End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.7422222222222222,
|
| 4 |
+
"eval_loss": 0.9125025868415833,
|
| 5 |
+
"eval_runtime": 3.3527,
|
| 6 |
+
"eval_samples_per_second": 67.111,
|
| 7 |
+
"eval_steps_per_second": 2.386,
|
| 8 |
+
"total_flos": 5.0884874272512e+16,
|
| 9 |
+
"train_loss": 1.0160289406776428,
|
| 10 |
+
"train_runtime": 55.9358,
|
| 11 |
+
"train_samples_per_second": 36.202,
|
| 12 |
+
"train_steps_per_second": 0.286
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.7422222222222222,
|
| 4 |
+
"eval_loss": 0.9125025868415833,
|
| 5 |
+
"eval_runtime": 3.3527,
|
| 6 |
+
"eval_samples_per_second": 67.111,
|
| 7 |
+
"eval_steps_per_second": 2.386
|
| 8 |
+
}
|
runs/Jun26_09-36-16_8d8dcdc5b963/events.out.tfevents.1656236418.8d8dcdc5b963.73.39
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55efe951028bafd1f18fc94d731cb0f3f78fc3f6e6c20a9d8fd2e5c6fbbe7a98
|
| 3 |
+
size 674
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 5.0884874272512e+16,
|
| 4 |
+
"train_loss": 1.0160289406776428,
|
| 5 |
+
"train_runtime": 55.9358,
|
| 6 |
+
"train_samples_per_second": 36.202,
|
| 7 |
+
"train_steps_per_second": 0.286
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 16,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.62,
|
| 12 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 13 |
+
"loss": 1.0681,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.7422222222222222,
|
| 19 |
+
"eval_loss": 0.9125025868415833,
|
| 20 |
+
"eval_runtime": 3.1968,
|
| 21 |
+
"eval_samples_per_second": 70.383,
|
| 22 |
+
"eval_steps_per_second": 2.503,
|
| 23 |
+
"step": 16
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"step": 16,
|
| 28 |
+
"total_flos": 5.0884874272512e+16,
|
| 29 |
+
"train_loss": 1.0160289406776428,
|
| 30 |
+
"train_runtime": 55.9358,
|
| 31 |
+
"train_samples_per_second": 36.202,
|
| 32 |
+
"train_steps_per_second": 0.286
|
| 33 |
+
}
|
| 34 |
+
],
|
| 35 |
+
"max_steps": 16,
|
| 36 |
+
"num_train_epochs": 1,
|
| 37 |
+
"total_flos": 5.0884874272512e+16,
|
| 38 |
+
"trial_name": null,
|
| 39 |
+
"trial_params": null
|
| 40 |
+
}
|