Commit
•
ee8f6a7
1
Parent(s):
6ca4dba
model init
Browse files- config.json +41 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- trainer_state.json +457 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "negative",
|
| 14 |
+
"1": "neutral",
|
| 15 |
+
"2": "positive"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"negative": 0,
|
| 21 |
+
"neutral": 1,
|
| 22 |
+
"positive": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"pooler_fc_size": 768,
|
| 31 |
+
"pooler_num_attention_heads": 12,
|
| 32 |
+
"pooler_num_fc_layers": 3,
|
| 33 |
+
"pooler_size_per_head": 128,
|
| 34 |
+
"pooler_type": "first_token_transform",
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.21.0.dev0",
|
| 38 |
+
"type_vocab_size": 2,
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 119547
|
| 41 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ed77b30f2e050c50b9b4c6041ea2f4e10e9f41413b5565af17f7fb5b86f4fb6
|
| 3 |
+
size 711493997
|
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 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_lower_case": false,
|
| 4 |
+
"mask_token": "[MASK]",
|
| 5 |
+
"model_max_length": 512,
|
| 6 |
+
"name_or_path": "bert-base-multilingual-cased",
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"special_tokens_map_file": null,
|
| 10 |
+
"strip_accents": null,
|
| 11 |
+
"tokenize_chinese_chars": true,
|
| 12 |
+
"tokenizer_class": "BertTokenizer",
|
| 13 |
+
"unk_token": "[UNK]"
|
| 14 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,457 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7886478688599108,
|
| 3 |
+
"best_model_checkpoint": "/home/bram/shares/predict/trained/dutch/hebban-reviews/bert-base-multilingual-cased/checkpoint-11000",
|
| 4 |
+
"epoch": 3.9447731755424065,
|
| 5 |
+
"global_step": 12000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.16,
|
| 12 |
+
"learning_rate": 4.793333333333334e-05,
|
| 13 |
+
"loss": 0.9625,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"eval_accuracy": 0.6706114398422091,
|
| 19 |
+
"eval_f1": 0.6931944548479266,
|
| 20 |
+
"eval_loss": 0.8083919882774353,
|
| 21 |
+
"eval_precision": 0.7343487735413422,
|
| 22 |
+
"eval_recall": 0.6706114398422091,
|
| 23 |
+
"eval_runtime": 24.6562,
|
| 24 |
+
"eval_samples_per_second": 658.009,
|
| 25 |
+
"eval_steps_per_second": 27.417,
|
| 26 |
+
"step": 500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.33,
|
| 30 |
+
"learning_rate": 4.585e-05,
|
| 31 |
+
"loss": 0.8186,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.33,
|
| 36 |
+
"eval_accuracy": 0.6870685404339251,
|
| 37 |
+
"eval_f1": 0.7088564060365691,
|
| 38 |
+
"eval_loss": 0.7797691226005554,
|
| 39 |
+
"eval_precision": 0.753903679506183,
|
| 40 |
+
"eval_recall": 0.6870685404339251,
|
| 41 |
+
"eval_runtime": 24.786,
|
| 42 |
+
"eval_samples_per_second": 654.562,
|
| 43 |
+
"eval_steps_per_second": 27.273,
|
| 44 |
+
"step": 1000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.49,
|
| 48 |
+
"learning_rate": 4.376666666666667e-05,
|
| 49 |
+
"loss": 0.7658,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.49,
|
| 54 |
+
"eval_accuracy": 0.7040803747534516,
|
| 55 |
+
"eval_f1": 0.7250925730375316,
|
| 56 |
+
"eval_loss": 0.7284208536148071,
|
| 57 |
+
"eval_precision": 0.777831708888876,
|
| 58 |
+
"eval_recall": 0.7040803747534516,
|
| 59 |
+
"eval_runtime": 24.7754,
|
| 60 |
+
"eval_samples_per_second": 654.842,
|
| 61 |
+
"eval_steps_per_second": 27.285,
|
| 62 |
+
"step": 1500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.66,
|
| 66 |
+
"learning_rate": 4.1683333333333335e-05,
|
| 67 |
+
"loss": 0.7318,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.66,
|
| 72 |
+
"eval_accuracy": 0.7891395463510849,
|
| 73 |
+
"eval_f1": 0.7822709378126483,
|
| 74 |
+
"eval_loss": 0.7148900032043457,
|
| 75 |
+
"eval_precision": 0.7780706309716242,
|
| 76 |
+
"eval_recall": 0.7891395463510849,
|
| 77 |
+
"eval_runtime": 24.6279,
|
| 78 |
+
"eval_samples_per_second": 658.766,
|
| 79 |
+
"eval_steps_per_second": 27.449,
|
| 80 |
+
"step": 2000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.82,
|
| 84 |
+
"learning_rate": 3.960000000000001e-05,
|
| 85 |
+
"loss": 0.6977,
|
| 86 |
+
"step": 2500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.82,
|
| 90 |
+
"eval_accuracy": 0.7249753451676528,
|
| 91 |
+
"eval_f1": 0.7429677966966411,
|
| 92 |
+
"eval_loss": 0.6928562521934509,
|
| 93 |
+
"eval_precision": 0.7807492770659993,
|
| 94 |
+
"eval_recall": 0.7249753451676528,
|
| 95 |
+
"eval_runtime": 24.6337,
|
| 96 |
+
"eval_samples_per_second": 658.61,
|
| 97 |
+
"eval_steps_per_second": 27.442,
|
| 98 |
+
"step": 2500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.99,
|
| 102 |
+
"learning_rate": 3.7516666666666666e-05,
|
| 103 |
+
"loss": 0.7032,
|
| 104 |
+
"step": 3000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.99,
|
| 108 |
+
"eval_accuracy": 0.7484590729783037,
|
| 109 |
+
"eval_f1": 0.7594497306385251,
|
| 110 |
+
"eval_loss": 0.6671503782272339,
|
| 111 |
+
"eval_precision": 0.7788847542194782,
|
| 112 |
+
"eval_recall": 0.7484590729783037,
|
| 113 |
+
"eval_runtime": 24.5732,
|
| 114 |
+
"eval_samples_per_second": 660.231,
|
| 115 |
+
"eval_steps_per_second": 27.51,
|
| 116 |
+
"step": 3000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.15,
|
| 120 |
+
"learning_rate": 3.543333333333333e-05,
|
| 121 |
+
"loss": 0.6227,
|
| 122 |
+
"step": 3500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.15,
|
| 126 |
+
"eval_accuracy": 0.7747781065088757,
|
| 127 |
+
"eval_f1": 0.7788314002376725,
|
| 128 |
+
"eval_loss": 0.6905977129936218,
|
| 129 |
+
"eval_precision": 0.7840673104698108,
|
| 130 |
+
"eval_recall": 0.7747781065088757,
|
| 131 |
+
"eval_runtime": 24.7721,
|
| 132 |
+
"eval_samples_per_second": 654.931,
|
| 133 |
+
"eval_steps_per_second": 27.289,
|
| 134 |
+
"step": 3500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.31,
|
| 138 |
+
"learning_rate": 3.3350000000000004e-05,
|
| 139 |
+
"loss": 0.6309,
|
| 140 |
+
"step": 4000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.31,
|
| 144 |
+
"eval_accuracy": 0.7607864891518737,
|
| 145 |
+
"eval_f1": 0.7709664128632473,
|
| 146 |
+
"eval_loss": 0.6686555743217468,
|
| 147 |
+
"eval_precision": 0.7878354043029604,
|
| 148 |
+
"eval_recall": 0.7607864891518737,
|
| 149 |
+
"eval_runtime": 24.6117,
|
| 150 |
+
"eval_samples_per_second": 659.198,
|
| 151 |
+
"eval_steps_per_second": 27.467,
|
| 152 |
+
"step": 4000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.48,
|
| 156 |
+
"learning_rate": 3.126666666666666e-05,
|
| 157 |
+
"loss": 0.6256,
|
| 158 |
+
"step": 4500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.48,
|
| 162 |
+
"eval_accuracy": 0.6715359960552268,
|
| 163 |
+
"eval_f1": 0.7001277240194975,
|
| 164 |
+
"eval_loss": 0.6691098809242249,
|
| 165 |
+
"eval_precision": 0.7948795089365344,
|
| 166 |
+
"eval_recall": 0.6715359960552268,
|
| 167 |
+
"eval_runtime": 24.6266,
|
| 168 |
+
"eval_samples_per_second": 658.801,
|
| 169 |
+
"eval_steps_per_second": 27.45,
|
| 170 |
+
"step": 4500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.64,
|
| 174 |
+
"learning_rate": 2.91875e-05,
|
| 175 |
+
"loss": 0.6152,
|
| 176 |
+
"step": 5000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.64,
|
| 180 |
+
"eval_accuracy": 0.7810034516765286,
|
| 181 |
+
"eval_f1": 0.7815583569804468,
|
| 182 |
+
"eval_loss": 0.6452860832214355,
|
| 183 |
+
"eval_precision": 0.7840264023525906,
|
| 184 |
+
"eval_recall": 0.7810034516765286,
|
| 185 |
+
"eval_runtime": 24.5688,
|
| 186 |
+
"eval_samples_per_second": 660.348,
|
| 187 |
+
"eval_steps_per_second": 27.515,
|
| 188 |
+
"step": 5000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.81,
|
| 192 |
+
"learning_rate": 2.710416666666667e-05,
|
| 193 |
+
"loss": 0.6068,
|
| 194 |
+
"step": 5500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.81,
|
| 198 |
+
"eval_accuracy": 0.7764423076923077,
|
| 199 |
+
"eval_f1": 0.7843276562987542,
|
| 200 |
+
"eval_loss": 0.6676753759384155,
|
| 201 |
+
"eval_precision": 0.8001617824983851,
|
| 202 |
+
"eval_recall": 0.7764423076923077,
|
| 203 |
+
"eval_runtime": 24.7224,
|
| 204 |
+
"eval_samples_per_second": 656.247,
|
| 205 |
+
"eval_steps_per_second": 27.344,
|
| 206 |
+
"step": 5500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.97,
|
| 210 |
+
"learning_rate": 2.5020833333333333e-05,
|
| 211 |
+
"loss": 0.6016,
|
| 212 |
+
"step": 6000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.97,
|
| 216 |
+
"eval_accuracy": 0.7220784023668639,
|
| 217 |
+
"eval_f1": 0.7405665635983271,
|
| 218 |
+
"eval_loss": 0.6461244821548462,
|
| 219 |
+
"eval_precision": 0.782308061609766,
|
| 220 |
+
"eval_recall": 0.7220784023668639,
|
| 221 |
+
"eval_runtime": 24.6746,
|
| 222 |
+
"eval_samples_per_second": 657.518,
|
| 223 |
+
"eval_steps_per_second": 27.397,
|
| 224 |
+
"step": 6000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.14,
|
| 228 |
+
"learning_rate": 2.2937500000000002e-05,
|
| 229 |
+
"loss": 0.521,
|
| 230 |
+
"step": 6500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.14,
|
| 234 |
+
"eval_accuracy": 0.7281188362919132,
|
| 235 |
+
"eval_f1": 0.7466913370432308,
|
| 236 |
+
"eval_loss": 0.7071252465248108,
|
| 237 |
+
"eval_precision": 0.7878399669333115,
|
| 238 |
+
"eval_recall": 0.7281188362919132,
|
| 239 |
+
"eval_runtime": 24.7635,
|
| 240 |
+
"eval_samples_per_second": 655.158,
|
| 241 |
+
"eval_steps_per_second": 27.298,
|
| 242 |
+
"step": 6500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.3,
|
| 246 |
+
"learning_rate": 2.0854166666666668e-05,
|
| 247 |
+
"loss": 0.5137,
|
| 248 |
+
"step": 7000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.3,
|
| 252 |
+
"eval_accuracy": 0.7346523668639053,
|
| 253 |
+
"eval_f1": 0.752395675119321,
|
| 254 |
+
"eval_loss": 0.6949610114097595,
|
| 255 |
+
"eval_precision": 0.7902262301474485,
|
| 256 |
+
"eval_recall": 0.7346523668639053,
|
| 257 |
+
"eval_runtime": 24.761,
|
| 258 |
+
"eval_samples_per_second": 655.225,
|
| 259 |
+
"eval_steps_per_second": 27.301,
|
| 260 |
+
"step": 7000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.47,
|
| 264 |
+
"learning_rate": 1.8770833333333333e-05,
|
| 265 |
+
"loss": 0.504,
|
| 266 |
+
"step": 7500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.47,
|
| 270 |
+
"eval_accuracy": 0.7453772189349113,
|
| 271 |
+
"eval_f1": 0.7618113431887504,
|
| 272 |
+
"eval_loss": 0.6824287176132202,
|
| 273 |
+
"eval_precision": 0.7979845371909847,
|
| 274 |
+
"eval_recall": 0.7453772189349113,
|
| 275 |
+
"eval_runtime": 24.7586,
|
| 276 |
+
"eval_samples_per_second": 655.287,
|
| 277 |
+
"eval_steps_per_second": 27.304,
|
| 278 |
+
"step": 7500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.63,
|
| 282 |
+
"learning_rate": 1.6691666666666668e-05,
|
| 283 |
+
"loss": 0.5049,
|
| 284 |
+
"step": 8000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.63,
|
| 288 |
+
"eval_accuracy": 0.7816814595660749,
|
| 289 |
+
"eval_f1": 0.7878816281164417,
|
| 290 |
+
"eval_loss": 0.6992799043655396,
|
| 291 |
+
"eval_precision": 0.7967192296633613,
|
| 292 |
+
"eval_recall": 0.7816814595660749,
|
| 293 |
+
"eval_runtime": 24.7558,
|
| 294 |
+
"eval_samples_per_second": 655.361,
|
| 295 |
+
"eval_steps_per_second": 27.307,
|
| 296 |
+
"step": 8000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.79,
|
| 300 |
+
"learning_rate": 1.4608333333333335e-05,
|
| 301 |
+
"loss": 0.4987,
|
| 302 |
+
"step": 8500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.79,
|
| 306 |
+
"eval_accuracy": 0.7680596646942801,
|
| 307 |
+
"eval_f1": 0.779595614035326,
|
| 308 |
+
"eval_loss": 0.7158842086791992,
|
| 309 |
+
"eval_precision": 0.8023493022129313,
|
| 310 |
+
"eval_recall": 0.7680596646942801,
|
| 311 |
+
"eval_runtime": 24.6159,
|
| 312 |
+
"eval_samples_per_second": 659.087,
|
| 313 |
+
"eval_steps_per_second": 27.462,
|
| 314 |
+
"step": 8500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.96,
|
| 318 |
+
"learning_rate": 1.2525000000000001e-05,
|
| 319 |
+
"loss": 0.4978,
|
| 320 |
+
"step": 9000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.96,
|
| 324 |
+
"eval_accuracy": 0.7757026627218935,
|
| 325 |
+
"eval_f1": 0.7846497142505,
|
| 326 |
+
"eval_loss": 0.6755026578903198,
|
| 327 |
+
"eval_precision": 0.7992058416315558,
|
| 328 |
+
"eval_recall": 0.7757026627218935,
|
| 329 |
+
"eval_runtime": 24.6076,
|
| 330 |
+
"eval_samples_per_second": 659.309,
|
| 331 |
+
"eval_steps_per_second": 27.471,
|
| 332 |
+
"step": 9000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.12,
|
| 336 |
+
"learning_rate": 1.0441666666666667e-05,
|
| 337 |
+
"loss": 0.4236,
|
| 338 |
+
"step": 9500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.12,
|
| 342 |
+
"eval_accuracy": 0.7638067061143984,
|
| 343 |
+
"eval_f1": 0.7757104932531658,
|
| 344 |
+
"eval_loss": 0.740465521812439,
|
| 345 |
+
"eval_precision": 0.7974750781708845,
|
| 346 |
+
"eval_recall": 0.7638067061143984,
|
| 347 |
+
"eval_runtime": 24.6338,
|
| 348 |
+
"eval_samples_per_second": 658.607,
|
| 349 |
+
"eval_steps_per_second": 27.442,
|
| 350 |
+
"step": 9500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.29,
|
| 354 |
+
"learning_rate": 8.358333333333333e-06,
|
| 355 |
+
"loss": 0.3987,
|
| 356 |
+
"step": 10000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.29,
|
| 360 |
+
"eval_accuracy": 0.7555473372781065,
|
| 361 |
+
"eval_f1": 0.7701303707262471,
|
| 362 |
+
"eval_loss": 0.7569716572761536,
|
| 363 |
+
"eval_precision": 0.80053210602621,
|
| 364 |
+
"eval_recall": 0.7555473372781065,
|
| 365 |
+
"eval_runtime": 24.6348,
|
| 366 |
+
"eval_samples_per_second": 658.58,
|
| 367 |
+
"eval_steps_per_second": 27.441,
|
| 368 |
+
"step": 10000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.45,
|
| 372 |
+
"learning_rate": 6.275e-06,
|
| 373 |
+
"loss": 0.3914,
|
| 374 |
+
"step": 10500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.45,
|
| 378 |
+
"eval_accuracy": 0.7660256410256411,
|
| 379 |
+
"eval_f1": 0.7781937770368635,
|
| 380 |
+
"eval_loss": 0.7907547354698181,
|
| 381 |
+
"eval_precision": 0.8023937992057022,
|
| 382 |
+
"eval_recall": 0.7660256410256411,
|
| 383 |
+
"eval_runtime": 24.7673,
|
| 384 |
+
"eval_samples_per_second": 655.057,
|
| 385 |
+
"eval_steps_per_second": 27.294,
|
| 386 |
+
"step": 10500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.62,
|
| 390 |
+
"learning_rate": 4.195833333333334e-06,
|
| 391 |
+
"loss": 0.4007,
|
| 392 |
+
"step": 11000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 3.62,
|
| 396 |
+
"eval_accuracy": 0.7821745562130178,
|
| 397 |
+
"eval_f1": 0.7886478688599108,
|
| 398 |
+
"eval_loss": 0.7599502801895142,
|
| 399 |
+
"eval_precision": 0.7983440482619892,
|
| 400 |
+
"eval_recall": 0.7821745562130178,
|
| 401 |
+
"eval_runtime": 24.6844,
|
| 402 |
+
"eval_samples_per_second": 657.258,
|
| 403 |
+
"eval_steps_per_second": 27.386,
|
| 404 |
+
"step": 11000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.78,
|
| 408 |
+
"learning_rate": 2.1125e-06,
|
| 409 |
+
"loss": 0.3878,
|
| 410 |
+
"step": 11500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 3.78,
|
| 414 |
+
"eval_accuracy": 0.7740384615384616,
|
| 415 |
+
"eval_f1": 0.7836077149829459,
|
| 416 |
+
"eval_loss": 0.7647958993911743,
|
| 417 |
+
"eval_precision": 0.8007153395014647,
|
| 418 |
+
"eval_recall": 0.7740384615384616,
|
| 419 |
+
"eval_runtime": 24.6189,
|
| 420 |
+
"eval_samples_per_second": 659.006,
|
| 421 |
+
"eval_steps_per_second": 27.459,
|
| 422 |
+
"step": 11500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.94,
|
| 426 |
+
"learning_rate": 2.916666666666667e-08,
|
| 427 |
+
"loss": 0.3829,
|
| 428 |
+
"step": 12000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.94,
|
| 432 |
+
"eval_accuracy": 0.7662721893491125,
|
| 433 |
+
"eval_f1": 0.7779778325177736,
|
| 434 |
+
"eval_loss": 0.752331018447876,
|
| 435 |
+
"eval_precision": 0.7995290654452684,
|
| 436 |
+
"eval_recall": 0.7662721893491125,
|
| 437 |
+
"eval_runtime": 24.6488,
|
| 438 |
+
"eval_samples_per_second": 658.206,
|
| 439 |
+
"eval_steps_per_second": 27.425,
|
| 440 |
+
"step": 12000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.94,
|
| 444 |
+
"step": 12000,
|
| 445 |
+
"total_flos": 1.502407617014661e+17,
|
| 446 |
+
"train_loss": 0.5753211771647135,
|
| 447 |
+
"train_runtime": 3636.5588,
|
| 448 |
+
"train_samples_per_second": 158.391,
|
| 449 |
+
"train_steps_per_second": 3.3
|
| 450 |
+
}
|
| 451 |
+
],
|
| 452 |
+
"max_steps": 12000,
|
| 453 |
+
"num_train_epochs": 4,
|
| 454 |
+
"total_flos": 1.502407617014661e+17,
|
| 455 |
+
"trial_name": null,
|
| 456 |
+
"trial_params": null
|
| 457 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a1b1bde55632273fa2d79fa4e7449972067ad76fcbd823e01f19e5d013eba50
|
| 3 |
+
size 3439
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|