upload ipc_level1_E model
Browse files- config.json +47 -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 +390 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "21"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 4096,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"01": 0,
|
| 27 |
+
"02": 1,
|
| 28 |
+
"03": 2,
|
| 29 |
+
"04": 3,
|
| 30 |
+
"05": 4,
|
| 31 |
+
"06": 5,
|
| 32 |
+
"21": 6
|
| 33 |
+
},
|
| 34 |
+
"layer_norm_eps": 1e-05,
|
| 35 |
+
"max_position_embeddings": 514,
|
| 36 |
+
"model_type": "roberta",
|
| 37 |
+
"num_attention_heads": 16,
|
| 38 |
+
"num_hidden_layers": 24,
|
| 39 |
+
"pad_token_id": 1,
|
| 40 |
+
"position_embedding_type": "absolute",
|
| 41 |
+
"problem_type": "multi_label_classification",
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.9.2",
|
| 44 |
+
"type_vocab_size": 1,
|
| 45 |
+
"use_cache": true,
|
| 46 |
+
"vocab_size": 50265
|
| 47 |
+
}
|
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 sha256:14ddfbbe335a13ef34042e255f2aadce00e06a8219309f81822695b0d64275d2
|
| 3 |
+
size 1421631789
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e51777377b5d972e5dcfc19cacedfea595280d65c2d4c71e14ddfe228b5eeecb
|
| 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 +1,390 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9173800019578199,
|
| 3 |
+
"best_model_checkpoint": "./output//roberta-large_ipc1_E_5_32_5e-6_0.01_0.06_07-08-22_05-38/checkpoint-42000",
|
| 4 |
+
"epoch": 0.8361998517645717,
|
| 5 |
+
"global_step": 44000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 6.334726973267452e-07,
|
| 13 |
+
"loss": 0.3829,
|
| 14 |
+
"step": 2000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"eval_accuracy": 0.7333631854505374,
|
| 19 |
+
"eval_f1": 0.8072349594700899,
|
| 20 |
+
"eval_loss": 0.1738697588443756,
|
| 21 |
+
"eval_roc_auc": 0.8691996632382517,
|
| 22 |
+
"eval_runtime": 2556.9417,
|
| 23 |
+
"eval_samples_per_second": 34.063,
|
| 24 |
+
"eval_steps_per_second": 2.129,
|
| 25 |
+
"step": 2000
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.08,
|
| 29 |
+
"learning_rate": 1.2669453946534904e-06,
|
| 30 |
+
"loss": 0.152,
|
| 31 |
+
"step": 4000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08,
|
| 35 |
+
"eval_accuracy": 0.8074768072012491,
|
| 36 |
+
"eval_f1": 0.8585274784241828,
|
| 37 |
+
"eval_loss": 0.12472031265497208,
|
| 38 |
+
"eval_roc_auc": 0.9038230127982044,
|
| 39 |
+
"eval_runtime": 2557.151,
|
| 40 |
+
"eval_samples_per_second": 34.06,
|
| 41 |
+
"eval_steps_per_second": 2.129,
|
| 42 |
+
"step": 4000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.11,
|
| 46 |
+
"learning_rate": 1.900418091980236e-06,
|
| 47 |
+
"loss": 0.1207,
|
| 48 |
+
"step": 6000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.11,
|
| 52 |
+
"eval_accuracy": 0.8247680720124919,
|
| 53 |
+
"eval_f1": 0.8746601834456846,
|
| 54 |
+
"eval_loss": 0.10768114030361176,
|
| 55 |
+
"eval_roc_auc": 0.9167191830505206,
|
| 56 |
+
"eval_runtime": 2559.7707,
|
| 57 |
+
"eval_samples_per_second": 34.025,
|
| 58 |
+
"eval_steps_per_second": 2.127,
|
| 59 |
+
"step": 6000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.15,
|
| 63 |
+
"learning_rate": 2.5338907893069808e-06,
|
| 64 |
+
"loss": 0.1068,
|
| 65 |
+
"step": 8000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.15,
|
| 69 |
+
"eval_accuracy": 0.8348489023606136,
|
| 70 |
+
"eval_f1": 0.8825789946684457,
|
| 71 |
+
"eval_loss": 0.09896202385425568,
|
| 72 |
+
"eval_roc_auc": 0.9219814574886337,
|
| 73 |
+
"eval_runtime": 2560.9139,
|
| 74 |
+
"eval_samples_per_second": 34.01,
|
| 75 |
+
"eval_steps_per_second": 2.126,
|
| 76 |
+
"step": 8000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.19,
|
| 80 |
+
"learning_rate": 3.1673634866337266e-06,
|
| 81 |
+
"loss": 0.1011,
|
| 82 |
+
"step": 10000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.19,
|
| 86 |
+
"eval_accuracy": 0.8379948562505741,
|
| 87 |
+
"eval_f1": 0.8862482315394654,
|
| 88 |
+
"eval_loss": 0.0956236720085144,
|
| 89 |
+
"eval_roc_auc": 0.9259124171373225,
|
| 90 |
+
"eval_runtime": 2559.6669,
|
| 91 |
+
"eval_samples_per_second": 34.026,
|
| 92 |
+
"eval_steps_per_second": 2.127,
|
| 93 |
+
"step": 10000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.23,
|
| 97 |
+
"learning_rate": 3.800836183960472e-06,
|
| 98 |
+
"loss": 0.0947,
|
| 99 |
+
"step": 12000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.23,
|
| 103 |
+
"eval_accuracy": 0.8484890236061358,
|
| 104 |
+
"eval_f1": 0.8952724037759265,
|
| 105 |
+
"eval_loss": 0.08779484033584595,
|
| 106 |
+
"eval_roc_auc": 0.9306411069461392,
|
| 107 |
+
"eval_runtime": 2561.9326,
|
| 108 |
+
"eval_samples_per_second": 33.996,
|
| 109 |
+
"eval_steps_per_second": 2.125,
|
| 110 |
+
"step": 12000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.27,
|
| 114 |
+
"learning_rate": 4.434308881287217e-06,
|
| 115 |
+
"loss": 0.0915,
|
| 116 |
+
"step": 14000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.27,
|
| 120 |
+
"eval_accuracy": 0.849901258381556,
|
| 121 |
+
"eval_f1": 0.8959137400012078,
|
| 122 |
+
"eval_loss": 0.08673737943172455,
|
| 123 |
+
"eval_roc_auc": 0.9310974491642802,
|
| 124 |
+
"eval_runtime": 2561.6246,
|
| 125 |
+
"eval_samples_per_second": 34.0,
|
| 126 |
+
"eval_steps_per_second": 2.125,
|
| 127 |
+
"step": 14000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.3,
|
| 131 |
+
"learning_rate": 4.995673428787469e-06,
|
| 132 |
+
"loss": 0.0878,
|
| 133 |
+
"step": 16000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.3,
|
| 137 |
+
"eval_accuracy": 0.8544020391292367,
|
| 138 |
+
"eval_f1": 0.8991452427312628,
|
| 139 |
+
"eval_loss": 0.08379313349723816,
|
| 140 |
+
"eval_roc_auc": 0.9323214390537408,
|
| 141 |
+
"eval_runtime": 2562.3097,
|
| 142 |
+
"eval_samples_per_second": 33.991,
|
| 143 |
+
"eval_steps_per_second": 2.125,
|
| 144 |
+
"step": 16000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.34,
|
| 148 |
+
"learning_rate": 4.9552381838105365e-06,
|
| 149 |
+
"loss": 0.0865,
|
| 150 |
+
"step": 18000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.34,
|
| 154 |
+
"eval_accuracy": 0.8521631303389363,
|
| 155 |
+
"eval_f1": 0.8989961118555455,
|
| 156 |
+
"eval_loss": 0.08386027067899704,
|
| 157 |
+
"eval_roc_auc": 0.9327737350993932,
|
| 158 |
+
"eval_runtime": 2560.8339,
|
| 159 |
+
"eval_samples_per_second": 34.011,
|
| 160 |
+
"eval_steps_per_second": 2.126,
|
| 161 |
+
"step": 18000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.38,
|
| 165 |
+
"learning_rate": 4.914802938833605e-06,
|
| 166 |
+
"loss": 0.0835,
|
| 167 |
+
"step": 20000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.38,
|
| 171 |
+
"eval_accuracy": 0.8534605492789565,
|
| 172 |
+
"eval_f1": 0.9011981436136274,
|
| 173 |
+
"eval_loss": 0.08270147442817688,
|
| 174 |
+
"eval_roc_auc": 0.9364532450443123,
|
| 175 |
+
"eval_runtime": 2562.5704,
|
| 176 |
+
"eval_samples_per_second": 33.988,
|
| 177 |
+
"eval_steps_per_second": 2.124,
|
| 178 |
+
"step": 20000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.42,
|
| 182 |
+
"learning_rate": 4.874367693856674e-06,
|
| 183 |
+
"loss": 0.0813,
|
| 184 |
+
"step": 22000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.42,
|
| 188 |
+
"eval_accuracy": 0.8624391476072379,
|
| 189 |
+
"eval_f1": 0.9062087330430322,
|
| 190 |
+
"eval_loss": 0.07851053774356842,
|
| 191 |
+
"eval_roc_auc": 0.9391581637644638,
|
| 192 |
+
"eval_runtime": 2562.0501,
|
| 193 |
+
"eval_samples_per_second": 33.995,
|
| 194 |
+
"eval_steps_per_second": 2.125,
|
| 195 |
+
"step": 22000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.46,
|
| 199 |
+
"learning_rate": 4.8339324488797415e-06,
|
| 200 |
+
"loss": 0.0799,
|
| 201 |
+
"step": 24000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.46,
|
| 205 |
+
"eval_accuracy": 0.8644139799761184,
|
| 206 |
+
"eval_f1": 0.9090770321103419,
|
| 207 |
+
"eval_loss": 0.07563477754592896,
|
| 208 |
+
"eval_roc_auc": 0.9411536483338017,
|
| 209 |
+
"eval_runtime": 2560.4534,
|
| 210 |
+
"eval_samples_per_second": 34.016,
|
| 211 |
+
"eval_steps_per_second": 2.126,
|
| 212 |
+
"step": 24000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.49,
|
| 216 |
+
"learning_rate": 4.79349720390281e-06,
|
| 217 |
+
"loss": 0.0792,
|
| 218 |
+
"step": 26000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.49,
|
| 222 |
+
"eval_accuracy": 0.8651832460732984,
|
| 223 |
+
"eval_f1": 0.9101030478163677,
|
| 224 |
+
"eval_loss": 0.07443315535783768,
|
| 225 |
+
"eval_roc_auc": 0.9417119100729429,
|
| 226 |
+
"eval_runtime": 2562.0577,
|
| 227 |
+
"eval_samples_per_second": 33.995,
|
| 228 |
+
"eval_steps_per_second": 2.125,
|
| 229 |
+
"step": 26000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.53,
|
| 233 |
+
"learning_rate": 4.753061958925879e-06,
|
| 234 |
+
"loss": 0.0764,
|
| 235 |
+
"step": 28000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.53,
|
| 239 |
+
"eval_accuracy": 0.8657573252502985,
|
| 240 |
+
"eval_f1": 0.9101674732621782,
|
| 241 |
+
"eval_loss": 0.07442668080329895,
|
| 242 |
+
"eval_roc_auc": 0.9411051257108755,
|
| 243 |
+
"eval_runtime": 2562.7135,
|
| 244 |
+
"eval_samples_per_second": 33.986,
|
| 245 |
+
"eval_steps_per_second": 2.124,
|
| 246 |
+
"step": 28000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.57,
|
| 250 |
+
"learning_rate": 4.7126267139489465e-06,
|
| 251 |
+
"loss": 0.0758,
|
| 252 |
+
"step": 30000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.57,
|
| 256 |
+
"eval_accuracy": 0.8675369706989988,
|
| 257 |
+
"eval_f1": 0.9117887285597605,
|
| 258 |
+
"eval_loss": 0.0741124227643013,
|
| 259 |
+
"eval_roc_auc": 0.9431533957100788,
|
| 260 |
+
"eval_runtime": 2561.7593,
|
| 261 |
+
"eval_samples_per_second": 33.999,
|
| 262 |
+
"eval_steps_per_second": 2.125,
|
| 263 |
+
"step": 30000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.61,
|
| 267 |
+
"learning_rate": 4.672191468972015e-06,
|
| 268 |
+
"loss": 0.075,
|
| 269 |
+
"step": 32000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.61,
|
| 273 |
+
"eval_accuracy": 0.8696840268209791,
|
| 274 |
+
"eval_f1": 0.9111988941522289,
|
| 275 |
+
"eval_loss": 0.07489842176437378,
|
| 276 |
+
"eval_roc_auc": 0.941613439232639,
|
| 277 |
+
"eval_runtime": 2562.3874,
|
| 278 |
+
"eval_samples_per_second": 33.99,
|
| 279 |
+
"eval_steps_per_second": 2.125,
|
| 280 |
+
"step": 32000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.65,
|
| 284 |
+
"learning_rate": 4.631756223995084e-06,
|
| 285 |
+
"loss": 0.0744,
|
| 286 |
+
"step": 34000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.65,
|
| 290 |
+
"eval_accuracy": 0.8696610636538992,
|
| 291 |
+
"eval_f1": 0.9132626153335907,
|
| 292 |
+
"eval_loss": 0.07311609387397766,
|
| 293 |
+
"eval_roc_auc": 0.944537581534918,
|
| 294 |
+
"eval_runtime": 2561.9943,
|
| 295 |
+
"eval_samples_per_second": 33.995,
|
| 296 |
+
"eval_steps_per_second": 2.125,
|
| 297 |
+
"step": 34000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.68,
|
| 301 |
+
"learning_rate": 4.5913209790181515e-06,
|
| 302 |
+
"loss": 0.0741,
|
| 303 |
+
"step": 36000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.68,
|
| 307 |
+
"eval_accuracy": 0.8714177459355195,
|
| 308 |
+
"eval_f1": 0.9147231870702489,
|
| 309 |
+
"eval_loss": 0.07061254978179932,
|
| 310 |
+
"eval_roc_auc": 0.9443614210381402,
|
| 311 |
+
"eval_runtime": 2562.603,
|
| 312 |
+
"eval_samples_per_second": 33.987,
|
| 313 |
+
"eval_steps_per_second": 2.124,
|
| 314 |
+
"step": 36000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.72,
|
| 318 |
+
"learning_rate": 4.55088573404122e-06,
|
| 319 |
+
"loss": 0.0726,
|
| 320 |
+
"step": 38000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.72,
|
| 324 |
+
"eval_accuracy": 0.8722903462845596,
|
| 325 |
+
"eval_f1": 0.9149092652418596,
|
| 326 |
+
"eval_loss": 0.07059279829263687,
|
| 327 |
+
"eval_roc_auc": 0.9447903799628505,
|
| 328 |
+
"eval_runtime": 2562.4912,
|
| 329 |
+
"eval_samples_per_second": 33.989,
|
| 330 |
+
"eval_steps_per_second": 2.124,
|
| 331 |
+
"step": 38000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.76,
|
| 335 |
+
"learning_rate": 4.510450489064289e-06,
|
| 336 |
+
"loss": 0.0728,
|
| 337 |
+
"step": 40000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 0.76,
|
| 341 |
+
"eval_accuracy": 0.8742766602369799,
|
| 342 |
+
"eval_f1": 0.9169329073482427,
|
| 343 |
+
"eval_loss": 0.06948799639940262,
|
| 344 |
+
"eval_roc_auc": 0.9469121100055765,
|
| 345 |
+
"eval_runtime": 2562.6751,
|
| 346 |
+
"eval_samples_per_second": 33.986,
|
| 347 |
+
"eval_steps_per_second": 2.124,
|
| 348 |
+
"step": 40000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.8,
|
| 352 |
+
"learning_rate": 4.470015244087356e-06,
|
| 353 |
+
"loss": 0.071,
|
| 354 |
+
"step": 42000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.8,
|
| 358 |
+
"eval_accuracy": 0.87463258932672,
|
| 359 |
+
"eval_f1": 0.9173800019578199,
|
| 360 |
+
"eval_loss": 0.06844224780797958,
|
| 361 |
+
"eval_roc_auc": 0.9468508740850688,
|
| 362 |
+
"eval_runtime": 2572.6023,
|
| 363 |
+
"eval_samples_per_second": 33.855,
|
| 364 |
+
"eval_steps_per_second": 2.116,
|
| 365 |
+
"step": 42000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.84,
|
| 369 |
+
"learning_rate": 4.429579999110425e-06,
|
| 370 |
+
"loss": 0.0713,
|
| 371 |
+
"step": 44000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.84,
|
| 375 |
+
"eval_accuracy": 0.8746555524937999,
|
| 376 |
+
"eval_f1": 0.9166339527174387,
|
| 377 |
+
"eval_loss": 0.06880520284175873,
|
| 378 |
+
"eval_roc_auc": 0.9455051967809519,
|
| 379 |
+
"eval_runtime": 2562.466,
|
| 380 |
+
"eval_samples_per_second": 33.989,
|
| 381 |
+
"eval_steps_per_second": 2.125,
|
| 382 |
+
"step": 44000
|
| 383 |
+
}
|
| 384 |
+
],
|
| 385 |
+
"max_steps": 263095,
|
| 386 |
+
"num_train_epochs": 5,
|
| 387 |
+
"total_flos": 1.312181527117824e+18,
|
| 388 |
+
"trial_name": null,
|
| 389 |
+
"trial_params": null
|
| 390 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:198b3e365aece9bde9345a57c8dfc9f4eac304b98376c399d196be2d126f6304
|
| 3 |
+
size 2735
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|