Commit
•
1967198
1
Parent(s):
7903541
End of training
Browse files- trainer_state.json +54 -18
trainer_state.json
CHANGED
|
@@ -1,35 +1,71 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.0,
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"train_runtime": 2.4372,
|
| 16 |
-
"train_samples_per_second": 1.231,
|
| 17 |
-
"train_steps_per_second": 1.231
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
"
|
| 27 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
| 29 |
],
|
| 30 |
-
"max_steps":
|
| 31 |
"num_train_epochs": 1,
|
| 32 |
-
"total_flos":
|
| 33 |
"trial_name": null,
|
| 34 |
"trial_params": null
|
| 35 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.02139495079161318,
|
| 5 |
+
"global_step": 150,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 13 |
+
"loss": 1.3206,
|
| 14 |
+
"step": 25
|
|
|
|
|
|
|
|
|
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"learning_rate": 8.8e-07,
|
| 19 |
+
"loss": 1.247,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.01,
|
| 24 |
+
"learning_rate": 1.3800000000000001e-06,
|
| 25 |
+
"loss": 1.1224,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.01,
|
| 30 |
+
"learning_rate": 1.8800000000000002e-06,
|
| 31 |
+
"loss": 0.9567,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.02,
|
| 36 |
+
"learning_rate": 2.38e-06,
|
| 37 |
+
"loss": 0.964,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02,
|
| 42 |
+
"learning_rate": 2.88e-06,
|
| 43 |
+
"loss": 0.7427,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"step": 150,
|
| 49 |
+
"total_flos": 9728999424000000.0,
|
| 50 |
+
"train_loss": 1.0588922500610352,
|
| 51 |
+
"train_runtime": 31.6687,
|
| 52 |
+
"train_samples_per_second": 4.737,
|
| 53 |
+
"train_steps_per_second": 4.737
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.02,
|
| 57 |
+
"eval_cer": 16.883464889935755,
|
| 58 |
+
"eval_loss": 0.8340538144111633,
|
| 59 |
+
"eval_runtime": 2688.9813,
|
| 60 |
+
"eval_samples_per_second": 0.727,
|
| 61 |
+
"eval_steps_per_second": 0.363,
|
| 62 |
+
"eval_wer": 41.865416504595984,
|
| 63 |
+
"step": 150
|
| 64 |
}
|
| 65 |
],
|
| 66 |
+
"max_steps": 150,
|
| 67 |
"num_train_epochs": 1,
|
| 68 |
+
"total_flos": 9728999424000000.0,
|
| 69 |
"trial_name": null,
|
| 70 |
"trial_params": null
|
| 71 |
}
|