Upload folder using huggingface_hub
Browse files- config.json +64 -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 +337 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "allenai/scibert_scivocab_cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "1",
|
| 13 |
+
"1": "2",
|
| 14 |
+
"2": "3",
|
| 15 |
+
"3": "4",
|
| 16 |
+
"4": "5",
|
| 17 |
+
"5": "6",
|
| 18 |
+
"6": "7",
|
| 19 |
+
"7": "8",
|
| 20 |
+
"8": "9",
|
| 21 |
+
"9": "10",
|
| 22 |
+
"10": "11",
|
| 23 |
+
"11": "12",
|
| 24 |
+
"12": "13",
|
| 25 |
+
"13": "14",
|
| 26 |
+
"14": "15",
|
| 27 |
+
"15": "16",
|
| 28 |
+
"16": "17"
|
| 29 |
+
},
|
| 30 |
+
"initializer_range": 0.02,
|
| 31 |
+
"intermediate_size": 3072,
|
| 32 |
+
"label2id": {
|
| 33 |
+
"1": 0,
|
| 34 |
+
"10": 9,
|
| 35 |
+
"11": 10,
|
| 36 |
+
"12": 11,
|
| 37 |
+
"13": 12,
|
| 38 |
+
"14": 13,
|
| 39 |
+
"15": 14,
|
| 40 |
+
"16": 15,
|
| 41 |
+
"17": 16,
|
| 42 |
+
"2": 1,
|
| 43 |
+
"3": 2,
|
| 44 |
+
"4": 3,
|
| 45 |
+
"5": 4,
|
| 46 |
+
"6": 5,
|
| 47 |
+
"7": 6,
|
| 48 |
+
"8": 7,
|
| 49 |
+
"9": 8
|
| 50 |
+
},
|
| 51 |
+
"layer_norm_eps": 1e-12,
|
| 52 |
+
"max_position_embeddings": 512,
|
| 53 |
+
"model_type": "bert",
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_hidden_layers": 12,
|
| 56 |
+
"pad_token_id": 0,
|
| 57 |
+
"position_embedding_type": "absolute",
|
| 58 |
+
"problem_type": "single_label_classification",
|
| 59 |
+
"torch_dtype": "float32",
|
| 60 |
+
"transformers_version": "4.41.2",
|
| 61 |
+
"type_vocab_size": 2,
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"vocab_size": 31116
|
| 64 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6330d6a6be098cc1449320165fa8683bc7905ac8997955e417f7a129766342c
|
| 3 |
+
size 439829556
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:508af0103bbb0ef25ce793eebf2852732c065cfcd0154c2c8916c07d67bb0f3d
|
| 3 |
+
size 879780154
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbce969d2f5c5ca7c892f4ff7f988df1e6b20087ce06123a7049e21f892cbc81
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ea890829a2b9370cab8c6c2b036fa5cffe400b83fabed47affe9ed40f21f77d
|
| 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 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 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 +1,337 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7712177121771218,
|
| 3 |
+
"best_model_checkpoint": "/srv/scratch2/dbielik/.cache/huggingface/checkpoints/final/allenai/scibert_scivocab_cased-zo_up/checkpoint-432",
|
| 4 |
+
"epoch": 16.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 432,
|
| 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 |
+
"grad_norm": 9.934002876281738,
|
| 14 |
+
"learning_rate": 9.5e-06,
|
| 15 |
+
"loss": 2.8387,
|
| 16 |
+
"step": 27
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.1033210332103321,
|
| 21 |
+
"eval_f1": 0.07709920253414887,
|
| 22 |
+
"eval_loss": 2.758859395980835,
|
| 23 |
+
"eval_precision": 0.10450163475993733,
|
| 24 |
+
"eval_recall": 0.1033210332103321,
|
| 25 |
+
"eval_runtime": 1.3397,
|
| 26 |
+
"eval_samples_per_second": 202.279,
|
| 27 |
+
"eval_steps_per_second": 8.957,
|
| 28 |
+
"step": 27
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 2.0,
|
| 32 |
+
"grad_norm": 8.466582298278809,
|
| 33 |
+
"learning_rate": 9e-06,
|
| 34 |
+
"loss": 2.6687,
|
| 35 |
+
"step": 54
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.0,
|
| 39 |
+
"eval_accuracy": 0.25830258302583026,
|
| 40 |
+
"eval_f1": 0.2284463868863592,
|
| 41 |
+
"eval_loss": 2.6112310886383057,
|
| 42 |
+
"eval_precision": 0.28493199473562614,
|
| 43 |
+
"eval_recall": 0.25830258302583026,
|
| 44 |
+
"eval_runtime": 1.3145,
|
| 45 |
+
"eval_samples_per_second": 206.155,
|
| 46 |
+
"eval_steps_per_second": 9.129,
|
| 47 |
+
"step": 54
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.0,
|
| 51 |
+
"grad_norm": 11.356733322143555,
|
| 52 |
+
"learning_rate": 8.5e-06,
|
| 53 |
+
"loss": 2.4398,
|
| 54 |
+
"step": 81
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.0,
|
| 58 |
+
"eval_accuracy": 0.4354243542435424,
|
| 59 |
+
"eval_f1": 0.381253286711997,
|
| 60 |
+
"eval_loss": 2.360955238342285,
|
| 61 |
+
"eval_precision": 0.40620812098283454,
|
| 62 |
+
"eval_recall": 0.4354243542435424,
|
| 63 |
+
"eval_runtime": 1.2981,
|
| 64 |
+
"eval_samples_per_second": 208.77,
|
| 65 |
+
"eval_steps_per_second": 9.244,
|
| 66 |
+
"step": 81
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.0,
|
| 70 |
+
"grad_norm": 13.148231506347656,
|
| 71 |
+
"learning_rate": 8.000000000000001e-06,
|
| 72 |
+
"loss": 2.1223,
|
| 73 |
+
"step": 108
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.0,
|
| 77 |
+
"eval_accuracy": 0.5756457564575646,
|
| 78 |
+
"eval_f1": 0.5459700567948665,
|
| 79 |
+
"eval_loss": 2.0634419918060303,
|
| 80 |
+
"eval_precision": 0.5859418937087851,
|
| 81 |
+
"eval_recall": 0.5756457564575646,
|
| 82 |
+
"eval_runtime": 1.2527,
|
| 83 |
+
"eval_samples_per_second": 216.329,
|
| 84 |
+
"eval_steps_per_second": 9.579,
|
| 85 |
+
"step": 108
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 5.0,
|
| 89 |
+
"grad_norm": 10.06527042388916,
|
| 90 |
+
"learning_rate": 7.500000000000001e-06,
|
| 91 |
+
"loss": 1.8247,
|
| 92 |
+
"step": 135
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.0,
|
| 96 |
+
"eval_accuracy": 0.6531365313653137,
|
| 97 |
+
"eval_f1": 0.6254590334029755,
|
| 98 |
+
"eval_loss": 1.8168519735336304,
|
| 99 |
+
"eval_precision": 0.6682549359951895,
|
| 100 |
+
"eval_recall": 0.6531365313653137,
|
| 101 |
+
"eval_runtime": 1.3328,
|
| 102 |
+
"eval_samples_per_second": 203.332,
|
| 103 |
+
"eval_steps_per_second": 9.004,
|
| 104 |
+
"step": 135
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.0,
|
| 108 |
+
"grad_norm": 14.93287467956543,
|
| 109 |
+
"learning_rate": 7e-06,
|
| 110 |
+
"loss": 1.5665,
|
| 111 |
+
"step": 162
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 6.0,
|
| 115 |
+
"eval_accuracy": 0.7084870848708487,
|
| 116 |
+
"eval_f1": 0.6909028725740709,
|
| 117 |
+
"eval_loss": 1.590735912322998,
|
| 118 |
+
"eval_precision": 0.6983839902665424,
|
| 119 |
+
"eval_recall": 0.7084870848708487,
|
| 120 |
+
"eval_runtime": 1.5285,
|
| 121 |
+
"eval_samples_per_second": 177.303,
|
| 122 |
+
"eval_steps_per_second": 7.851,
|
| 123 |
+
"step": 162
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"grad_norm": 13.733495712280273,
|
| 128 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 129 |
+
"loss": 1.3405,
|
| 130 |
+
"step": 189
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 7.0,
|
| 134 |
+
"eval_accuracy": 0.7269372693726938,
|
| 135 |
+
"eval_f1": 0.7118111768214795,
|
| 136 |
+
"eval_loss": 1.422202229499817,
|
| 137 |
+
"eval_precision": 0.7273552449363285,
|
| 138 |
+
"eval_recall": 0.7269372693726938,
|
| 139 |
+
"eval_runtime": 1.3212,
|
| 140 |
+
"eval_samples_per_second": 205.115,
|
| 141 |
+
"eval_steps_per_second": 9.083,
|
| 142 |
+
"step": 189
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 8.0,
|
| 146 |
+
"grad_norm": 12.636699676513672,
|
| 147 |
+
"learning_rate": 6e-06,
|
| 148 |
+
"loss": 1.1401,
|
| 149 |
+
"step": 216
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_accuracy": 0.7527675276752768,
|
| 154 |
+
"eval_f1": 0.7446176669003964,
|
| 155 |
+
"eval_loss": 1.2776741981506348,
|
| 156 |
+
"eval_precision": 0.7541910880891607,
|
| 157 |
+
"eval_recall": 0.7527675276752768,
|
| 158 |
+
"eval_runtime": 1.5275,
|
| 159 |
+
"eval_samples_per_second": 177.414,
|
| 160 |
+
"eval_steps_per_second": 7.856,
|
| 161 |
+
"step": 216
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 9.0,
|
| 165 |
+
"grad_norm": 12.018023490905762,
|
| 166 |
+
"learning_rate": 5.500000000000001e-06,
|
| 167 |
+
"loss": 0.9726,
|
| 168 |
+
"step": 243
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 9.0,
|
| 172 |
+
"eval_accuracy": 0.7380073800738007,
|
| 173 |
+
"eval_f1": 0.7283869268501074,
|
| 174 |
+
"eval_loss": 1.191291332244873,
|
| 175 |
+
"eval_precision": 0.7393310690625704,
|
| 176 |
+
"eval_recall": 0.7380073800738007,
|
| 177 |
+
"eval_runtime": 1.3288,
|
| 178 |
+
"eval_samples_per_second": 203.948,
|
| 179 |
+
"eval_steps_per_second": 9.031,
|
| 180 |
+
"step": 243
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 10.0,
|
| 184 |
+
"grad_norm": 12.431900024414062,
|
| 185 |
+
"learning_rate": 5e-06,
|
| 186 |
+
"loss": 0.8393,
|
| 187 |
+
"step": 270
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 10.0,
|
| 191 |
+
"eval_accuracy": 0.7564575645756457,
|
| 192 |
+
"eval_f1": 0.7476978666822599,
|
| 193 |
+
"eval_loss": 1.1135777235031128,
|
| 194 |
+
"eval_precision": 0.7561729602587051,
|
| 195 |
+
"eval_recall": 0.7564575645756457,
|
| 196 |
+
"eval_runtime": 1.3261,
|
| 197 |
+
"eval_samples_per_second": 204.36,
|
| 198 |
+
"eval_steps_per_second": 9.049,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 11.0,
|
| 203 |
+
"grad_norm": 14.116780281066895,
|
| 204 |
+
"learning_rate": 4.5e-06,
|
| 205 |
+
"loss": 0.7209,
|
| 206 |
+
"step": 297
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 11.0,
|
| 210 |
+
"eval_accuracy": 0.7527675276752768,
|
| 211 |
+
"eval_f1": 0.7446247192959354,
|
| 212 |
+
"eval_loss": 1.053971529006958,
|
| 213 |
+
"eval_precision": 0.7499033596795298,
|
| 214 |
+
"eval_recall": 0.7527675276752768,
|
| 215 |
+
"eval_runtime": 1.3614,
|
| 216 |
+
"eval_samples_per_second": 199.067,
|
| 217 |
+
"eval_steps_per_second": 8.815,
|
| 218 |
+
"step": 297
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 12.0,
|
| 222 |
+
"grad_norm": 4.1638922691345215,
|
| 223 |
+
"learning_rate": 4.000000000000001e-06,
|
| 224 |
+
"loss": 0.6125,
|
| 225 |
+
"step": 324
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 12.0,
|
| 229 |
+
"eval_accuracy": 0.7601476014760148,
|
| 230 |
+
"eval_f1": 0.752596751208132,
|
| 231 |
+
"eval_loss": 1.0184677839279175,
|
| 232 |
+
"eval_precision": 0.7563512209074453,
|
| 233 |
+
"eval_recall": 0.7601476014760148,
|
| 234 |
+
"eval_runtime": 1.329,
|
| 235 |
+
"eval_samples_per_second": 203.918,
|
| 236 |
+
"eval_steps_per_second": 9.03,
|
| 237 |
+
"step": 324
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 13.0,
|
| 241 |
+
"grad_norm": 14.60648250579834,
|
| 242 |
+
"learning_rate": 3.5e-06,
|
| 243 |
+
"loss": 0.5704,
|
| 244 |
+
"step": 351
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 13.0,
|
| 248 |
+
"eval_accuracy": 0.7564575645756457,
|
| 249 |
+
"eval_f1": 0.7496637461027665,
|
| 250 |
+
"eval_loss": 0.995012104511261,
|
| 251 |
+
"eval_precision": 0.7548258823457891,
|
| 252 |
+
"eval_recall": 0.7564575645756457,
|
| 253 |
+
"eval_runtime": 1.3367,
|
| 254 |
+
"eval_samples_per_second": 202.734,
|
| 255 |
+
"eval_steps_per_second": 8.977,
|
| 256 |
+
"step": 351
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 14.0,
|
| 260 |
+
"grad_norm": 3.8977322578430176,
|
| 261 |
+
"learning_rate": 3e-06,
|
| 262 |
+
"loss": 0.4939,
|
| 263 |
+
"step": 378
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 14.0,
|
| 267 |
+
"eval_accuracy": 0.7675276752767528,
|
| 268 |
+
"eval_f1": 0.7618750835491949,
|
| 269 |
+
"eval_loss": 0.9737688302993774,
|
| 270 |
+
"eval_precision": 0.7664142901616198,
|
| 271 |
+
"eval_recall": 0.7675276752767528,
|
| 272 |
+
"eval_runtime": 1.3436,
|
| 273 |
+
"eval_samples_per_second": 201.691,
|
| 274 |
+
"eval_steps_per_second": 8.931,
|
| 275 |
+
"step": 378
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 15.0,
|
| 279 |
+
"grad_norm": 15.754039764404297,
|
| 280 |
+
"learning_rate": 2.5e-06,
|
| 281 |
+
"loss": 0.467,
|
| 282 |
+
"step": 405
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 15.0,
|
| 286 |
+
"eval_accuracy": 0.7601476014760148,
|
| 287 |
+
"eval_f1": 0.7550647299408412,
|
| 288 |
+
"eval_loss": 0.9670635461807251,
|
| 289 |
+
"eval_precision": 0.7608612393303595,
|
| 290 |
+
"eval_recall": 0.7601476014760148,
|
| 291 |
+
"eval_runtime": 1.3334,
|
| 292 |
+
"eval_samples_per_second": 203.247,
|
| 293 |
+
"eval_steps_per_second": 9.0,
|
| 294 |
+
"step": 405
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 16.0,
|
| 298 |
+
"grad_norm": 4.923061847686768,
|
| 299 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 300 |
+
"loss": 0.4176,
|
| 301 |
+
"step": 432
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 16.0,
|
| 305 |
+
"eval_accuracy": 0.7712177121771218,
|
| 306 |
+
"eval_f1": 0.767099786720493,
|
| 307 |
+
"eval_loss": 0.9529668688774109,
|
| 308 |
+
"eval_precision": 0.7719573695224307,
|
| 309 |
+
"eval_recall": 0.7712177121771218,
|
| 310 |
+
"eval_runtime": 1.5294,
|
| 311 |
+
"eval_samples_per_second": 177.199,
|
| 312 |
+
"eval_steps_per_second": 7.846,
|
| 313 |
+
"step": 432
|
| 314 |
+
}
|
| 315 |
+
],
|
| 316 |
+
"logging_steps": 500,
|
| 317 |
+
"max_steps": 540,
|
| 318 |
+
"num_input_tokens_seen": 0,
|
| 319 |
+
"num_train_epochs": 20,
|
| 320 |
+
"save_steps": 500,
|
| 321 |
+
"stateful_callbacks": {
|
| 322 |
+
"TrainerControl": {
|
| 323 |
+
"args": {
|
| 324 |
+
"should_epoch_stop": false,
|
| 325 |
+
"should_evaluate": false,
|
| 326 |
+
"should_log": false,
|
| 327 |
+
"should_save": true,
|
| 328 |
+
"should_training_stop": false
|
| 329 |
+
},
|
| 330 |
+
"attributes": {}
|
| 331 |
+
}
|
| 332 |
+
},
|
| 333 |
+
"total_flos": 2652516628070400.0,
|
| 334 |
+
"train_batch_size": 24,
|
| 335 |
+
"trial_name": null,
|
| 336 |
+
"trial_params": null
|
| 337 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a07a3011f2414b1e1b491fa36d8ad11fa0a10bfec0bc2623df1c462c1d04be15
|
| 3 |
+
size 5304
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|