Commit
·
12de0e9
1
Parent(s):
89773d5
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.5,
|
| 3 |
+
"eval_loss": 1.344416856765747,
|
| 4 |
+
"eval_runtime": 6.9513,
|
| 5 |
+
"eval_samples": 10,
|
| 6 |
+
"eval_samples_per_second": 1.439,
|
| 7 |
+
"eval_steps_per_second": 0.144,
|
| 8 |
+
"eval_wer": 231.8840579710145,
|
| 9 |
+
"train_loss": 1.3101277351379395,
|
| 10 |
+
"train_runtime": 10.9615,
|
| 11 |
+
"train_samples": 10,
|
| 12 |
+
"train_samples_per_second": 5.839,
|
| 13 |
+
"train_steps_per_second": 0.182
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.5,
|
| 3 |
+
"eval_loss": 1.344416856765747,
|
| 4 |
+
"eval_runtime": 6.9513,
|
| 5 |
+
"eval_samples": 10,
|
| 6 |
+
"eval_samples_per_second": 1.439,
|
| 7 |
+
"eval_steps_per_second": 0.144,
|
| 8 |
+
"eval_wer": 231.8840579710145
|
| 9 |
+
}
|
runs/Jan20_14-59-56_47bd09836e6b407eb4b7bfb55742b2da000000/events.out.tfevents.1674226845.47bd09836e6b407eb4b7bfb55742b2da000000.16.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d47194011b0716ee97198b690917d5abcc360a756f49eee8379128a7ab2d495
|
| 3 |
+
size 352
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.5,
|
| 3 |
+
"train_loss": 1.3101277351379395,
|
| 4 |
+
"train_runtime": 10.9615,
|
| 5 |
+
"train_samples": 10,
|
| 6 |
+
"train_samples_per_second": 5.839,
|
| 7 |
+
"train_steps_per_second": 0.182
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.5,
|
| 5 |
+
"global_step": 2,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.5,
|
| 12 |
+
"eval_loss": 1.344416856765747,
|
| 13 |
+
"eval_runtime": 7.2282,
|
| 14 |
+
"eval_samples_per_second": 1.383,
|
| 15 |
+
"eval_steps_per_second": 0.138,
|
| 16 |
+
"eval_wer": 231.8840579710145,
|
| 17 |
+
"step": 2
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.5,
|
| 21 |
+
"step": 2,
|
| 22 |
+
"total_flos": 1297199923200000.0,
|
| 23 |
+
"train_loss": 1.3101277351379395,
|
| 24 |
+
"train_runtime": 10.9615,
|
| 25 |
+
"train_samples_per_second": 5.839,
|
| 26 |
+
"train_steps_per_second": 0.182
|
| 27 |
+
}
|
| 28 |
+
],
|
| 29 |
+
"max_steps": 2,
|
| 30 |
+
"num_train_epochs": 9223372036854775807,
|
| 31 |
+
"total_flos": 1297199923200000.0,
|
| 32 |
+
"trial_name": null,
|
| 33 |
+
"trial_params": null
|
| 34 |
+
}
|