Upload 11 files
Browse files- checkpoint-19000/config.json +42 -0
- checkpoint-19000/model.safetensors +3 -0
- checkpoint-19000/optimizer.pt +3 -0
- checkpoint-19000/rng_state.pth +3 -0
- checkpoint-19000/scheduler.pt +3 -0
- checkpoint-19000/special_tokens_map.json +7 -0
- checkpoint-19000/tokenizer.json +0 -0
- checkpoint-19000/tokenizer_config.json +55 -0
- checkpoint-19000/trainer_state.json +287 -0
- checkpoint-19000/training_args.bin +3 -0
- checkpoint-19000/vocab.txt +0 -0
checkpoint-19000/config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google-bert/bert-large-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"finetuning_task": "text-classification",
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "0",
|
| 16 |
+
"1": "1"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 4096,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"0": 0,
|
| 22 |
+
"1": 1
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 16,
|
| 28 |
+
"num_hidden_layers": 24,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"pooler_fc_size": 768,
|
| 31 |
+
"pooler_num_attention_heads": 12,
|
| 32 |
+
"pooler_num_fc_layers": 3,
|
| 33 |
+
"pooler_size_per_head": 128,
|
| 34 |
+
"pooler_type": "first_token_transform",
|
| 35 |
+
"position_embedding_type": "absolute",
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.39.0.dev0",
|
| 39 |
+
"type_vocab_size": 2,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 28996
|
| 42 |
+
}
|
checkpoint-19000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca28f99649e5606bfbdd95b8c5bc529a059238cd11089887dd23fddc9910cb39
|
| 3 |
+
size 1334372264
|
checkpoint-19000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1f8d539a5d94d828ca56b8d75ec558a9e62be0a7e2e24500184029313440569
|
| 3 |
+
size 2668979437
|
checkpoint-19000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84df1c57ae4ab5eb5fcf4a02445721129e24a7776a43a6d2daf018ba7ab0cf54
|
| 3 |
+
size 14308
|
checkpoint-19000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04501795a453f947ccc697c977d86ae65e81fc2490316843136cd0578f939861
|
| 3 |
+
size 1064
|
checkpoint-19000/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-19000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-19000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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_lower_case": false,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
checkpoint-19000/trainer_state.json
ADDED
|
@@ -0,0 +1,287 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.5,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 19000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.25,
|
| 13 |
+
"grad_norm": 8.33536148071289,
|
| 14 |
+
"learning_rate": 1.9545454545454546e-05,
|
| 15 |
+
"loss": 0.5027,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5,
|
| 20 |
+
"grad_norm": 142.45716857910156,
|
| 21 |
+
"learning_rate": 1.9090909090909094e-05,
|
| 22 |
+
"loss": 0.3982,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.75,
|
| 27 |
+
"grad_norm": 41.095272064208984,
|
| 28 |
+
"learning_rate": 1.8636363636363638e-05,
|
| 29 |
+
"loss": 0.3902,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.0,
|
| 34 |
+
"grad_norm": 1.3833879232406616,
|
| 35 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 36 |
+
"loss": 0.3792,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.25,
|
| 41 |
+
"grad_norm": 22.25682258605957,
|
| 42 |
+
"learning_rate": 1.772727272727273e-05,
|
| 43 |
+
"loss": 0.2412,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.5,
|
| 48 |
+
"grad_norm": 0.08785621076822281,
|
| 49 |
+
"learning_rate": 1.7272727272727274e-05,
|
| 50 |
+
"loss": 0.2646,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.75,
|
| 55 |
+
"grad_norm": 0.1938224732875824,
|
| 56 |
+
"learning_rate": 1.681818181818182e-05,
|
| 57 |
+
"loss": 0.2591,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.0,
|
| 62 |
+
"grad_norm": 0.19619984924793243,
|
| 63 |
+
"learning_rate": 1.6363636363636366e-05,
|
| 64 |
+
"loss": 0.2579,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.25,
|
| 69 |
+
"grad_norm": 0.052116330713033676,
|
| 70 |
+
"learning_rate": 1.590909090909091e-05,
|
| 71 |
+
"loss": 0.1256,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 2.5,
|
| 76 |
+
"grad_norm": 19.55641746520996,
|
| 77 |
+
"learning_rate": 1.5454545454545454e-05,
|
| 78 |
+
"loss": 0.1313,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.75,
|
| 83 |
+
"grad_norm": 0.09100260585546494,
|
| 84 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 85 |
+
"loss": 0.1431,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 3.0,
|
| 90 |
+
"grad_norm": 0.006416453048586845,
|
| 91 |
+
"learning_rate": 1.4545454545454546e-05,
|
| 92 |
+
"loss": 0.1158,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.25,
|
| 97 |
+
"grad_norm": 0.9075784087181091,
|
| 98 |
+
"learning_rate": 1.4090909090909092e-05,
|
| 99 |
+
"loss": 0.0716,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 3.5,
|
| 104 |
+
"grad_norm": 0.0059479945339262486,
|
| 105 |
+
"learning_rate": 1.3636363636363637e-05,
|
| 106 |
+
"loss": 0.0638,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.75,
|
| 111 |
+
"grad_norm": 0.03586824983358383,
|
| 112 |
+
"learning_rate": 1.3181818181818183e-05,
|
| 113 |
+
"loss": 0.0713,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.0,
|
| 118 |
+
"grad_norm": 0.029572978615760803,
|
| 119 |
+
"learning_rate": 1.2727272727272728e-05,
|
| 120 |
+
"loss": 0.0798,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 4.25,
|
| 125 |
+
"grad_norm": 0.029360467568039894,
|
| 126 |
+
"learning_rate": 1.2272727272727274e-05,
|
| 127 |
+
"loss": 0.0432,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.5,
|
| 132 |
+
"grad_norm": 1.2467519044876099,
|
| 133 |
+
"learning_rate": 1.181818181818182e-05,
|
| 134 |
+
"loss": 0.0563,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.75,
|
| 139 |
+
"grad_norm": 0.03312988951802254,
|
| 140 |
+
"learning_rate": 1.1363636363636366e-05,
|
| 141 |
+
"loss": 0.05,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 5.0,
|
| 146 |
+
"grad_norm": 0.034050144255161285,
|
| 147 |
+
"learning_rate": 1.0909090909090909e-05,
|
| 148 |
+
"loss": 0.0727,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 5.25,
|
| 153 |
+
"grad_norm": 0.012058685533702374,
|
| 154 |
+
"learning_rate": 1.0454545454545455e-05,
|
| 155 |
+
"loss": 0.0158,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 5.5,
|
| 160 |
+
"grad_norm": 0.004920224193483591,
|
| 161 |
+
"learning_rate": 1e-05,
|
| 162 |
+
"loss": 0.0524,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 5.75,
|
| 167 |
+
"grad_norm": 0.038101330399513245,
|
| 168 |
+
"learning_rate": 9.545454545454547e-06,
|
| 169 |
+
"loss": 0.0604,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 6.0,
|
| 174 |
+
"grad_norm": 0.019437963142991066,
|
| 175 |
+
"learning_rate": 9.090909090909091e-06,
|
| 176 |
+
"loss": 0.0386,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 6.25,
|
| 181 |
+
"grad_norm": 0.012455708347260952,
|
| 182 |
+
"learning_rate": 8.636363636363637e-06,
|
| 183 |
+
"loss": 0.0285,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 6.5,
|
| 188 |
+
"grad_norm": 0.04723620414733887,
|
| 189 |
+
"learning_rate": 8.181818181818183e-06,
|
| 190 |
+
"loss": 0.03,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 6.75,
|
| 195 |
+
"grad_norm": 0.005396988242864609,
|
| 196 |
+
"learning_rate": 7.727272727272727e-06,
|
| 197 |
+
"loss": 0.0169,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 7.0,
|
| 202 |
+
"grad_norm": 0.002131987828761339,
|
| 203 |
+
"learning_rate": 7.272727272727273e-06,
|
| 204 |
+
"loss": 0.0326,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 7.25,
|
| 209 |
+
"grad_norm": 0.01090204156935215,
|
| 210 |
+
"learning_rate": 6.818181818181818e-06,
|
| 211 |
+
"loss": 0.0181,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.5,
|
| 216 |
+
"grad_norm": 0.010536236688494682,
|
| 217 |
+
"learning_rate": 6.363636363636364e-06,
|
| 218 |
+
"loss": 0.0115,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.75,
|
| 223 |
+
"grad_norm": 0.004000788554549217,
|
| 224 |
+
"learning_rate": 5.90909090909091e-06,
|
| 225 |
+
"loss": 0.0161,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 8.0,
|
| 230 |
+
"grad_norm": 0.0018032905645668507,
|
| 231 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 232 |
+
"loss": 0.0254,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 8.25,
|
| 237 |
+
"grad_norm": 0.004049360752105713,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.0122,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 8.5,
|
| 244 |
+
"grad_norm": 0.005948635283857584,
|
| 245 |
+
"learning_rate": 4.5454545454545455e-06,
|
| 246 |
+
"loss": 0.0096,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 8.75,
|
| 251 |
+
"grad_norm": 0.12555870413780212,
|
| 252 |
+
"learning_rate": 4.0909090909090915e-06,
|
| 253 |
+
"loss": 0.0096,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 9.0,
|
| 258 |
+
"grad_norm": 0.0012050127843394876,
|
| 259 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 260 |
+
"loss": 0.0042,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 9.25,
|
| 265 |
+
"grad_norm": 0.0018056471599265933,
|
| 266 |
+
"learning_rate": 3.181818181818182e-06,
|
| 267 |
+
"loss": 0.0045,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 9.5,
|
| 272 |
+
"grad_norm": 0.00016128216520883143,
|
| 273 |
+
"learning_rate": 2.7272727272727272e-06,
|
| 274 |
+
"loss": 0.0052,
|
| 275 |
+
"step": 19000
|
| 276 |
+
}
|
| 277 |
+
],
|
| 278 |
+
"logging_steps": 500,
|
| 279 |
+
"max_steps": 22000,
|
| 280 |
+
"num_input_tokens_seen": 0,
|
| 281 |
+
"num_train_epochs": 11,
|
| 282 |
+
"save_steps": 500,
|
| 283 |
+
"total_flos": 1.4159485554996634e+17,
|
| 284 |
+
"train_batch_size": 8,
|
| 285 |
+
"trial_name": null,
|
| 286 |
+
"trial_params": null
|
| 287 |
+
}
|
checkpoint-19000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:841cca5ca8f442bb498a1e599a68b8668b20af506517904fc9f8db7b28756855
|
| 3 |
+
size 4920
|
checkpoint-19000/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|