Upload trainer_state.json
Browse files- trainer_state.json +75 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 10,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 2.0,
|
| 12 |
+
"eval_cer": 0.4666666666666667,
|
| 13 |
+
"eval_loss": 86.90267944335938,
|
| 14 |
+
"eval_runtime": 17.2823,
|
| 15 |
+
"eval_samples_per_second": 0.116,
|
| 16 |
+
"eval_steps_per_second": 0.058,
|
| 17 |
+
"eval_wer": 1.0,
|
| 18 |
+
"step": 2
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 4.0,
|
| 22 |
+
"eval_cer": 0.4666666666666667,
|
| 23 |
+
"eval_loss": 75.15727233886719,
|
| 24 |
+
"eval_runtime": 15.1141,
|
| 25 |
+
"eval_samples_per_second": 0.132,
|
| 26 |
+
"eval_steps_per_second": 0.066,
|
| 27 |
+
"eval_wer": 1.0,
|
| 28 |
+
"step": 4
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 6.0,
|
| 32 |
+
"eval_cer": 0.4666666666666667,
|
| 33 |
+
"eval_loss": 73.1053237915039,
|
| 34 |
+
"eval_runtime": 3.6762,
|
| 35 |
+
"eval_samples_per_second": 0.544,
|
| 36 |
+
"eval_steps_per_second": 0.272,
|
| 37 |
+
"eval_wer": 1.0,
|
| 38 |
+
"step": 6
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 8.0,
|
| 42 |
+
"eval_cer": 0.4666666666666667,
|
| 43 |
+
"eval_loss": 75.6639404296875,
|
| 44 |
+
"eval_runtime": 3.6084,
|
| 45 |
+
"eval_samples_per_second": 0.554,
|
| 46 |
+
"eval_steps_per_second": 0.277,
|
| 47 |
+
"eval_wer": 1.0,
|
| 48 |
+
"step": 8
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 10.0,
|
| 52 |
+
"eval_cer": 0.4666666666666667,
|
| 53 |
+
"eval_loss": 77.0830078125,
|
| 54 |
+
"eval_runtime": 3.2264,
|
| 55 |
+
"eval_samples_per_second": 0.62,
|
| 56 |
+
"eval_steps_per_second": 0.31,
|
| 57 |
+
"eval_wer": 1.0,
|
| 58 |
+
"step": 10
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 10.0,
|
| 62 |
+
"step": 10,
|
| 63 |
+
"total_flos": 3043080072115200.0,
|
| 64 |
+
"train_loss": 22.953053283691407,
|
| 65 |
+
"train_runtime": 1186.2575,
|
| 66 |
+
"train_samples_per_second": 0.017,
|
| 67 |
+
"train_steps_per_second": 0.008
|
| 68 |
+
}
|
| 69 |
+
],
|
| 70 |
+
"max_steps": 10,
|
| 71 |
+
"num_train_epochs": 10,
|
| 72 |
+
"total_flos": 3043080072115200.0,
|
| 73 |
+
"trial_name": null,
|
| 74 |
+
"trial_params": null
|
| 75 |
+
}
|