Upload folder using huggingface_hub
Browse files- config.json +34 -0
- model.safetensors +3 -0
- optimizer_state_dict.pth +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +53 -0
- trainer_state.json +238 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "zhihan1996/DNABERT-2-117M",
|
| 3 |
+
"alibi_starting_size": 512,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "zhihan1996/DNABERT-2-117M--configuration_bert.BertConfig",
|
| 10 |
+
"AutoModel": "zhihan1996/DNABERT-2-117M--bert_layers.BertModel",
|
| 11 |
+
"AutoModelForMaskedLM": "zhihan1996/DNABERT-2-117M--bert_layers.BertForMaskedLM",
|
| 12 |
+
"AutoModelForSequenceClassification": "zhihan1996/DNABERT-2-117M--bert_layers.BertForSequenceClassification"
|
| 13 |
+
},
|
| 14 |
+
"classifier_dropout": null,
|
| 15 |
+
"gradient_checkpointing": false,
|
| 16 |
+
"hidden_act": "gelu",
|
| 17 |
+
"hidden_dropout_prob": 0.1,
|
| 18 |
+
"hidden_size": 768,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 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 |
+
"pad_token_id": 0,
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.45.2",
|
| 31 |
+
"type_vocab_size": 2,
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 4096
|
| 34 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de5d78935d50096fe6466cbce89f0c0f469b9122dfbaa29085551f5528dd5915
|
| 3 |
+
size 468296408
|
optimizer_state_dict.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f024fc7063b162d5183dc95d21f9b94982cf3e125e5566eec22a5de2f9ee658
|
| 3 |
+
size 936682546
|
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 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[PAD]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"mask_token": "[MASK]",
|
| 47 |
+
"model_max_length": 256,
|
| 48 |
+
"pad_token": "[PAD]",
|
| 49 |
+
"padding_side": "right",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 52 |
+
"unk_token": "[UNK]"
|
| 53 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,238 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5978685021400452,
|
| 3 |
+
"best_model_checkpoint": "output_pipe/H3K4me2/origin/checkpoint-600",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 200,
|
| 6 |
+
"global_step": 1536,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.2604166666666667,
|
| 13 |
+
"grad_norm": 1.0357736349105835,
|
| 14 |
+
"learning_rate": 2.8990578734858683e-05,
|
| 15 |
+
"loss": 0.6584,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5208333333333334,
|
| 20 |
+
"grad_norm": 1.2759062051773071,
|
| 21 |
+
"learning_rate": 2.6971736204576044e-05,
|
| 22 |
+
"loss": 0.6222,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.5208333333333334,
|
| 27 |
+
"eval_accuracy": 0.6614532420984034,
|
| 28 |
+
"eval_f1": 0.6361047175053332,
|
| 29 |
+
"eval_loss": 0.6185658574104309,
|
| 30 |
+
"eval_matthews_correlation": 0.284168383038996,
|
| 31 |
+
"eval_precision": 0.6497384693163257,
|
| 32 |
+
"eval_recall": 0.6348211823716587,
|
| 33 |
+
"eval_runtime": 0.9343,
|
| 34 |
+
"eval_samples_per_second": 3284.819,
|
| 35 |
+
"eval_steps_per_second": 51.375,
|
| 36 |
+
"step": 200
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.78125,
|
| 40 |
+
"grad_norm": 1.4777441024780273,
|
| 41 |
+
"learning_rate": 2.4952893674293406e-05,
|
| 42 |
+
"loss": 0.6177,
|
| 43 |
+
"step": 300
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 1.0416666666666667,
|
| 47 |
+
"grad_norm": 1.9883569478988647,
|
| 48 |
+
"learning_rate": 2.293405114401077e-05,
|
| 49 |
+
"loss": 0.6007,
|
| 50 |
+
"step": 400
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.0416666666666667,
|
| 54 |
+
"eval_accuracy": 0.6709025741283806,
|
| 55 |
+
"eval_f1": 0.6631700218287655,
|
| 56 |
+
"eval_loss": 0.6283741593360901,
|
| 57 |
+
"eval_matthews_correlation": 0.3269374978804985,
|
| 58 |
+
"eval_precision": 0.6624143979883257,
|
| 59 |
+
"eval_recall": 0.6645299444573319,
|
| 60 |
+
"eval_runtime": 0.9012,
|
| 61 |
+
"eval_samples_per_second": 3405.571,
|
| 62 |
+
"eval_steps_per_second": 53.264,
|
| 63 |
+
"step": 400
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.3020833333333333,
|
| 67 |
+
"grad_norm": 2.09269642829895,
|
| 68 |
+
"learning_rate": 2.091520861372813e-05,
|
| 69 |
+
"loss": 0.5654,
|
| 70 |
+
"step": 500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.5625,
|
| 74 |
+
"grad_norm": 3.317641019821167,
|
| 75 |
+
"learning_rate": 1.8896366083445493e-05,
|
| 76 |
+
"loss": 0.5463,
|
| 77 |
+
"step": 600
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.5625,
|
| 81 |
+
"eval_accuracy": 0.6813294232649071,
|
| 82 |
+
"eval_f1": 0.6726760569524175,
|
| 83 |
+
"eval_loss": 0.5978685021400452,
|
| 84 |
+
"eval_matthews_correlation": 0.34548601335973167,
|
| 85 |
+
"eval_precision": 0.6721798495455928,
|
| 86 |
+
"eval_recall": 0.6733080057599804,
|
| 87 |
+
"eval_runtime": 0.9094,
|
| 88 |
+
"eval_samples_per_second": 3374.893,
|
| 89 |
+
"eval_steps_per_second": 52.784,
|
| 90 |
+
"step": 600
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.8229166666666665,
|
| 94 |
+
"grad_norm": 3.3898849487304688,
|
| 95 |
+
"learning_rate": 1.6877523553162854e-05,
|
| 96 |
+
"loss": 0.5393,
|
| 97 |
+
"step": 700
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 2.0833333333333335,
|
| 101 |
+
"grad_norm": 4.201281547546387,
|
| 102 |
+
"learning_rate": 1.4858681022880215e-05,
|
| 103 |
+
"loss": 0.5177,
|
| 104 |
+
"step": 800
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.0833333333333335,
|
| 108 |
+
"eval_accuracy": 0.692733789507983,
|
| 109 |
+
"eval_f1": 0.6796600224409894,
|
| 110 |
+
"eval_loss": 0.6286787986755371,
|
| 111 |
+
"eval_matthews_correlation": 0.36059533610994504,
|
| 112 |
+
"eval_precision": 0.6825659356193707,
|
| 113 |
+
"eval_recall": 0.6780575822963764,
|
| 114 |
+
"eval_runtime": 0.9064,
|
| 115 |
+
"eval_samples_per_second": 3385.737,
|
| 116 |
+
"eval_steps_per_second": 52.954,
|
| 117 |
+
"step": 800
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.34375,
|
| 121 |
+
"grad_norm": 5.131877899169922,
|
| 122 |
+
"learning_rate": 1.2839838492597578e-05,
|
| 123 |
+
"loss": 0.4415,
|
| 124 |
+
"step": 900
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 2.6041666666666665,
|
| 128 |
+
"grad_norm": 5.814933776855469,
|
| 129 |
+
"learning_rate": 1.082099596231494e-05,
|
| 130 |
+
"loss": 0.4314,
|
| 131 |
+
"step": 1000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 2.6041666666666665,
|
| 135 |
+
"eval_accuracy": 0.6982730531117628,
|
| 136 |
+
"eval_f1": 0.6850430893083546,
|
| 137 |
+
"eval_loss": 0.6425515413284302,
|
| 138 |
+
"eval_matthews_correlation": 0.37164248219863616,
|
| 139 |
+
"eval_precision": 0.6884331834568802,
|
| 140 |
+
"eval_recall": 0.6832455038450933,
|
| 141 |
+
"eval_runtime": 0.9061,
|
| 142 |
+
"eval_samples_per_second": 3387.158,
|
| 143 |
+
"eval_steps_per_second": 52.976,
|
| 144 |
+
"step": 1000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.8645833333333335,
|
| 148 |
+
"grad_norm": 9.033439636230469,
|
| 149 |
+
"learning_rate": 8.8021534320323e-06,
|
| 150 |
+
"loss": 0.4256,
|
| 151 |
+
"step": 1100
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 3.125,
|
| 155 |
+
"grad_norm": 9.079912185668945,
|
| 156 |
+
"learning_rate": 6.80349932705249e-06,
|
| 157 |
+
"loss": 0.3744,
|
| 158 |
+
"step": 1200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.125,
|
| 162 |
+
"eval_accuracy": 0.6982730531117628,
|
| 163 |
+
"eval_f1": 0.6806473145055805,
|
| 164 |
+
"eval_loss": 0.7084661722183228,
|
| 165 |
+
"eval_matthews_correlation": 0.3671364961531174,
|
| 166 |
+
"eval_precision": 0.6893956477618672,
|
| 167 |
+
"eval_recall": 0.6779201481137815,
|
| 168 |
+
"eval_runtime": 0.9066,
|
| 169 |
+
"eval_samples_per_second": 3385.043,
|
| 170 |
+
"eval_steps_per_second": 52.943,
|
| 171 |
+
"step": 1200
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 3.3854166666666665,
|
| 175 |
+
"grad_norm": 7.958479881286621,
|
| 176 |
+
"learning_rate": 4.784656796769853e-06,
|
| 177 |
+
"loss": 0.3306,
|
| 178 |
+
"step": 1300
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 3.6458333333333335,
|
| 182 |
+
"grad_norm": 7.019222259521484,
|
| 183 |
+
"learning_rate": 2.7658142664872143e-06,
|
| 184 |
+
"loss": 0.3262,
|
| 185 |
+
"step": 1400
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 3.6458333333333335,
|
| 189 |
+
"eval_accuracy": 0.6953405017921147,
|
| 190 |
+
"eval_f1": 0.6757699928081087,
|
| 191 |
+
"eval_loss": 0.74341881275177,
|
| 192 |
+
"eval_matthews_correlation": 0.35958292147177084,
|
| 193 |
+
"eval_precision": 0.6868629082587893,
|
| 194 |
+
"eval_recall": 0.6729876177929122,
|
| 195 |
+
"eval_runtime": 0.938,
|
| 196 |
+
"eval_samples_per_second": 3272.017,
|
| 197 |
+
"eval_steps_per_second": 51.175,
|
| 198 |
+
"step": 1400
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 3.90625,
|
| 202 |
+
"grad_norm": 9.089224815368652,
|
| 203 |
+
"learning_rate": 7.469717362045761e-07,
|
| 204 |
+
"loss": 0.308,
|
| 205 |
+
"step": 1500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 4.0,
|
| 209 |
+
"step": 1536,
|
| 210 |
+
"total_flos": 7784719820783040.0,
|
| 211 |
+
"train_loss": 0.4835930106540521,
|
| 212 |
+
"train_runtime": 112.0977,
|
| 213 |
+
"train_samples_per_second": 875.843,
|
| 214 |
+
"train_steps_per_second": 13.702
|
| 215 |
+
}
|
| 216 |
+
],
|
| 217 |
+
"logging_steps": 100,
|
| 218 |
+
"max_steps": 1536,
|
| 219 |
+
"num_input_tokens_seen": 0,
|
| 220 |
+
"num_train_epochs": 4,
|
| 221 |
+
"save_steps": 200,
|
| 222 |
+
"stateful_callbacks": {
|
| 223 |
+
"TrainerControl": {
|
| 224 |
+
"args": {
|
| 225 |
+
"should_epoch_stop": false,
|
| 226 |
+
"should_evaluate": false,
|
| 227 |
+
"should_log": false,
|
| 228 |
+
"should_save": true,
|
| 229 |
+
"should_training_stop": true
|
| 230 |
+
},
|
| 231 |
+
"attributes": {}
|
| 232 |
+
}
|
| 233 |
+
},
|
| 234 |
+
"total_flos": 7784719820783040.0,
|
| 235 |
+
"train_batch_size": 64,
|
| 236 |
+
"trial_name": null,
|
| 237 |
+
"trial_params": null
|
| 238 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:731563dcc05e74da042d85410715df11b914db3a5f028db6619010f338e8065b
|
| 3 |
+
size 5368
|