Upload 7 files
Browse files- config.json +55 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +57 -0
- trainer_state.json +375 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "../model/tibetan-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": "Politics",
|
| 14 |
+
"1": "Economics",
|
| 15 |
+
"2": "Education",
|
| 16 |
+
"3": "Tourism",
|
| 17 |
+
"4": "Environment",
|
| 18 |
+
"5": "Language",
|
| 19 |
+
"6": "Literature",
|
| 20 |
+
"7": "Religion",
|
| 21 |
+
"8": "Arts",
|
| 22 |
+
"9": "Medicine",
|
| 23 |
+
"10": "Customs",
|
| 24 |
+
"11": "Instruments"
|
| 25 |
+
},
|
| 26 |
+
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 3072,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"Arts": 8,
|
| 30 |
+
"Customs": 10,
|
| 31 |
+
"Economics": 1,
|
| 32 |
+
"Education": 2,
|
| 33 |
+
"Environment": 4,
|
| 34 |
+
"Instruments": 11,
|
| 35 |
+
"Language": 5,
|
| 36 |
+
"Literature": 6,
|
| 37 |
+
"Medicine": 9,
|
| 38 |
+
"Politics": 0,
|
| 39 |
+
"Religion": 7,
|
| 40 |
+
"Tourism": 3
|
| 41 |
+
},
|
| 42 |
+
"layer_norm_eps": 1e-12,
|
| 43 |
+
"max_position_embeddings": 512,
|
| 44 |
+
"model_type": "bert",
|
| 45 |
+
"num_attention_heads": 12,
|
| 46 |
+
"num_hidden_layers": 12,
|
| 47 |
+
"pad_token_id": 0,
|
| 48 |
+
"position_embedding_type": "absolute",
|
| 49 |
+
"problem_type": "single_label_classification",
|
| 50 |
+
"torch_dtype": "float32",
|
| 51 |
+
"transformers_version": "4.36.2",
|
| 52 |
+
"type_vocab_size": 2,
|
| 53 |
+
"use_cache": true,
|
| 54 |
+
"vocab_size": 32267
|
| 55 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04e476487d8b8d60d2f52616207f8b80a2df4b1e9a2f2b7fe9db4230f499f8bc
|
| 3 |
+
size 443393007
|
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_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 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_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,375 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6057453163676313,
|
| 3 |
+
"best_model_checkpoint": "../saved_model/tibetan-bert_tncc-title_v3/checkpoint-4640",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4640,
|
| 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 |
+
"eval_accuracy": 0.5717367853290184,
|
| 14 |
+
"eval_loss": 1.3059929609298706,
|
| 15 |
+
"eval_macro-f1": 0.4599932337899495,
|
| 16 |
+
"eval_macro-precision": 0.5198165980322329,
|
| 17 |
+
"eval_macro-recall": 0.47524513594607626,
|
| 18 |
+
"eval_runtime": 7.3569,
|
| 19 |
+
"eval_samples_per_second": 126.004,
|
| 20 |
+
"eval_steps_per_second": 3.942,
|
| 21 |
+
"eval_weighted-f1": 0.5542294574300444,
|
| 22 |
+
"eval_weighted-precision": 0.591566389333376,
|
| 23 |
+
"eval_weighted-recall": 0.5717367853290184,
|
| 24 |
+
"step": 232
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.6148867313915858,
|
| 29 |
+
"eval_loss": 1.2135106325149536,
|
| 30 |
+
"eval_macro-f1": 0.5584398853408242,
|
| 31 |
+
"eval_macro-precision": 0.5749611619851209,
|
| 32 |
+
"eval_macro-recall": 0.5695895916407867,
|
| 33 |
+
"eval_runtime": 7.3464,
|
| 34 |
+
"eval_samples_per_second": 126.185,
|
| 35 |
+
"eval_steps_per_second": 3.948,
|
| 36 |
+
"eval_weighted-f1": 0.608666635280638,
|
| 37 |
+
"eval_weighted-precision": 0.6187269920143599,
|
| 38 |
+
"eval_weighted-recall": 0.6148867313915858,
|
| 39 |
+
"step": 464
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.16,
|
| 43 |
+
"learning_rate": 4.461206896551724e-05,
|
| 44 |
+
"loss": 1.2716,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.0,
|
| 49 |
+
"eval_accuracy": 0.6170442286947141,
|
| 50 |
+
"eval_loss": 1.2330070734024048,
|
| 51 |
+
"eval_macro-f1": 0.5516603706806994,
|
| 52 |
+
"eval_macro-precision": 0.575159910949547,
|
| 53 |
+
"eval_macro-recall": 0.5503575961333385,
|
| 54 |
+
"eval_runtime": 7.2744,
|
| 55 |
+
"eval_samples_per_second": 127.433,
|
| 56 |
+
"eval_steps_per_second": 3.987,
|
| 57 |
+
"eval_weighted-f1": 0.6100508919269417,
|
| 58 |
+
"eval_weighted-precision": 0.6247775875728347,
|
| 59 |
+
"eval_weighted-recall": 0.6170442286947141,
|
| 60 |
+
"step": 696
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.0,
|
| 64 |
+
"eval_accuracy": 0.6192017259978425,
|
| 65 |
+
"eval_loss": 1.3646526336669922,
|
| 66 |
+
"eval_macro-f1": 0.5686376693802021,
|
| 67 |
+
"eval_macro-precision": 0.5941264267230656,
|
| 68 |
+
"eval_macro-recall": 0.5623900177716177,
|
| 69 |
+
"eval_runtime": 7.3362,
|
| 70 |
+
"eval_samples_per_second": 126.359,
|
| 71 |
+
"eval_steps_per_second": 3.953,
|
| 72 |
+
"eval_weighted-f1": 0.6165925170578278,
|
| 73 |
+
"eval_weighted-precision": 0.6295963103897588,
|
| 74 |
+
"eval_weighted-recall": 0.6192017259978425,
|
| 75 |
+
"step": 928
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 4.31,
|
| 79 |
+
"learning_rate": 3.922413793103448e-05,
|
| 80 |
+
"loss": 0.5952,
|
| 81 |
+
"step": 1000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 5.0,
|
| 85 |
+
"eval_accuracy": 0.6256742179072277,
|
| 86 |
+
"eval_loss": 1.435981035232544,
|
| 87 |
+
"eval_macro-f1": 0.5864237155073179,
|
| 88 |
+
"eval_macro-precision": 0.641734562145522,
|
| 89 |
+
"eval_macro-recall": 0.5708896457267656,
|
| 90 |
+
"eval_runtime": 7.3366,
|
| 91 |
+
"eval_samples_per_second": 126.353,
|
| 92 |
+
"eval_steps_per_second": 3.953,
|
| 93 |
+
"eval_weighted-f1": 0.6206257136654274,
|
| 94 |
+
"eval_weighted-precision": 0.6340957047257687,
|
| 95 |
+
"eval_weighted-recall": 0.6256742179072277,
|
| 96 |
+
"step": 1160
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 6.0,
|
| 100 |
+
"eval_accuracy": 0.6213592233009708,
|
| 101 |
+
"eval_loss": 1.639809489250183,
|
| 102 |
+
"eval_macro-f1": 0.5665517506857142,
|
| 103 |
+
"eval_macro-precision": 0.579234133027197,
|
| 104 |
+
"eval_macro-recall": 0.5645134686065383,
|
| 105 |
+
"eval_runtime": 7.3778,
|
| 106 |
+
"eval_samples_per_second": 125.647,
|
| 107 |
+
"eval_steps_per_second": 3.931,
|
| 108 |
+
"eval_weighted-f1": 0.61941625450029,
|
| 109 |
+
"eval_weighted-precision": 0.6256700095561613,
|
| 110 |
+
"eval_weighted-recall": 0.6213592233009708,
|
| 111 |
+
"step": 1392
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.47,
|
| 115 |
+
"learning_rate": 3.383620689655172e-05,
|
| 116 |
+
"loss": 0.259,
|
| 117 |
+
"step": 1500
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 7.0,
|
| 121 |
+
"eval_accuracy": 0.6127292340884574,
|
| 122 |
+
"eval_loss": 1.7420923709869385,
|
| 123 |
+
"eval_macro-f1": 0.5600620804632168,
|
| 124 |
+
"eval_macro-precision": 0.580446830474752,
|
| 125 |
+
"eval_macro-recall": 0.5638504244142538,
|
| 126 |
+
"eval_runtime": 7.3417,
|
| 127 |
+
"eval_samples_per_second": 126.265,
|
| 128 |
+
"eval_steps_per_second": 3.95,
|
| 129 |
+
"eval_weighted-f1": 0.609536126843797,
|
| 130 |
+
"eval_weighted-precision": 0.6248423019885316,
|
| 131 |
+
"eval_weighted-recall": 0.6127292340884574,
|
| 132 |
+
"step": 1624
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 8.0,
|
| 136 |
+
"eval_accuracy": 0.6138079827400216,
|
| 137 |
+
"eval_loss": 1.8710674047470093,
|
| 138 |
+
"eval_macro-f1": 0.5822983345441143,
|
| 139 |
+
"eval_macro-precision": 0.5948063750427987,
|
| 140 |
+
"eval_macro-recall": 0.5794954217168365,
|
| 141 |
+
"eval_runtime": 7.3262,
|
| 142 |
+
"eval_samples_per_second": 126.532,
|
| 143 |
+
"eval_steps_per_second": 3.958,
|
| 144 |
+
"eval_weighted-f1": 0.6125939186272255,
|
| 145 |
+
"eval_weighted-precision": 0.6180044167574804,
|
| 146 |
+
"eval_weighted-recall": 0.6138079827400216,
|
| 147 |
+
"step": 1856
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 8.62,
|
| 151 |
+
"learning_rate": 2.844827586206897e-05,
|
| 152 |
+
"loss": 0.1433,
|
| 153 |
+
"step": 2000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 9.0,
|
| 157 |
+
"eval_accuracy": 0.6084142394822006,
|
| 158 |
+
"eval_loss": 1.9591827392578125,
|
| 159 |
+
"eval_macro-f1": 0.5632816067487086,
|
| 160 |
+
"eval_macro-precision": 0.5909968207291227,
|
| 161 |
+
"eval_macro-recall": 0.5509900757560654,
|
| 162 |
+
"eval_runtime": 7.3577,
|
| 163 |
+
"eval_samples_per_second": 125.991,
|
| 164 |
+
"eval_steps_per_second": 3.941,
|
| 165 |
+
"eval_weighted-f1": 0.6058400058395833,
|
| 166 |
+
"eval_weighted-precision": 0.615382962851156,
|
| 167 |
+
"eval_weighted-recall": 0.6084142394822006,
|
| 168 |
+
"step": 2088
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 10.0,
|
| 172 |
+
"eval_accuracy": 0.627831715210356,
|
| 173 |
+
"eval_loss": 1.9844281673431396,
|
| 174 |
+
"eval_macro-f1": 0.5720261323200381,
|
| 175 |
+
"eval_macro-precision": 0.6115468809046185,
|
| 176 |
+
"eval_macro-recall": 0.5521363552960614,
|
| 177 |
+
"eval_runtime": 7.2941,
|
| 178 |
+
"eval_samples_per_second": 127.089,
|
| 179 |
+
"eval_steps_per_second": 3.976,
|
| 180 |
+
"eval_weighted-f1": 0.6186046402157037,
|
| 181 |
+
"eval_weighted-precision": 0.6241715352593074,
|
| 182 |
+
"eval_weighted-recall": 0.627831715210356,
|
| 183 |
+
"step": 2320
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 10.78,
|
| 187 |
+
"learning_rate": 2.306034482758621e-05,
|
| 188 |
+
"loss": 0.0918,
|
| 189 |
+
"step": 2500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 11.0,
|
| 193 |
+
"eval_accuracy": 0.622437971952535,
|
| 194 |
+
"eval_loss": 2.121650218963623,
|
| 195 |
+
"eval_macro-f1": 0.575328889968513,
|
| 196 |
+
"eval_macro-precision": 0.6046131450610978,
|
| 197 |
+
"eval_macro-recall": 0.5644507417595815,
|
| 198 |
+
"eval_runtime": 7.3602,
|
| 199 |
+
"eval_samples_per_second": 125.948,
|
| 200 |
+
"eval_steps_per_second": 3.94,
|
| 201 |
+
"eval_weighted-f1": 0.6210201377968305,
|
| 202 |
+
"eval_weighted-precision": 0.6318263677896466,
|
| 203 |
+
"eval_weighted-recall": 0.622437971952535,
|
| 204 |
+
"step": 2552
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 12.0,
|
| 208 |
+
"eval_accuracy": 0.6148867313915858,
|
| 209 |
+
"eval_loss": 2.1600427627563477,
|
| 210 |
+
"eval_macro-f1": 0.5634622559142987,
|
| 211 |
+
"eval_macro-precision": 0.5755339049051247,
|
| 212 |
+
"eval_macro-recall": 0.5624852754080202,
|
| 213 |
+
"eval_runtime": 7.3312,
|
| 214 |
+
"eval_samples_per_second": 126.446,
|
| 215 |
+
"eval_steps_per_second": 3.956,
|
| 216 |
+
"eval_weighted-f1": 0.611920153364688,
|
| 217 |
+
"eval_weighted-precision": 0.6153916861013311,
|
| 218 |
+
"eval_weighted-recall": 0.6148867313915858,
|
| 219 |
+
"step": 2784
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 12.93,
|
| 223 |
+
"learning_rate": 1.767241379310345e-05,
|
| 224 |
+
"loss": 0.0677,
|
| 225 |
+
"step": 3000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 13.0,
|
| 229 |
+
"eval_accuracy": 0.627831715210356,
|
| 230 |
+
"eval_loss": 2.1390113830566406,
|
| 231 |
+
"eval_macro-f1": 0.5765388673761228,
|
| 232 |
+
"eval_macro-precision": 0.5891444176758638,
|
| 233 |
+
"eval_macro-recall": 0.5793730614376024,
|
| 234 |
+
"eval_runtime": 7.2808,
|
| 235 |
+
"eval_samples_per_second": 127.321,
|
| 236 |
+
"eval_steps_per_second": 3.983,
|
| 237 |
+
"eval_weighted-f1": 0.6268062992828414,
|
| 238 |
+
"eval_weighted-precision": 0.6385775273222236,
|
| 239 |
+
"eval_weighted-recall": 0.627831715210356,
|
| 240 |
+
"step": 3016
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 14.0,
|
| 244 |
+
"eval_accuracy": 0.6440129449838188,
|
| 245 |
+
"eval_loss": 2.148944854736328,
|
| 246 |
+
"eval_macro-f1": 0.6041323498671228,
|
| 247 |
+
"eval_macro-precision": 0.6330168044904465,
|
| 248 |
+
"eval_macro-recall": 0.5906969006063283,
|
| 249 |
+
"eval_runtime": 7.3225,
|
| 250 |
+
"eval_samples_per_second": 126.597,
|
| 251 |
+
"eval_steps_per_second": 3.96,
|
| 252 |
+
"eval_weighted-f1": 0.6385550648663262,
|
| 253 |
+
"eval_weighted-precision": 0.645638414060538,
|
| 254 |
+
"eval_weighted-recall": 0.6440129449838188,
|
| 255 |
+
"step": 3248
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 15.0,
|
| 259 |
+
"eval_accuracy": 0.6353829557713053,
|
| 260 |
+
"eval_loss": 2.176727056503296,
|
| 261 |
+
"eval_macro-f1": 0.5855092053952029,
|
| 262 |
+
"eval_macro-precision": 0.6205452521876899,
|
| 263 |
+
"eval_macro-recall": 0.5749431187067001,
|
| 264 |
+
"eval_runtime": 7.2634,
|
| 265 |
+
"eval_samples_per_second": 127.627,
|
| 266 |
+
"eval_steps_per_second": 3.993,
|
| 267 |
+
"eval_weighted-f1": 0.6299837224200732,
|
| 268 |
+
"eval_weighted-precision": 0.6440851231945072,
|
| 269 |
+
"eval_weighted-recall": 0.6353829557713053,
|
| 270 |
+
"step": 3480
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 15.09,
|
| 274 |
+
"learning_rate": 1.228448275862069e-05,
|
| 275 |
+
"loss": 0.0481,
|
| 276 |
+
"step": 3500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 16.0,
|
| 280 |
+
"eval_accuracy": 0.6343042071197411,
|
| 281 |
+
"eval_loss": 2.2005436420440674,
|
| 282 |
+
"eval_macro-f1": 0.5953777118862926,
|
| 283 |
+
"eval_macro-precision": 0.6279439331751326,
|
| 284 |
+
"eval_macro-recall": 0.5827314498455615,
|
| 285 |
+
"eval_runtime": 7.3585,
|
| 286 |
+
"eval_samples_per_second": 125.977,
|
| 287 |
+
"eval_steps_per_second": 3.941,
|
| 288 |
+
"eval_weighted-f1": 0.6295400705432875,
|
| 289 |
+
"eval_weighted-precision": 0.6407972206921422,
|
| 290 |
+
"eval_weighted-recall": 0.6343042071197411,
|
| 291 |
+
"step": 3712
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 17.0,
|
| 295 |
+
"eval_accuracy": 0.6353829557713053,
|
| 296 |
+
"eval_loss": 2.2075998783111572,
|
| 297 |
+
"eval_macro-f1": 0.5922748273767572,
|
| 298 |
+
"eval_macro-precision": 0.6185327701706522,
|
| 299 |
+
"eval_macro-recall": 0.5831902307851583,
|
| 300 |
+
"eval_runtime": 7.315,
|
| 301 |
+
"eval_samples_per_second": 126.726,
|
| 302 |
+
"eval_steps_per_second": 3.964,
|
| 303 |
+
"eval_weighted-f1": 0.6292221063855338,
|
| 304 |
+
"eval_weighted-precision": 0.640744637974118,
|
| 305 |
+
"eval_weighted-recall": 0.6353829557713053,
|
| 306 |
+
"step": 3944
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 17.24,
|
| 310 |
+
"learning_rate": 6.896551724137932e-06,
|
| 311 |
+
"loss": 0.0344,
|
| 312 |
+
"step": 4000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 18.0,
|
| 316 |
+
"eval_accuracy": 0.639697950377562,
|
| 317 |
+
"eval_loss": 2.186396598815918,
|
| 318 |
+
"eval_macro-f1": 0.5937344000879472,
|
| 319 |
+
"eval_macro-precision": 0.6082172147504935,
|
| 320 |
+
"eval_macro-recall": 0.586912298660763,
|
| 321 |
+
"eval_runtime": 7.2683,
|
| 322 |
+
"eval_samples_per_second": 127.54,
|
| 323 |
+
"eval_steps_per_second": 3.99,
|
| 324 |
+
"eval_weighted-f1": 0.6356937811215412,
|
| 325 |
+
"eval_weighted-precision": 0.6386402558809051,
|
| 326 |
+
"eval_weighted-recall": 0.639697950377562,
|
| 327 |
+
"step": 4176
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 19.0,
|
| 331 |
+
"eval_accuracy": 0.6461704422869471,
|
| 332 |
+
"eval_loss": 2.172349691390991,
|
| 333 |
+
"eval_macro-f1": 0.6048666691904897,
|
| 334 |
+
"eval_macro-precision": 0.6140548549534073,
|
| 335 |
+
"eval_macro-recall": 0.6011637605520835,
|
| 336 |
+
"eval_runtime": 7.3386,
|
| 337 |
+
"eval_samples_per_second": 126.318,
|
| 338 |
+
"eval_steps_per_second": 3.952,
|
| 339 |
+
"eval_weighted-f1": 0.6432377710619339,
|
| 340 |
+
"eval_weighted-precision": 0.6448782718814935,
|
| 341 |
+
"eval_weighted-recall": 0.6461704422869471,
|
| 342 |
+
"step": 4408
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 19.4,
|
| 346 |
+
"learning_rate": 1.5086206896551726e-06,
|
| 347 |
+
"loss": 0.0272,
|
| 348 |
+
"step": 4500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 20.0,
|
| 352 |
+
"eval_accuracy": 0.6461704422869471,
|
| 353 |
+
"eval_loss": 2.182253837585449,
|
| 354 |
+
"eval_macro-f1": 0.6057453163676313,
|
| 355 |
+
"eval_macro-precision": 0.6251264122566944,
|
| 356 |
+
"eval_macro-recall": 0.5956135892129149,
|
| 357 |
+
"eval_runtime": 7.2862,
|
| 358 |
+
"eval_samples_per_second": 127.227,
|
| 359 |
+
"eval_steps_per_second": 3.98,
|
| 360 |
+
"eval_weighted-f1": 0.6423371190506697,
|
| 361 |
+
"eval_weighted-precision": 0.645041986434426,
|
| 362 |
+
"eval_weighted-recall": 0.6461704422869471,
|
| 363 |
+
"step": 4640
|
| 364 |
+
}
|
| 365 |
+
],
|
| 366 |
+
"logging_steps": 500,
|
| 367 |
+
"max_steps": 4640,
|
| 368 |
+
"num_input_tokens_seen": 0,
|
| 369 |
+
"num_train_epochs": 20,
|
| 370 |
+
"save_steps": 500,
|
| 371 |
+
"total_flos": 3.90597117566976e+16,
|
| 372 |
+
"train_batch_size": 32,
|
| 373 |
+
"trial_name": null,
|
| 374 |
+
"trial_params": null
|
| 375 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8baded73932b11fa0855701a78474f2c24dbe084ee26a21f4d74720ae6b8d2fe
|
| 3 |
+
size 4335
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|