End of training
Browse files- all_results.json +17 -0
- eval_results.json +12 -0
- runs/Dec20_16-33-48_pod-pasha/events.out.tfevents.1671554414.pod-pasha.537084.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +37 -0
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.13,
|
| 3 |
+
"eval_accuracy": 0.9093539054966249,
|
| 4 |
+
"eval_f1": 0.8845947396672033,
|
| 5 |
+
"eval_loss": 0.6478922367095947,
|
| 6 |
+
"eval_precision": 0.8787771062922147,
|
| 7 |
+
"eval_recall": 0.8904899135446686,
|
| 8 |
+
"eval_runtime": 14.0235,
|
| 9 |
+
"eval_samples": 189,
|
| 10 |
+
"eval_samples_per_second": 13.477,
|
| 11 |
+
"eval_steps_per_second": 0.856,
|
| 12 |
+
"train_loss": 1.3186872863769532,
|
| 13 |
+
"train_runtime": 168.7443,
|
| 14 |
+
"train_samples": 752,
|
| 15 |
+
"train_samples_per_second": 9.482,
|
| 16 |
+
"train_steps_per_second": 0.593
|
| 17 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.13,
|
| 3 |
+
"eval_accuracy": 0.9093539054966249,
|
| 4 |
+
"eval_f1": 0.8845947396672033,
|
| 5 |
+
"eval_loss": 0.6478922367095947,
|
| 6 |
+
"eval_precision": 0.8787771062922147,
|
| 7 |
+
"eval_recall": 0.8904899135446686,
|
| 8 |
+
"eval_runtime": 14.0235,
|
| 9 |
+
"eval_samples": 189,
|
| 10 |
+
"eval_samples_per_second": 13.477,
|
| 11 |
+
"eval_steps_per_second": 0.856
|
| 12 |
+
}
|
runs/Dec20_16-33-48_pod-pasha/events.out.tfevents.1671554414.pod-pasha.537084.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c264fde4efb371f2bf6e2fa707a7a4d72607508245a8475bae839d45a1c03369
|
| 3 |
+
size 503
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.13,
|
| 3 |
+
"train_loss": 1.3186872863769532,
|
| 4 |
+
"train_runtime": 168.7443,
|
| 5 |
+
"train_samples": 752,
|
| 6 |
+
"train_samples_per_second": 9.482,
|
| 7 |
+
"train_steps_per_second": 0.593
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.127659574468085,
|
| 5 |
+
"global_step": 100,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 2.13,
|
| 12 |
+
"eval_accuracy": 0.9093539054966249,
|
| 13 |
+
"eval_f1": 0.8845947396672033,
|
| 14 |
+
"eval_loss": 0.6478922367095947,
|
| 15 |
+
"eval_precision": 0.8787771062922147,
|
| 16 |
+
"eval_recall": 0.8904899135446686,
|
| 17 |
+
"eval_runtime": 13.9513,
|
| 18 |
+
"eval_samples_per_second": 13.547,
|
| 19 |
+
"eval_steps_per_second": 0.86,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 2.13,
|
| 24 |
+
"step": 100,
|
| 25 |
+
"total_flos": 424705445068800.0,
|
| 26 |
+
"train_loss": 1.3186872863769532,
|
| 27 |
+
"train_runtime": 168.7443,
|
| 28 |
+
"train_samples_per_second": 9.482,
|
| 29 |
+
"train_steps_per_second": 0.593
|
| 30 |
+
}
|
| 31 |
+
],
|
| 32 |
+
"max_steps": 100,
|
| 33 |
+
"num_train_epochs": 3,
|
| 34 |
+
"total_flos": 424705445068800.0,
|
| 35 |
+
"trial_name": null,
|
| 36 |
+
"trial_params": null
|
| 37 |
+
}
|