Commit
•
f1eb16e
1
Parent(s):
a222a26
init model
Browse files- config.json +36 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- trainer_state.json +457 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "GroNLP/bert-base-dutch-cased",
|
| 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": "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": 3,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.21.0.dev0",
|
| 33 |
+
"type_vocab_size": 2,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 30073
|
| 36 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c24b6e7600731f4f827d6ebf7c530b3919a7fcdc81f0ec28aab9b152f169cb40
|
| 3 |
+
size 436629869
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"name_or_path": "GroNLP/bert-base-dutch-cased",
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": "/home/bram/.cache/huggingface/transformers/adb82a117c09b0f8768357de8e836a9e0610730782f82edc49dd0020c48f1d03.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
|
| 12 |
+
"strip_accents": null,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "BertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,457 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8199536621312183,
|
| 3 |
+
"best_model_checkpoint": "/home/bram/shares/predict/trained/dutch/hebban-reviews/bert-base-dutch-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": 4.792083333333334e-05,
|
| 13 |
+
"loss": 0.7371,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"eval_accuracy": 0.7546844181459567,
|
| 19 |
+
"eval_f1": 0.7629915603619231,
|
| 20 |
+
"eval_loss": 0.6527217626571655,
|
| 21 |
+
"eval_precision": 0.7780177612862748,
|
| 22 |
+
"eval_recall": 0.7546844181459567,
|
| 23 |
+
"eval_runtime": 24.4866,
|
| 24 |
+
"eval_samples_per_second": 662.566,
|
| 25 |
+
"eval_steps_per_second": 27.607,
|
| 26 |
+
"step": 500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.33,
|
| 30 |
+
"learning_rate": 4.58375e-05,
|
| 31 |
+
"loss": 0.6457,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.33,
|
| 36 |
+
"eval_accuracy": 0.7643614398422091,
|
| 37 |
+
"eval_f1": 0.7769010779814548,
|
| 38 |
+
"eval_loss": 0.6216204166412354,
|
| 39 |
+
"eval_precision": 0.8017754901402682,
|
| 40 |
+
"eval_recall": 0.7643614398422091,
|
| 41 |
+
"eval_runtime": 24.6912,
|
| 42 |
+
"eval_samples_per_second": 657.077,
|
| 43 |
+
"eval_steps_per_second": 27.378,
|
| 44 |
+
"step": 1000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.49,
|
| 48 |
+
"learning_rate": 4.375416666666667e-05,
|
| 49 |
+
"loss": 0.6184,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.49,
|
| 54 |
+
"eval_accuracy": 0.7790310650887574,
|
| 55 |
+
"eval_f1": 0.789661025567087,
|
| 56 |
+
"eval_loss": 0.6005069017410278,
|
| 57 |
+
"eval_precision": 0.8094066060995802,
|
| 58 |
+
"eval_recall": 0.7790310650887574,
|
| 59 |
+
"eval_runtime": 24.5988,
|
| 60 |
+
"eval_samples_per_second": 659.544,
|
| 61 |
+
"eval_steps_per_second": 27.481,
|
| 62 |
+
"step": 1500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.66,
|
| 66 |
+
"learning_rate": 4.1670833333333334e-05,
|
| 67 |
+
"loss": 0.6042,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.66,
|
| 72 |
+
"eval_accuracy": 0.8077539447731755,
|
| 73 |
+
"eval_f1": 0.8118714417209679,
|
| 74 |
+
"eval_loss": 0.5989466309547424,
|
| 75 |
+
"eval_precision": 0.8220143498287384,
|
| 76 |
+
"eval_recall": 0.8077539447731755,
|
| 77 |
+
"eval_runtime": 24.5976,
|
| 78 |
+
"eval_samples_per_second": 659.577,
|
| 79 |
+
"eval_steps_per_second": 27.482,
|
| 80 |
+
"step": 2000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.82,
|
| 84 |
+
"learning_rate": 3.959166666666667e-05,
|
| 85 |
+
"loss": 0.5744,
|
| 86 |
+
"step": 2500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.82,
|
| 90 |
+
"eval_accuracy": 0.7972140039447732,
|
| 91 |
+
"eval_f1": 0.8043419281165946,
|
| 92 |
+
"eval_loss": 0.5735336542129517,
|
| 93 |
+
"eval_precision": 0.8156333669948874,
|
| 94 |
+
"eval_recall": 0.7972140039447732,
|
| 95 |
+
"eval_runtime": 24.5948,
|
| 96 |
+
"eval_samples_per_second": 659.651,
|
| 97 |
+
"eval_steps_per_second": 27.485,
|
| 98 |
+
"step": 2500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.99,
|
| 102 |
+
"learning_rate": 3.7512500000000004e-05,
|
| 103 |
+
"loss": 0.5833,
|
| 104 |
+
"step": 3000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.99,
|
| 108 |
+
"eval_accuracy": 0.8060281065088757,
|
| 109 |
+
"eval_f1": 0.8074379985793598,
|
| 110 |
+
"eval_loss": 0.5610195994377136,
|
| 111 |
+
"eval_precision": 0.8123421315309852,
|
| 112 |
+
"eval_recall": 0.8060281065088757,
|
| 113 |
+
"eval_runtime": 24.5935,
|
| 114 |
+
"eval_samples_per_second": 659.686,
|
| 115 |
+
"eval_steps_per_second": 27.487,
|
| 116 |
+
"step": 3000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.15,
|
| 120 |
+
"learning_rate": 3.542916666666667e-05,
|
| 121 |
+
"loss": 0.4633,
|
| 122 |
+
"step": 3500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.15,
|
| 126 |
+
"eval_accuracy": 0.8055966469428008,
|
| 127 |
+
"eval_f1": 0.8112577676458685,
|
| 128 |
+
"eval_loss": 0.5967000126838684,
|
| 129 |
+
"eval_precision": 0.8196531984723394,
|
| 130 |
+
"eval_recall": 0.8055966469428008,
|
| 131 |
+
"eval_runtime": 24.7636,
|
| 132 |
+
"eval_samples_per_second": 655.155,
|
| 133 |
+
"eval_steps_per_second": 27.298,
|
| 134 |
+
"step": 3500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.31,
|
| 138 |
+
"learning_rate": 3.3345833333333335e-05,
|
| 139 |
+
"loss": 0.4473,
|
| 140 |
+
"step": 4000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.31,
|
| 144 |
+
"eval_accuracy": 0.8108357988165681,
|
| 145 |
+
"eval_f1": 0.8144157036046853,
|
| 146 |
+
"eval_loss": 0.6390397548675537,
|
| 147 |
+
"eval_precision": 0.8190905659244092,
|
| 148 |
+
"eval_recall": 0.8108357988165681,
|
| 149 |
+
"eval_runtime": 24.7631,
|
| 150 |
+
"eval_samples_per_second": 655.169,
|
| 151 |
+
"eval_steps_per_second": 27.299,
|
| 152 |
+
"step": 4000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.48,
|
| 156 |
+
"learning_rate": 3.12625e-05,
|
| 157 |
+
"loss": 0.4493,
|
| 158 |
+
"step": 4500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.48,
|
| 162 |
+
"eval_accuracy": 0.7642998027613412,
|
| 163 |
+
"eval_f1": 0.780188565362406,
|
| 164 |
+
"eval_loss": 0.6074336171150208,
|
| 165 |
+
"eval_precision": 0.818173356753982,
|
| 166 |
+
"eval_recall": 0.7642998027613412,
|
| 167 |
+
"eval_runtime": 24.6961,
|
| 168 |
+
"eval_samples_per_second": 656.945,
|
| 169 |
+
"eval_steps_per_second": 27.373,
|
| 170 |
+
"step": 4500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.64,
|
| 174 |
+
"learning_rate": 2.917916666666667e-05,
|
| 175 |
+
"loss": 0.4402,
|
| 176 |
+
"step": 5000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.64,
|
| 180 |
+
"eval_accuracy": 0.817430966469428,
|
| 181 |
+
"eval_f1": 0.818650395547064,
|
| 182 |
+
"eval_loss": 0.6175166368484497,
|
| 183 |
+
"eval_precision": 0.8200081119899918,
|
| 184 |
+
"eval_recall": 0.817430966469428,
|
| 185 |
+
"eval_runtime": 24.5978,
|
| 186 |
+
"eval_samples_per_second": 659.57,
|
| 187 |
+
"eval_steps_per_second": 27.482,
|
| 188 |
+
"step": 5000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.81,
|
| 192 |
+
"learning_rate": 2.7100000000000005e-05,
|
| 193 |
+
"loss": 0.4406,
|
| 194 |
+
"step": 5500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.81,
|
| 198 |
+
"eval_accuracy": 0.8167529585798816,
|
| 199 |
+
"eval_f1": 0.8194587497642177,
|
| 200 |
+
"eval_loss": 0.6328938603401184,
|
| 201 |
+
"eval_precision": 0.8229261899048395,
|
| 202 |
+
"eval_recall": 0.8167529585798816,
|
| 203 |
+
"eval_runtime": 24.611,
|
| 204 |
+
"eval_samples_per_second": 659.218,
|
| 205 |
+
"eval_steps_per_second": 27.467,
|
| 206 |
+
"step": 5500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.97,
|
| 210 |
+
"learning_rate": 2.5016666666666667e-05,
|
| 211 |
+
"loss": 0.4457,
|
| 212 |
+
"step": 6000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.97,
|
| 216 |
+
"eval_accuracy": 0.8178007889546351,
|
| 217 |
+
"eval_f1": 0.8196437981366307,
|
| 218 |
+
"eval_loss": 0.6221566796302795,
|
| 219 |
+
"eval_precision": 0.8219923397562409,
|
| 220 |
+
"eval_recall": 0.8178007889546351,
|
| 221 |
+
"eval_runtime": 24.6955,
|
| 222 |
+
"eval_samples_per_second": 656.961,
|
| 223 |
+
"eval_steps_per_second": 27.373,
|
| 224 |
+
"step": 6000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.14,
|
| 228 |
+
"learning_rate": 2.2933333333333333e-05,
|
| 229 |
+
"loss": 0.3013,
|
| 230 |
+
"step": 6500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.14,
|
| 234 |
+
"eval_accuracy": 0.8099112426035503,
|
| 235 |
+
"eval_f1": 0.8154916160650456,
|
| 236 |
+
"eval_loss": 0.7676593661308289,
|
| 237 |
+
"eval_precision": 0.8240038245839082,
|
| 238 |
+
"eval_recall": 0.8099112426035503,
|
| 239 |
+
"eval_runtime": 24.7339,
|
| 240 |
+
"eval_samples_per_second": 655.941,
|
| 241 |
+
"eval_steps_per_second": 27.331,
|
| 242 |
+
"step": 6500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.3,
|
| 246 |
+
"learning_rate": 2.0854166666666668e-05,
|
| 247 |
+
"loss": 0.2875,
|
| 248 |
+
"step": 7000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.3,
|
| 252 |
+
"eval_accuracy": 0.8025764299802761,
|
| 253 |
+
"eval_f1": 0.8097813881432507,
|
| 254 |
+
"eval_loss": 0.7549890279769897,
|
| 255 |
+
"eval_precision": 0.8215043597038734,
|
| 256 |
+
"eval_recall": 0.8025764299802761,
|
| 257 |
+
"eval_runtime": 24.7599,
|
| 258 |
+
"eval_samples_per_second": 655.252,
|
| 259 |
+
"eval_steps_per_second": 27.302,
|
| 260 |
+
"step": 7000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.47,
|
| 264 |
+
"learning_rate": 1.8770833333333333e-05,
|
| 265 |
+
"loss": 0.2804,
|
| 266 |
+
"step": 7500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.47,
|
| 270 |
+
"eval_accuracy": 0.8102194280078896,
|
| 271 |
+
"eval_f1": 0.8148870229811181,
|
| 272 |
+
"eval_loss": 0.804236114025116,
|
| 273 |
+
"eval_precision": 0.8221239914552869,
|
| 274 |
+
"eval_recall": 0.8102194280078896,
|
| 275 |
+
"eval_runtime": 24.6532,
|
| 276 |
+
"eval_samples_per_second": 658.09,
|
| 277 |
+
"eval_steps_per_second": 27.42,
|
| 278 |
+
"step": 7500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.63,
|
| 282 |
+
"learning_rate": 1.66875e-05,
|
| 283 |
+
"loss": 0.2784,
|
| 284 |
+
"step": 8000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.63,
|
| 288 |
+
"eval_accuracy": 0.8136711045364892,
|
| 289 |
+
"eval_f1": 0.8173932526970648,
|
| 290 |
+
"eval_loss": 0.8103494644165039,
|
| 291 |
+
"eval_precision": 0.8223803033268108,
|
| 292 |
+
"eval_recall": 0.8136711045364892,
|
| 293 |
+
"eval_runtime": 24.5862,
|
| 294 |
+
"eval_samples_per_second": 659.883,
|
| 295 |
+
"eval_steps_per_second": 27.495,
|
| 296 |
+
"step": 8000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.79,
|
| 300 |
+
"learning_rate": 1.4604166666666666e-05,
|
| 301 |
+
"loss": 0.275,
|
| 302 |
+
"step": 8500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.79,
|
| 306 |
+
"eval_accuracy": 0.8132396449704142,
|
| 307 |
+
"eval_f1": 0.8172151251977423,
|
| 308 |
+
"eval_loss": 0.8132022619247437,
|
| 309 |
+
"eval_precision": 0.8227088066747076,
|
| 310 |
+
"eval_recall": 0.8132396449704142,
|
| 311 |
+
"eval_runtime": 24.5279,
|
| 312 |
+
"eval_samples_per_second": 661.452,
|
| 313 |
+
"eval_steps_per_second": 27.56,
|
| 314 |
+
"step": 8500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.96,
|
| 318 |
+
"learning_rate": 1.2520833333333334e-05,
|
| 319 |
+
"loss": 0.2651,
|
| 320 |
+
"step": 9000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.96,
|
| 324 |
+
"eval_accuracy": 0.8065212031558185,
|
| 325 |
+
"eval_f1": 0.8120431442321697,
|
| 326 |
+
"eval_loss": 0.7826108336448669,
|
| 327 |
+
"eval_precision": 0.8202960014382004,
|
| 328 |
+
"eval_recall": 0.8065212031558185,
|
| 329 |
+
"eval_runtime": 24.7019,
|
| 330 |
+
"eval_samples_per_second": 656.791,
|
| 331 |
+
"eval_steps_per_second": 27.366,
|
| 332 |
+
"step": 9000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.12,
|
| 336 |
+
"learning_rate": 1.0441666666666667e-05,
|
| 337 |
+
"loss": 0.1855,
|
| 338 |
+
"step": 9500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.12,
|
| 342 |
+
"eval_accuracy": 0.8140409270216963,
|
| 343 |
+
"eval_f1": 0.8173959290765784,
|
| 344 |
+
"eval_loss": 1.0370513200759888,
|
| 345 |
+
"eval_precision": 0.8233538681349268,
|
| 346 |
+
"eval_recall": 0.8140409270216963,
|
| 347 |
+
"eval_runtime": 24.6749,
|
| 348 |
+
"eval_samples_per_second": 657.51,
|
| 349 |
+
"eval_steps_per_second": 27.396,
|
| 350 |
+
"step": 9500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.29,
|
| 354 |
+
"learning_rate": 8.358333333333333e-06,
|
| 355 |
+
"loss": 0.1571,
|
| 356 |
+
"step": 10000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.29,
|
| 360 |
+
"eval_accuracy": 0.8128081854043393,
|
| 361 |
+
"eval_f1": 0.8173020798805183,
|
| 362 |
+
"eval_loss": 1.036438226699829,
|
| 363 |
+
"eval_precision": 0.8246320290318612,
|
| 364 |
+
"eval_recall": 0.8128081854043393,
|
| 365 |
+
"eval_runtime": 24.6314,
|
| 366 |
+
"eval_samples_per_second": 658.672,
|
| 367 |
+
"eval_steps_per_second": 27.445,
|
| 368 |
+
"step": 10000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.45,
|
| 372 |
+
"learning_rate": 6.275e-06,
|
| 373 |
+
"loss": 0.1608,
|
| 374 |
+
"step": 10500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.45,
|
| 378 |
+
"eval_accuracy": 0.8108357988165681,
|
| 379 |
+
"eval_f1": 0.8154023680396078,
|
| 380 |
+
"eval_loss": 1.0521161556243896,
|
| 381 |
+
"eval_precision": 0.8221458981635473,
|
| 382 |
+
"eval_recall": 0.8108357988165681,
|
| 383 |
+
"eval_runtime": 24.6401,
|
| 384 |
+
"eval_samples_per_second": 658.44,
|
| 385 |
+
"eval_steps_per_second": 27.435,
|
| 386 |
+
"step": 10500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.62,
|
| 390 |
+
"learning_rate": 4.191666666666667e-06,
|
| 391 |
+
"loss": 0.1542,
|
| 392 |
+
"step": 11000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 3.62,
|
| 396 |
+
"eval_accuracy": 0.8197115384615384,
|
| 397 |
+
"eval_f1": 0.8199536621312183,
|
| 398 |
+
"eval_loss": 1.108322262763977,
|
| 399 |
+
"eval_precision": 0.8205846609719522,
|
| 400 |
+
"eval_recall": 0.8197115384615384,
|
| 401 |
+
"eval_runtime": 24.5935,
|
| 402 |
+
"eval_samples_per_second": 659.687,
|
| 403 |
+
"eval_steps_per_second": 27.487,
|
| 404 |
+
"step": 11000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.78,
|
| 408 |
+
"learning_rate": 2.108333333333333e-06,
|
| 409 |
+
"loss": 0.1561,
|
| 410 |
+
"step": 11500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 3.78,
|
| 414 |
+
"eval_accuracy": 0.8138560157790927,
|
| 415 |
+
"eval_f1": 0.8166825272884544,
|
| 416 |
+
"eval_loss": 1.0635404586791992,
|
| 417 |
+
"eval_precision": 0.8205938348020483,
|
| 418 |
+
"eval_recall": 0.8138560157790927,
|
| 419 |
+
"eval_runtime": 24.8393,
|
| 420 |
+
"eval_samples_per_second": 653.159,
|
| 421 |
+
"eval_steps_per_second": 27.215,
|
| 422 |
+
"step": 11500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.94,
|
| 426 |
+
"learning_rate": 2.916666666666667e-08,
|
| 427 |
+
"loss": 0.1415,
|
| 428 |
+
"step": 12000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.94,
|
| 432 |
+
"eval_accuracy": 0.815396942800789,
|
| 433 |
+
"eval_f1": 0.8176978993348879,
|
| 434 |
+
"eval_loss": 1.0898783206939697,
|
| 435 |
+
"eval_precision": 0.8208248888308868,
|
| 436 |
+
"eval_recall": 0.815396942800789,
|
| 437 |
+
"eval_runtime": 24.6997,
|
| 438 |
+
"eval_samples_per_second": 656.85,
|
| 439 |
+
"eval_steps_per_second": 27.369,
|
| 440 |
+
"step": 12000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.94,
|
| 444 |
+
"step": 12000,
|
| 445 |
+
"total_flos": 1.4832731619013427e+17,
|
| 446 |
+
"train_loss": 0.37884856541951495,
|
| 447 |
+
"train_runtime": 3446.9333,
|
| 448 |
+
"train_samples_per_second": 167.105,
|
| 449 |
+
"train_steps_per_second": 3.481
|
| 450 |
+
}
|
| 451 |
+
],
|
| 452 |
+
"max_steps": 12000,
|
| 453 |
+
"num_train_epochs": 4,
|
| 454 |
+
"total_flos": 1.4832731619013427e+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:e629a85d11014bed4fb4099bbcedecc04daead523e24b38fb4e2c394f89df7a2
|
| 3 |
+
size 3375
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|