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 sha256:067ad937a4aafc747cc081c0e95c7fe00364b02ec3b3707b515063e119b4cdf2
|
| 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": 0.6611545464384188,
|
| 3 |
+
"best_model_checkpoint": "../saved_model/tibetan-bert_tncc-document_v3/checkpoint-3234",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4620,
|
| 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": 0.6271739130434782,
|
| 14 |
+
"eval_loss": 1.15811288356781,
|
| 15 |
+
"eval_macro-f1": 0.5321491435605941,
|
| 16 |
+
"eval_macro-precision": 0.5499509034708364,
|
| 17 |
+
"eval_macro-recall": 0.5513303846525741,
|
| 18 |
+
"eval_runtime": 7.2664,
|
| 19 |
+
"eval_samples_per_second": 126.61,
|
| 20 |
+
"eval_steps_per_second": 3.991,
|
| 21 |
+
"eval_weighted-f1": 0.6286606311348418,
|
| 22 |
+
"eval_weighted-precision": 0.6570526714130747,
|
| 23 |
+
"eval_weighted-recall": 0.6271739130434782,
|
| 24 |
+
"step": 231
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.6467391304347826,
|
| 29 |
+
"eval_loss": 1.068244218826294,
|
| 30 |
+
"eval_macro-f1": 0.5647362494157037,
|
| 31 |
+
"eval_macro-precision": 0.6183747770237591,
|
| 32 |
+
"eval_macro-recall": 0.5557985823725112,
|
| 33 |
+
"eval_runtime": 7.286,
|
| 34 |
+
"eval_samples_per_second": 126.269,
|
| 35 |
+
"eval_steps_per_second": 3.98,
|
| 36 |
+
"eval_weighted-f1": 0.6340133102826743,
|
| 37 |
+
"eval_weighted-precision": 0.661646599688849,
|
| 38 |
+
"eval_weighted-recall": 0.6467391304347826,
|
| 39 |
+
"step": 462
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.16,
|
| 43 |
+
"learning_rate": 4.458874458874459e-05,
|
| 44 |
+
"loss": 1.1735,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.0,
|
| 49 |
+
"eval_accuracy": 0.6760869565217391,
|
| 50 |
+
"eval_loss": 0.9934693574905396,
|
| 51 |
+
"eval_macro-f1": 0.5945571067918397,
|
| 52 |
+
"eval_macro-precision": 0.6219488737703451,
|
| 53 |
+
"eval_macro-recall": 0.5845017075090547,
|
| 54 |
+
"eval_runtime": 7.2737,
|
| 55 |
+
"eval_samples_per_second": 126.483,
|
| 56 |
+
"eval_steps_per_second": 3.987,
|
| 57 |
+
"eval_weighted-f1": 0.6693675078151828,
|
| 58 |
+
"eval_weighted-precision": 0.6716730940106624,
|
| 59 |
+
"eval_weighted-recall": 0.6760869565217391,
|
| 60 |
+
"step": 693
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.0,
|
| 64 |
+
"eval_accuracy": 0.6760869565217391,
|
| 65 |
+
"eval_loss": 1.0614756345748901,
|
| 66 |
+
"eval_macro-f1": 0.6069076519660962,
|
| 67 |
+
"eval_macro-precision": 0.6513367891333143,
|
| 68 |
+
"eval_macro-recall": 0.5927988194005301,
|
| 69 |
+
"eval_runtime": 7.33,
|
| 70 |
+
"eval_samples_per_second": 125.511,
|
| 71 |
+
"eval_steps_per_second": 3.956,
|
| 72 |
+
"eval_weighted-f1": 0.668192819938365,
|
| 73 |
+
"eval_weighted-precision": 0.6913129775105903,
|
| 74 |
+
"eval_weighted-recall": 0.6760869565217391,
|
| 75 |
+
"step": 924
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 4.33,
|
| 79 |
+
"learning_rate": 3.917748917748918e-05,
|
| 80 |
+
"loss": 0.6662,
|
| 81 |
+
"step": 1000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 5.0,
|
| 85 |
+
"eval_accuracy": 0.6608695652173913,
|
| 86 |
+
"eval_loss": 1.1701490879058838,
|
| 87 |
+
"eval_macro-f1": 0.594957375773476,
|
| 88 |
+
"eval_macro-precision": 0.6170952632020997,
|
| 89 |
+
"eval_macro-recall": 0.6011833102671116,
|
| 90 |
+
"eval_runtime": 7.2756,
|
| 91 |
+
"eval_samples_per_second": 126.45,
|
| 92 |
+
"eval_steps_per_second": 3.986,
|
| 93 |
+
"eval_weighted-f1": 0.6654696189795196,
|
| 94 |
+
"eval_weighted-precision": 0.6851333084994409,
|
| 95 |
+
"eval_weighted-recall": 0.6608695652173913,
|
| 96 |
+
"step": 1155
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 6.0,
|
| 100 |
+
"eval_accuracy": 0.6510869565217391,
|
| 101 |
+
"eval_loss": 1.292517066001892,
|
| 102 |
+
"eval_macro-f1": 0.607937784808065,
|
| 103 |
+
"eval_macro-precision": 0.630719857369284,
|
| 104 |
+
"eval_macro-recall": 0.6225829586625629,
|
| 105 |
+
"eval_runtime": 7.2833,
|
| 106 |
+
"eval_samples_per_second": 126.317,
|
| 107 |
+
"eval_steps_per_second": 3.982,
|
| 108 |
+
"eval_weighted-f1": 0.6579657588719497,
|
| 109 |
+
"eval_weighted-precision": 0.68649865311892,
|
| 110 |
+
"eval_weighted-recall": 0.6510869565217391,
|
| 111 |
+
"step": 1386
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.49,
|
| 115 |
+
"learning_rate": 3.376623376623377e-05,
|
| 116 |
+
"loss": 0.3247,
|
| 117 |
+
"step": 1500
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 7.0,
|
| 121 |
+
"eval_accuracy": 0.6695652173913044,
|
| 122 |
+
"eval_loss": 1.3797581195831299,
|
| 123 |
+
"eval_macro-f1": 0.6129092280782845,
|
| 124 |
+
"eval_macro-precision": 0.6387021571282967,
|
| 125 |
+
"eval_macro-recall": 0.609094564757661,
|
| 126 |
+
"eval_runtime": 7.2749,
|
| 127 |
+
"eval_samples_per_second": 126.461,
|
| 128 |
+
"eval_steps_per_second": 3.986,
|
| 129 |
+
"eval_weighted-f1": 0.6640159054651581,
|
| 130 |
+
"eval_weighted-precision": 0.6700483998986603,
|
| 131 |
+
"eval_weighted-recall": 0.6695652173913044,
|
| 132 |
+
"step": 1617
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 8.0,
|
| 136 |
+
"eval_accuracy": 0.6706521739130434,
|
| 137 |
+
"eval_loss": 1.4838347434997559,
|
| 138 |
+
"eval_macro-f1": 0.6061542359667785,
|
| 139 |
+
"eval_macro-precision": 0.611272244576803,
|
| 140 |
+
"eval_macro-recall": 0.6146650230118652,
|
| 141 |
+
"eval_runtime": 7.2825,
|
| 142 |
+
"eval_samples_per_second": 126.33,
|
| 143 |
+
"eval_steps_per_second": 3.982,
|
| 144 |
+
"eval_weighted-f1": 0.6720993101087696,
|
| 145 |
+
"eval_weighted-precision": 0.6820628069048843,
|
| 146 |
+
"eval_weighted-recall": 0.6706521739130434,
|
| 147 |
+
"step": 1848
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 8.66,
|
| 151 |
+
"learning_rate": 2.8354978354978357e-05,
|
| 152 |
+
"loss": 0.1507,
|
| 153 |
+
"step": 2000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 9.0,
|
| 157 |
+
"eval_accuracy": 0.6880434782608695,
|
| 158 |
+
"eval_loss": 1.5808299779891968,
|
| 159 |
+
"eval_macro-f1": 0.6506642163845188,
|
| 160 |
+
"eval_macro-precision": 0.6540683372674448,
|
| 161 |
+
"eval_macro-recall": 0.6603270904104771,
|
| 162 |
+
"eval_runtime": 7.2595,
|
| 163 |
+
"eval_samples_per_second": 126.731,
|
| 164 |
+
"eval_steps_per_second": 3.995,
|
| 165 |
+
"eval_weighted-f1": 0.6915267384661025,
|
| 166 |
+
"eval_weighted-precision": 0.7075992309158492,
|
| 167 |
+
"eval_weighted-recall": 0.6880434782608695,
|
| 168 |
+
"step": 2079
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 10.0,
|
| 172 |
+
"eval_accuracy": 0.6717391304347826,
|
| 173 |
+
"eval_loss": 1.650195837020874,
|
| 174 |
+
"eval_macro-f1": 0.6034609083187376,
|
| 175 |
+
"eval_macro-precision": 0.6321546665662738,
|
| 176 |
+
"eval_macro-recall": 0.5917026419660609,
|
| 177 |
+
"eval_runtime": 7.2865,
|
| 178 |
+
"eval_samples_per_second": 126.261,
|
| 179 |
+
"eval_steps_per_second": 3.98,
|
| 180 |
+
"eval_weighted-f1": 0.6684456866047149,
|
| 181 |
+
"eval_weighted-precision": 0.6745276629705688,
|
| 182 |
+
"eval_weighted-recall": 0.6717391304347826,
|
| 183 |
+
"step": 2310
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 10.82,
|
| 187 |
+
"learning_rate": 2.2943722943722946e-05,
|
| 188 |
+
"loss": 0.0896,
|
| 189 |
+
"step": 2500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 11.0,
|
| 193 |
+
"eval_accuracy": 0.6804347826086956,
|
| 194 |
+
"eval_loss": 1.738294005393982,
|
| 195 |
+
"eval_macro-f1": 0.6302114432029545,
|
| 196 |
+
"eval_macro-precision": 0.64659326690522,
|
| 197 |
+
"eval_macro-recall": 0.6353590685660309,
|
| 198 |
+
"eval_runtime": 7.3402,
|
| 199 |
+
"eval_samples_per_second": 125.337,
|
| 200 |
+
"eval_steps_per_second": 3.951,
|
| 201 |
+
"eval_weighted-f1": 0.6820100289567567,
|
| 202 |
+
"eval_weighted-precision": 0.6975783236550734,
|
| 203 |
+
"eval_weighted-recall": 0.6804347826086956,
|
| 204 |
+
"step": 2541
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 12.0,
|
| 208 |
+
"eval_accuracy": 0.6989130434782609,
|
| 209 |
+
"eval_loss": 1.7147595882415771,
|
| 210 |
+
"eval_macro-f1": 0.6515414811628367,
|
| 211 |
+
"eval_macro-precision": 0.6658442974988088,
|
| 212 |
+
"eval_macro-recall": 0.6496260625897462,
|
| 213 |
+
"eval_runtime": 7.2787,
|
| 214 |
+
"eval_samples_per_second": 126.396,
|
| 215 |
+
"eval_steps_per_second": 3.984,
|
| 216 |
+
"eval_weighted-f1": 0.6976782715450106,
|
| 217 |
+
"eval_weighted-precision": 0.7017023034717548,
|
| 218 |
+
"eval_weighted-recall": 0.6989130434782609,
|
| 219 |
+
"step": 2772
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 12.99,
|
| 223 |
+
"learning_rate": 1.7532467532467535e-05,
|
| 224 |
+
"loss": 0.0646,
|
| 225 |
+
"step": 3000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 13.0,
|
| 229 |
+
"eval_accuracy": 0.6891304347826087,
|
| 230 |
+
"eval_loss": 1.7946357727050781,
|
| 231 |
+
"eval_macro-f1": 0.648332711071471,
|
| 232 |
+
"eval_macro-precision": 0.6479765490771864,
|
| 233 |
+
"eval_macro-recall": 0.6515217848664077,
|
| 234 |
+
"eval_runtime": 7.3066,
|
| 235 |
+
"eval_samples_per_second": 125.913,
|
| 236 |
+
"eval_steps_per_second": 3.969,
|
| 237 |
+
"eval_weighted-f1": 0.6915983518325557,
|
| 238 |
+
"eval_weighted-precision": 0.6986485129748002,
|
| 239 |
+
"eval_weighted-recall": 0.6891304347826087,
|
| 240 |
+
"step": 3003
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 14.0,
|
| 244 |
+
"eval_accuracy": 0.7,
|
| 245 |
+
"eval_loss": 1.7724699974060059,
|
| 246 |
+
"eval_macro-f1": 0.6611545464384188,
|
| 247 |
+
"eval_macro-precision": 0.667409141168159,
|
| 248 |
+
"eval_macro-recall": 0.6627804433172214,
|
| 249 |
+
"eval_runtime": 7.2494,
|
| 250 |
+
"eval_samples_per_second": 126.906,
|
| 251 |
+
"eval_steps_per_second": 4.0,
|
| 252 |
+
"eval_weighted-f1": 0.7033455944346818,
|
| 253 |
+
"eval_weighted-precision": 0.7140252489602517,
|
| 254 |
+
"eval_weighted-recall": 0.7,
|
| 255 |
+
"step": 3234
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 15.0,
|
| 259 |
+
"eval_accuracy": 0.6923913043478261,
|
| 260 |
+
"eval_loss": 1.819846510887146,
|
| 261 |
+
"eval_macro-f1": 0.6556012492821643,
|
| 262 |
+
"eval_macro-precision": 0.6602686382879858,
|
| 263 |
+
"eval_macro-recall": 0.6668664107682606,
|
| 264 |
+
"eval_runtime": 7.2775,
|
| 265 |
+
"eval_samples_per_second": 126.418,
|
| 266 |
+
"eval_steps_per_second": 3.985,
|
| 267 |
+
"eval_weighted-f1": 0.6965952163097968,
|
| 268 |
+
"eval_weighted-precision": 0.7083445248462037,
|
| 269 |
+
"eval_weighted-recall": 0.6923913043478261,
|
| 270 |
+
"step": 3465
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 15.15,
|
| 274 |
+
"learning_rate": 1.2121212121212122e-05,
|
| 275 |
+
"loss": 0.042,
|
| 276 |
+
"step": 3500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 16.0,
|
| 280 |
+
"eval_accuracy": 0.6945652173913044,
|
| 281 |
+
"eval_loss": 1.784122109413147,
|
| 282 |
+
"eval_macro-f1": 0.6563585998978742,
|
| 283 |
+
"eval_macro-precision": 0.6655291218706761,
|
| 284 |
+
"eval_macro-recall": 0.6534120619783158,
|
| 285 |
+
"eval_runtime": 7.297,
|
| 286 |
+
"eval_samples_per_second": 126.08,
|
| 287 |
+
"eval_steps_per_second": 3.974,
|
| 288 |
+
"eval_weighted-f1": 0.6949462526633576,
|
| 289 |
+
"eval_weighted-precision": 0.6993999521302994,
|
| 290 |
+
"eval_weighted-recall": 0.6945652173913044,
|
| 291 |
+
"step": 3696
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 17.0,
|
| 295 |
+
"eval_accuracy": 0.6945652173913044,
|
| 296 |
+
"eval_loss": 1.7921020984649658,
|
| 297 |
+
"eval_macro-f1": 0.654978142271046,
|
| 298 |
+
"eval_macro-precision": 0.6614421486999998,
|
| 299 |
+
"eval_macro-recall": 0.657140253465508,
|
| 300 |
+
"eval_runtime": 7.359,
|
| 301 |
+
"eval_samples_per_second": 125.018,
|
| 302 |
+
"eval_steps_per_second": 3.941,
|
| 303 |
+
"eval_weighted-f1": 0.6972072799287201,
|
| 304 |
+
"eval_weighted-precision": 0.705999712282921,
|
| 305 |
+
"eval_weighted-recall": 0.6945652173913044,
|
| 306 |
+
"step": 3927
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 17.32,
|
| 310 |
+
"learning_rate": 6.709956709956711e-06,
|
| 311 |
+
"loss": 0.0314,
|
| 312 |
+
"step": 4000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 18.0,
|
| 316 |
+
"eval_accuracy": 0.6945652173913044,
|
| 317 |
+
"eval_loss": 1.824020266532898,
|
| 318 |
+
"eval_macro-f1": 0.6548614235086001,
|
| 319 |
+
"eval_macro-precision": 0.6544996322588115,
|
| 320 |
+
"eval_macro-recall": 0.660921203092836,
|
| 321 |
+
"eval_runtime": 7.3304,
|
| 322 |
+
"eval_samples_per_second": 125.504,
|
| 323 |
+
"eval_steps_per_second": 3.956,
|
| 324 |
+
"eval_weighted-f1": 0.6960752624759597,
|
| 325 |
+
"eval_weighted-precision": 0.7018632204313372,
|
| 326 |
+
"eval_weighted-recall": 0.6945652173913044,
|
| 327 |
+
"step": 4158
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 19.0,
|
| 331 |
+
"eval_accuracy": 0.6923913043478261,
|
| 332 |
+
"eval_loss": 1.8412573337554932,
|
| 333 |
+
"eval_macro-f1": 0.6506506908222951,
|
| 334 |
+
"eval_macro-precision": 0.6468541951851238,
|
| 335 |
+
"eval_macro-recall": 0.6600299174294355,
|
| 336 |
+
"eval_runtime": 7.2351,
|
| 337 |
+
"eval_samples_per_second": 127.157,
|
| 338 |
+
"eval_steps_per_second": 4.008,
|
| 339 |
+
"eval_weighted-f1": 0.69621624934211,
|
| 340 |
+
"eval_weighted-precision": 0.7054368084525598,
|
| 341 |
+
"eval_weighted-recall": 0.6923913043478261,
|
| 342 |
+
"step": 4389
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 19.48,
|
| 346 |
+
"learning_rate": 1.2987012987012988e-06,
|
| 347 |
+
"loss": 0.0233,
|
| 348 |
+
"step": 4500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 20.0,
|
| 352 |
+
"eval_accuracy": 0.691304347826087,
|
| 353 |
+
"eval_loss": 1.8325966596603394,
|
| 354 |
+
"eval_macro-f1": 0.6463398836192601,
|
| 355 |
+
"eval_macro-precision": 0.6403230244612891,
|
| 356 |
+
"eval_macro-recall": 0.6567581821874694,
|
| 357 |
+
"eval_runtime": 7.2741,
|
| 358 |
+
"eval_samples_per_second": 126.476,
|
| 359 |
+
"eval_steps_per_second": 3.987,
|
| 360 |
+
"eval_weighted-f1": 0.6940975925997279,
|
| 361 |
+
"eval_weighted-precision": 0.7008420722361637,
|
| 362 |
+
"eval_weighted-recall": 0.691304347826087,
|
| 363 |
+
"step": 4620
|
| 364 |
+
}
|
| 365 |
+
],
|
| 366 |
+
"logging_steps": 500,
|
| 367 |
+
"max_steps": 4620,
|
| 368 |
+
"num_input_tokens_seen": 0,
|
| 369 |
+
"num_train_epochs": 20,
|
| 370 |
+
"save_steps": 500,
|
| 371 |
+
"total_flos": 3.87544755290112e+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:d09a8b1217d68c16be078162fca229fc44ec2ee2b8bf5eb7b87dc0918594bfa5
|
| 3 |
+
size 4335
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|