End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.9822222222222222,
|
| 4 |
+
"eval_loss": 0.19010965526103973,
|
| 5 |
+
"eval_runtime": 3.4014,
|
| 6 |
+
"eval_samples_per_second": 66.149,
|
| 7 |
+
"eval_steps_per_second": 2.352,
|
| 8 |
+
"total_flos": 5.03347841321472e+16,
|
| 9 |
+
"train_loss": 0.6244367808103561,
|
| 10 |
+
"train_runtime": 54.3895,
|
| 11 |
+
"train_samples_per_second": 37.231,
|
| 12 |
+
"train_steps_per_second": 0.294
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.9822222222222222,
|
| 4 |
+
"eval_loss": 0.19010965526103973,
|
| 5 |
+
"eval_runtime": 3.4014,
|
| 6 |
+
"eval_samples_per_second": 66.149,
|
| 7 |
+
"eval_steps_per_second": 2.352
|
| 8 |
+
}
|
runs/Jun26_09-46-25_8d8dcdc5b963/events.out.tfevents.1656237020.8d8dcdc5b963.73.45
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:652467fe16ab735154f71671af074e445efcaf4f8db8201432b38e7460d82a2d
|
| 3 |
+
size 674
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 5.03347841321472e+16,
|
| 4 |
+
"train_loss": 0.6244367808103561,
|
| 5 |
+
"train_runtime": 54.3895,
|
| 6 |
+
"train_samples_per_second": 37.231,
|
| 7 |
+
"train_steps_per_second": 0.294
|
| 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": 0.8198,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.9822222222222222,
|
| 19 |
+
"eval_loss": 0.19010965526103973,
|
| 20 |
+
"eval_runtime": 3.2652,
|
| 21 |
+
"eval_samples_per_second": 68.909,
|
| 22 |
+
"eval_steps_per_second": 2.45,
|
| 23 |
+
"step": 16
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"step": 16,
|
| 28 |
+
"total_flos": 5.03347841321472e+16,
|
| 29 |
+
"train_loss": 0.6244367808103561,
|
| 30 |
+
"train_runtime": 54.3895,
|
| 31 |
+
"train_samples_per_second": 37.231,
|
| 32 |
+
"train_steps_per_second": 0.294
|
| 33 |
+
}
|
| 34 |
+
],
|
| 35 |
+
"max_steps": 16,
|
| 36 |
+
"num_train_epochs": 1,
|
| 37 |
+
"total_flos": 5.03347841321472e+16,
|
| 38 |
+
"trial_name": null,
|
| 39 |
+
"trial_params": null
|
| 40 |
+
}
|