Upload 11 files
Browse files- config.json +45 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +450 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "NBAiLab/nb-bert-large",
|
| 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": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": 0,
|
| 14 |
+
"1": 1,
|
| 15 |
+
"2": 2,
|
| 16 |
+
"3": 3,
|
| 17 |
+
"4": 4,
|
| 18 |
+
"5": 5,
|
| 19 |
+
"6": 6
|
| 20 |
+
},
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 4096,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"0": 0,
|
| 25 |
+
"1": 1,
|
| 26 |
+
"2": 2,
|
| 27 |
+
"3": 3,
|
| 28 |
+
"4": 4,
|
| 29 |
+
"5": 5,
|
| 30 |
+
"6": 6
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-12,
|
| 33 |
+
"max_position_embeddings": 512,
|
| 34 |
+
"model_type": "bert",
|
| 35 |
+
"num_attention_heads": 16,
|
| 36 |
+
"num_hidden_layers": 24,
|
| 37 |
+
"pad_token_id": 0,
|
| 38 |
+
"position_embedding_type": "absolute",
|
| 39 |
+
"problem_type": "single_label_classification",
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.39.3",
|
| 42 |
+
"type_vocab_size": 2,
|
| 43 |
+
"use_cache": true,
|
| 44 |
+
"vocab_size": 50000
|
| 45 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12eeb610bd18010f3c6e2057d99485f7cfdbe9c05598b4aae48f195b779c6df7
|
| 3 |
+
size 1420425204
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fb3009ebd2e4e3b85eea6205b9f8dfed05d43e270fcafb455e6137f4d55a5b9
|
| 3 |
+
size 2841074157
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8098b3ea1099554a17a75b08e08b0801f551831d4783349401defb321e1c1c1d
|
| 3 |
+
size 13990
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c55db0959645b5bcba5cd2a1c02cf128ffc563a767405b57f513d30b13263dd5
|
| 3 |
+
size 1064
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"501": {
|
| 4 |
+
"content": "[CLS]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"502": {
|
| 12 |
+
"content": "[MASK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"503": {
|
| 20 |
+
"content": "[PAD]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"504": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"505": {
|
| 36 |
+
"content": "[UNK]",
|
| 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": false,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,450 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 1715,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.15,
|
| 13 |
+
"eval_accuracy": 0.35737704918032787,
|
| 14 |
+
"eval_f1": 0.07522429261559696,
|
| 15 |
+
"eval_loss": 1.667272925376892,
|
| 16 |
+
"eval_precision": 0.05105386416861827,
|
| 17 |
+
"eval_recall": 0.14285714285714285,
|
| 18 |
+
"eval_runtime": 25.9688,
|
| 19 |
+
"eval_samples_per_second": 11.745,
|
| 20 |
+
"eval_steps_per_second": 1.502,
|
| 21 |
+
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.29,
|
| 25 |
+
"eval_accuracy": 0.5016393442622951,
|
| 26 |
+
"eval_f1": 0.2412952804098472,
|
| 27 |
+
"eval_loss": 1.472964882850647,
|
| 28 |
+
"eval_precision": 0.22701762523191094,
|
| 29 |
+
"eval_recall": 0.2760011649919907,
|
| 30 |
+
"eval_runtime": 25.1854,
|
| 31 |
+
"eval_samples_per_second": 12.11,
|
| 32 |
+
"eval_steps_per_second": 1.549,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.44,
|
| 37 |
+
"eval_accuracy": 0.5672131147540984,
|
| 38 |
+
"eval_f1": 0.35741119048011755,
|
| 39 |
+
"eval_loss": 1.2623624801635742,
|
| 40 |
+
"eval_precision": 0.46281513214918163,
|
| 41 |
+
"eval_recall": 0.34605526990848096,
|
| 42 |
+
"eval_runtime": 24.7658,
|
| 43 |
+
"eval_samples_per_second": 12.315,
|
| 44 |
+
"eval_steps_per_second": 1.575,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.58,
|
| 49 |
+
"eval_accuracy": 0.5639344262295082,
|
| 50 |
+
"eval_f1": 0.3512701619659464,
|
| 51 |
+
"eval_loss": 1.2795928716659546,
|
| 52 |
+
"eval_precision": 0.48283711313562055,
|
| 53 |
+
"eval_recall": 0.34593069478390576,
|
| 54 |
+
"eval_runtime": 26.4061,
|
| 55 |
+
"eval_samples_per_second": 11.55,
|
| 56 |
+
"eval_steps_per_second": 1.477,
|
| 57 |
+
"step": 200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.73,
|
| 61 |
+
"eval_accuracy": 0.639344262295082,
|
| 62 |
+
"eval_f1": 0.42203695116777995,
|
| 63 |
+
"eval_loss": 1.0558925867080688,
|
| 64 |
+
"eval_precision": 0.48377222428420436,
|
| 65 |
+
"eval_recall": 0.4281083079248217,
|
| 66 |
+
"eval_runtime": 24.1696,
|
| 67 |
+
"eval_samples_per_second": 12.619,
|
| 68 |
+
"eval_steps_per_second": 1.614,
|
| 69 |
+
"step": 250
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.87,
|
| 73 |
+
"eval_accuracy": 0.659016393442623,
|
| 74 |
+
"eval_f1": 0.5624420508569995,
|
| 75 |
+
"eval_loss": 0.9904302954673767,
|
| 76 |
+
"eval_precision": 0.6148969264343321,
|
| 77 |
+
"eval_recall": 0.5786355212960718,
|
| 78 |
+
"eval_runtime": 24.8748,
|
| 79 |
+
"eval_samples_per_second": 12.261,
|
| 80 |
+
"eval_steps_per_second": 1.568,
|
| 81 |
+
"step": 300
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.02,
|
| 85 |
+
"eval_accuracy": 0.5967213114754099,
|
| 86 |
+
"eval_f1": 0.42053130606223654,
|
| 87 |
+
"eval_loss": 1.1112089157104492,
|
| 88 |
+
"eval_precision": 0.5042065435600455,
|
| 89 |
+
"eval_recall": 0.42027804344318104,
|
| 90 |
+
"eval_runtime": 26.735,
|
| 91 |
+
"eval_samples_per_second": 11.408,
|
| 92 |
+
"eval_steps_per_second": 1.459,
|
| 93 |
+
"step": 350
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.17,
|
| 97 |
+
"eval_accuracy": 0.6622950819672131,
|
| 98 |
+
"eval_f1": 0.540005974333324,
|
| 99 |
+
"eval_loss": 1.0169768333435059,
|
| 100 |
+
"eval_precision": 0.6707201514365236,
|
| 101 |
+
"eval_recall": 0.5058656801776068,
|
| 102 |
+
"eval_runtime": 24.681,
|
| 103 |
+
"eval_samples_per_second": 12.358,
|
| 104 |
+
"eval_steps_per_second": 1.58,
|
| 105 |
+
"step": 400
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.31,
|
| 109 |
+
"eval_accuracy": 0.7049180327868853,
|
| 110 |
+
"eval_f1": 0.5548474859699348,
|
| 111 |
+
"eval_loss": 0.963288426399231,
|
| 112 |
+
"eval_precision": 0.6737802840434419,
|
| 113 |
+
"eval_recall": 0.5320264412007532,
|
| 114 |
+
"eval_runtime": 85.8855,
|
| 115 |
+
"eval_samples_per_second": 3.551,
|
| 116 |
+
"eval_steps_per_second": 0.454,
|
| 117 |
+
"step": 450
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.46,
|
| 121 |
+
"grad_norm": 6.387063980102539,
|
| 122 |
+
"learning_rate": 3.542274052478135e-05,
|
| 123 |
+
"loss": 1.2491,
|
| 124 |
+
"step": 500
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.46,
|
| 128 |
+
"eval_accuracy": 0.740983606557377,
|
| 129 |
+
"eval_f1": 0.6032578704144542,
|
| 130 |
+
"eval_loss": 0.8153039216995239,
|
| 131 |
+
"eval_precision": 0.6389329389702317,
|
| 132 |
+
"eval_recall": 0.5814238802770912,
|
| 133 |
+
"eval_runtime": 25.7584,
|
| 134 |
+
"eval_samples_per_second": 11.841,
|
| 135 |
+
"eval_steps_per_second": 1.514,
|
| 136 |
+
"step": 500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.6,
|
| 140 |
+
"eval_accuracy": 0.7311475409836066,
|
| 141 |
+
"eval_f1": 0.59968879894362,
|
| 142 |
+
"eval_loss": 0.8648873567581177,
|
| 143 |
+
"eval_precision": 0.7235630919034282,
|
| 144 |
+
"eval_recall": 0.5553548759970778,
|
| 145 |
+
"eval_runtime": 26.1622,
|
| 146 |
+
"eval_samples_per_second": 11.658,
|
| 147 |
+
"eval_steps_per_second": 1.491,
|
| 148 |
+
"step": 550
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.75,
|
| 152 |
+
"eval_accuracy": 0.780327868852459,
|
| 153 |
+
"eval_f1": 0.6441369205133565,
|
| 154 |
+
"eval_loss": 0.7085286974906921,
|
| 155 |
+
"eval_precision": 0.6888112350883506,
|
| 156 |
+
"eval_recall": 0.6200901173378238,
|
| 157 |
+
"eval_runtime": 25.1463,
|
| 158 |
+
"eval_samples_per_second": 12.129,
|
| 159 |
+
"eval_steps_per_second": 1.551,
|
| 160 |
+
"step": 600
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.9,
|
| 164 |
+
"eval_accuracy": 0.7639344262295082,
|
| 165 |
+
"eval_f1": 0.6348228528062524,
|
| 166 |
+
"eval_loss": 0.778355062007904,
|
| 167 |
+
"eval_precision": 0.6448629451780713,
|
| 168 |
+
"eval_recall": 0.6364373118960275,
|
| 169 |
+
"eval_runtime": 25.0645,
|
| 170 |
+
"eval_samples_per_second": 12.169,
|
| 171 |
+
"eval_steps_per_second": 1.556,
|
| 172 |
+
"step": 650
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 2.04,
|
| 176 |
+
"eval_accuracy": 0.7475409836065574,
|
| 177 |
+
"eval_f1": 0.6299370987134999,
|
| 178 |
+
"eval_loss": 0.7480295896530151,
|
| 179 |
+
"eval_precision": 0.6783989867133294,
|
| 180 |
+
"eval_recall": 0.6207732331585543,
|
| 181 |
+
"eval_runtime": 24.3631,
|
| 182 |
+
"eval_samples_per_second": 12.519,
|
| 183 |
+
"eval_steps_per_second": 1.601,
|
| 184 |
+
"step": 700
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.19,
|
| 188 |
+
"eval_accuracy": 0.7672131147540984,
|
| 189 |
+
"eval_f1": 0.6541376568128562,
|
| 190 |
+
"eval_loss": 0.7434977293014526,
|
| 191 |
+
"eval_precision": 0.7108263630655515,
|
| 192 |
+
"eval_recall": 0.6220120665074793,
|
| 193 |
+
"eval_runtime": 25.2918,
|
| 194 |
+
"eval_samples_per_second": 12.059,
|
| 195 |
+
"eval_steps_per_second": 1.542,
|
| 196 |
+
"step": 750
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.33,
|
| 200 |
+
"eval_accuracy": 0.7311475409836066,
|
| 201 |
+
"eval_f1": 0.6427856362037365,
|
| 202 |
+
"eval_loss": 0.9037203192710876,
|
| 203 |
+
"eval_precision": 0.7008431166108425,
|
| 204 |
+
"eval_recall": 0.6458018130036478,
|
| 205 |
+
"eval_runtime": 24.5352,
|
| 206 |
+
"eval_samples_per_second": 12.431,
|
| 207 |
+
"eval_steps_per_second": 1.59,
|
| 208 |
+
"step": 800
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.48,
|
| 212 |
+
"eval_accuracy": 0.7508196721311475,
|
| 213 |
+
"eval_f1": 0.6470554102382174,
|
| 214 |
+
"eval_loss": 0.7644699215888977,
|
| 215 |
+
"eval_precision": 0.6814040333813435,
|
| 216 |
+
"eval_recall": 0.6477453030205323,
|
| 217 |
+
"eval_runtime": 24.2035,
|
| 218 |
+
"eval_samples_per_second": 12.601,
|
| 219 |
+
"eval_steps_per_second": 1.611,
|
| 220 |
+
"step": 850
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 2.62,
|
| 224 |
+
"eval_accuracy": 0.8,
|
| 225 |
+
"eval_f1": 0.677888944499949,
|
| 226 |
+
"eval_loss": 0.7002153396606445,
|
| 227 |
+
"eval_precision": 0.7160759040458288,
|
| 228 |
+
"eval_recall": 0.6559052650795769,
|
| 229 |
+
"eval_runtime": 24.4891,
|
| 230 |
+
"eval_samples_per_second": 12.455,
|
| 231 |
+
"eval_steps_per_second": 1.593,
|
| 232 |
+
"step": 900
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 2.77,
|
| 236 |
+
"eval_accuracy": 0.8098360655737705,
|
| 237 |
+
"eval_f1": 0.6772457805812352,
|
| 238 |
+
"eval_loss": 0.6718072891235352,
|
| 239 |
+
"eval_precision": 0.6894471952583333,
|
| 240 |
+
"eval_recall": 0.6719617414571543,
|
| 241 |
+
"eval_runtime": 25.7261,
|
| 242 |
+
"eval_samples_per_second": 11.856,
|
| 243 |
+
"eval_steps_per_second": 1.516,
|
| 244 |
+
"step": 950
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.92,
|
| 248 |
+
"grad_norm": 6.155330181121826,
|
| 249 |
+
"learning_rate": 2.0845481049562683e-05,
|
| 250 |
+
"loss": 0.6665,
|
| 251 |
+
"step": 1000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.92,
|
| 255 |
+
"eval_accuracy": 0.7868852459016393,
|
| 256 |
+
"eval_f1": 0.6645166174577939,
|
| 257 |
+
"eval_loss": 0.6745351552963257,
|
| 258 |
+
"eval_precision": 0.6831230788775687,
|
| 259 |
+
"eval_recall": 0.6611539278970471,
|
| 260 |
+
"eval_runtime": 23.8162,
|
| 261 |
+
"eval_samples_per_second": 12.806,
|
| 262 |
+
"eval_steps_per_second": 1.638,
|
| 263 |
+
"step": 1000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3.06,
|
| 267 |
+
"eval_accuracy": 0.8,
|
| 268 |
+
"eval_f1": 0.6707482450301798,
|
| 269 |
+
"eval_loss": 0.6912632584571838,
|
| 270 |
+
"eval_precision": 0.7038907777116936,
|
| 271 |
+
"eval_recall": 0.6636155184320323,
|
| 272 |
+
"eval_runtime": 25.3425,
|
| 273 |
+
"eval_samples_per_second": 12.035,
|
| 274 |
+
"eval_steps_per_second": 1.539,
|
| 275 |
+
"step": 1050
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.21,
|
| 279 |
+
"eval_accuracy": 0.7344262295081967,
|
| 280 |
+
"eval_f1": 0.6124227128896254,
|
| 281 |
+
"eval_loss": 0.839020848274231,
|
| 282 |
+
"eval_precision": 0.6036382548711792,
|
| 283 |
+
"eval_recall": 0.6331067003085352,
|
| 284 |
+
"eval_runtime": 25.3402,
|
| 285 |
+
"eval_samples_per_second": 12.036,
|
| 286 |
+
"eval_steps_per_second": 1.539,
|
| 287 |
+
"step": 1100
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 3.35,
|
| 291 |
+
"eval_accuracy": 0.7901639344262295,
|
| 292 |
+
"eval_f1": 0.6632550969550687,
|
| 293 |
+
"eval_loss": 0.7742147445678711,
|
| 294 |
+
"eval_precision": 0.6782513190376637,
|
| 295 |
+
"eval_recall": 0.6595217659437844,
|
| 296 |
+
"eval_runtime": 24.3329,
|
| 297 |
+
"eval_samples_per_second": 12.534,
|
| 298 |
+
"eval_steps_per_second": 1.603,
|
| 299 |
+
"step": 1150
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.5,
|
| 303 |
+
"eval_accuracy": 0.8131147540983606,
|
| 304 |
+
"eval_f1": 0.6727344613312225,
|
| 305 |
+
"eval_loss": 0.6753232479095459,
|
| 306 |
+
"eval_precision": 0.6878592989192068,
|
| 307 |
+
"eval_recall": 0.6654702186812278,
|
| 308 |
+
"eval_runtime": 24.7418,
|
| 309 |
+
"eval_samples_per_second": 12.327,
|
| 310 |
+
"eval_steps_per_second": 1.576,
|
| 311 |
+
"step": 1200
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 3.64,
|
| 315 |
+
"eval_accuracy": 0.760655737704918,
|
| 316 |
+
"eval_f1": 0.6525488286572031,
|
| 317 |
+
"eval_loss": 0.8542010188102722,
|
| 318 |
+
"eval_precision": 0.6985802437047138,
|
| 319 |
+
"eval_recall": 0.6503794246913512,
|
| 320 |
+
"eval_runtime": 23.8367,
|
| 321 |
+
"eval_samples_per_second": 12.795,
|
| 322 |
+
"eval_steps_per_second": 1.636,
|
| 323 |
+
"step": 1250
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.79,
|
| 327 |
+
"eval_accuracy": 0.8065573770491803,
|
| 328 |
+
"eval_f1": 0.6740742285136359,
|
| 329 |
+
"eval_loss": 0.7735392451286316,
|
| 330 |
+
"eval_precision": 0.6767778649921506,
|
| 331 |
+
"eval_recall": 0.676755828820049,
|
| 332 |
+
"eval_runtime": 24.4555,
|
| 333 |
+
"eval_samples_per_second": 12.472,
|
| 334 |
+
"eval_steps_per_second": 1.595,
|
| 335 |
+
"step": 1300
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.94,
|
| 339 |
+
"eval_accuracy": 0.8131147540983606,
|
| 340 |
+
"eval_f1": 0.6832302669636724,
|
| 341 |
+
"eval_loss": 0.6795472502708435,
|
| 342 |
+
"eval_precision": 0.7133861439312567,
|
| 343 |
+
"eval_recall": 0.6736156637532783,
|
| 344 |
+
"eval_runtime": 25.0647,
|
| 345 |
+
"eval_samples_per_second": 12.169,
|
| 346 |
+
"eval_steps_per_second": 1.556,
|
| 347 |
+
"step": 1350
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 4.08,
|
| 351 |
+
"eval_accuracy": 0.7967213114754098,
|
| 352 |
+
"eval_f1": 0.6579730420842168,
|
| 353 |
+
"eval_loss": 0.7954936623573303,
|
| 354 |
+
"eval_precision": 0.6799340904944353,
|
| 355 |
+
"eval_recall": 0.654890922780831,
|
| 356 |
+
"eval_runtime": 25.0454,
|
| 357 |
+
"eval_samples_per_second": 12.178,
|
| 358 |
+
"eval_steps_per_second": 1.557,
|
| 359 |
+
"step": 1400
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 4.23,
|
| 363 |
+
"eval_accuracy": 0.8229508196721311,
|
| 364 |
+
"eval_f1": 0.6892471358587405,
|
| 365 |
+
"eval_loss": 0.7999194264411926,
|
| 366 |
+
"eval_precision": 0.7156453634629862,
|
| 367 |
+
"eval_recall": 0.6809495048027159,
|
| 368 |
+
"eval_runtime": 25.4511,
|
| 369 |
+
"eval_samples_per_second": 11.984,
|
| 370 |
+
"eval_steps_per_second": 1.532,
|
| 371 |
+
"step": 1450
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 4.37,
|
| 375 |
+
"grad_norm": 22.507097244262695,
|
| 376 |
+
"learning_rate": 6.268221574344024e-06,
|
| 377 |
+
"loss": 0.3776,
|
| 378 |
+
"step": 1500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 4.37,
|
| 382 |
+
"eval_accuracy": 0.7934426229508197,
|
| 383 |
+
"eval_f1": 0.6679894092876133,
|
| 384 |
+
"eval_loss": 0.9446977376937866,
|
| 385 |
+
"eval_precision": 0.686414129348912,
|
| 386 |
+
"eval_recall": 0.6591507199305365,
|
| 387 |
+
"eval_runtime": 25.6463,
|
| 388 |
+
"eval_samples_per_second": 11.893,
|
| 389 |
+
"eval_steps_per_second": 1.521,
|
| 390 |
+
"step": 1500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 4.52,
|
| 394 |
+
"eval_accuracy": 0.8065573770491803,
|
| 395 |
+
"eval_f1": 0.6705779982361941,
|
| 396 |
+
"eval_loss": 0.9103355407714844,
|
| 397 |
+
"eval_precision": 0.6804748603360347,
|
| 398 |
+
"eval_recall": 0.6682874981040119,
|
| 399 |
+
"eval_runtime": 24.8615,
|
| 400 |
+
"eval_samples_per_second": 12.268,
|
| 401 |
+
"eval_steps_per_second": 1.569,
|
| 402 |
+
"step": 1550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 4.66,
|
| 406 |
+
"eval_accuracy": 0.7868852459016393,
|
| 407 |
+
"eval_f1": 0.6581300883025021,
|
| 408 |
+
"eval_loss": 0.9052944779396057,
|
| 409 |
+
"eval_precision": 0.6659523069247808,
|
| 410 |
+
"eval_recall": 0.6643693723968953,
|
| 411 |
+
"eval_runtime": 24.6745,
|
| 412 |
+
"eval_samples_per_second": 12.361,
|
| 413 |
+
"eval_steps_per_second": 1.581,
|
| 414 |
+
"step": 1600
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 4.81,
|
| 418 |
+
"eval_accuracy": 0.819672131147541,
|
| 419 |
+
"eval_f1": 0.6860677167570124,
|
| 420 |
+
"eval_loss": 0.85903000831604,
|
| 421 |
+
"eval_precision": 0.7103231643472162,
|
| 422 |
+
"eval_recall": 0.678005387179699,
|
| 423 |
+
"eval_runtime": 25.3638,
|
| 424 |
+
"eval_samples_per_second": 12.025,
|
| 425 |
+
"eval_steps_per_second": 1.538,
|
| 426 |
+
"step": 1650
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 4.96,
|
| 430 |
+
"eval_accuracy": 0.8229508196721311,
|
| 431 |
+
"eval_f1": 0.6861351260633056,
|
| 432 |
+
"eval_loss": 0.8571685552597046,
|
| 433 |
+
"eval_precision": 0.7088281080916173,
|
| 434 |
+
"eval_recall": 0.6787861482815611,
|
| 435 |
+
"eval_runtime": 23.7505,
|
| 436 |
+
"eval_samples_per_second": 12.842,
|
| 437 |
+
"eval_steps_per_second": 1.642,
|
| 438 |
+
"step": 1700
|
| 439 |
+
}
|
| 440 |
+
],
|
| 441 |
+
"logging_steps": 500,
|
| 442 |
+
"max_steps": 1715,
|
| 443 |
+
"num_input_tokens_seen": 0,
|
| 444 |
+
"num_train_epochs": 5,
|
| 445 |
+
"save_steps": 500,
|
| 446 |
+
"total_flos": 1.278165457700352e+16,
|
| 447 |
+
"train_batch_size": 8,
|
| 448 |
+
"trial_name": null,
|
| 449 |
+
"trial_params": null
|
| 450 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d241bb276f98fb82e4d4997f83163a436e161fcf08810a4b7b8fff9ba63bec89
|
| 3 |
+
size 4920
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|