End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_loss": 2.984119415283203,
|
| 4 |
+
"eval_runtime": 59.5908,
|
| 5 |
+
"eval_samples": 1647,
|
| 6 |
+
"eval_samples_per_second": 27.638,
|
| 7 |
+
"eval_steps_per_second": 0.436,
|
| 8 |
+
"eval_wer": 0.9998978653865795,
|
| 9 |
+
"train_loss": 6.1072265625,
|
| 10 |
+
"train_runtime": 7028.2199,
|
| 11 |
+
"train_samples": 3478,
|
| 12 |
+
"train_samples_per_second": 7.423,
|
| 13 |
+
"train_steps_per_second": 0.03
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_loss": 2.984119415283203,
|
| 4 |
+
"eval_runtime": 59.5908,
|
| 5 |
+
"eval_samples": 1647,
|
| 6 |
+
"eval_samples_per_second": 27.638,
|
| 7 |
+
"eval_steps_per_second": 0.436,
|
| 8 |
+
"eval_wer": 0.9998978653865795
|
| 9 |
+
}
|
runs/Mar31_17-35-45_8b2dcae2e182/events.out.tfevents.1648726782.8b2dcae2e182.1036943.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc6e62a940a86d2d15b6ef996d79a03dbe88bb5610692ea0c9adefde1c3855cd
|
| 3 |
+
size 358
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"train_loss": 6.1072265625,
|
| 4 |
+
"train_runtime": 7028.2199,
|
| 5 |
+
"train_samples": 3478,
|
| 6 |
+
"train_samples_per_second": 7.423,
|
| 7 |
+
"train_steps_per_second": 0.03
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"global_step": 210,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 7.14,
|
| 12 |
+
"eval_loss": 3.668884754180908,
|
| 13 |
+
"eval_runtime": 59.5291,
|
| 14 |
+
"eval_samples_per_second": 27.667,
|
| 15 |
+
"eval_steps_per_second": 0.437,
|
| 16 |
+
"eval_wer": 1.0,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 14.29,
|
| 21 |
+
"eval_loss": 3.0279765129089355,
|
| 22 |
+
"eval_runtime": 59.2605,
|
| 23 |
+
"eval_samples_per_second": 27.793,
|
| 24 |
+
"eval_steps_per_second": 0.439,
|
| 25 |
+
"eval_wer": 0.9998978653865795,
|
| 26 |
+
"step": 200
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 15.0,
|
| 30 |
+
"step": 210,
|
| 31 |
+
"total_flos": 7.615693269162799e+18,
|
| 32 |
+
"train_loss": 6.1072265625,
|
| 33 |
+
"train_runtime": 7028.2199,
|
| 34 |
+
"train_samples_per_second": 7.423,
|
| 35 |
+
"train_steps_per_second": 0.03
|
| 36 |
+
}
|
| 37 |
+
],
|
| 38 |
+
"max_steps": 210,
|
| 39 |
+
"num_train_epochs": 15,
|
| 40 |
+
"total_flos": 7.615693269162799e+18,
|
| 41 |
+
"trial_name": null,
|
| 42 |
+
"trial_params": null
|
| 43 |
+
}
|