Commit
•
3a8809c
1
Parent(s):
176a11f
init model
Browse files- config.json +38 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +20 -0
- trainer_state.json +457 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "xlm-roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "negative",
|
| 15 |
+
"1": "neutral",
|
| 16 |
+
"2": "positive"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"negative": 0,
|
| 22 |
+
"neutral": 1,
|
| 23 |
+
"positive": 2
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"max_position_embeddings": 514,
|
| 27 |
+
"model_type": "xlm-roberta",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"output_past": true,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.21.0.dev0",
|
| 35 |
+
"type_vocab_size": 1,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 250002
|
| 38 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71bc1033e544364f7f5b1a44e5c7a8c073c3f1b62d52a5272e43fb8b73b15d72
|
| 3 |
+
size 1112255469
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
|
| 3 |
+
size 17082660
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"__type": "AddedToken",
|
| 7 |
+
"content": "<mask>",
|
| 8 |
+
"lstrip": true,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"model_max_length": 512,
|
| 14 |
+
"name_or_path": "xlm-roberta-base",
|
| 15 |
+
"pad_token": "<pad>",
|
| 16 |
+
"sep_token": "</s>",
|
| 17 |
+
"special_tokens_map_file": null,
|
| 18 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 19 |
+
"unk_token": "<unk>"
|
| 20 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,457 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8169879527109274,
|
| 3 |
+
"best_model_checkpoint": "/home/bram/shares/predict/trained/dutch/hebban-reviews/xlm-roberta-base/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": 4.794166666666667e-05,
|
| 13 |
+
"loss": 0.913,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"eval_accuracy": 0.7665803747534516,
|
| 19 |
+
"eval_f1": 0.7649545454029377,
|
| 20 |
+
"eval_loss": 0.7253644466400146,
|
| 21 |
+
"eval_precision": 0.7641565688780922,
|
| 22 |
+
"eval_recall": 0.7665803747534516,
|
| 23 |
+
"eval_runtime": 24.3431,
|
| 24 |
+
"eval_samples_per_second": 666.472,
|
| 25 |
+
"eval_steps_per_second": 27.77,
|
| 26 |
+
"step": 500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.33,
|
| 30 |
+
"learning_rate": 4.5858333333333334e-05,
|
| 31 |
+
"loss": 0.7582,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.33,
|
| 36 |
+
"eval_accuracy": 0.6934787968441815,
|
| 37 |
+
"eval_f1": 0.7165538695299023,
|
| 38 |
+
"eval_loss": 0.7026467323303223,
|
| 39 |
+
"eval_precision": 0.7706797791371907,
|
| 40 |
+
"eval_recall": 0.6934787968441815,
|
| 41 |
+
"eval_runtime": 24.1169,
|
| 42 |
+
"eval_samples_per_second": 672.723,
|
| 43 |
+
"eval_steps_per_second": 28.03,
|
| 44 |
+
"step": 1000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.49,
|
| 48 |
+
"learning_rate": 4.3775e-05,
|
| 49 |
+
"loss": 0.6847,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.49,
|
| 54 |
+
"eval_accuracy": 0.7233727810650887,
|
| 55 |
+
"eval_f1": 0.7442026185547411,
|
| 56 |
+
"eval_loss": 0.6611877083778381,
|
| 57 |
+
"eval_precision": 0.8038626962859567,
|
| 58 |
+
"eval_recall": 0.7233727810650887,
|
| 59 |
+
"eval_runtime": 24.1771,
|
| 60 |
+
"eval_samples_per_second": 671.047,
|
| 61 |
+
"eval_steps_per_second": 27.96,
|
| 62 |
+
"step": 1500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.66,
|
| 66 |
+
"learning_rate": 4.1691666666666666e-05,
|
| 67 |
+
"loss": 0.6532,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.66,
|
| 72 |
+
"eval_accuracy": 0.8156434911242604,
|
| 73 |
+
"eval_f1": 0.8093687626348003,
|
| 74 |
+
"eval_loss": 0.6557860374450684,
|
| 75 |
+
"eval_precision": 0.8059505966835585,
|
| 76 |
+
"eval_recall": 0.8156434911242604,
|
| 77 |
+
"eval_runtime": 24.3135,
|
| 78 |
+
"eval_samples_per_second": 667.283,
|
| 79 |
+
"eval_steps_per_second": 27.803,
|
| 80 |
+
"step": 2000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.82,
|
| 84 |
+
"learning_rate": 3.960833333333334e-05,
|
| 85 |
+
"loss": 0.6281,
|
| 86 |
+
"step": 2500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.82,
|
| 90 |
+
"eval_accuracy": 0.7695389546351085,
|
| 91 |
+
"eval_f1": 0.7795959943899675,
|
| 92 |
+
"eval_loss": 0.616236686706543,
|
| 93 |
+
"eval_precision": 0.7973850176423627,
|
| 94 |
+
"eval_recall": 0.7695389546351085,
|
| 95 |
+
"eval_runtime": 24.3023,
|
| 96 |
+
"eval_samples_per_second": 667.59,
|
| 97 |
+
"eval_steps_per_second": 27.816,
|
| 98 |
+
"step": 2500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.99,
|
| 102 |
+
"learning_rate": 3.7525e-05,
|
| 103 |
+
"loss": 0.6281,
|
| 104 |
+
"step": 3000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.99,
|
| 108 |
+
"eval_accuracy": 0.8015902366863905,
|
| 109 |
+
"eval_f1": 0.803170220169187,
|
| 110 |
+
"eval_loss": 0.5991469621658325,
|
| 111 |
+
"eval_precision": 0.806066258666526,
|
| 112 |
+
"eval_recall": 0.8015902366863905,
|
| 113 |
+
"eval_runtime": 24.3429,
|
| 114 |
+
"eval_samples_per_second": 666.477,
|
| 115 |
+
"eval_steps_per_second": 27.77,
|
| 116 |
+
"step": 3000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.15,
|
| 120 |
+
"learning_rate": 3.544583333333333e-05,
|
| 121 |
+
"loss": 0.5668,
|
| 122 |
+
"step": 3500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.15,
|
| 126 |
+
"eval_accuracy": 0.7874753451676528,
|
| 127 |
+
"eval_f1": 0.7971578305557919,
|
| 128 |
+
"eval_loss": 0.5982191562652588,
|
| 129 |
+
"eval_precision": 0.8156521173286116,
|
| 130 |
+
"eval_recall": 0.7874753451676528,
|
| 131 |
+
"eval_runtime": 24.3367,
|
| 132 |
+
"eval_samples_per_second": 666.646,
|
| 133 |
+
"eval_steps_per_second": 27.777,
|
| 134 |
+
"step": 3500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.31,
|
| 138 |
+
"learning_rate": 3.3362500000000005e-05,
|
| 139 |
+
"loss": 0.567,
|
| 140 |
+
"step": 4000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.31,
|
| 144 |
+
"eval_accuracy": 0.8007889546351085,
|
| 145 |
+
"eval_f1": 0.8041408078539543,
|
| 146 |
+
"eval_loss": 0.6023094654083252,
|
| 147 |
+
"eval_precision": 0.8088979038333125,
|
| 148 |
+
"eval_recall": 0.8007889546351085,
|
| 149 |
+
"eval_runtime": 24.2641,
|
| 150 |
+
"eval_samples_per_second": 668.643,
|
| 151 |
+
"eval_steps_per_second": 27.86,
|
| 152 |
+
"step": 4000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.48,
|
| 156 |
+
"learning_rate": 3.127916666666667e-05,
|
| 157 |
+
"loss": 0.5704,
|
| 158 |
+
"step": 4500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.48,
|
| 162 |
+
"eval_accuracy": 0.7429117357001972,
|
| 163 |
+
"eval_f1": 0.7619810076683907,
|
| 164 |
+
"eval_loss": 0.6065093278884888,
|
| 165 |
+
"eval_precision": 0.8107750610152921,
|
| 166 |
+
"eval_recall": 0.7429117357001972,
|
| 167 |
+
"eval_runtime": 24.3353,
|
| 168 |
+
"eval_samples_per_second": 666.686,
|
| 169 |
+
"eval_steps_per_second": 27.779,
|
| 170 |
+
"step": 4500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.64,
|
| 174 |
+
"learning_rate": 2.9195833333333333e-05,
|
| 175 |
+
"loss": 0.5596,
|
| 176 |
+
"step": 5000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.64,
|
| 180 |
+
"eval_accuracy": 0.8072608481262328,
|
| 181 |
+
"eval_f1": 0.8104579115041036,
|
| 182 |
+
"eval_loss": 0.5900022983551025,
|
| 183 |
+
"eval_precision": 0.8144869336926288,
|
| 184 |
+
"eval_recall": 0.8072608481262328,
|
| 185 |
+
"eval_runtime": 24.3429,
|
| 186 |
+
"eval_samples_per_second": 666.477,
|
| 187 |
+
"eval_steps_per_second": 27.77,
|
| 188 |
+
"step": 5000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.81,
|
| 192 |
+
"learning_rate": 2.7116666666666667e-05,
|
| 193 |
+
"loss": 0.5495,
|
| 194 |
+
"step": 5500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.81,
|
| 198 |
+
"eval_accuracy": 0.810034516765286,
|
| 199 |
+
"eval_f1": 0.8141305380075001,
|
| 200 |
+
"eval_loss": 0.613106906414032,
|
| 201 |
+
"eval_precision": 0.8219044900382881,
|
| 202 |
+
"eval_recall": 0.810034516765286,
|
| 203 |
+
"eval_runtime": 24.3418,
|
| 204 |
+
"eval_samples_per_second": 666.509,
|
| 205 |
+
"eval_steps_per_second": 27.771,
|
| 206 |
+
"step": 5500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.97,
|
| 210 |
+
"learning_rate": 2.5033333333333336e-05,
|
| 211 |
+
"loss": 0.5449,
|
| 212 |
+
"step": 6000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.97,
|
| 216 |
+
"eval_accuracy": 0.8124383629191322,
|
| 217 |
+
"eval_f1": 0.8140798132169556,
|
| 218 |
+
"eval_loss": 0.6060279011726379,
|
| 219 |
+
"eval_precision": 0.816286158402022,
|
| 220 |
+
"eval_recall": 0.8124383629191322,
|
| 221 |
+
"eval_runtime": 24.332,
|
| 222 |
+
"eval_samples_per_second": 666.777,
|
| 223 |
+
"eval_steps_per_second": 27.782,
|
| 224 |
+
"step": 6000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.14,
|
| 228 |
+
"learning_rate": 2.2950000000000002e-05,
|
| 229 |
+
"loss": 0.4898,
|
| 230 |
+
"step": 6500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.14,
|
| 234 |
+
"eval_accuracy": 0.7848865877712031,
|
| 235 |
+
"eval_f1": 0.7964804879952159,
|
| 236 |
+
"eval_loss": 0.6215521693229675,
|
| 237 |
+
"eval_precision": 0.820125366434727,
|
| 238 |
+
"eval_recall": 0.7848865877712031,
|
| 239 |
+
"eval_runtime": 24.3196,
|
| 240 |
+
"eval_samples_per_second": 667.117,
|
| 241 |
+
"eval_steps_per_second": 27.797,
|
| 242 |
+
"step": 6500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.3,
|
| 246 |
+
"learning_rate": 2.0866666666666668e-05,
|
| 247 |
+
"loss": 0.4837,
|
| 248 |
+
"step": 7000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.3,
|
| 252 |
+
"eval_accuracy": 0.7318786982248521,
|
| 253 |
+
"eval_f1": 0.7528823670992008,
|
| 254 |
+
"eval_loss": 0.6411539912223816,
|
| 255 |
+
"eval_precision": 0.8100101192694165,
|
| 256 |
+
"eval_recall": 0.7318786982248521,
|
| 257 |
+
"eval_runtime": 24.3327,
|
| 258 |
+
"eval_samples_per_second": 666.758,
|
| 259 |
+
"eval_steps_per_second": 27.782,
|
| 260 |
+
"step": 7000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.47,
|
| 264 |
+
"learning_rate": 1.87875e-05,
|
| 265 |
+
"loss": 0.4671,
|
| 266 |
+
"step": 7500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.47,
|
| 270 |
+
"eval_accuracy": 0.803870808678501,
|
| 271 |
+
"eval_f1": 0.810953536758238,
|
| 272 |
+
"eval_loss": 0.6316830515861511,
|
| 273 |
+
"eval_precision": 0.8241951591967538,
|
| 274 |
+
"eval_recall": 0.803870808678501,
|
| 275 |
+
"eval_runtime": 24.3331,
|
| 276 |
+
"eval_samples_per_second": 666.747,
|
| 277 |
+
"eval_steps_per_second": 27.781,
|
| 278 |
+
"step": 7500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.63,
|
| 282 |
+
"learning_rate": 1.670416666666667e-05,
|
| 283 |
+
"loss": 0.4791,
|
| 284 |
+
"step": 8000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.63,
|
| 288 |
+
"eval_accuracy": 0.8032544378698225,
|
| 289 |
+
"eval_f1": 0.8091355876498971,
|
| 290 |
+
"eval_loss": 0.5908682942390442,
|
| 291 |
+
"eval_precision": 0.8179762946015251,
|
| 292 |
+
"eval_recall": 0.8032544378698225,
|
| 293 |
+
"eval_runtime": 24.3361,
|
| 294 |
+
"eval_samples_per_second": 666.664,
|
| 295 |
+
"eval_steps_per_second": 27.778,
|
| 296 |
+
"step": 8000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.79,
|
| 300 |
+
"learning_rate": 1.4620833333333334e-05,
|
| 301 |
+
"loss": 0.4739,
|
| 302 |
+
"step": 8500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.79,
|
| 306 |
+
"eval_accuracy": 0.8067061143984221,
|
| 307 |
+
"eval_f1": 0.8120892015198095,
|
| 308 |
+
"eval_loss": 0.6165759563446045,
|
| 309 |
+
"eval_precision": 0.8199753861011193,
|
| 310 |
+
"eval_recall": 0.8067061143984221,
|
| 311 |
+
"eval_runtime": 24.1747,
|
| 312 |
+
"eval_samples_per_second": 671.116,
|
| 313 |
+
"eval_steps_per_second": 27.963,
|
| 314 |
+
"step": 8500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.96,
|
| 318 |
+
"learning_rate": 1.25375e-05,
|
| 319 |
+
"loss": 0.4587,
|
| 320 |
+
"step": 9000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.96,
|
| 324 |
+
"eval_accuracy": 0.8041173570019724,
|
| 325 |
+
"eval_f1": 0.8104680056938384,
|
| 326 |
+
"eval_loss": 0.5887444019317627,
|
| 327 |
+
"eval_precision": 0.820271897699825,
|
| 328 |
+
"eval_recall": 0.8041173570019724,
|
| 329 |
+
"eval_runtime": 24.1945,
|
| 330 |
+
"eval_samples_per_second": 670.564,
|
| 331 |
+
"eval_steps_per_second": 27.94,
|
| 332 |
+
"step": 9000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.12,
|
| 336 |
+
"learning_rate": 1.0454166666666667e-05,
|
| 337 |
+
"loss": 0.4147,
|
| 338 |
+
"step": 9500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.12,
|
| 342 |
+
"eval_accuracy": 0.780448717948718,
|
| 343 |
+
"eval_f1": 0.7927207824065717,
|
| 344 |
+
"eval_loss": 0.6190515160560608,
|
| 345 |
+
"eval_precision": 0.8178157106781372,
|
| 346 |
+
"eval_recall": 0.780448717948718,
|
| 347 |
+
"eval_runtime": 24.1866,
|
| 348 |
+
"eval_samples_per_second": 670.784,
|
| 349 |
+
"eval_steps_per_second": 27.949,
|
| 350 |
+
"step": 9500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.29,
|
| 354 |
+
"learning_rate": 8.370833333333333e-06,
|
| 355 |
+
"loss": 0.3861,
|
| 356 |
+
"step": 10000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.29,
|
| 360 |
+
"eval_accuracy": 0.7917899408284024,
|
| 361 |
+
"eval_f1": 0.8013705698417323,
|
| 362 |
+
"eval_loss": 0.6606641411781311,
|
| 363 |
+
"eval_precision": 0.8190127006775076,
|
| 364 |
+
"eval_recall": 0.7917899408284024,
|
| 365 |
+
"eval_runtime": 24.3416,
|
| 366 |
+
"eval_samples_per_second": 666.514,
|
| 367 |
+
"eval_steps_per_second": 27.771,
|
| 368 |
+
"step": 10000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.45,
|
| 372 |
+
"learning_rate": 6.2875e-06,
|
| 373 |
+
"loss": 0.3897,
|
| 374 |
+
"step": 10500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.45,
|
| 378 |
+
"eval_accuracy": 0.788646449704142,
|
| 379 |
+
"eval_f1": 0.7987527519476123,
|
| 380 |
+
"eval_loss": 0.6613931059837341,
|
| 381 |
+
"eval_precision": 0.8177063830689373,
|
| 382 |
+
"eval_recall": 0.788646449704142,
|
| 383 |
+
"eval_runtime": 24.342,
|
| 384 |
+
"eval_samples_per_second": 666.503,
|
| 385 |
+
"eval_steps_per_second": 27.771,
|
| 386 |
+
"step": 10500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.62,
|
| 390 |
+
"learning_rate": 4.204166666666667e-06,
|
| 391 |
+
"loss": 0.3877,
|
| 392 |
+
"step": 11000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 3.62,
|
| 396 |
+
"eval_accuracy": 0.8135478303747534,
|
| 397 |
+
"eval_f1": 0.8169879527109274,
|
| 398 |
+
"eval_loss": 0.6640126705169678,
|
| 399 |
+
"eval_precision": 0.8215474627622835,
|
| 400 |
+
"eval_recall": 0.8135478303747534,
|
| 401 |
+
"eval_runtime": 24.3344,
|
| 402 |
+
"eval_samples_per_second": 666.71,
|
| 403 |
+
"eval_steps_per_second": 27.78,
|
| 404 |
+
"step": 11000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.78,
|
| 408 |
+
"learning_rate": 2.1208333333333335e-06,
|
| 409 |
+
"loss": 0.3795,
|
| 410 |
+
"step": 11500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 3.78,
|
| 414 |
+
"eval_accuracy": 0.8053500986193294,
|
| 415 |
+
"eval_f1": 0.8113411583628731,
|
| 416 |
+
"eval_loss": 0.6599082350730896,
|
| 417 |
+
"eval_precision": 0.8205901740056264,
|
| 418 |
+
"eval_recall": 0.8053500986193294,
|
| 419 |
+
"eval_runtime": 24.3271,
|
| 420 |
+
"eval_samples_per_second": 666.91,
|
| 421 |
+
"eval_steps_per_second": 27.788,
|
| 422 |
+
"step": 11500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.94,
|
| 426 |
+
"learning_rate": 3.7500000000000005e-08,
|
| 427 |
+
"loss": 0.3863,
|
| 428 |
+
"step": 12000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.94,
|
| 432 |
+
"eval_accuracy": 0.8009122287968442,
|
| 433 |
+
"eval_f1": 0.8081790831347971,
|
| 434 |
+
"eval_loss": 0.6572125554084778,
|
| 435 |
+
"eval_precision": 0.8200806840462704,
|
| 436 |
+
"eval_recall": 0.8009122287968442,
|
| 437 |
+
"eval_runtime": 24.3366,
|
| 438 |
+
"eval_samples_per_second": 666.651,
|
| 439 |
+
"eval_steps_per_second": 27.777,
|
| 440 |
+
"step": 12000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.94,
|
| 444 |
+
"step": 12000,
|
| 445 |
+
"total_flos": 1.4962346001065574e+17,
|
| 446 |
+
"train_loss": 0.5341533139546712,
|
| 447 |
+
"train_runtime": 3936.6668,
|
| 448 |
+
"train_samples_per_second": 146.317,
|
| 449 |
+
"train_steps_per_second": 3.048
|
| 450 |
+
}
|
| 451 |
+
],
|
| 452 |
+
"max_steps": 12000,
|
| 453 |
+
"num_train_epochs": 4,
|
| 454 |
+
"total_flos": 1.4962346001065574e+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 sha256:5972df5698b926a1dd5ed254cf898167128666e13f9d4375f9c4a79adc0d7e20
|
| 3 |
+
size 3375
|