upload nace2_level1_25 model
Browse files- config.json +48 -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 +448 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "nace",
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "1",
|
| 16 |
+
"1": "2",
|
| 17 |
+
"2": "3",
|
| 18 |
+
"3": "4",
|
| 19 |
+
"4": "5",
|
| 20 |
+
"5": "6",
|
| 21 |
+
"6": "7",
|
| 22 |
+
"7": "9"
|
| 23 |
+
},
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 4096,
|
| 26 |
+
"label2id": {
|
| 27 |
+
"1": 0,
|
| 28 |
+
"2": 1,
|
| 29 |
+
"3": 2,
|
| 30 |
+
"4": 3,
|
| 31 |
+
"5": 4,
|
| 32 |
+
"6": 5,
|
| 33 |
+
"7": 6,
|
| 34 |
+
"9": 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 |
+
"transformers_version": "4.6.1",
|
| 45 |
+
"type_vocab_size": 1,
|
| 46 |
+
"use_cache": true,
|
| 47 |
+
"vocab_size": 50265
|
| 48 |
+
}
|
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 sha256:7ba741b44af928ff4d276d7b771ccf6021c9f91d856e4771436503eb1a50fe08
|
| 3 |
+
size 1421635885
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecbcb226af75a8cdbf42917d1a1ace9dd9c926679b04eba0f216c4d390fd2179
|
| 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/"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,448 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9506395189108336,
|
| 3 |
+
"best_model_checkpoint": "./output//25_roberta-large_nace_5__5e-6_0.01_0.06_07-21-22_10-40/checkpoint-54000",
|
| 4 |
+
"epoch": 3.01255230125523,
|
| 5 |
+
"global_step": 54000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 1.8594272963927112e-06,
|
| 13 |
+
"loss": 0.2318,
|
| 14 |
+
"step": 2000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.11,
|
| 18 |
+
"eval_accuracy": 0.876702441473671,
|
| 19 |
+
"eval_f1": 0.90677030703459,
|
| 20 |
+
"eval_loss": 0.08175961673259735,
|
| 21 |
+
"eval_roc_auc": 0.9387159436934914,
|
| 22 |
+
"eval_runtime": 942.0949,
|
| 23 |
+
"eval_samples_per_second": 33.825,
|
| 24 |
+
"step": 2000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.22,
|
| 28 |
+
"learning_rate": 3.7188545927854224e-06,
|
| 29 |
+
"loss": 0.0732,
|
| 30 |
+
"step": 4000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.22,
|
| 34 |
+
"eval_accuracy": 0.8966296366032762,
|
| 35 |
+
"eval_f1": 0.9234467455621302,
|
| 36 |
+
"eval_loss": 0.060932476073503494,
|
| 37 |
+
"eval_roc_auc": 0.9514088251746582,
|
| 38 |
+
"eval_runtime": 942.3301,
|
| 39 |
+
"eval_samples_per_second": 33.816,
|
| 40 |
+
"step": 4000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.33,
|
| 44 |
+
"learning_rate": 4.963084738922455e-06,
|
| 45 |
+
"loss": 0.0584,
|
| 46 |
+
"step": 6000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.33,
|
| 50 |
+
"eval_accuracy": 0.8969434506998054,
|
| 51 |
+
"eval_f1": 0.9278133577310156,
|
| 52 |
+
"eval_loss": 0.05285193771123886,
|
| 53 |
+
"eval_roc_auc": 0.9578889777085196,
|
| 54 |
+
"eval_runtime": 943.2116,
|
| 55 |
+
"eval_samples_per_second": 33.785,
|
| 56 |
+
"step": 6000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.45,
|
| 60 |
+
"learning_rate": 4.844386150248674e-06,
|
| 61 |
+
"loss": 0.0521,
|
| 62 |
+
"step": 8000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.45,
|
| 66 |
+
"eval_accuracy": 0.9035649281365719,
|
| 67 |
+
"eval_f1": 0.931070919922204,
|
| 68 |
+
"eval_loss": 0.049892134964466095,
|
| 69 |
+
"eval_roc_auc": 0.9581022789802229,
|
| 70 |
+
"eval_runtime": 943.267,
|
| 71 |
+
"eval_samples_per_second": 33.783,
|
| 72 |
+
"step": 8000
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.56,
|
| 76 |
+
"learning_rate": 4.7256875615748935e-06,
|
| 77 |
+
"loss": 0.0488,
|
| 78 |
+
"step": 10000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.56,
|
| 82 |
+
"eval_accuracy": 0.9092449632837507,
|
| 83 |
+
"eval_f1": 0.9369276016030965,
|
| 84 |
+
"eval_loss": 0.046968165785074234,
|
| 85 |
+
"eval_roc_auc": 0.9633660743801509,
|
| 86 |
+
"eval_runtime": 943.3238,
|
| 87 |
+
"eval_samples_per_second": 33.781,
|
| 88 |
+
"step": 10000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.67,
|
| 92 |
+
"learning_rate": 4.606988972901112e-06,
|
| 93 |
+
"loss": 0.0469,
|
| 94 |
+
"step": 12000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.67,
|
| 98 |
+
"eval_accuracy": 0.913512834996548,
|
| 99 |
+
"eval_f1": 0.941321897843637,
|
| 100 |
+
"eval_loss": 0.04364275932312012,
|
| 101 |
+
"eval_roc_auc": 0.9653120464218385,
|
| 102 |
+
"eval_runtime": 943.108,
|
| 103 |
+
"eval_samples_per_second": 33.788,
|
| 104 |
+
"step": 12000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.78,
|
| 108 |
+
"learning_rate": 4.4882903842273315e-06,
|
| 109 |
+
"loss": 0.0447,
|
| 110 |
+
"step": 14000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.78,
|
| 114 |
+
"eval_accuracy": 0.9181886650348333,
|
| 115 |
+
"eval_f1": 0.9415976522286926,
|
| 116 |
+
"eval_loss": 0.04153330251574516,
|
| 117 |
+
"eval_roc_auc": 0.9628170726293566,
|
| 118 |
+
"eval_runtime": 943.4861,
|
| 119 |
+
"eval_samples_per_second": 33.775,
|
| 120 |
+
"step": 14000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.89,
|
| 124 |
+
"learning_rate": 4.369591795553551e-06,
|
| 125 |
+
"loss": 0.0444,
|
| 126 |
+
"step": 16000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.89,
|
| 130 |
+
"eval_accuracy": 0.9147994727923179,
|
| 131 |
+
"eval_f1": 0.9419169981558534,
|
| 132 |
+
"eval_loss": 0.042323991656303406,
|
| 133 |
+
"eval_roc_auc": 0.9661668065711105,
|
| 134 |
+
"eval_runtime": 943.053,
|
| 135 |
+
"eval_samples_per_second": 33.79,
|
| 136 |
+
"step": 16000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.0,
|
| 140 |
+
"learning_rate": 4.25089320687977e-06,
|
| 141 |
+
"loss": 0.0428,
|
| 142 |
+
"step": 18000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0,
|
| 146 |
+
"eval_accuracy": 0.92073055921672,
|
| 147 |
+
"eval_f1": 0.945392908407904,
|
| 148 |
+
"eval_loss": 0.040571972727775574,
|
| 149 |
+
"eval_roc_auc": 0.967396285229951,
|
| 150 |
+
"eval_runtime": 943.6862,
|
| 151 |
+
"eval_samples_per_second": 33.768,
|
| 152 |
+
"step": 18000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.12,
|
| 156 |
+
"learning_rate": 4.13219461820599e-06,
|
| 157 |
+
"loss": 0.038,
|
| 158 |
+
"step": 20000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.12,
|
| 162 |
+
"eval_accuracy": 0.9201343124333144,
|
| 163 |
+
"eval_f1": 0.9434847253943194,
|
| 164 |
+
"eval_loss": 0.04074249416589737,
|
| 165 |
+
"eval_roc_auc": 0.9648247119998007,
|
| 166 |
+
"eval_runtime": 943.7404,
|
| 167 |
+
"eval_samples_per_second": 33.766,
|
| 168 |
+
"step": 20000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.23,
|
| 172 |
+
"learning_rate": 4.013496029532209e-06,
|
| 173 |
+
"loss": 0.0365,
|
| 174 |
+
"step": 22000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.23,
|
| 178 |
+
"eval_accuracy": 0.9186280047699743,
|
| 179 |
+
"eval_f1": 0.9448325191374088,
|
| 180 |
+
"eval_loss": 0.04050755128264427,
|
| 181 |
+
"eval_roc_auc": 0.968414370803744,
|
| 182 |
+
"eval_runtime": 944.2502,
|
| 183 |
+
"eval_samples_per_second": 33.747,
|
| 184 |
+
"step": 22000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.34,
|
| 188 |
+
"learning_rate": 3.8947974408584285e-06,
|
| 189 |
+
"loss": 0.0363,
|
| 190 |
+
"step": 24000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.34,
|
| 194 |
+
"eval_accuracy": 0.9201343124333144,
|
| 195 |
+
"eval_f1": 0.9443637975031708,
|
| 196 |
+
"eval_loss": 0.0401209257543087,
|
| 197 |
+
"eval_roc_auc": 0.9665495515278828,
|
| 198 |
+
"eval_runtime": 943.3154,
|
| 199 |
+
"eval_samples_per_second": 33.781,
|
| 200 |
+
"step": 24000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.45,
|
| 204 |
+
"learning_rate": 3.7760988521846475e-06,
|
| 205 |
+
"loss": 0.0369,
|
| 206 |
+
"step": 26000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.45,
|
| 210 |
+
"eval_accuracy": 0.9228331136634658,
|
| 211 |
+
"eval_f1": 0.9453032652246665,
|
| 212 |
+
"eval_loss": 0.03975052386522293,
|
| 213 |
+
"eval_roc_auc": 0.9652725030917011,
|
| 214 |
+
"eval_runtime": 943.3891,
|
| 215 |
+
"eval_samples_per_second": 33.778,
|
| 216 |
+
"step": 26000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.56,
|
| 220 |
+
"learning_rate": 3.6574002635108673e-06,
|
| 221 |
+
"loss": 0.0367,
|
| 222 |
+
"step": 28000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.56,
|
| 226 |
+
"eval_accuracy": 0.924308039917153,
|
| 227 |
+
"eval_f1": 0.9483727178359894,
|
| 228 |
+
"eval_loss": 0.03769804537296295,
|
| 229 |
+
"eval_roc_auc": 0.9692338448531075,
|
| 230 |
+
"eval_runtime": 943.731,
|
| 231 |
+
"eval_samples_per_second": 33.766,
|
| 232 |
+
"step": 28000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.67,
|
| 236 |
+
"learning_rate": 3.5387016748370867e-06,
|
| 237 |
+
"loss": 0.0357,
|
| 238 |
+
"step": 30000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.67,
|
| 242 |
+
"eval_accuracy": 0.9256888219418816,
|
| 243 |
+
"eval_f1": 0.9485330073349634,
|
| 244 |
+
"eval_loss": 0.03771040216088295,
|
| 245 |
+
"eval_roc_auc": 0.9689151700049551,
|
| 246 |
+
"eval_runtime": 943.5531,
|
| 247 |
+
"eval_samples_per_second": 33.772,
|
| 248 |
+
"step": 30000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.79,
|
| 252 |
+
"learning_rate": 3.420003086163306e-06,
|
| 253 |
+
"loss": 0.0353,
|
| 254 |
+
"step": 32000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.79,
|
| 258 |
+
"eval_accuracy": 0.9218289085545722,
|
| 259 |
+
"eval_f1": 0.945624456015514,
|
| 260 |
+
"eval_loss": 0.03922228887677193,
|
| 261 |
+
"eval_roc_auc": 0.9675467885174716,
|
| 262 |
+
"eval_runtime": 943.7902,
|
| 263 |
+
"eval_samples_per_second": 33.764,
|
| 264 |
+
"step": 32000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.9,
|
| 268 |
+
"learning_rate": 3.3013044974895255e-06,
|
| 269 |
+
"loss": 0.0361,
|
| 270 |
+
"step": 34000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.9,
|
| 274 |
+
"eval_accuracy": 0.9247159982426411,
|
| 275 |
+
"eval_f1": 0.9477583383080007,
|
| 276 |
+
"eval_loss": 0.03780689090490341,
|
| 277 |
+
"eval_roc_auc": 0.9678151508441292,
|
| 278 |
+
"eval_runtime": 943.8287,
|
| 279 |
+
"eval_samples_per_second": 33.762,
|
| 280 |
+
"step": 34000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.01,
|
| 284 |
+
"learning_rate": 3.1826059088157445e-06,
|
| 285 |
+
"loss": 0.0352,
|
| 286 |
+
"step": 36000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.01,
|
| 290 |
+
"eval_accuracy": 0.9262536873156342,
|
| 291 |
+
"eval_f1": 0.9494783086216365,
|
| 292 |
+
"eval_loss": 0.03738059848546982,
|
| 293 |
+
"eval_roc_auc": 0.970156686689613,
|
| 294 |
+
"eval_runtime": 944.0794,
|
| 295 |
+
"eval_samples_per_second": 33.754,
|
| 296 |
+
"step": 36000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.12,
|
| 300 |
+
"learning_rate": 3.063907320141964e-06,
|
| 301 |
+
"loss": 0.0304,
|
| 302 |
+
"step": 38000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.12,
|
| 306 |
+
"eval_accuracy": 0.9259084918094521,
|
| 307 |
+
"eval_f1": 0.948512218605291,
|
| 308 |
+
"eval_loss": 0.03789151459932327,
|
| 309 |
+
"eval_roc_auc": 0.9688610378201717,
|
| 310 |
+
"eval_runtime": 943.994,
|
| 311 |
+
"eval_samples_per_second": 33.757,
|
| 312 |
+
"step": 38000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.23,
|
| 316 |
+
"learning_rate": 2.9452087314681833e-06,
|
| 317 |
+
"loss": 0.03,
|
| 318 |
+
"step": 40000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.23,
|
| 322 |
+
"eval_accuracy": 0.9245904726040294,
|
| 323 |
+
"eval_f1": 0.9488459898909932,
|
| 324 |
+
"eval_loss": 0.03766411170363426,
|
| 325 |
+
"eval_roc_auc": 0.9705674249639594,
|
| 326 |
+
"eval_runtime": 943.9278,
|
| 327 |
+
"eval_samples_per_second": 33.759,
|
| 328 |
+
"step": 40000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.34,
|
| 332 |
+
"learning_rate": 2.8265101427944027e-06,
|
| 333 |
+
"loss": 0.0293,
|
| 334 |
+
"step": 42000
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.34,
|
| 338 |
+
"eval_accuracy": 0.9265675014121635,
|
| 339 |
+
"eval_f1": 0.9496503709571762,
|
| 340 |
+
"eval_loss": 0.03824329748749733,
|
| 341 |
+
"eval_roc_auc": 0.9707690753304716,
|
| 342 |
+
"eval_runtime": 943.7438,
|
| 343 |
+
"eval_samples_per_second": 33.766,
|
| 344 |
+
"step": 42000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.45,
|
| 348 |
+
"learning_rate": 2.7078115541206216e-06,
|
| 349 |
+
"loss": 0.0295,
|
| 350 |
+
"step": 44000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.45,
|
| 354 |
+
"eval_accuracy": 0.9280110462561978,
|
| 355 |
+
"eval_f1": 0.9498280736608847,
|
| 356 |
+
"eval_loss": 0.03822626546025276,
|
| 357 |
+
"eval_roc_auc": 0.9696253499219528,
|
| 358 |
+
"eval_runtime": 944.0868,
|
| 359 |
+
"eval_samples_per_second": 33.753,
|
| 360 |
+
"step": 44000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.57,
|
| 364 |
+
"learning_rate": 2.589112965446841e-06,
|
| 365 |
+
"loss": 0.0293,
|
| 366 |
+
"step": 46000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.57,
|
| 370 |
+
"eval_accuracy": 0.9273520366534864,
|
| 371 |
+
"eval_f1": 0.950136518250736,
|
| 372 |
+
"eval_loss": 0.0382731668651104,
|
| 373 |
+
"eval_roc_auc": 0.9705518129264687,
|
| 374 |
+
"eval_runtime": 944.2173,
|
| 375 |
+
"eval_samples_per_second": 33.749,
|
| 376 |
+
"step": 46000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.68,
|
| 380 |
+
"learning_rate": 2.4704143767730604e-06,
|
| 381 |
+
"loss": 0.0289,
|
| 382 |
+
"step": 48000
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.68,
|
| 386 |
+
"eval_accuracy": 0.9288583443168267,
|
| 387 |
+
"eval_f1": 0.9496914100188371,
|
| 388 |
+
"eval_loss": 0.038598936051130295,
|
| 389 |
+
"eval_roc_auc": 0.9687129340225382,
|
| 390 |
+
"eval_runtime": 943.702,
|
| 391 |
+
"eval_samples_per_second": 33.767,
|
| 392 |
+
"step": 48000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.79,
|
| 396 |
+
"learning_rate": 2.35171578809928e-06,
|
| 397 |
+
"loss": 0.0298,
|
| 398 |
+
"step": 50000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.79,
|
| 402 |
+
"eval_accuracy": 0.9273206552438336,
|
| 403 |
+
"eval_f1": 0.9502127205355373,
|
| 404 |
+
"eval_loss": 0.037168510258197784,
|
| 405 |
+
"eval_roc_auc": 0.9707164609217411,
|
| 406 |
+
"eval_runtime": 943.7733,
|
| 407 |
+
"eval_samples_per_second": 33.764,
|
| 408 |
+
"step": 50000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.9,
|
| 412 |
+
"learning_rate": 2.233017199425499e-06,
|
| 413 |
+
"loss": 0.0287,
|
| 414 |
+
"step": 52000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.9,
|
| 418 |
+
"eval_accuracy": 0.9278855206175861,
|
| 419 |
+
"eval_f1": 0.950306102196913,
|
| 420 |
+
"eval_loss": 0.03820985183119774,
|
| 421 |
+
"eval_roc_auc": 0.970297989008143,
|
| 422 |
+
"eval_runtime": 944.0102,
|
| 423 |
+
"eval_samples_per_second": 33.756,
|
| 424 |
+
"step": 52000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 3.01,
|
| 428 |
+
"learning_rate": 2.1143186107517182e-06,
|
| 429 |
+
"loss": 0.0286,
|
| 430 |
+
"step": 54000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 3.01,
|
| 434 |
+
"eval_accuracy": 0.9286072930396033,
|
| 435 |
+
"eval_f1": 0.9506395189108336,
|
| 436 |
+
"eval_loss": 0.03879757598042488,
|
| 437 |
+
"eval_roc_auc": 0.9705917028008494,
|
| 438 |
+
"eval_runtime": 943.6083,
|
| 439 |
+
"eval_samples_per_second": 33.77,
|
| 440 |
+
"step": 54000
|
| 441 |
+
}
|
| 442 |
+
],
|
| 443 |
+
"max_steps": 89625,
|
| 444 |
+
"num_train_epochs": 5,
|
| 445 |
+
"total_flos": 6.986708904362803e+16,
|
| 446 |
+
"trial_name": null,
|
| 447 |
+
"trial_params": null
|
| 448 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c96fce6c03c7036bda8d6d9f590b0f619ce6226897e80f1ed70d2676b3862d3
|
| 3 |
+
size 2479
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|