Push best model used for final benchmarks (single-trial)
Browse files- checkpoint-1647/config.json +40 -0
- checkpoint-1647/model.safetensors +3 -0
- checkpoint-1647/optimizer.pt +3 -0
- checkpoint-1647/rng_state.pth +3 -0
- checkpoint-1647/scheduler.pt +3 -0
- checkpoint-1647/special_tokens_map.json +7 -0
- checkpoint-1647/tokenizer.json +0 -0
- checkpoint-1647/tokenizer_config.json +58 -0
- checkpoint-1647/trainer_state.json +267 -0
- checkpoint-1647/training_args.bin +3 -0
- checkpoint-1647/vocab.txt +0 -0
- model.safetensors +1 -1
- training_args.bin +1 -1
checkpoint-1647/config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"classifier_dropout": null,
|
| 7 |
+
"directionality": "bidi",
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "Seguro",
|
| 13 |
+
"1": "Inseguro"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"Inseguro": 1,
|
| 19 |
+
"Seguro": 0
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-12,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "bert",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_hidden_layers": 12,
|
| 26 |
+
"output_past": true,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"pooler_fc_size": 768,
|
| 29 |
+
"pooler_num_attention_heads": 12,
|
| 30 |
+
"pooler_num_fc_layers": 3,
|
| 31 |
+
"pooler_size_per_head": 128,
|
| 32 |
+
"pooler_type": "first_token_transform",
|
| 33 |
+
"position_embedding_type": "absolute",
|
| 34 |
+
"problem_type": "single_label_classification",
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.55.4",
|
| 37 |
+
"type_vocab_size": 2,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 29794
|
| 40 |
+
}
|
checkpoint-1647/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b36091d1fd63a3f365189ab7b00abb485de8d159c7174e1d711f6a66aeafdba
|
| 3 |
+
size 435722224
|
checkpoint-1647/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5c45065a14534808adb919d4dfb749a07e17e544125b1a29265b2f53112112e
|
| 3 |
+
size 871568779
|
checkpoint-1647/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1323aea319bd811e052d9be477961aa9a57a0c42fb8c589d68fe3107ac9cfda0
|
| 3 |
+
size 14645
|
checkpoint-1647/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:236964c179140e0046e90da60ccabcca353fd0854fde6f90620ec02440f0623c
|
| 3 |
+
size 1465
|
checkpoint-1647/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 |
+
}
|
checkpoint-1647/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1647/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
checkpoint-1647/trainer_state.json
ADDED
|
@@ -0,0 +1,267 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1647,
|
| 3 |
+
"best_metric": 0.8439615808534089,
|
| 4 |
+
"best_model_checkpoint": "outputs/final-run/checkpoint-1647",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1647,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.030367446097783177,
|
| 14 |
+
"grad_norm": 3.759279251098633,
|
| 15 |
+
"learning_rate": 4.9993175434955904e-05,
|
| 16 |
+
"loss": 0.5855,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.06073489219556635,
|
| 21 |
+
"grad_norm": 3.995187997817993,
|
| 22 |
+
"learning_rate": 4.997214569648075e-05,
|
| 23 |
+
"loss": 0.4801,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.09110233829334953,
|
| 28 |
+
"grad_norm": 4.418132305145264,
|
| 29 |
+
"learning_rate": 4.993691989695869e-05,
|
| 30 |
+
"loss": 0.4644,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.1214697843911327,
|
| 35 |
+
"grad_norm": 7.35609245300293,
|
| 36 |
+
"learning_rate": 4.9887518061405046e-05,
|
| 37 |
+
"loss": 0.4708,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.15183723048891587,
|
| 42 |
+
"grad_norm": 3.4698946475982666,
|
| 43 |
+
"learning_rate": 4.98239682735689e-05,
|
| 44 |
+
"loss": 0.4769,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.18220467658669906,
|
| 49 |
+
"grad_norm": 5.190053462982178,
|
| 50 |
+
"learning_rate": 4.97463066599681e-05,
|
| 51 |
+
"loss": 0.462,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.21257212268448222,
|
| 56 |
+
"grad_norm": 3.3676445484161377,
|
| 57 |
+
"learning_rate": 4.9654577369352275e-05,
|
| 58 |
+
"loss": 0.4263,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.2429395687822654,
|
| 63 |
+
"grad_norm": 4.057737827301025,
|
| 64 |
+
"learning_rate": 4.954883254760527e-05,
|
| 65 |
+
"loss": 0.4322,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.2733070148800486,
|
| 70 |
+
"grad_norm": 4.348636627197266,
|
| 71 |
+
"learning_rate": 4.942913230810156e-05,
|
| 72 |
+
"loss": 0.4368,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.30367446097783174,
|
| 77 |
+
"grad_norm": 4.458230972290039,
|
| 78 |
+
"learning_rate": 4.929554469753313e-05,
|
| 79 |
+
"loss": 0.4383,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.33404190707561493,
|
| 84 |
+
"grad_norm": 3.5264790058135986,
|
| 85 |
+
"learning_rate": 4.914814565722671e-05,
|
| 86 |
+
"loss": 0.4101,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.3644093531733981,
|
| 91 |
+
"grad_norm": 2.5985169410705566,
|
| 92 |
+
"learning_rate": 4.898701897997286e-05,
|
| 93 |
+
"loss": 0.4349,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.3947767992711813,
|
| 98 |
+
"grad_norm": 4.361725330352783,
|
| 99 |
+
"learning_rate": 4.881225626239183e-05,
|
| 100 |
+
"loss": 0.4352,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.42514424536896445,
|
| 105 |
+
"grad_norm": 6.791547775268555,
|
| 106 |
+
"learning_rate": 4.862395685286315e-05,
|
| 107 |
+
"loss": 0.4302,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.45551169146674764,
|
| 112 |
+
"grad_norm": 3.1053969860076904,
|
| 113 |
+
"learning_rate": 4.8422227795048366e-05,
|
| 114 |
+
"loss": 0.4309,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.4858791375645308,
|
| 119 |
+
"grad_norm": 3.0548689365386963,
|
| 120 |
+
"learning_rate": 4.820718376703942e-05,
|
| 121 |
+
"loss": 0.416,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.516246583662314,
|
| 126 |
+
"grad_norm": 2.279533863067627,
|
| 127 |
+
"learning_rate": 4.797894701616685e-05,
|
| 128 |
+
"loss": 0.389,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.5466140297600972,
|
| 133 |
+
"grad_norm": 2.994495153427124,
|
| 134 |
+
"learning_rate": 4.7737647289505165e-05,
|
| 135 |
+
"loss": 0.4273,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.5769814758578804,
|
| 140 |
+
"grad_norm": 8.744857788085938,
|
| 141 |
+
"learning_rate": 4.7483421760114794e-05,
|
| 142 |
+
"loss": 0.3995,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6073489219556635,
|
| 147 |
+
"grad_norm": 4.29746675491333,
|
| 148 |
+
"learning_rate": 4.721641494906247e-05,
|
| 149 |
+
"loss": 0.4138,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.6377163680534467,
|
| 154 |
+
"grad_norm": 3.721235752105713,
|
| 155 |
+
"learning_rate": 4.6936778643264536e-05,
|
| 156 |
+
"loss": 0.4512,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.6680838141512299,
|
| 161 |
+
"grad_norm": 3.44572377204895,
|
| 162 |
+
"learning_rate": 4.6644671809199724e-05,
|
| 163 |
+
"loss": 0.3942,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.698451260249013,
|
| 168 |
+
"grad_norm": 4.377917289733887,
|
| 169 |
+
"learning_rate": 4.634026050254061e-05,
|
| 170 |
+
"loss": 0.4073,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.7288187063467962,
|
| 175 |
+
"grad_norm": 5.745212078094482,
|
| 176 |
+
"learning_rate": 4.6023717773754885e-05,
|
| 177 |
+
"loss": 0.4088,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.7591861524445794,
|
| 182 |
+
"grad_norm": 3.8439931869506836,
|
| 183 |
+
"learning_rate": 4.569522356973043e-05,
|
| 184 |
+
"loss": 0.418,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.7895535985423626,
|
| 189 |
+
"grad_norm": 5.334071636199951,
|
| 190 |
+
"learning_rate": 4.535496463147986e-05,
|
| 191 |
+
"loss": 0.4025,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.8199210446401458,
|
| 196 |
+
"grad_norm": 6.255934715270996,
|
| 197 |
+
"learning_rate": 4.50031343879827e-05,
|
| 198 |
+
"loss": 0.4123,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.8502884907379289,
|
| 203 |
+
"grad_norm": 3.375969886779785,
|
| 204 |
+
"learning_rate": 4.463993284622576e-05,
|
| 205 |
+
"loss": 0.4252,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.8806559368357121,
|
| 210 |
+
"grad_norm": 2.6879310607910156,
|
| 211 |
+
"learning_rate": 4.4265566477503974e-05,
|
| 212 |
+
"loss": 0.4036,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.9110233829334953,
|
| 217 |
+
"grad_norm": 5.248851299285889,
|
| 218 |
+
"learning_rate": 4.388024810004645e-05,
|
| 219 |
+
"loss": 0.3834,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.9413908290312785,
|
| 224 |
+
"grad_norm": 2.5022025108337402,
|
| 225 |
+
"learning_rate": 4.3484196758034466e-05,
|
| 226 |
+
"loss": 0.4122,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.9717582751290617,
|
| 231 |
+
"grad_norm": 4.558413982391357,
|
| 232 |
+
"learning_rate": 4.3077637597080155e-05,
|
| 233 |
+
"loss": 0.3766,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.0,
|
| 238 |
+
"eval_f1": 0.8439615808534089,
|
| 239 |
+
"eval_loss": 0.39440903067588806,
|
| 240 |
+
"eval_runtime": 7.9221,
|
| 241 |
+
"eval_samples_per_second": 738.823,
|
| 242 |
+
"eval_steps_per_second": 23.1,
|
| 243 |
+
"step": 1647
|
| 244 |
+
}
|
| 245 |
+
],
|
| 246 |
+
"logging_steps": 50,
|
| 247 |
+
"max_steps": 6588,
|
| 248 |
+
"num_input_tokens_seen": 0,
|
| 249 |
+
"num_train_epochs": 4,
|
| 250 |
+
"save_steps": 500,
|
| 251 |
+
"stateful_callbacks": {
|
| 252 |
+
"TrainerControl": {
|
| 253 |
+
"args": {
|
| 254 |
+
"should_epoch_stop": false,
|
| 255 |
+
"should_evaluate": false,
|
| 256 |
+
"should_log": false,
|
| 257 |
+
"should_save": true,
|
| 258 |
+
"should_training_stop": false
|
| 259 |
+
},
|
| 260 |
+
"attributes": {}
|
| 261 |
+
}
|
| 262 |
+
},
|
| 263 |
+
"total_flos": 1.385884861897728e+16,
|
| 264 |
+
"train_batch_size": 16,
|
| 265 |
+
"trial_name": null,
|
| 266 |
+
"trial_params": null
|
| 267 |
+
}
|
checkpoint-1647/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d50f02e3b26ffa6e3258d1872fcceca06867b6d55c47fa4471293944f8b4653
|
| 3 |
+
size 5841
|
checkpoint-1647/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 435722224
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b36091d1fd63a3f365189ab7b00abb485de8d159c7174e1d711f6a66aeafdba
|
| 3 |
size 435722224
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d50f02e3b26ffa6e3258d1872fcceca06867b6d55c47fa4471293944f8b4653
|
| 3 |
size 5841
|