gyr66
commited on
Commit
β’
366ec82
1
Parent(s):
bc2e637
Add Model
Browse files- added_tokens.json +3 -0
- config.json +89 -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 +58 -0
- trainer_state.json +667 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[UNK]": 39979
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nghuyong/ernie-3.0-xbase-zh",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ErnieForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "O",
|
| 13 |
+
"1": "B-position",
|
| 14 |
+
"2": "I-position",
|
| 15 |
+
"3": "B-name",
|
| 16 |
+
"4": "I-name",
|
| 17 |
+
"5": "B-movie",
|
| 18 |
+
"6": "I-movie",
|
| 19 |
+
"7": "B-organization",
|
| 20 |
+
"8": "I-organization",
|
| 21 |
+
"9": "B-company",
|
| 22 |
+
"10": "I-company",
|
| 23 |
+
"11": "B-book",
|
| 24 |
+
"12": "I-book",
|
| 25 |
+
"13": "B-address",
|
| 26 |
+
"14": "I-address",
|
| 27 |
+
"15": "B-scene",
|
| 28 |
+
"16": "I-scene",
|
| 29 |
+
"17": "B-mobile",
|
| 30 |
+
"18": "I-mobile",
|
| 31 |
+
"19": "B-email",
|
| 32 |
+
"20": "I-email",
|
| 33 |
+
"21": "B-game",
|
| 34 |
+
"22": "I-game",
|
| 35 |
+
"23": "B-government",
|
| 36 |
+
"24": "I-government",
|
| 37 |
+
"25": "B-QQ",
|
| 38 |
+
"26": "I-QQ",
|
| 39 |
+
"27": "B-vx",
|
| 40 |
+
"28": "I-vx"
|
| 41 |
+
},
|
| 42 |
+
"initializer_range": 0.02,
|
| 43 |
+
"intermediate_size": 4096,
|
| 44 |
+
"label2id": {
|
| 45 |
+
"B-QQ": 25,
|
| 46 |
+
"B-address": 13,
|
| 47 |
+
"B-book": 11,
|
| 48 |
+
"B-company": 9,
|
| 49 |
+
"B-email": 19,
|
| 50 |
+
"B-game": 21,
|
| 51 |
+
"B-government": 23,
|
| 52 |
+
"B-mobile": 17,
|
| 53 |
+
"B-movie": 5,
|
| 54 |
+
"B-name": 3,
|
| 55 |
+
"B-organization": 7,
|
| 56 |
+
"B-position": 1,
|
| 57 |
+
"B-scene": 15,
|
| 58 |
+
"B-vx": 27,
|
| 59 |
+
"I-QQ": 26,
|
| 60 |
+
"I-address": 14,
|
| 61 |
+
"I-book": 12,
|
| 62 |
+
"I-company": 10,
|
| 63 |
+
"I-email": 20,
|
| 64 |
+
"I-game": 22,
|
| 65 |
+
"I-government": 24,
|
| 66 |
+
"I-mobile": 18,
|
| 67 |
+
"I-movie": 6,
|
| 68 |
+
"I-name": 4,
|
| 69 |
+
"I-organization": 8,
|
| 70 |
+
"I-position": 2,
|
| 71 |
+
"I-scene": 16,
|
| 72 |
+
"I-vx": 28,
|
| 73 |
+
"O": 0
|
| 74 |
+
},
|
| 75 |
+
"layer_norm_eps": 1e-05,
|
| 76 |
+
"max_position_embeddings": 2048,
|
| 77 |
+
"model_type": "ernie",
|
| 78 |
+
"num_attention_heads": 16,
|
| 79 |
+
"num_hidden_layers": 20,
|
| 80 |
+
"pad_token_id": 0,
|
| 81 |
+
"position_embedding_type": "absolute",
|
| 82 |
+
"task_type_vocab_size": 16,
|
| 83 |
+
"torch_dtype": "float32",
|
| 84 |
+
"transformers_version": "4.35.2",
|
| 85 |
+
"type_vocab_size": 4,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"use_task_id": true,
|
| 88 |
+
"vocab_size": 40000
|
| 89 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7de358cfdae2565e545095e22b9b6baa1f210f34cea150839d594d7a4a595df2
|
| 3 |
+
size 1180175012
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed717cfcb9b86276595d2d947497e8b709cb5d79272a85565f833ddbf291464f
|
| 3 |
+
size 2360545210
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bad960e5f27bf370fe9b0d11733039b61e3de26728906f85e05d2a58f7978531
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:219f4d64086ccfdb80cef48db3e01581583aed2c709577da652b2e88e2ab0789
|
| 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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[MASK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"39979": {
|
| 36 |
+
"content": "[UNK]",
|
| 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_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"ignore_mismatched_sizes": true,
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,667 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7295733911785972,
|
| 3 |
+
"best_model_checkpoint": "Ernie-3.0-large-chinese-finetuned-ner/checkpoint-9072",
|
| 4 |
+
"epoch": 36.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 9072,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 14 |
+
"loss": 0.7619,
|
| 15 |
+
"step": 252
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"eval_accuracy": 0.8891147174729265,
|
| 20 |
+
"eval_f1": 0.5908584169453734,
|
| 21 |
+
"eval_loss": 0.371647447347641,
|
| 22 |
+
"eval_precision": 0.5302120848339336,
|
| 23 |
+
"eval_recall": 0.6671701913393756,
|
| 24 |
+
"eval_runtime": 30.5213,
|
| 25 |
+
"eval_samples_per_second": 16.48,
|
| 26 |
+
"eval_steps_per_second": 2.064,
|
| 27 |
+
"step": 252
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.0,
|
| 31 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 32 |
+
"loss": 0.3277,
|
| 33 |
+
"step": 504
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.0,
|
| 37 |
+
"eval_accuracy": 0.9043503894250163,
|
| 38 |
+
"eval_f1": 0.6514158800666296,
|
| 39 |
+
"eval_loss": 0.31230422854423523,
|
| 40 |
+
"eval_precision": 0.5827538247566064,
|
| 41 |
+
"eval_recall": 0.7384189325276939,
|
| 42 |
+
"eval_runtime": 30.3199,
|
| 43 |
+
"eval_samples_per_second": 16.59,
|
| 44 |
+
"eval_steps_per_second": 2.078,
|
| 45 |
+
"step": 504
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.0,
|
| 49 |
+
"learning_rate": 1.88e-05,
|
| 50 |
+
"loss": 0.2539,
|
| 51 |
+
"step": 756
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 3.0,
|
| 55 |
+
"eval_accuracy": 0.9070344741986534,
|
| 56 |
+
"eval_f1": 0.6798141221806642,
|
| 57 |
+
"eval_loss": 0.3259331285953522,
|
| 58 |
+
"eval_precision": 0.6182230467944754,
|
| 59 |
+
"eval_recall": 0.7550352467270897,
|
| 60 |
+
"eval_runtime": 31.8667,
|
| 61 |
+
"eval_samples_per_second": 15.785,
|
| 62 |
+
"eval_steps_per_second": 1.977,
|
| 63 |
+
"step": 756
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 4.0,
|
| 67 |
+
"learning_rate": 1.8400000000000003e-05,
|
| 68 |
+
"loss": 0.209,
|
| 69 |
+
"step": 1008
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"eval_accuracy": 0.899121854345735,
|
| 74 |
+
"eval_f1": 0.6714031971580817,
|
| 75 |
+
"eval_loss": 0.3699039816856384,
|
| 76 |
+
"eval_precision": 0.6004765687053217,
|
| 77 |
+
"eval_recall": 0.7613293051359517,
|
| 78 |
+
"eval_runtime": 29.8895,
|
| 79 |
+
"eval_samples_per_second": 16.829,
|
| 80 |
+
"eval_steps_per_second": 2.108,
|
| 81 |
+
"step": 1008
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 5.0,
|
| 85 |
+
"learning_rate": 1.8e-05,
|
| 86 |
+
"loss": 0.1696,
|
| 87 |
+
"step": 1260
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 5.0,
|
| 91 |
+
"eval_accuracy": 0.9081980947652589,
|
| 92 |
+
"eval_f1": 0.7022252810277587,
|
| 93 |
+
"eval_loss": 0.35198503732681274,
|
| 94 |
+
"eval_precision": 0.6449641803624104,
|
| 95 |
+
"eval_recall": 0.7706445115810675,
|
| 96 |
+
"eval_runtime": 31.5563,
|
| 97 |
+
"eval_samples_per_second": 15.94,
|
| 98 |
+
"eval_steps_per_second": 1.996,
|
| 99 |
+
"step": 1260
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 6.0,
|
| 103 |
+
"learning_rate": 1.76e-05,
|
| 104 |
+
"loss": 0.1394,
|
| 105 |
+
"step": 1512
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.0,
|
| 109 |
+
"eval_accuracy": 0.9099047382629473,
|
| 110 |
+
"eval_f1": 0.6968929804372841,
|
| 111 |
+
"eval_loss": 0.36153343319892883,
|
| 112 |
+
"eval_precision": 0.6417973717676981,
|
| 113 |
+
"eval_recall": 0.7623363544813696,
|
| 114 |
+
"eval_runtime": 30.5397,
|
| 115 |
+
"eval_samples_per_second": 16.47,
|
| 116 |
+
"eval_steps_per_second": 2.063,
|
| 117 |
+
"step": 1512
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 7.0,
|
| 121 |
+
"learning_rate": 1.72e-05,
|
| 122 |
+
"loss": 0.1184,
|
| 123 |
+
"step": 1764
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"eval_accuracy": 0.9082911844105874,
|
| 128 |
+
"eval_f1": 0.7067113318701628,
|
| 129 |
+
"eval_loss": 0.37900495529174805,
|
| 130 |
+
"eval_precision": 0.6529348986125934,
|
| 131 |
+
"eval_recall": 0.7701409869083585,
|
| 132 |
+
"eval_runtime": 30.8222,
|
| 133 |
+
"eval_samples_per_second": 16.319,
|
| 134 |
+
"eval_steps_per_second": 2.044,
|
| 135 |
+
"step": 1764
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.0,
|
| 139 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 140 |
+
"loss": 0.1011,
|
| 141 |
+
"step": 2016
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 8.0,
|
| 145 |
+
"eval_accuracy": 0.9137214137214137,
|
| 146 |
+
"eval_f1": 0.7153439153439154,
|
| 147 |
+
"eval_loss": 0.38163959980010986,
|
| 148 |
+
"eval_precision": 0.671078755790867,
|
| 149 |
+
"eval_recall": 0.7658610271903323,
|
| 150 |
+
"eval_runtime": 30.6484,
|
| 151 |
+
"eval_samples_per_second": 16.412,
|
| 152 |
+
"eval_steps_per_second": 2.056,
|
| 153 |
+
"step": 2016
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 9.0,
|
| 157 |
+
"learning_rate": 1.64e-05,
|
| 158 |
+
"loss": 0.0853,
|
| 159 |
+
"step": 2268
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 9.0,
|
| 163 |
+
"eval_accuracy": 0.9104477611940298,
|
| 164 |
+
"eval_f1": 0.7113811638233232,
|
| 165 |
+
"eval_loss": 0.4221731722354889,
|
| 166 |
+
"eval_precision": 0.6637592673353685,
|
| 167 |
+
"eval_recall": 0.7663645518630413,
|
| 168 |
+
"eval_runtime": 29.8305,
|
| 169 |
+
"eval_samples_per_second": 16.862,
|
| 170 |
+
"eval_steps_per_second": 2.112,
|
| 171 |
+
"step": 2268
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 10.0,
|
| 175 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 176 |
+
"loss": 0.0726,
|
| 177 |
+
"step": 2520
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 10.0,
|
| 181 |
+
"eval_accuracy": 0.9108201197753436,
|
| 182 |
+
"eval_f1": 0.7088488276187108,
|
| 183 |
+
"eval_loss": 0.45063257217407227,
|
| 184 |
+
"eval_precision": 0.6662236987818383,
|
| 185 |
+
"eval_recall": 0.75730110775428,
|
| 186 |
+
"eval_runtime": 31.119,
|
| 187 |
+
"eval_samples_per_second": 16.164,
|
| 188 |
+
"eval_steps_per_second": 2.024,
|
| 189 |
+
"step": 2520
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 11.0,
|
| 193 |
+
"learning_rate": 1.5600000000000003e-05,
|
| 194 |
+
"loss": 0.0625,
|
| 195 |
+
"step": 2772
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 11.0,
|
| 199 |
+
"eval_accuracy": 0.9118596208148447,
|
| 200 |
+
"eval_f1": 0.7197667638483967,
|
| 201 |
+
"eval_loss": 0.465919554233551,
|
| 202 |
+
"eval_precision": 0.6704323267434282,
|
| 203 |
+
"eval_recall": 0.7769385699899295,
|
| 204 |
+
"eval_runtime": 30.3792,
|
| 205 |
+
"eval_samples_per_second": 16.557,
|
| 206 |
+
"eval_steps_per_second": 2.074,
|
| 207 |
+
"step": 2772
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 12.0,
|
| 211 |
+
"learning_rate": 1.5200000000000002e-05,
|
| 212 |
+
"loss": 0.0554,
|
| 213 |
+
"step": 3024
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 12.0,
|
| 217 |
+
"eval_accuracy": 0.9138920780711826,
|
| 218 |
+
"eval_f1": 0.7228513529622126,
|
| 219 |
+
"eval_loss": 0.4619043469429016,
|
| 220 |
+
"eval_precision": 0.6864387593389178,
|
| 221 |
+
"eval_recall": 0.7633434038267876,
|
| 222 |
+
"eval_runtime": 32.0505,
|
| 223 |
+
"eval_samples_per_second": 15.694,
|
| 224 |
+
"eval_steps_per_second": 1.966,
|
| 225 |
+
"step": 3024
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 13.0,
|
| 229 |
+
"learning_rate": 1.48e-05,
|
| 230 |
+
"loss": 0.0468,
|
| 231 |
+
"step": 3276
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 13.0,
|
| 235 |
+
"eval_accuracy": 0.9101840071989326,
|
| 236 |
+
"eval_f1": 0.7200470311581422,
|
| 237 |
+
"eval_loss": 0.5248007774353027,
|
| 238 |
+
"eval_precision": 0.6754908449150673,
|
| 239 |
+
"eval_recall": 0.770896273917422,
|
| 240 |
+
"eval_runtime": 30.3642,
|
| 241 |
+
"eval_samples_per_second": 16.566,
|
| 242 |
+
"eval_steps_per_second": 2.075,
|
| 243 |
+
"step": 3276
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 14.0,
|
| 247 |
+
"learning_rate": 1.4400000000000001e-05,
|
| 248 |
+
"loss": 0.0416,
|
| 249 |
+
"step": 3528
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 14.0,
|
| 253 |
+
"eval_accuracy": 0.9106649703664629,
|
| 254 |
+
"eval_f1": 0.7144713526284701,
|
| 255 |
+
"eval_loss": 0.5338897109031677,
|
| 256 |
+
"eval_precision": 0.6730469619407968,
|
| 257 |
+
"eval_recall": 0.7613293051359517,
|
| 258 |
+
"eval_runtime": 30.627,
|
| 259 |
+
"eval_samples_per_second": 16.423,
|
| 260 |
+
"eval_steps_per_second": 2.057,
|
| 261 |
+
"step": 3528
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 15.0,
|
| 265 |
+
"learning_rate": 1.4e-05,
|
| 266 |
+
"loss": 0.0349,
|
| 267 |
+
"step": 3780
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 15.0,
|
| 271 |
+
"eval_accuracy": 0.9078877959474975,
|
| 272 |
+
"eval_f1": 0.71319108805847,
|
| 273 |
+
"eval_loss": 0.5588390827178955,
|
| 274 |
+
"eval_precision": 0.6705830192861894,
|
| 275 |
+
"eval_recall": 0.7615810674723061,
|
| 276 |
+
"eval_runtime": 30.9024,
|
| 277 |
+
"eval_samples_per_second": 16.277,
|
| 278 |
+
"eval_steps_per_second": 2.039,
|
| 279 |
+
"step": 3780
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 16.0,
|
| 283 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 284 |
+
"loss": 0.0301,
|
| 285 |
+
"step": 4032
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 16.0,
|
| 289 |
+
"eval_accuracy": 0.9083687591150278,
|
| 290 |
+
"eval_f1": 0.7168475696083058,
|
| 291 |
+
"eval_loss": 0.5909355878829956,
|
| 292 |
+
"eval_precision": 0.6745115452930728,
|
| 293 |
+
"eval_recall": 0.7648539778449144,
|
| 294 |
+
"eval_runtime": 31.5608,
|
| 295 |
+
"eval_samples_per_second": 15.938,
|
| 296 |
+
"eval_steps_per_second": 1.996,
|
| 297 |
+
"step": 4032
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 17.0,
|
| 301 |
+
"learning_rate": 1.3200000000000002e-05,
|
| 302 |
+
"loss": 0.0293,
|
| 303 |
+
"step": 4284
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 17.0,
|
| 307 |
+
"eval_accuracy": 0.9139075930120706,
|
| 308 |
+
"eval_f1": 0.7264906201457759,
|
| 309 |
+
"eval_loss": 0.557870090007782,
|
| 310 |
+
"eval_precision": 0.6913804866954741,
|
| 311 |
+
"eval_recall": 0.7653575025176234,
|
| 312 |
+
"eval_runtime": 31.1498,
|
| 313 |
+
"eval_samples_per_second": 16.148,
|
| 314 |
+
"eval_steps_per_second": 2.022,
|
| 315 |
+
"step": 4284
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 18.0,
|
| 319 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 320 |
+
"loss": 0.0264,
|
| 321 |
+
"step": 4536
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 18.0,
|
| 325 |
+
"eval_accuracy": 0.9099047382629473,
|
| 326 |
+
"eval_f1": 0.7172199665631717,
|
| 327 |
+
"eval_loss": 0.5989866256713867,
|
| 328 |
+
"eval_precision": 0.682189913675602,
|
| 329 |
+
"eval_recall": 0.7560422960725075,
|
| 330 |
+
"eval_runtime": 29.8647,
|
| 331 |
+
"eval_samples_per_second": 16.843,
|
| 332 |
+
"eval_steps_per_second": 2.11,
|
| 333 |
+
"step": 4536
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 19.0,
|
| 337 |
+
"learning_rate": 1.2400000000000002e-05,
|
| 338 |
+
"loss": 0.0223,
|
| 339 |
+
"step": 4788
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 19.0,
|
| 343 |
+
"eval_accuracy": 0.9099357681447233,
|
| 344 |
+
"eval_f1": 0.718458082062197,
|
| 345 |
+
"eval_loss": 0.6070677638053894,
|
| 346 |
+
"eval_precision": 0.6773690078037904,
|
| 347 |
+
"eval_recall": 0.7648539778449144,
|
| 348 |
+
"eval_runtime": 30.5876,
|
| 349 |
+
"eval_samples_per_second": 16.445,
|
| 350 |
+
"eval_steps_per_second": 2.06,
|
| 351 |
+
"step": 4788
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 20.0,
|
| 355 |
+
"learning_rate": 1.2e-05,
|
| 356 |
+
"loss": 0.0195,
|
| 357 |
+
"step": 5040
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 20.0,
|
| 361 |
+
"eval_accuracy": 0.9119992552828373,
|
| 362 |
+
"eval_f1": 0.720656439529076,
|
| 363 |
+
"eval_loss": 0.6215817928314209,
|
| 364 |
+
"eval_precision": 0.68289384719405,
|
| 365 |
+
"eval_recall": 0.7628398791540786,
|
| 366 |
+
"eval_runtime": 30.3859,
|
| 367 |
+
"eval_samples_per_second": 16.554,
|
| 368 |
+
"eval_steps_per_second": 2.073,
|
| 369 |
+
"step": 5040
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 21.0,
|
| 373 |
+
"learning_rate": 1.16e-05,
|
| 374 |
+
"loss": 0.0181,
|
| 375 |
+
"step": 5292
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 21.0,
|
| 379 |
+
"eval_accuracy": 0.9089428119278865,
|
| 380 |
+
"eval_f1": 0.7139341380522678,
|
| 381 |
+
"eval_loss": 0.6391084790229797,
|
| 382 |
+
"eval_precision": 0.6678360008770007,
|
| 383 |
+
"eval_recall": 0.7668680765357503,
|
| 384 |
+
"eval_runtime": 31.753,
|
| 385 |
+
"eval_samples_per_second": 15.841,
|
| 386 |
+
"eval_steps_per_second": 1.984,
|
| 387 |
+
"step": 5292
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 22.0,
|
| 391 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 392 |
+
"loss": 0.016,
|
| 393 |
+
"step": 5544
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 22.0,
|
| 397 |
+
"eval_accuracy": 0.9129766965587861,
|
| 398 |
+
"eval_f1": 0.7200477326968974,
|
| 399 |
+
"eval_loss": 0.6382994055747986,
|
| 400 |
+
"eval_precision": 0.684437386569873,
|
| 401 |
+
"eval_recall": 0.7595669687814703,
|
| 402 |
+
"eval_runtime": 30.7224,
|
| 403 |
+
"eval_samples_per_second": 16.372,
|
| 404 |
+
"eval_steps_per_second": 2.051,
|
| 405 |
+
"step": 5544
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 23.0,
|
| 409 |
+
"learning_rate": 1.0800000000000002e-05,
|
| 410 |
+
"loss": 0.0153,
|
| 411 |
+
"step": 5796
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 23.0,
|
| 415 |
+
"eval_accuracy": 0.9136903838396375,
|
| 416 |
+
"eval_f1": 0.7225759942328487,
|
| 417 |
+
"eval_loss": 0.6503807902336121,
|
| 418 |
+
"eval_precision": 0.6911054929901173,
|
| 419 |
+
"eval_recall": 0.7570493454179255,
|
| 420 |
+
"eval_runtime": 30.4671,
|
| 421 |
+
"eval_samples_per_second": 16.51,
|
| 422 |
+
"eval_steps_per_second": 2.068,
|
| 423 |
+
"step": 5796
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 24.0,
|
| 427 |
+
"learning_rate": 1.04e-05,
|
| 428 |
+
"loss": 0.0135,
|
| 429 |
+
"step": 6048
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 24.0,
|
| 433 |
+
"eval_accuracy": 0.911083873770441,
|
| 434 |
+
"eval_f1": 0.7179244165383247,
|
| 435 |
+
"eval_loss": 0.6738658547401428,
|
| 436 |
+
"eval_precision": 0.6780040277466994,
|
| 437 |
+
"eval_recall": 0.7628398791540786,
|
| 438 |
+
"eval_runtime": 31.8247,
|
| 439 |
+
"eval_samples_per_second": 15.805,
|
| 440 |
+
"eval_steps_per_second": 1.98,
|
| 441 |
+
"step": 6048
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 25.0,
|
| 445 |
+
"learning_rate": 1e-05,
|
| 446 |
+
"loss": 0.0103,
|
| 447 |
+
"step": 6300
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 25.0,
|
| 451 |
+
"eval_accuracy": 0.9127284575045769,
|
| 452 |
+
"eval_f1": 0.7242580800192239,
|
| 453 |
+
"eval_loss": 0.677778422832489,
|
| 454 |
+
"eval_precision": 0.6927143185474604,
|
| 455 |
+
"eval_recall": 0.7588116817724069,
|
| 456 |
+
"eval_runtime": 31.5342,
|
| 457 |
+
"eval_samples_per_second": 15.951,
|
| 458 |
+
"eval_steps_per_second": 1.998,
|
| 459 |
+
"step": 6300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 26.0,
|
| 463 |
+
"learning_rate": 9.600000000000001e-06,
|
| 464 |
+
"loss": 0.0109,
|
| 465 |
+
"step": 6552
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 26.0,
|
| 469 |
+
"eval_accuracy": 0.9117665311695162,
|
| 470 |
+
"eval_f1": 0.7213822894168466,
|
| 471 |
+
"eval_loss": 0.6734189987182617,
|
| 472 |
+
"eval_precision": 0.6891334250343879,
|
| 473 |
+
"eval_recall": 0.756797583081571,
|
| 474 |
+
"eval_runtime": 30.9002,
|
| 475 |
+
"eval_samples_per_second": 16.278,
|
| 476 |
+
"eval_steps_per_second": 2.039,
|
| 477 |
+
"step": 6552
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 27.0,
|
| 481 |
+
"learning_rate": 9.200000000000002e-06,
|
| 482 |
+
"loss": 0.0097,
|
| 483 |
+
"step": 6804
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 27.0,
|
| 487 |
+
"eval_accuracy": 0.9124647035094796,
|
| 488 |
+
"eval_f1": 0.7231973434535104,
|
| 489 |
+
"eval_loss": 0.6837841272354126,
|
| 490 |
+
"eval_precision": 0.6836322869955157,
|
| 491 |
+
"eval_recall": 0.7676233635448136,
|
| 492 |
+
"eval_runtime": 30.4438,
|
| 493 |
+
"eval_samples_per_second": 16.522,
|
| 494 |
+
"eval_steps_per_second": 2.069,
|
| 495 |
+
"step": 6804
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 28.0,
|
| 499 |
+
"learning_rate": 8.8e-06,
|
| 500 |
+
"loss": 0.0092,
|
| 501 |
+
"step": 7056
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 28.0,
|
| 505 |
+
"eval_accuracy": 0.9118130759921804,
|
| 506 |
+
"eval_f1": 0.7228887320630439,
|
| 507 |
+
"eval_loss": 0.7063636183738708,
|
| 508 |
+
"eval_precision": 0.6783664459161148,
|
| 509 |
+
"eval_recall": 0.7736656596173213,
|
| 510 |
+
"eval_runtime": 32.0989,
|
| 511 |
+
"eval_samples_per_second": 15.67,
|
| 512 |
+
"eval_steps_per_second": 1.963,
|
| 513 |
+
"step": 7056
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 29.0,
|
| 517 |
+
"learning_rate": 8.400000000000001e-06,
|
| 518 |
+
"loss": 0.0079,
|
| 519 |
+
"step": 7308
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 29.0,
|
| 523 |
+
"eval_accuracy": 0.9113941725882024,
|
| 524 |
+
"eval_f1": 0.7218511450381679,
|
| 525 |
+
"eval_loss": 0.6944219470024109,
|
| 526 |
+
"eval_precision": 0.685856754306437,
|
| 527 |
+
"eval_recall": 0.7618328298086606,
|
| 528 |
+
"eval_runtime": 31.0056,
|
| 529 |
+
"eval_samples_per_second": 16.223,
|
| 530 |
+
"eval_steps_per_second": 2.032,
|
| 531 |
+
"step": 7308
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 30.0,
|
| 535 |
+
"learning_rate": 8.000000000000001e-06,
|
| 536 |
+
"loss": 0.0078,
|
| 537 |
+
"step": 7560
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 30.0,
|
| 541 |
+
"eval_accuracy": 0.9092220808638719,
|
| 542 |
+
"eval_f1": 0.717688679245283,
|
| 543 |
+
"eval_loss": 0.7390450835227966,
|
| 544 |
+
"eval_precision": 0.6750221827861579,
|
| 545 |
+
"eval_recall": 0.7661127895266868,
|
| 546 |
+
"eval_runtime": 32.0929,
|
| 547 |
+
"eval_samples_per_second": 15.673,
|
| 548 |
+
"eval_steps_per_second": 1.963,
|
| 549 |
+
"step": 7560
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 31.0,
|
| 553 |
+
"learning_rate": 7.600000000000001e-06,
|
| 554 |
+
"loss": 0.0066,
|
| 555 |
+
"step": 7812
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 31.0,
|
| 559 |
+
"eval_accuracy": 0.9112235082384336,
|
| 560 |
+
"eval_f1": 0.7232323232323231,
|
| 561 |
+
"eval_loss": 0.7528515458106995,
|
| 562 |
+
"eval_precision": 0.6848975917173081,
|
| 563 |
+
"eval_recall": 0.7661127895266868,
|
| 564 |
+
"eval_runtime": 31.1215,
|
| 565 |
+
"eval_samples_per_second": 16.162,
|
| 566 |
+
"eval_steps_per_second": 2.024,
|
| 567 |
+
"step": 7812
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 32.0,
|
| 571 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 572 |
+
"loss": 0.0061,
|
| 573 |
+
"step": 8064
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 32.0,
|
| 577 |
+
"eval_accuracy": 0.9128680919725696,
|
| 578 |
+
"eval_f1": 0.7292161520190024,
|
| 579 |
+
"eval_loss": 0.7525067925453186,
|
| 580 |
+
"eval_precision": 0.6901978417266187,
|
| 581 |
+
"eval_recall": 0.7729103726082578,
|
| 582 |
+
"eval_runtime": 30.5355,
|
| 583 |
+
"eval_samples_per_second": 16.473,
|
| 584 |
+
"eval_steps_per_second": 2.063,
|
| 585 |
+
"step": 8064
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 33.0,
|
| 589 |
+
"learning_rate": 6.800000000000001e-06,
|
| 590 |
+
"loss": 0.005,
|
| 591 |
+
"step": 8316
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 33.0,
|
| 595 |
+
"eval_accuracy": 0.9131939057312192,
|
| 596 |
+
"eval_f1": 0.7289473684210527,
|
| 597 |
+
"eval_loss": 0.7354016304016113,
|
| 598 |
+
"eval_precision": 0.6943938012762079,
|
| 599 |
+
"eval_recall": 0.7671198388721048,
|
| 600 |
+
"eval_runtime": 30.6675,
|
| 601 |
+
"eval_samples_per_second": 16.402,
|
| 602 |
+
"eval_steps_per_second": 2.054,
|
| 603 |
+
"step": 8316
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 34.0,
|
| 607 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 608 |
+
"loss": 0.0059,
|
| 609 |
+
"step": 8568
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 34.0,
|
| 613 |
+
"eval_accuracy": 0.9108666645980079,
|
| 614 |
+
"eval_f1": 0.723687336659539,
|
| 615 |
+
"eval_loss": 0.7652931809425354,
|
| 616 |
+
"eval_precision": 0.6851102114260009,
|
| 617 |
+
"eval_recall": 0.7668680765357503,
|
| 618 |
+
"eval_runtime": 31.9436,
|
| 619 |
+
"eval_samples_per_second": 15.747,
|
| 620 |
+
"eval_steps_per_second": 1.972,
|
| 621 |
+
"step": 8568
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 35.0,
|
| 625 |
+
"learning_rate": 6e-06,
|
| 626 |
+
"loss": 0.0047,
|
| 627 |
+
"step": 8820
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 35.0,
|
| 631 |
+
"eval_accuracy": 0.9116113817606355,
|
| 632 |
+
"eval_f1": 0.7277705035114866,
|
| 633 |
+
"eval_loss": 0.7705232501029968,
|
| 634 |
+
"eval_precision": 0.6902235267554753,
|
| 635 |
+
"eval_recall": 0.7696374622356495,
|
| 636 |
+
"eval_runtime": 30.572,
|
| 637 |
+
"eval_samples_per_second": 16.453,
|
| 638 |
+
"eval_steps_per_second": 2.061,
|
| 639 |
+
"step": 8820
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 36.0,
|
| 643 |
+
"learning_rate": 5.600000000000001e-06,
|
| 644 |
+
"loss": 0.0049,
|
| 645 |
+
"step": 9072
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 36.0,
|
| 649 |
+
"eval_accuracy": 0.9124336736277034,
|
| 650 |
+
"eval_f1": 0.7295733911785972,
|
| 651 |
+
"eval_loss": 0.7525166273117065,
|
| 652 |
+
"eval_precision": 0.6997226074895978,
|
| 653 |
+
"eval_recall": 0.7620845921450151,
|
| 654 |
+
"eval_runtime": 30.7353,
|
| 655 |
+
"eval_samples_per_second": 16.366,
|
| 656 |
+
"eval_steps_per_second": 2.05,
|
| 657 |
+
"step": 9072
|
| 658 |
+
}
|
| 659 |
+
],
|
| 660 |
+
"logging_steps": 500,
|
| 661 |
+
"max_steps": 12600,
|
| 662 |
+
"num_train_epochs": 50,
|
| 663 |
+
"save_steps": 500,
|
| 664 |
+
"total_flos": 3.469062692905536e+16,
|
| 665 |
+
"trial_name": null,
|
| 666 |
+
"trial_params": null
|
| 667 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f2a53f67b72df3731a22e15fcd641c1c36da21621bbfbcbdfddbde9cf04d603
|
| 3 |
+
size 4600
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|