Upload 5 files
Browse files- trainer_state.json +3 -31
trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -148,34 +148,6 @@
|
|
| 148 |
"eval_samples_per_second": 8.882,
|
| 149 |
"eval_steps_per_second": 1.131,
|
| 150 |
"step": 260
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 5.289156626506024,
|
| 154 |
-
"grad_norm": 0.04389314353466034,
|
| 155 |
-
"learning_rate": 7.766978814259806e-05,
|
| 156 |
-
"loss": 0.0122,
|
| 157 |
-
"mean_token_accuracy": 0.9414373160007611,
|
| 158 |
-
"num_tokens": 111938446.0,
|
| 159 |
-
"step": 275
|
| 160 |
-
},
|
| 161 |
-
{
|
| 162 |
-
"epoch": 5.771084337349397,
|
| 163 |
-
"grad_norm": 0.03338490426540375,
|
| 164 |
-
"learning_rate": 4.1571241979147114e-05,
|
| 165 |
-
"loss": 0.0094,
|
| 166 |
-
"mean_token_accuracy": 0.9374336645007133,
|
| 167 |
-
"num_tokens": 122190732.0,
|
| 168 |
-
"step": 300
|
| 169 |
-
},
|
| 170 |
-
{
|
| 171 |
-
"epoch": 6.0,
|
| 172 |
-
"eval_loss": NaN,
|
| 173 |
-
"eval_mean_token_accuracy": 0.983714316753631,
|
| 174 |
-
"eval_num_tokens": 126386752.0,
|
| 175 |
-
"eval_runtime": 42.0902,
|
| 176 |
-
"eval_samples_per_second": 8.767,
|
| 177 |
-
"eval_steps_per_second": 1.117,
|
| 178 |
-
"step": 312
|
| 179 |
}
|
| 180 |
],
|
| 181 |
"logging_steps": 25,
|
|
@@ -195,7 +167,7 @@
|
|
| 195 |
"attributes": {}
|
| 196 |
}
|
| 197 |
},
|
| 198 |
-
"total_flos":
|
| 199 |
"train_batch_size": 1,
|
| 200 |
"trial_name": null,
|
| 201 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 260,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 148 |
"eval_samples_per_second": 8.882,
|
| 149 |
"eval_steps_per_second": 1.131,
|
| 150 |
"step": 260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 151 |
}
|
| 152 |
],
|
| 153 |
"logging_steps": 25,
|
|
|
|
| 167 |
"attributes": {}
|
| 168 |
}
|
| 169 |
},
|
| 170 |
+
"total_flos": 4.624520070050087e+18,
|
| 171 |
"train_batch_size": 1,
|
| 172 |
"trial_name": null,
|
| 173 |
"trial_params": null
|