Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +3 -18
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -37,21 +37,6 @@
|
|
| 37 |
"eval_samples_per_second": 10.629,
|
| 38 |
"eval_steps_per_second": 1.772,
|
| 39 |
"step": 50
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"epoch": 6.25,
|
| 43 |
-
"grad_norm": 0.427622526884079,
|
| 44 |
-
"learning_rate": 5.050505050505051e-05,
|
| 45 |
-
"loss": 0.733,
|
| 46 |
-
"step": 75
|
| 47 |
-
},
|
| 48 |
-
{
|
| 49 |
-
"epoch": 6.25,
|
| 50 |
-
"eval_loss": 0.7211847901344299,
|
| 51 |
-
"eval_runtime": 1.1314,
|
| 52 |
-
"eval_samples_per_second": 10.606,
|
| 53 |
-
"eval_steps_per_second": 1.768,
|
| 54 |
-
"step": 75
|
| 55 |
}
|
| 56 |
],
|
| 57 |
"logging_steps": 25,
|
|
@@ -71,7 +56,7 @@
|
|
| 71 |
"attributes": {}
|
| 72 |
}
|
| 73 |
},
|
| 74 |
-
"total_flos":
|
| 75 |
"train_batch_size": 1,
|
| 76 |
"trial_name": null,
|
| 77 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.166666666666667,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 50,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 37 |
"eval_samples_per_second": 10.629,
|
| 38 |
"eval_steps_per_second": 1.772,
|
| 39 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
}
|
| 41 |
],
|
| 42 |
"logging_steps": 25,
|
|
|
|
| 56 |
"attributes": {}
|
| 57 |
}
|
| 58 |
},
|
| 59 |
+
"total_flos": 132486878822400.0,
|
| 60 |
"train_batch_size": 1,
|
| 61 |
"trial_name": null,
|
| 62 |
"trial_params": null
|