Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +243 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 1.4591705799102783,
|
| 14 |
+
"learning_rate": 9.982023428222962e-05,
|
| 15 |
+
"loss": 2.6337,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 2.0,
|
| 20 |
+
"grad_norm": 0.8328539133071899,
|
| 21 |
+
"learning_rate": 9.91045243455787e-05,
|
| 22 |
+
"loss": 1.5372,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 3.0,
|
| 27 |
+
"grad_norm": 0.8647604584693909,
|
| 28 |
+
"learning_rate": 9.785081496441527e-05,
|
| 29 |
+
"loss": 1.1526,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 4.0,
|
| 34 |
+
"grad_norm": 1.6284393072128296,
|
| 35 |
+
"learning_rate": 9.607284204107493e-05,
|
| 36 |
+
"loss": 0.7283,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 5.0,
|
| 41 |
+
"grad_norm": 2.7794511318206787,
|
| 42 |
+
"learning_rate": 9.379008541897054e-05,
|
| 43 |
+
"loss": 0.3829,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 6.0,
|
| 48 |
+
"grad_norm": 0.7847722768783569,
|
| 49 |
+
"learning_rate": 9.102755545735141e-05,
|
| 50 |
+
"loss": 0.2319,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 7.0,
|
| 55 |
+
"grad_norm": 0.7915834784507751,
|
| 56 |
+
"learning_rate": 8.78155190125736e-05,
|
| 57 |
+
"loss": 0.1744,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 8.0,
|
| 62 |
+
"grad_norm": 1.0084211826324463,
|
| 63 |
+
"learning_rate": 8.418916782808795e-05,
|
| 64 |
+
"loss": 0.1513,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 9.0,
|
| 69 |
+
"grad_norm": 1.6660008430480957,
|
| 70 |
+
"learning_rate": 8.018823296633441e-05,
|
| 71 |
+
"loss": 0.1396,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 10.0,
|
| 76 |
+
"grad_norm": 0.6257602572441101,
|
| 77 |
+
"learning_rate": 7.585654950690786e-05,
|
| 78 |
+
"loss": 0.1256,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 11.0,
|
| 83 |
+
"grad_norm": 0.7090705633163452,
|
| 84 |
+
"learning_rate": 7.124157628025278e-05,
|
| 85 |
+
"loss": 0.1179,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 12.0,
|
| 90 |
+
"grad_norm": 0.4159357249736786,
|
| 91 |
+
"learning_rate": 6.639387589878566e-05,
|
| 92 |
+
"loss": 0.1166,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 13.0,
|
| 97 |
+
"grad_norm": 0.3188364505767822,
|
| 98 |
+
"learning_rate": 6.136656078233232e-05,
|
| 99 |
+
"loss": 0.114,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 14.0,
|
| 104 |
+
"grad_norm": 0.34499579668045044,
|
| 105 |
+
"learning_rate": 5.621471124734201e-05,
|
| 106 |
+
"loss": 0.1101,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 15.0,
|
| 111 |
+
"grad_norm": 0.6969137787818909,
|
| 112 |
+
"learning_rate": 5.09947720354139e-05,
|
| 113 |
+
"loss": 0.1092,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 16.0,
|
| 118 |
+
"grad_norm": 0.8777207136154175,
|
| 119 |
+
"learning_rate": 4.576393389289633e-05,
|
| 120 |
+
"loss": 0.1072,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 17.0,
|
| 125 |
+
"grad_norm": 0.34652048349380493,
|
| 126 |
+
"learning_rate": 4.0579506977102036e-05,
|
| 127 |
+
"loss": 0.1063,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 18.0,
|
| 132 |
+
"grad_norm": 0.2864055931568146,
|
| 133 |
+
"learning_rate": 3.5498292954231496e-05,
|
| 134 |
+
"loss": 0.1062,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 19.0,
|
| 139 |
+
"grad_norm": 0.5659065842628479,
|
| 140 |
+
"learning_rate": 3.05759626684317e-05,
|
| 141 |
+
"loss": 0.1036,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 20.0,
|
| 146 |
+
"grad_norm": 0.37669795751571655,
|
| 147 |
+
"learning_rate": 2.5866446200377688e-05,
|
| 148 |
+
"loss": 0.1021,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 21.0,
|
| 153 |
+
"grad_norm": 0.2888871133327484,
|
| 154 |
+
"learning_rate": 2.1421341998023163e-05,
|
| 155 |
+
"loss": 0.0996,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 22.0,
|
| 160 |
+
"grad_norm": 0.5899520516395569,
|
| 161 |
+
"learning_rate": 1.7289351553206952e-05,
|
| 162 |
+
"loss": 0.0983,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 23.0,
|
| 167 |
+
"grad_norm": 0.4493533968925476,
|
| 168 |
+
"learning_rate": 1.3515745817917069e-05,
|
| 169 |
+
"loss": 0.0977,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 24.0,
|
| 174 |
+
"grad_norm": 0.3612530529499054,
|
| 175 |
+
"learning_rate": 1.0141869206267095e-05,
|
| 176 |
+
"loss": 0.0965,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 25.0,
|
| 181 |
+
"grad_norm": 0.22373980283737183,
|
| 182 |
+
"learning_rate": 7.204686616443351e-06,
|
| 183 |
+
"loss": 0.0958,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 26.0,
|
| 188 |
+
"grad_norm": 0.44540122151374817,
|
| 189 |
+
"learning_rate": 4.73637843554493e-06,
|
| 190 |
+
"loss": 0.0948,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 27.0,
|
| 195 |
+
"grad_norm": 0.4003278613090515,
|
| 196 |
+
"learning_rate": 2.763987964528425e-06,
|
| 197 |
+
"loss": 0.0943,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 28.0,
|
| 202 |
+
"grad_norm": 0.4109736979007721,
|
| 203 |
+
"learning_rate": 1.3091251261435566e-06,
|
| 204 |
+
"loss": 0.0937,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 29.0,
|
| 209 |
+
"grad_norm": 0.4337215721607208,
|
| 210 |
+
"learning_rate": 3.877297020972781e-07,
|
| 211 |
+
"loss": 0.0933,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 30.0,
|
| 216 |
+
"grad_norm": 0.4439603090286255,
|
| 217 |
+
"learning_rate": 9.896693469829688e-09,
|
| 218 |
+
"loss": 0.093,
|
| 219 |
+
"step": 3000
|
| 220 |
+
}
|
| 221 |
+
],
|
| 222 |
+
"logging_steps": 500,
|
| 223 |
+
"max_steps": 3000,
|
| 224 |
+
"num_input_tokens_seen": 0,
|
| 225 |
+
"num_train_epochs": 30,
|
| 226 |
+
"save_steps": 500,
|
| 227 |
+
"stateful_callbacks": {
|
| 228 |
+
"TrainerControl": {
|
| 229 |
+
"args": {
|
| 230 |
+
"should_epoch_stop": false,
|
| 231 |
+
"should_evaluate": false,
|
| 232 |
+
"should_log": false,
|
| 233 |
+
"should_save": true,
|
| 234 |
+
"should_training_stop": true
|
| 235 |
+
},
|
| 236 |
+
"attributes": {}
|
| 237 |
+
}
|
| 238 |
+
},
|
| 239 |
+
"total_flos": 5757808997376000.0,
|
| 240 |
+
"train_batch_size": 1,
|
| 241 |
+
"trial_name": null,
|
| 242 |
+
"trial_params": null
|
| 243 |
+
}
|