Commit
•
28b1ed3
1
Parent(s):
9dbd880
Upload folder using huggingface_hub
Browse files- config.json +29 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +375 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "xlm-roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "xlm-roberta",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"problem_type": "single_label_classification",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.41.2",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 250002
|
| 29 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93709147351eec7d1734b52fbebe31cd3a2989a86d20eb946303eaac9aaa79d8
|
| 3 |
+
size 2239618672
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b3b3439f23c74c5b4f07f9d633824cb8456e544a4abbd15a0dc556028386dd2
|
| 3 |
+
size 4479472721
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a26fa195aba824656d9acc946849a090e13268ee15dc8cc09544185af1e2e5c
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e362ebab73ee91f56c60389c1d3f453064739eb675c1eabc49faabd6ba9f810
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,375 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8623634558093347,
|
| 3 |
+
"best_model_checkpoint": "./XLMR_large32-multi-outputs/checkpoint-18000",
|
| 4 |
+
"epoch": 12.91248206599713,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 18000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.7173601147776184,
|
| 13 |
+
"grad_norm": 16.311723709106445,
|
| 14 |
+
"learning_rate": 8.964589870013447e-07,
|
| 15 |
+
"loss": 0.6986,
|
| 16 |
+
"step": 1000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.7173601147776184,
|
| 20 |
+
"eval_accuracy": 0.5649409627611263,
|
| 21 |
+
"eval_f1": 0.6076986076986077,
|
| 22 |
+
"eval_loss": 0.6808627843856812,
|
| 23 |
+
"eval_precision": 0.5584545910687406,
|
| 24 |
+
"eval_recall": 0.6664670658682634,
|
| 25 |
+
"eval_runtime": 103.0001,
|
| 26 |
+
"eval_samples_per_second": 96.204,
|
| 27 |
+
"eval_steps_per_second": 1.505,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.4347202295552366,
|
| 32 |
+
"grad_norm": 10.006734848022461,
|
| 33 |
+
"learning_rate": 1.7929179740026893e-06,
|
| 34 |
+
"loss": 0.6307,
|
| 35 |
+
"step": 2000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.4347202295552366,
|
| 39 |
+
"eval_accuracy": 0.7109698254112423,
|
| 40 |
+
"eval_f1": 0.686720630059068,
|
| 41 |
+
"eval_loss": 0.510513424873352,
|
| 42 |
+
"eval_precision": 0.7596805421103582,
|
| 43 |
+
"eval_recall": 0.6265469061876248,
|
| 44 |
+
"eval_runtime": 102.7492,
|
| 45 |
+
"eval_samples_per_second": 96.439,
|
| 46 |
+
"eval_steps_per_second": 1.509,
|
| 47 |
+
"step": 2000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.152080344332855,
|
| 51 |
+
"grad_norm": 17.957138061523438,
|
| 52 |
+
"learning_rate": 1.9233796642255767e-06,
|
| 53 |
+
"loss": 0.4567,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.152080344332855,
|
| 58 |
+
"eval_accuracy": 0.75739226965385,
|
| 59 |
+
"eval_f1": 0.7636184857423796,
|
| 60 |
+
"eval_loss": 0.4005236327648163,
|
| 61 |
+
"eval_precision": 0.7525193798449612,
|
| 62 |
+
"eval_recall": 0.7750499001996008,
|
| 63 |
+
"eval_runtime": 102.7312,
|
| 64 |
+
"eval_samples_per_second": 96.456,
|
| 65 |
+
"eval_steps_per_second": 1.509,
|
| 66 |
+
"step": 3000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.869440459110473,
|
| 70 |
+
"grad_norm": 12.724874496459961,
|
| 71 |
+
"learning_rate": 1.8237433368206048e-06,
|
| 72 |
+
"loss": 0.3935,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.869440459110473,
|
| 77 |
+
"eval_accuracy": 0.7773741043495812,
|
| 78 |
+
"eval_f1": 0.7708766098878271,
|
| 79 |
+
"eval_loss": 0.36614805459976196,
|
| 80 |
+
"eval_precision": 0.8035946297098311,
|
| 81 |
+
"eval_recall": 0.7407185628742515,
|
| 82 |
+
"eval_runtime": 102.7412,
|
| 83 |
+
"eval_samples_per_second": 96.446,
|
| 84 |
+
"eval_steps_per_second": 1.509,
|
| 85 |
+
"step": 4000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 3.586800573888092,
|
| 89 |
+
"grad_norm": 16.976110458374023,
|
| 90 |
+
"learning_rate": 1.724107009415633e-06,
|
| 91 |
+
"loss": 0.3607,
|
| 92 |
+
"step": 5000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.586800573888092,
|
| 96 |
+
"eval_accuracy": 0.8000807346856393,
|
| 97 |
+
"eval_f1": 0.8191363096868438,
|
| 98 |
+
"eval_loss": 0.34079551696777344,
|
| 99 |
+
"eval_precision": 0.7548376240955746,
|
| 100 |
+
"eval_recall": 0.8954091816367266,
|
| 101 |
+
"eval_runtime": 102.5685,
|
| 102 |
+
"eval_samples_per_second": 96.609,
|
| 103 |
+
"eval_steps_per_second": 1.511,
|
| 104 |
+
"step": 5000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.30416068866571,
|
| 108 |
+
"grad_norm": 13.054981231689453,
|
| 109 |
+
"learning_rate": 1.624470682010661e-06,
|
| 110 |
+
"loss": 0.3314,
|
| 111 |
+
"step": 6000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 4.30416068866571,
|
| 115 |
+
"eval_accuracy": 0.8120900191744879,
|
| 116 |
+
"eval_f1": 0.8181640625,
|
| 117 |
+
"eval_loss": 0.3178483843803406,
|
| 118 |
+
"eval_precision": 0.8009560229445507,
|
| 119 |
+
"eval_recall": 0.836127744510978,
|
| 120 |
+
"eval_runtime": 102.6877,
|
| 121 |
+
"eval_samples_per_second": 96.497,
|
| 122 |
+
"eval_steps_per_second": 1.509,
|
| 123 |
+
"step": 6000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 5.0215208034433285,
|
| 127 |
+
"grad_norm": 22.831750869750977,
|
| 128 |
+
"learning_rate": 1.5248343546056892e-06,
|
| 129 |
+
"loss": 0.3034,
|
| 130 |
+
"step": 7000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 5.0215208034433285,
|
| 134 |
+
"eval_accuracy": 0.8225855283075991,
|
| 135 |
+
"eval_f1": 0.8238476953907815,
|
| 136 |
+
"eval_loss": 0.3033134341239929,
|
| 137 |
+
"eval_precision": 0.8271629778672032,
|
| 138 |
+
"eval_recall": 0.820558882235529,
|
| 139 |
+
"eval_runtime": 102.5363,
|
| 140 |
+
"eval_samples_per_second": 96.639,
|
| 141 |
+
"eval_steps_per_second": 1.512,
|
| 142 |
+
"step": 7000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 5.738880918220947,
|
| 146 |
+
"grad_norm": 34.70615005493164,
|
| 147 |
+
"learning_rate": 1.4251980272007174e-06,
|
| 148 |
+
"loss": 0.276,
|
| 149 |
+
"step": 8000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 5.738880918220947,
|
| 153 |
+
"eval_accuracy": 0.838934302149561,
|
| 154 |
+
"eval_f1": 0.8336113427856547,
|
| 155 |
+
"eval_loss": 0.2884746193885803,
|
| 156 |
+
"eval_precision": 0.8725447402880838,
|
| 157 |
+
"eval_recall": 0.7980039920159681,
|
| 158 |
+
"eval_runtime": 102.5026,
|
| 159 |
+
"eval_samples_per_second": 96.671,
|
| 160 |
+
"eval_steps_per_second": 1.512,
|
| 161 |
+
"step": 8000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 6.456241032998565,
|
| 165 |
+
"grad_norm": 12.14201831817627,
|
| 166 |
+
"learning_rate": 1.3255616997957455e-06,
|
| 167 |
+
"loss": 0.2633,
|
| 168 |
+
"step": 9000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 6.456241032998565,
|
| 172 |
+
"eval_accuracy": 0.8357049147239883,
|
| 173 |
+
"eval_f1": 0.833979196410361,
|
| 174 |
+
"eval_loss": 0.3028285503387451,
|
| 175 |
+
"eval_precision": 0.8525854879065888,
|
| 176 |
+
"eval_recall": 0.8161676646706587,
|
| 177 |
+
"eval_runtime": 102.6676,
|
| 178 |
+
"eval_samples_per_second": 96.515,
|
| 179 |
+
"eval_steps_per_second": 1.51,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 7.173601147776184,
|
| 184 |
+
"grad_norm": 27.226970672607422,
|
| 185 |
+
"learning_rate": 1.2259253723907737e-06,
|
| 186 |
+
"loss": 0.248,
|
| 187 |
+
"step": 10000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 7.173601147776184,
|
| 191 |
+
"eval_accuracy": 0.8506408315672621,
|
| 192 |
+
"eval_f1": 0.8506559031281534,
|
| 193 |
+
"eval_loss": 0.2664211690425873,
|
| 194 |
+
"eval_precision": 0.860204081632653,
|
| 195 |
+
"eval_recall": 0.8413173652694611,
|
| 196 |
+
"eval_runtime": 102.4829,
|
| 197 |
+
"eval_samples_per_second": 96.689,
|
| 198 |
+
"eval_steps_per_second": 1.512,
|
| 199 |
+
"step": 10000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 7.890961262553802,
|
| 203 |
+
"grad_norm": 14.358187675476074,
|
| 204 |
+
"learning_rate": 1.1262890449858017e-06,
|
| 205 |
+
"loss": 0.2351,
|
| 206 |
+
"step": 11000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 7.890961262553802,
|
| 210 |
+
"eval_accuracy": 0.85326470885054,
|
| 211 |
+
"eval_f1": 0.8551215623754483,
|
| 212 |
+
"eval_loss": 0.2719918191432953,
|
| 213 |
+
"eval_precision": 0.8537604456824512,
|
| 214 |
+
"eval_recall": 0.8564870259481038,
|
| 215 |
+
"eval_runtime": 102.5517,
|
| 216 |
+
"eval_samples_per_second": 96.624,
|
| 217 |
+
"eval_steps_per_second": 1.511,
|
| 218 |
+
"step": 11000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 8.60832137733142,
|
| 222 |
+
"grad_norm": 7.578697681427002,
|
| 223 |
+
"learning_rate": 1.02665271758083e-06,
|
| 224 |
+
"loss": 0.2247,
|
| 225 |
+
"step": 12000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 8.60832137733142,
|
| 229 |
+
"eval_accuracy": 0.8555858310626703,
|
| 230 |
+
"eval_f1": 0.852853470437018,
|
| 231 |
+
"eval_loss": 0.26294445991516113,
|
| 232 |
+
"eval_precision": 0.8795334040296925,
|
| 233 |
+
"eval_recall": 0.8277445109780439,
|
| 234 |
+
"eval_runtime": 102.496,
|
| 235 |
+
"eval_samples_per_second": 96.677,
|
| 236 |
+
"eval_steps_per_second": 1.512,
|
| 237 |
+
"step": 12000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 9.32568149210904,
|
| 241 |
+
"grad_norm": 46.33930969238281,
|
| 242 |
+
"learning_rate": 9.27016390175858e-07,
|
| 243 |
+
"loss": 0.2158,
|
| 244 |
+
"step": 13000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 9.32568149210904,
|
| 248 |
+
"eval_accuracy": 0.8530628721364416,
|
| 249 |
+
"eval_f1": 0.8558415841584158,
|
| 250 |
+
"eval_loss": 0.28966662287712097,
|
| 251 |
+
"eval_precision": 0.8491159135559921,
|
| 252 |
+
"eval_recall": 0.8626746506986028,
|
| 253 |
+
"eval_runtime": 102.3088,
|
| 254 |
+
"eval_samples_per_second": 96.854,
|
| 255 |
+
"eval_steps_per_second": 1.515,
|
| 256 |
+
"step": 13000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 10.043041606886657,
|
| 260 |
+
"grad_norm": 13.620414733886719,
|
| 261 |
+
"learning_rate": 8.273800627708863e-07,
|
| 262 |
+
"loss": 0.2085,
|
| 263 |
+
"step": 14000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 10.043041606886657,
|
| 267 |
+
"eval_accuracy": 0.8604299122010294,
|
| 268 |
+
"eval_f1": 0.8604017361461593,
|
| 269 |
+
"eval_loss": 0.2769163250923157,
|
| 270 |
+
"eval_precision": 0.8703287727179906,
|
| 271 |
+
"eval_recall": 0.8506986027944112,
|
| 272 |
+
"eval_runtime": 102.3036,
|
| 273 |
+
"eval_samples_per_second": 96.859,
|
| 274 |
+
"eval_steps_per_second": 1.515,
|
| 275 |
+
"step": 14000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 10.760401721664275,
|
| 279 |
+
"grad_norm": 5.338364601135254,
|
| 280 |
+
"learning_rate": 7.277437353659144e-07,
|
| 281 |
+
"loss": 0.1999,
|
| 282 |
+
"step": 15000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 10.760401721664275,
|
| 286 |
+
"eval_accuracy": 0.8576041982036532,
|
| 287 |
+
"eval_f1": 0.8572006881894545,
|
| 288 |
+
"eval_loss": 0.2730887830257416,
|
| 289 |
+
"eval_precision": 0.8694313282693492,
|
| 290 |
+
"eval_recall": 0.845309381237525,
|
| 291 |
+
"eval_runtime": 102.2525,
|
| 292 |
+
"eval_samples_per_second": 96.907,
|
| 293 |
+
"eval_steps_per_second": 1.516,
|
| 294 |
+
"step": 15000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 11.477761836441895,
|
| 298 |
+
"grad_norm": 19.627927780151367,
|
| 299 |
+
"learning_rate": 6.281074079609425e-07,
|
| 300 |
+
"loss": 0.1981,
|
| 301 |
+
"step": 16000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 11.477761836441895,
|
| 305 |
+
"eval_accuracy": 0.8634574629125038,
|
| 306 |
+
"eval_f1": 0.8587535233322894,
|
| 307 |
+
"eval_loss": 0.27952489256858826,
|
| 308 |
+
"eval_precision": 0.9001969796454367,
|
| 309 |
+
"eval_recall": 0.8209580838323354,
|
| 310 |
+
"eval_runtime": 102.2452,
|
| 311 |
+
"eval_samples_per_second": 96.914,
|
| 312 |
+
"eval_steps_per_second": 1.516,
|
| 313 |
+
"step": 16000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 12.195121951219512,
|
| 317 |
+
"grad_norm": 19.674339294433594,
|
| 318 |
+
"learning_rate": 5.284710805559706e-07,
|
| 319 |
+
"loss": 0.1933,
|
| 320 |
+
"step": 17000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 12.195121951219512,
|
| 324 |
+
"eval_accuracy": 0.858815218488243,
|
| 325 |
+
"eval_f1": 0.8589291116265,
|
| 326 |
+
"eval_loss": 0.28878509998321533,
|
| 327 |
+
"eval_precision": 0.8679437538210719,
|
| 328 |
+
"eval_recall": 0.8500998003992016,
|
| 329 |
+
"eval_runtime": 102.3747,
|
| 330 |
+
"eval_samples_per_second": 96.791,
|
| 331 |
+
"eval_steps_per_second": 1.514,
|
| 332 |
+
"step": 17000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 12.91248206599713,
|
| 336 |
+
"grad_norm": 7.702261447906494,
|
| 337 |
+
"learning_rate": 4.288347531509988e-07,
|
| 338 |
+
"loss": 0.1888,
|
| 339 |
+
"step": 18000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 12.91248206599713,
|
| 343 |
+
"eval_accuracy": 0.860127157129882,
|
| 344 |
+
"eval_f1": 0.8623634558093347,
|
| 345 |
+
"eval_loss": 0.2733915150165558,
|
| 346 |
+
"eval_precision": 0.858102766798419,
|
| 347 |
+
"eval_recall": 0.8666666666666667,
|
| 348 |
+
"eval_runtime": 102.3818,
|
| 349 |
+
"eval_samples_per_second": 96.785,
|
| 350 |
+
"eval_steps_per_second": 1.514,
|
| 351 |
+
"step": 18000
|
| 352 |
+
}
|
| 353 |
+
],
|
| 354 |
+
"logging_steps": 1000,
|
| 355 |
+
"max_steps": 22304,
|
| 356 |
+
"num_input_tokens_seen": 0,
|
| 357 |
+
"num_train_epochs": 16,
|
| 358 |
+
"save_steps": 1000,
|
| 359 |
+
"stateful_callbacks": {
|
| 360 |
+
"TrainerControl": {
|
| 361 |
+
"args": {
|
| 362 |
+
"should_epoch_stop": false,
|
| 363 |
+
"should_evaluate": false,
|
| 364 |
+
"should_log": false,
|
| 365 |
+
"should_save": true,
|
| 366 |
+
"should_training_stop": false
|
| 367 |
+
},
|
| 368 |
+
"attributes": {}
|
| 369 |
+
}
|
| 370 |
+
},
|
| 371 |
+
"total_flos": 1.0007259177082022e+18,
|
| 372 |
+
"train_batch_size": 64,
|
| 373 |
+
"trial_name": null,
|
| 374 |
+
"trial_params": null
|
| 375 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc8bd7d03569450979c0209e7d2725adc88949b89dfb56cc9b04d68f7e551dec
|
| 3 |
+
size 5048
|