Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +4 -49
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,
|
|
@@ -22,51 +22,6 @@
|
|
| 22 |
"eval_samples_per_second": 9.651,
|
| 23 |
"eval_steps_per_second": 1.608,
|
| 24 |
"step": 25
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 4.166666666666667,
|
| 28 |
-
"grad_norm": 0.3806462287902832,
|
| 29 |
-
"learning_rate": 0.00010101010101010102,
|
| 30 |
-
"loss": 1.0128,
|
| 31 |
-
"step": 50
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 4.166666666666667,
|
| 35 |
-
"eval_loss": 0.8326404094696045,
|
| 36 |
-
"eval_runtime": 1.129,
|
| 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 |
-
"epoch": 8.333333333333334,
|
| 58 |
-
"grad_norm": 0.4516367018222809,
|
| 59 |
-
"learning_rate": 0.0,
|
| 60 |
-
"loss": 0.6339,
|
| 61 |
-
"step": 100
|
| 62 |
-
},
|
| 63 |
-
{
|
| 64 |
-
"epoch": 8.333333333333334,
|
| 65 |
-
"eval_loss": 0.6972503662109375,
|
| 66 |
-
"eval_runtime": 1.1255,
|
| 67 |
-
"eval_samples_per_second": 10.662,
|
| 68 |
-
"eval_steps_per_second": 1.777,
|
| 69 |
-
"step": 100
|
| 70 |
}
|
| 71 |
],
|
| 72 |
"logging_steps": 25,
|
|
@@ -81,12 +36,12 @@
|
|
| 81 |
"should_evaluate": false,
|
| 82 |
"should_log": false,
|
| 83 |
"should_save": true,
|
| 84 |
-
"should_training_stop":
|
| 85 |
},
|
| 86 |
"attributes": {}
|
| 87 |
}
|
| 88 |
},
|
| 89 |
-
"total_flos":
|
| 90 |
"train_batch_size": 1,
|
| 91 |
"trial_name": null,
|
| 92 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0833333333333335,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 25,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 22 |
"eval_samples_per_second": 9.651,
|
| 23 |
"eval_steps_per_second": 1.608,
|
| 24 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
}
|
| 26 |
],
|
| 27 |
"logging_steps": 25,
|
|
|
|
| 36 |
"should_evaluate": false,
|
| 37 |
"should_log": false,
|
| 38 |
"should_save": true,
|
| 39 |
+
"should_training_stop": false
|
| 40 |
},
|
| 41 |
"attributes": {}
|
| 42 |
}
|
| 43 |
},
|
| 44 |
+
"total_flos": 66578485708800.0,
|
| 45 |
"train_batch_size": 1,
|
| 46 |
"trial_name": null,
|
| 47 |
"trial_params": null
|