|
| 1529 |
+
"loss": 0.041,
|
| 1530 |
+
"step": 105500
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 4.9316088210663445,
|
| 1534 |
+
"grad_norm": 0.9020711779594421,
|
| 1535 |
+
"learning_rate": 2.7356471573462365e-07,
|
| 1536 |
+
"loss": 0.0402,
|
| 1537 |
+
"step": 106000
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 4.954871126826091,
|
| 1541 |
+
"grad_norm": 1.875877857208252,
|
| 1542 |
+
"learning_rate": 1.80515492695636e-07,
|
| 1543 |
+
"loss": 0.0408,
|
| 1544 |
+
"step": 106500
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 4.978133432585838,
|
| 1548 |
+
"grad_norm": 3.464327335357666,
|
| 1549 |
+
"learning_rate": 8.746626965664838e-08,
|
| 1550 |
+
"loss": 0.0407,
|
| 1551 |
+
"step": 107000
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 5.0,
|
| 1555 |
+
"eval_accuracy": 0.5647157346236159,
|
| 1556 |
+
"eval_f1": 0.7594581273430615,
|
| 1557 |
+
"eval_loss": 0.1101851612329483,
|
| 1558 |
+
"eval_roc_auc": 0.8742792491333411,
|
| 1559 |
+
"eval_runtime": 22.5758,
|
| 1560 |
+
"eval_samples_per_second": 952.08,
|
| 1561 |
+
"eval_steps_per_second": 119.021,
|
| 1562 |
+
"step": 107470
|
| 1563 |
+
}
|
| 1564 |
+
],
|
| 1565 |
+
"logging_steps": 500,
|
| 1566 |
+
"max_steps": 107470,
|
| 1567 |
+
"num_input_tokens_seen": 0,
|
| 1568 |
+
"num_train_epochs": 5,
|
| 1569 |
+
"save_steps": 500,
|
| 1570 |
+
"stateful_callbacks": {
|
| 1571 |
+
"TrainerControl": {
|
| 1572 |
+
"args": {
|
| 1573 |
+
"should_epoch_stop": false,
|
| 1574 |
+
"should_evaluate": false,
|
| 1575 |
+
"should_log": false,
|
| 1576 |
+
"should_save": true,
|
| 1577 |
+
"should_training_stop": true
|
| 1578 |
+
},
|
| 1579 |
+
"attributes": {}
|
| 1580 |
+
}
|
| 1581 |
+
},
|
| 1582 |
+
"total_flos": 5.656124322596352e+16,
|
| 1583 |
+
"train_batch_size": 8,
|
| 1584 |
+
"trial_name": null,
|
| 1585 |
+
"trial_params": null
|
| 1586 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f09a088fc659036909375538a041709b83ecfa3173e60c7388d9eccad28cbfbe
|
| 3 |
+
size 5176
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|