upload ipc_level1_D model
Browse files- config.json +49 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +492 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "../models/roberta-large/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"finetuning_task": "ipc1",
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "01",
|
| 16 |
+
"1": "02",
|
| 17 |
+
"2": "03",
|
| 18 |
+
"3": "04",
|
| 19 |
+
"4": "05",
|
| 20 |
+
"5": "06",
|
| 21 |
+
"6": "07",
|
| 22 |
+
"7": "21"
|
| 23 |
+
},
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 4096,
|
| 26 |
+
"label2id": {
|
| 27 |
+
"01": 0,
|
| 28 |
+
"02": 1,
|
| 29 |
+
"03": 2,
|
| 30 |
+
"04": 3,
|
| 31 |
+
"05": 4,
|
| 32 |
+
"06": 5,
|
| 33 |
+
"07": 6,
|
| 34 |
+
"21": 7
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-05,
|
| 37 |
+
"max_position_embeddings": 514,
|
| 38 |
+
"model_type": "roberta",
|
| 39 |
+
"num_attention_heads": 16,
|
| 40 |
+
"num_hidden_layers": 24,
|
| 41 |
+
"pad_token_id": 1,
|
| 42 |
+
"position_embedding_type": "absolute",
|
| 43 |
+
"problem_type": "multi_label_classification",
|
| 44 |
+
"torch_dtype": "float32",
|
| 45 |
+
"transformers_version": "4.9.2",
|
| 46 |
+
"type_vocab_size": 1,
|
| 47 |
+
"use_cache": true,
|
| 48 |
+
"vocab_size": 50265
|
| 49 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee448e4685ee86bdc0db721c5dfef5da853dd4a23c369ef90e43db7614d005dc
|
| 3 |
+
size 1421635885
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2ebf2c4786daefdd1dccda1f3f9e42686385cb38f4fe0575c4bceddf3d34a93
|
| 3 |
+
size 15523
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "../models/roberta-large/", "tokenizer_class": "RobertaTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,492 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9099219196343554,
|
| 3 |
+
"best_model_checkpoint": "./output//roberta-large_ipc1_D_5_32_5e-6_0.01_0.06_07-08-22_05-38/checkpoint-54000",
|
| 4 |
+
"epoch": 3.8676404571981076,
|
| 5 |
+
"global_step": 56000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.14,
|
| 12 |
+
"learning_rate": 2.3020257826887664e-06,
|
| 13 |
+
"loss": 0.2633,
|
| 14 |
+
"step": 2000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.14,
|
| 18 |
+
"eval_accuracy": 0.782186065915728,
|
| 19 |
+
"eval_f1": 0.8434414112545581,
|
| 20 |
+
"eval_loss": 0.12234517931938171,
|
| 21 |
+
"eval_roc_auc": 0.8943263793686275,
|
| 22 |
+
"eval_runtime": 707.0346,
|
| 23 |
+
"eval_samples_per_second": 33.902,
|
| 24 |
+
"eval_steps_per_second": 2.12,
|
| 25 |
+
"step": 2000
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.28,
|
| 29 |
+
"learning_rate": 4.604051565377533e-06,
|
| 30 |
+
"loss": 0.1135,
|
| 31 |
+
"step": 4000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.28,
|
| 35 |
+
"eval_accuracy": 0.81543596161869,
|
| 36 |
+
"eval_f1": 0.8686181075561606,
|
| 37 |
+
"eval_loss": 0.09953225404024124,
|
| 38 |
+
"eval_roc_auc": 0.9126753468236911,
|
| 39 |
+
"eval_runtime": 707.1318,
|
| 40 |
+
"eval_samples_per_second": 33.897,
|
| 41 |
+
"eval_steps_per_second": 2.12,
|
| 42 |
+
"step": 4000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.41,
|
| 46 |
+
"learning_rate": 4.878326549205743e-06,
|
| 47 |
+
"loss": 0.0975,
|
| 48 |
+
"step": 6000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.41,
|
| 52 |
+
"eval_accuracy": 0.827784730913642,
|
| 53 |
+
"eval_f1": 0.8807810494379399,
|
| 54 |
+
"eval_loss": 0.08744705468416214,
|
| 55 |
+
"eval_roc_auc": 0.9195269073883311,
|
| 56 |
+
"eval_runtime": 707.2934,
|
| 57 |
+
"eval_samples_per_second": 33.89,
|
| 58 |
+
"eval_steps_per_second": 2.119,
|
| 59 |
+
"step": 6000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.55,
|
| 63 |
+
"learning_rate": 4.731377937135384e-06,
|
| 64 |
+
"loss": 0.0897,
|
| 65 |
+
"step": 8000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.55,
|
| 69 |
+
"eval_accuracy": 0.8280350438047559,
|
| 70 |
+
"eval_f1": 0.883428263546798,
|
| 71 |
+
"eval_loss": 0.08566972613334656,
|
| 72 |
+
"eval_roc_auc": 0.9246573113358266,
|
| 73 |
+
"eval_runtime": 707.7071,
|
| 74 |
+
"eval_samples_per_second": 33.87,
|
| 75 |
+
"eval_steps_per_second": 2.118,
|
| 76 |
+
"step": 8000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.69,
|
| 80 |
+
"learning_rate": 4.584429325065025e-06,
|
| 81 |
+
"loss": 0.0845,
|
| 82 |
+
"step": 10000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.69,
|
| 86 |
+
"eval_accuracy": 0.8415936587400917,
|
| 87 |
+
"eval_f1": 0.8920891085286283,
|
| 88 |
+
"eval_loss": 0.07975932210683823,
|
| 89 |
+
"eval_roc_auc": 0.928458970107628,
|
| 90 |
+
"eval_runtime": 707.3951,
|
| 91 |
+
"eval_samples_per_second": 33.885,
|
| 92 |
+
"eval_steps_per_second": 2.119,
|
| 93 |
+
"step": 10000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.83,
|
| 97 |
+
"learning_rate": 4.437480712994666e-06,
|
| 98 |
+
"loss": 0.0818,
|
| 99 |
+
"step": 12000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.83,
|
| 103 |
+
"eval_accuracy": 0.8427200667501042,
|
| 104 |
+
"eval_f1": 0.8958713920350749,
|
| 105 |
+
"eval_loss": 0.0771109014749527,
|
| 106 |
+
"eval_roc_auc": 0.9319582466091877,
|
| 107 |
+
"eval_runtime": 707.8327,
|
| 108 |
+
"eval_samples_per_second": 33.864,
|
| 109 |
+
"eval_steps_per_second": 2.118,
|
| 110 |
+
"step": 12000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.97,
|
| 114 |
+
"learning_rate": 4.2905321009243076e-06,
|
| 115 |
+
"loss": 0.0799,
|
| 116 |
+
"step": 14000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.97,
|
| 120 |
+
"eval_accuracy": 0.8450146015853149,
|
| 121 |
+
"eval_f1": 0.8957159726658537,
|
| 122 |
+
"eval_loss": 0.07565668225288391,
|
| 123 |
+
"eval_roc_auc": 0.9295314687703254,
|
| 124 |
+
"eval_runtime": 707.6287,
|
| 125 |
+
"eval_samples_per_second": 33.874,
|
| 126 |
+
"eval_steps_per_second": 2.118,
|
| 127 |
+
"step": 14000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.11,
|
| 131 |
+
"learning_rate": 4.143583488853948e-06,
|
| 132 |
+
"loss": 0.0732,
|
| 133 |
+
"step": 16000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.11,
|
| 137 |
+
"eval_accuracy": 0.8493950771798081,
|
| 138 |
+
"eval_f1": 0.8984909514907395,
|
| 139 |
+
"eval_loss": 0.07519076764583588,
|
| 140 |
+
"eval_roc_auc": 0.9326589314853615,
|
| 141 |
+
"eval_runtime": 707.9951,
|
| 142 |
+
"eval_samples_per_second": 33.856,
|
| 143 |
+
"eval_steps_per_second": 2.117,
|
| 144 |
+
"step": 16000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.24,
|
| 148 |
+
"learning_rate": 3.996634876783589e-06,
|
| 149 |
+
"loss": 0.0726,
|
| 150 |
+
"step": 18000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.24,
|
| 154 |
+
"eval_accuracy": 0.8492699207342511,
|
| 155 |
+
"eval_f1": 0.8975535762903036,
|
| 156 |
+
"eval_loss": 0.07450989633798599,
|
| 157 |
+
"eval_roc_auc": 0.9289754929708756,
|
| 158 |
+
"eval_runtime": 708.1958,
|
| 159 |
+
"eval_samples_per_second": 33.847,
|
| 160 |
+
"eval_steps_per_second": 2.117,
|
| 161 |
+
"step": 18000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.38,
|
| 165 |
+
"learning_rate": 3.84968626471323e-06,
|
| 166 |
+
"loss": 0.0716,
|
| 167 |
+
"step": 20000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.38,
|
| 171 |
+
"eval_accuracy": 0.8525657071339174,
|
| 172 |
+
"eval_f1": 0.9005084354055927,
|
| 173 |
+
"eval_loss": 0.07325474917888641,
|
| 174 |
+
"eval_roc_auc": 0.9340545363189772,
|
| 175 |
+
"eval_runtime": 707.8752,
|
| 176 |
+
"eval_samples_per_second": 33.862,
|
| 177 |
+
"eval_steps_per_second": 2.118,
|
| 178 |
+
"step": 20000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.52,
|
| 182 |
+
"learning_rate": 3.702737652642871e-06,
|
| 183 |
+
"loss": 0.0708,
|
| 184 |
+
"step": 22000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.52,
|
| 188 |
+
"eval_accuracy": 0.8506466416353775,
|
| 189 |
+
"eval_f1": 0.9017078523041694,
|
| 190 |
+
"eval_loss": 0.0716293528676033,
|
| 191 |
+
"eval_roc_auc": 0.9380172851232347,
|
| 192 |
+
"eval_runtime": 707.8218,
|
| 193 |
+
"eval_samples_per_second": 33.864,
|
| 194 |
+
"eval_steps_per_second": 2.118,
|
| 195 |
+
"step": 22000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.66,
|
| 199 |
+
"learning_rate": 3.555789040572512e-06,
|
| 200 |
+
"loss": 0.0695,
|
| 201 |
+
"step": 24000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.66,
|
| 205 |
+
"eval_accuracy": 0.8547350855235711,
|
| 206 |
+
"eval_f1": 0.9044931999464413,
|
| 207 |
+
"eval_loss": 0.07056614011526108,
|
| 208 |
+
"eval_roc_auc": 0.9387482370760931,
|
| 209 |
+
"eval_runtime": 708.0549,
|
| 210 |
+
"eval_samples_per_second": 33.853,
|
| 211 |
+
"eval_steps_per_second": 2.117,
|
| 212 |
+
"step": 24000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.8,
|
| 216 |
+
"learning_rate": 3.4088404285021533e-06,
|
| 217 |
+
"loss": 0.069,
|
| 218 |
+
"step": 26000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.8,
|
| 222 |
+
"eval_accuracy": 0.8569044639132248,
|
| 223 |
+
"eval_f1": 0.9042787144565763,
|
| 224 |
+
"eval_loss": 0.07104314118623734,
|
| 225 |
+
"eval_roc_auc": 0.9356039344541693,
|
| 226 |
+
"eval_runtime": 707.8507,
|
| 227 |
+
"eval_samples_per_second": 33.863,
|
| 228 |
+
"eval_steps_per_second": 2.118,
|
| 229 |
+
"step": 26000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.93,
|
| 233 |
+
"learning_rate": 3.261891816431794e-06,
|
| 234 |
+
"loss": 0.0682,
|
| 235 |
+
"step": 28000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.93,
|
| 239 |
+
"eval_accuracy": 0.8599499374217772,
|
| 240 |
+
"eval_f1": 0.9060724534406717,
|
| 241 |
+
"eval_loss": 0.06967160105705261,
|
| 242 |
+
"eval_roc_auc": 0.9372038441063302,
|
| 243 |
+
"eval_runtime": 708.2055,
|
| 244 |
+
"eval_samples_per_second": 33.846,
|
| 245 |
+
"eval_steps_per_second": 2.117,
|
| 246 |
+
"step": 28000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.07,
|
| 250 |
+
"learning_rate": 3.1149432043614354e-06,
|
| 251 |
+
"loss": 0.0639,
|
| 252 |
+
"step": 30000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.07,
|
| 256 |
+
"eval_accuracy": 0.854276178556529,
|
| 257 |
+
"eval_f1": 0.9025946730864763,
|
| 258 |
+
"eval_loss": 0.07231773436069489,
|
| 259 |
+
"eval_roc_auc": 0.9380671303178707,
|
| 260 |
+
"eval_runtime": 708.1848,
|
| 261 |
+
"eval_samples_per_second": 33.847,
|
| 262 |
+
"eval_steps_per_second": 2.117,
|
| 263 |
+
"step": 30000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.21,
|
| 267 |
+
"learning_rate": 2.9679945922910757e-06,
|
| 268 |
+
"loss": 0.0595,
|
| 269 |
+
"step": 32000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.21,
|
| 273 |
+
"eval_accuracy": 0.8584897788902796,
|
| 274 |
+
"eval_f1": 0.9064987752602572,
|
| 275 |
+
"eval_loss": 0.07001405209302902,
|
| 276 |
+
"eval_roc_auc": 0.9397355166673759,
|
| 277 |
+
"eval_runtime": 708.0437,
|
| 278 |
+
"eval_samples_per_second": 33.854,
|
| 279 |
+
"eval_steps_per_second": 2.117,
|
| 280 |
+
"step": 32000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.35,
|
| 284 |
+
"learning_rate": 2.821045980220717e-06,
|
| 285 |
+
"loss": 0.0609,
|
| 286 |
+
"step": 34000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.35,
|
| 290 |
+
"eval_accuracy": 0.8602002503128912,
|
| 291 |
+
"eval_f1": 0.9077644010972264,
|
| 292 |
+
"eval_loss": 0.06918834149837494,
|
| 293 |
+
"eval_roc_auc": 0.9421116895582996,
|
| 294 |
+
"eval_runtime": 707.9146,
|
| 295 |
+
"eval_samples_per_second": 33.86,
|
| 296 |
+
"eval_steps_per_second": 2.117,
|
| 297 |
+
"step": 34000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.49,
|
| 301 |
+
"learning_rate": 2.674097368150358e-06,
|
| 302 |
+
"loss": 0.0612,
|
| 303 |
+
"step": 36000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.49,
|
| 307 |
+
"eval_accuracy": 0.8603671255736337,
|
| 308 |
+
"eval_f1": 0.9078671395339969,
|
| 309 |
+
"eval_loss": 0.06887050718069077,
|
| 310 |
+
"eval_roc_auc": 0.9418260414584333,
|
| 311 |
+
"eval_runtime": 708.0484,
|
| 312 |
+
"eval_samples_per_second": 33.854,
|
| 313 |
+
"eval_steps_per_second": 2.117,
|
| 314 |
+
"step": 36000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.62,
|
| 318 |
+
"learning_rate": 2.527148756079999e-06,
|
| 319 |
+
"loss": 0.0607,
|
| 320 |
+
"step": 38000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.62,
|
| 324 |
+
"eval_accuracy": 0.8638715060492282,
|
| 325 |
+
"eval_f1": 0.9094039329711531,
|
| 326 |
+
"eval_loss": 0.0678349956870079,
|
| 327 |
+
"eval_roc_auc": 0.941532162317987,
|
| 328 |
+
"eval_runtime": 707.9126,
|
| 329 |
+
"eval_samples_per_second": 33.86,
|
| 330 |
+
"eval_steps_per_second": 2.117,
|
| 331 |
+
"step": 38000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.76,
|
| 335 |
+
"learning_rate": 2.38020014400964e-06,
|
| 336 |
+
"loss": 0.0598,
|
| 337 |
+
"step": 40000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 2.76,
|
| 341 |
+
"eval_accuracy": 0.8620775969962453,
|
| 342 |
+
"eval_f1": 0.9084244866628287,
|
| 343 |
+
"eval_loss": 0.06894223392009735,
|
| 344 |
+
"eval_roc_auc": 0.9398278292003405,
|
| 345 |
+
"eval_runtime": 708.1682,
|
| 346 |
+
"eval_samples_per_second": 33.848,
|
| 347 |
+
"eval_steps_per_second": 2.117,
|
| 348 |
+
"step": 40000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.9,
|
| 352 |
+
"learning_rate": 2.233251531939281e-06,
|
| 353 |
+
"loss": 0.0589,
|
| 354 |
+
"step": 42000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.9,
|
| 358 |
+
"eval_accuracy": 0.8625782227784731,
|
| 359 |
+
"eval_f1": 0.9087424782492046,
|
| 360 |
+
"eval_loss": 0.06813088804483414,
|
| 361 |
+
"eval_roc_auc": 0.9405057223889542,
|
| 362 |
+
"eval_runtime": 708.1038,
|
| 363 |
+
"eval_samples_per_second": 33.851,
|
| 364 |
+
"eval_steps_per_second": 2.117,
|
| 365 |
+
"step": 42000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.04,
|
| 369 |
+
"learning_rate": 2.086302919868922e-06,
|
| 370 |
+
"loss": 0.0584,
|
| 371 |
+
"step": 44000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.04,
|
| 375 |
+
"eval_accuracy": 0.863537755527743,
|
| 376 |
+
"eval_f1": 0.9081979164668188,
|
| 377 |
+
"eval_loss": 0.07025768607854843,
|
| 378 |
+
"eval_roc_auc": 0.9397884820006503,
|
| 379 |
+
"eval_runtime": 707.4211,
|
| 380 |
+
"eval_samples_per_second": 33.884,
|
| 381 |
+
"eval_steps_per_second": 2.119,
|
| 382 |
+
"step": 44000
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 3.18,
|
| 386 |
+
"learning_rate": 1.939354307798563e-06,
|
| 387 |
+
"loss": 0.0521,
|
| 388 |
+
"step": 46000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 3.18,
|
| 392 |
+
"eval_accuracy": 0.8621610346266166,
|
| 393 |
+
"eval_f1": 0.9091812742530537,
|
| 394 |
+
"eval_loss": 0.0701606273651123,
|
| 395 |
+
"eval_roc_auc": 0.941660515050063,
|
| 396 |
+
"eval_runtime": 707.6705,
|
| 397 |
+
"eval_samples_per_second": 33.872,
|
| 398 |
+
"eval_steps_per_second": 2.118,
|
| 399 |
+
"step": 46000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 3.32,
|
| 403 |
+
"learning_rate": 1.792405695728204e-06,
|
| 404 |
+
"loss": 0.0528,
|
| 405 |
+
"step": 48000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.32,
|
| 409 |
+
"eval_accuracy": 0.8632874426366292,
|
| 410 |
+
"eval_f1": 0.9089131684876366,
|
| 411 |
+
"eval_loss": 0.06941932439804077,
|
| 412 |
+
"eval_roc_auc": 0.9405201937068114,
|
| 413 |
+
"eval_runtime": 707.419,
|
| 414 |
+
"eval_samples_per_second": 33.884,
|
| 415 |
+
"eval_steps_per_second": 2.119,
|
| 416 |
+
"step": 48000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 3.45,
|
| 420 |
+
"learning_rate": 1.6454570836578452e-06,
|
| 421 |
+
"loss": 0.0527,
|
| 422 |
+
"step": 50000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.45,
|
| 426 |
+
"eval_accuracy": 0.8617855652899458,
|
| 427 |
+
"eval_f1": 0.9090562440419447,
|
| 428 |
+
"eval_loss": 0.069430410861969,
|
| 429 |
+
"eval_roc_auc": 0.9425349573751873,
|
| 430 |
+
"eval_runtime": 707.7016,
|
| 431 |
+
"eval_samples_per_second": 33.87,
|
| 432 |
+
"eval_steps_per_second": 2.118,
|
| 433 |
+
"step": 50000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 3.59,
|
| 437 |
+
"learning_rate": 1.498508471587486e-06,
|
| 438 |
+
"loss": 0.053,
|
| 439 |
+
"step": 52000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 3.59,
|
| 443 |
+
"eval_accuracy": 0.8624530663329162,
|
| 444 |
+
"eval_f1": 0.9087446678854357,
|
| 445 |
+
"eval_loss": 0.06918352842330933,
|
| 446 |
+
"eval_roc_auc": 0.9427842849830317,
|
| 447 |
+
"eval_runtime": 707.4215,
|
| 448 |
+
"eval_samples_per_second": 33.884,
|
| 449 |
+
"eval_steps_per_second": 2.119,
|
| 450 |
+
"step": 52000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 3.73,
|
| 454 |
+
"learning_rate": 1.351559859517127e-06,
|
| 455 |
+
"loss": 0.0522,
|
| 456 |
+
"step": 54000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.73,
|
| 460 |
+
"eval_accuracy": 0.8645390070921986,
|
| 461 |
+
"eval_f1": 0.9099219196343554,
|
| 462 |
+
"eval_loss": 0.0693092793226242,
|
| 463 |
+
"eval_roc_auc": 0.943445813623303,
|
| 464 |
+
"eval_runtime": 717.1057,
|
| 465 |
+
"eval_samples_per_second": 33.426,
|
| 466 |
+
"eval_steps_per_second": 2.09,
|
| 467 |
+
"step": 54000
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.87,
|
| 471 |
+
"learning_rate": 1.2046112474467679e-06,
|
| 472 |
+
"loss": 0.0521,
|
| 473 |
+
"step": 56000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 3.87,
|
| 477 |
+
"eval_accuracy": 0.8630788485607008,
|
| 478 |
+
"eval_f1": 0.9097205045758101,
|
| 479 |
+
"eval_loss": 0.06953160464763641,
|
| 480 |
+
"eval_roc_auc": 0.9436689409083443,
|
| 481 |
+
"eval_runtime": 707.5176,
|
| 482 |
+
"eval_samples_per_second": 33.879,
|
| 483 |
+
"eval_steps_per_second": 2.119,
|
| 484 |
+
"step": 56000
|
| 485 |
+
}
|
| 486 |
+
],
|
| 487 |
+
"max_steps": 72395,
|
| 488 |
+
"num_train_epochs": 5,
|
| 489 |
+
"total_flos": 1.6700995925936701e+18,
|
| 490 |
+
"trial_name": null,
|
| 491 |
+
"trial_params": null
|
| 492 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95a952fd434a75f742f88bdab3305a9b515a0d70980fc9495fafda7418e65bc3
|
| 3 |
+
size 2735
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|