Upload 8 files
Browse files- config.json +32 -0
- generation_config.json +5 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +278 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "hfl/chinese-bert-wwm",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"output_past": true,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"pooler_fc_size": 768,
|
| 22 |
+
"pooler_num_attention_heads": 12,
|
| 23 |
+
"pooler_num_fc_layers": 3,
|
| 24 |
+
"pooler_size_per_head": 128,
|
| 25 |
+
"pooler_type": "first_token_transform",
|
| 26 |
+
"position_embedding_type": "absolute",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.42.0.dev0",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 21128
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"pad_token_id": 0,
|
| 4 |
+
"transformers_version": "4.42.0.dev0"
|
| 5 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d87709382d23cd04c5fc114b7711b81a0cb5b20e63356c25192dac784ec4d0b1
|
| 3 |
+
size 409184912
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 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 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,278 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 17799,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08427439743805831,
|
| 13 |
+
"grad_norm": 2.7859835624694824,
|
| 14 |
+
"learning_rate": 4.85954267093657e-05,
|
| 15 |
+
"loss": 1.5305,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16854879487611663,
|
| 20 |
+
"grad_norm": 2.8764379024505615,
|
| 21 |
+
"learning_rate": 4.719085341873139e-05,
|
| 22 |
+
"loss": 1.392,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.25282319231417494,
|
| 27 |
+
"grad_norm": 2.9515156745910645,
|
| 28 |
+
"learning_rate": 4.578628012809709e-05,
|
| 29 |
+
"loss": 1.3312,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.33709758975223325,
|
| 34 |
+
"grad_norm": 2.6709630489349365,
|
| 35 |
+
"learning_rate": 4.438170683746278e-05,
|
| 36 |
+
"loss": 1.294,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.42137198719029156,
|
| 41 |
+
"grad_norm": 2.601968765258789,
|
| 42 |
+
"learning_rate": 4.2977133546828475e-05,
|
| 43 |
+
"loss": 1.2561,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5056463846283499,
|
| 48 |
+
"grad_norm": 2.6964409351348877,
|
| 49 |
+
"learning_rate": 4.157256025619417e-05,
|
| 50 |
+
"loss": 1.2364,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5899207820664082,
|
| 55 |
+
"grad_norm": 2.479663610458374,
|
| 56 |
+
"learning_rate": 4.016798696555987e-05,
|
| 57 |
+
"loss": 1.215,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.6741951795044665,
|
| 62 |
+
"grad_norm": 2.6350433826446533,
|
| 63 |
+
"learning_rate": 3.876341367492556e-05,
|
| 64 |
+
"loss": 1.1925,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.7584695769425248,
|
| 69 |
+
"grad_norm": 2.7347450256347656,
|
| 70 |
+
"learning_rate": 3.7358840384291254e-05,
|
| 71 |
+
"loss": 1.1831,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8427439743805831,
|
| 76 |
+
"grad_norm": 2.7404720783233643,
|
| 77 |
+
"learning_rate": 3.5954267093656953e-05,
|
| 78 |
+
"loss": 1.1657,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.9270183718186416,
|
| 83 |
+
"grad_norm": 2.71294903755188,
|
| 84 |
+
"learning_rate": 3.454969380302264e-05,
|
| 85 |
+
"loss": 1.1629,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0112927692566998,
|
| 90 |
+
"grad_norm": 2.6705377101898193,
|
| 91 |
+
"learning_rate": 3.314512051238834e-05,
|
| 92 |
+
"loss": 1.1435,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.0955671666947582,
|
| 97 |
+
"grad_norm": 2.524048089981079,
|
| 98 |
+
"learning_rate": 3.174054722175403e-05,
|
| 99 |
+
"loss": 1.1304,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.1798415641328164,
|
| 104 |
+
"grad_norm": 2.6250593662261963,
|
| 105 |
+
"learning_rate": 3.0335973931119726e-05,
|
| 106 |
+
"loss": 1.1167,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.2641159615708748,
|
| 111 |
+
"grad_norm": 2.3546817302703857,
|
| 112 |
+
"learning_rate": 2.8931400640485422e-05,
|
| 113 |
+
"loss": 1.1121,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.348390359008933,
|
| 118 |
+
"grad_norm": 2.7167067527770996,
|
| 119 |
+
"learning_rate": 2.7526827349851115e-05,
|
| 120 |
+
"loss": 1.1065,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.4326647564469914,
|
| 125 |
+
"grad_norm": 2.4628195762634277,
|
| 126 |
+
"learning_rate": 2.6122254059216812e-05,
|
| 127 |
+
"loss": 1.0953,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.5169391538850499,
|
| 132 |
+
"grad_norm": 2.47514009475708,
|
| 133 |
+
"learning_rate": 2.4717680768582505e-05,
|
| 134 |
+
"loss": 1.0898,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.601213551323108,
|
| 139 |
+
"grad_norm": 2.240252733230591,
|
| 140 |
+
"learning_rate": 2.33131074779482e-05,
|
| 141 |
+
"loss": 1.0734,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.6854879487611663,
|
| 146 |
+
"grad_norm": 2.6827552318573,
|
| 147 |
+
"learning_rate": 2.1908534187313894e-05,
|
| 148 |
+
"loss": 1.0771,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.7697623461992247,
|
| 153 |
+
"grad_norm": 2.446568012237549,
|
| 154 |
+
"learning_rate": 2.0503960896679587e-05,
|
| 155 |
+
"loss": 1.0727,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.854036743637283,
|
| 160 |
+
"grad_norm": 2.437731981277466,
|
| 161 |
+
"learning_rate": 1.9099387606045284e-05,
|
| 162 |
+
"loss": 1.0573,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.9383111410753413,
|
| 167 |
+
"grad_norm": 2.6201038360595703,
|
| 168 |
+
"learning_rate": 1.769481431541098e-05,
|
| 169 |
+
"loss": 1.0561,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.0225855385133995,
|
| 174 |
+
"grad_norm": 2.4613335132598877,
|
| 175 |
+
"learning_rate": 1.6290241024776673e-05,
|
| 176 |
+
"loss": 1.0531,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.106859935951458,
|
| 181 |
+
"grad_norm": 2.459319591522217,
|
| 182 |
+
"learning_rate": 1.488566773414237e-05,
|
| 183 |
+
"loss": 1.0409,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.1911343333895164,
|
| 188 |
+
"grad_norm": 2.536198616027832,
|
| 189 |
+
"learning_rate": 1.3481094443508063e-05,
|
| 190 |
+
"loss": 1.0388,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.2754087308275746,
|
| 195 |
+
"grad_norm": 2.503535270690918,
|
| 196 |
+
"learning_rate": 1.2076521152873758e-05,
|
| 197 |
+
"loss": 1.0326,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.3596831282656328,
|
| 202 |
+
"grad_norm": 2.47710919380188,
|
| 203 |
+
"learning_rate": 1.0671947862239452e-05,
|
| 204 |
+
"loss": 1.0246,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.4439575257036914,
|
| 209 |
+
"grad_norm": 2.4275453090667725,
|
| 210 |
+
"learning_rate": 9.267374571605147e-06,
|
| 211 |
+
"loss": 1.0228,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.5282319231417496,
|
| 216 |
+
"grad_norm": 2.4777779579162598,
|
| 217 |
+
"learning_rate": 7.862801280970842e-06,
|
| 218 |
+
"loss": 1.029,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.612506320579808,
|
| 223 |
+
"grad_norm": 2.574960470199585,
|
| 224 |
+
"learning_rate": 6.458227990336537e-06,
|
| 225 |
+
"loss": 1.0215,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.696780718017866,
|
| 230 |
+
"grad_norm": 2.5446507930755615,
|
| 231 |
+
"learning_rate": 5.053654699702231e-06,
|
| 232 |
+
"loss": 1.0206,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.7810551154559247,
|
| 237 |
+
"grad_norm": 2.7360856533050537,
|
| 238 |
+
"learning_rate": 3.6490814090679254e-06,
|
| 239 |
+
"loss": 1.0215,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.865329512893983,
|
| 244 |
+
"grad_norm": 2.4522464275360107,
|
| 245 |
+
"learning_rate": 2.2445081184336198e-06,
|
| 246 |
+
"loss": 1.017,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.949603910332041,
|
| 251 |
+
"grad_norm": 2.5468955039978027,
|
| 252 |
+
"learning_rate": 8.399348277993145e-07,
|
| 253 |
+
"loss": 1.0105,
|
| 254 |
+
"step": 17500
|
| 255 |
+
}
|
| 256 |
+
],
|
| 257 |
+
"logging_steps": 500,
|
| 258 |
+
"max_steps": 17799,
|
| 259 |
+
"num_input_tokens_seen": 0,
|
| 260 |
+
"num_train_epochs": 3,
|
| 261 |
+
"save_steps": 500,
|
| 262 |
+
"stateful_callbacks": {
|
| 263 |
+
"TrainerControl": {
|
| 264 |
+
"args": {
|
| 265 |
+
"should_epoch_stop": false,
|
| 266 |
+
"should_evaluate": false,
|
| 267 |
+
"should_log": false,
|
| 268 |
+
"should_save": true,
|
| 269 |
+
"should_training_stop": true
|
| 270 |
+
},
|
| 271 |
+
"attributes": {}
|
| 272 |
+
}
|
| 273 |
+
},
|
| 274 |
+
"total_flos": 1.4989245699264307e+17,
|
| 275 |
+
"train_batch_size": 128,
|
| 276 |
+
"trial_name": null,
|
| 277 |
+
"trial_params": null
|
| 278 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|