Commit
•
b71f1e1
1
Parent(s):
d0fb1a4
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +55 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 70.0,
|
| 3 |
+
"eval_loss": 0.617826521396637,
|
| 4 |
+
"eval_runtime": 12.9706,
|
| 5 |
+
"eval_samples": 301,
|
| 6 |
+
"eval_samples_per_second": 23.206,
|
| 7 |
+
"eval_steps_per_second": 2.93,
|
| 8 |
+
"eval_wer": 0.579388353581902,
|
| 9 |
+
"train_loss": 2.7389903675426135,
|
| 10 |
+
"train_runtime": 3757.1772,
|
| 11 |
+
"train_samples": 704,
|
| 12 |
+
"train_samples_per_second": 13.116,
|
| 13 |
+
"train_steps_per_second": 0.205
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 70.0,
|
| 3 |
+
"eval_loss": 0.617826521396637,
|
| 4 |
+
"eval_runtime": 12.9706,
|
| 5 |
+
"eval_samples": 301,
|
| 6 |
+
"eval_samples_per_second": 23.206,
|
| 7 |
+
"eval_steps_per_second": 2.93,
|
| 8 |
+
"eval_wer": 0.579388353581902
|
| 9 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262108145
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a2714bff2398ab7fafb43dafa29eb9ded2eabc93b25793c08510e35fad67b8a
|
| 3 |
size 1262108145
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 70.0,
|
| 3 |
+
"train_loss": 2.7389903675426135,
|
| 4 |
+
"train_runtime": 3757.1772,
|
| 5 |
+
"train_samples": 704,
|
| 6 |
+
"train_samples_per_second": 13.116,
|
| 7 |
+
"train_steps_per_second": 0.205
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 70.0,
|
| 5 |
+
"global_step": 770,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 27.27,
|
| 12 |
+
"learning_rate": 0.0001495,
|
| 13 |
+
"loss": 5.2793,
|
| 14 |
+
"step": 300
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 27.27,
|
| 18 |
+
"eval_loss": 3.073740243911743,
|
| 19 |
+
"eval_runtime": 13.7846,
|
| 20 |
+
"eval_samples_per_second": 21.836,
|
| 21 |
+
"eval_steps_per_second": 2.757,
|
| 22 |
+
"eval_wer": 1.0,
|
| 23 |
+
"step": 300
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 54.55,
|
| 27 |
+
"learning_rate": 0.00015833333333333332,
|
| 28 |
+
"loss": 1.5348,
|
| 29 |
+
"step": 600
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 54.55,
|
| 33 |
+
"eval_loss": 0.6312472820281982,
|
| 34 |
+
"eval_runtime": 13.5036,
|
| 35 |
+
"eval_samples_per_second": 22.29,
|
| 36 |
+
"eval_steps_per_second": 2.814,
|
| 37 |
+
"eval_wer": 0.6334310850439883,
|
| 38 |
+
"step": 600
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 70.0,
|
| 42 |
+
"step": 770,
|
| 43 |
+
"total_flos": 1.0714540362717635e+19,
|
| 44 |
+
"train_loss": 2.7389903675426135,
|
| 45 |
+
"train_runtime": 3757.1772,
|
| 46 |
+
"train_samples_per_second": 13.116,
|
| 47 |
+
"train_steps_per_second": 0.205
|
| 48 |
+
}
|
| 49 |
+
],
|
| 50 |
+
"max_steps": 770,
|
| 51 |
+
"num_train_epochs": 70,
|
| 52 |
+
"total_flos": 1.0714540362717635e+19,
|
| 53 |
+
"trial_name": null,
|
| 54 |
+
"trial_params": null
|
| 55 |
+
}
|