End of training
Browse files- all_results.json +13 -0
- eval_results.json +9 -0
- runs/Mar18_16-33-00_terra/events.out.tfevents.1679158648.terra.1789432.2 +3 -0
- train_results.json +7 -0
- trainer_state.json +52 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.679447650909424,
|
| 4 |
+
"eval_runtime": 444.9769,
|
| 5 |
+
"eval_samples": 1000,
|
| 6 |
+
"eval_samples_per_second": 2.247,
|
| 7 |
+
"eval_steps_per_second": 0.142,
|
| 8 |
+
"eval_wer": 115.42439147433473,
|
| 9 |
+
"train_loss": 3.2194599151611327,
|
| 10 |
+
"train_runtime": 862.9787,
|
| 11 |
+
"train_samples_per_second": 1.112,
|
| 12 |
+
"train_steps_per_second": 0.017
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.679447650909424,
|
| 4 |
+
"eval_runtime": 444.9769,
|
| 5 |
+
"eval_samples": 1000,
|
| 6 |
+
"eval_samples_per_second": 2.247,
|
| 7 |
+
"eval_steps_per_second": 0.142,
|
| 8 |
+
"eval_wer": 115.42439147433473
|
| 9 |
+
}
|
runs/Mar18_16-33-00_terra/events.out.tfevents.1679158648.terra.1789432.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50b17cdefde0ab1db5bab12c1e11be26cf1641eebac36680cb2b60ac02957dad
|
| 3 |
+
size 400
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 3.2194599151611327,
|
| 4 |
+
"train_runtime": 862.9787,
|
| 5 |
+
"train_samples_per_second": 1.112,
|
| 6 |
+
"train_steps_per_second": 0.017
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 115.42439147433473,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-15",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 15,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.33,
|
| 12 |
+
"learning_rate": 6e-06,
|
| 13 |
+
"loss": 3.675,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.67,
|
| 18 |
+
"learning_rate": 7e-06,
|
| 19 |
+
"loss": 3.2974,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.0,
|
| 24 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 25 |
+
"loss": 2.686,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.0,
|
| 30 |
+
"eval_loss": 2.679447650909424,
|
| 31 |
+
"eval_runtime": 455.8706,
|
| 32 |
+
"eval_samples_per_second": 2.194,
|
| 33 |
+
"eval_steps_per_second": 0.138,
|
| 34 |
+
"eval_wer": 115.42439147433473,
|
| 35 |
+
"step": 15
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.0,
|
| 39 |
+
"step": 15,
|
| 40 |
+
"total_flos": 2.36341297152e+16,
|
| 41 |
+
"train_loss": 3.2194599151611327,
|
| 42 |
+
"train_runtime": 862.9787,
|
| 43 |
+
"train_samples_per_second": 1.112,
|
| 44 |
+
"train_steps_per_second": 0.017
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"max_steps": 15,
|
| 48 |
+
"num_train_epochs": 9223372036854775807,
|
| 49 |
+
"total_flos": 2.36341297152e+16,
|
| 50 |
+
"trial_name": null,
|
| 51 |
+
"trial_params": null
|
| 52 |
+
}
|