Upload trainer_state.json
Browse files- trainer_state.json +91 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 89.28571428571429,
|
| 5 |
+
"global_step": 2500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 17.86,
|
| 12 |
+
"learning_rate": 4.94e-05,
|
| 13 |
+
"loss": 19.5604,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 17.86,
|
| 18 |
+
"eval_loss": 3.8375885486602783,
|
| 19 |
+
"eval_runtime": 2.2223,
|
| 20 |
+
"eval_samples_per_second": 86.395,
|
| 21 |
+
"eval_steps_per_second": 10.799,
|
| 22 |
+
"eval_wer": 1.0,
|
| 23 |
+
"step": 500
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 35.71,
|
| 27 |
+
"learning_rate": 9.94e-05,
|
| 28 |
+
"loss": 2.0837,
|
| 29 |
+
"step": 1000
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 35.71,
|
| 33 |
+
"eval_loss": 1.0887540578842163,
|
| 34 |
+
"eval_runtime": 2.2007,
|
| 35 |
+
"eval_samples_per_second": 87.246,
|
| 36 |
+
"eval_steps_per_second": 10.906,
|
| 37 |
+
"eval_wer": 0.6354166666666666,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 53.57,
|
| 42 |
+
"learning_rate": 7.255555555555555e-05,
|
| 43 |
+
"loss": 0.3185,
|
| 44 |
+
"step": 1500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 53.57,
|
| 48 |
+
"eval_loss": 0.3722864091396332,
|
| 49 |
+
"eval_runtime": 2.1581,
|
| 50 |
+
"eval_samples_per_second": 88.967,
|
| 51 |
+
"eval_steps_per_second": 11.121,
|
| 52 |
+
"eval_wer": 0.296875,
|
| 53 |
+
"step": 1500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 71.43,
|
| 57 |
+
"learning_rate": 4.477777777777778e-05,
|
| 58 |
+
"loss": 0.1425,
|
| 59 |
+
"step": 2000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 71.43,
|
| 63 |
+
"eval_loss": 0.22876793146133423,
|
| 64 |
+
"eval_runtime": 2.2468,
|
| 65 |
+
"eval_samples_per_second": 85.454,
|
| 66 |
+
"eval_steps_per_second": 10.682,
|
| 67 |
+
"eval_wer": 0.28125,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 89.29,
|
| 72 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 73 |
+
"loss": 0.0932,
|
| 74 |
+
"step": 2500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 89.29,
|
| 78 |
+
"eval_loss": 0.16792654991149902,
|
| 79 |
+
"eval_runtime": 2.2364,
|
| 80 |
+
"eval_samples_per_second": 85.85,
|
| 81 |
+
"eval_steps_per_second": 10.731,
|
| 82 |
+
"eval_wer": 0.18229166666666666,
|
| 83 |
+
"step": 2500
|
| 84 |
+
}
|
| 85 |
+
],
|
| 86 |
+
"max_steps": 2800,
|
| 87 |
+
"num_train_epochs": 100,
|
| 88 |
+
"total_flos": 3.050974757946286e+18,
|
| 89 |
+
"trial_name": null,
|
| 90 |
+
"trial_params": null
|
| 91 |
+
}
|