Commit
•
c37baee
1
Parent(s):
40410c5
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +70 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 2.7618001302083335,
|
| 4 |
+
"train_runtime": 2178.1486,
|
| 5 |
+
"train_samples": 156,
|
| 6 |
+
"train_samples_per_second": 0.072,
|
| 7 |
+
"train_steps_per_second": 0.001
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 2.7618001302083335,
|
| 4 |
+
"train_runtime": 2178.1486,
|
| 5 |
+
"train_samples": 156,
|
| 6 |
+
"train_samples_per_second": 0.072,
|
| 7 |
+
"train_steps_per_second": 0.001
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 3,
|
| 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": 0,
|
| 13 |
+
"loss": 2.6917,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.33,
|
| 18 |
+
"eval_accuracy": 0.05304531642224865,
|
| 19 |
+
"eval_loss": 2.66796875,
|
| 20 |
+
"eval_runtime": 1.8653,
|
| 21 |
+
"eval_samples_per_second": 15.547,
|
| 22 |
+
"eval_steps_per_second": 0.536,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.67,
|
| 27 |
+
"learning_rate": 0,
|
| 28 |
+
"loss": 2.8435,
|
| 29 |
+
"step": 2
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.67,
|
| 33 |
+
"eval_accuracy": 0.05304531642224865,
|
| 34 |
+
"eval_loss": 2.66796875,
|
| 35 |
+
"eval_runtime": 2.1123,
|
| 36 |
+
"eval_samples_per_second": 13.729,
|
| 37 |
+
"eval_steps_per_second": 0.473,
|
| 38 |
+
"step": 2
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0,
|
| 42 |
+
"learning_rate": 0.0,
|
| 43 |
+
"loss": 2.7502,
|
| 44 |
+
"step": 3
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_accuracy": 0.055489496630994846,
|
| 49 |
+
"eval_loss": 2.6171875,
|
| 50 |
+
"eval_runtime": 1.0076,
|
| 51 |
+
"eval_samples_per_second": 28.782,
|
| 52 |
+
"eval_steps_per_second": 0.992,
|
| 53 |
+
"step": 3
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.0,
|
| 57 |
+
"step": 3,
|
| 58 |
+
"total_flos": 303365357568.0,
|
| 59 |
+
"train_loss": 2.7618001302083335,
|
| 60 |
+
"train_runtime": 2178.1486,
|
| 61 |
+
"train_samples_per_second": 0.072,
|
| 62 |
+
"train_steps_per_second": 0.001
|
| 63 |
+
}
|
| 64 |
+
],
|
| 65 |
+
"max_steps": 3,
|
| 66 |
+
"num_train_epochs": 1,
|
| 67 |
+
"total_flos": 303365357568.0,
|
| 68 |
+
"trial_name": null,
|
| 69 |
+
"trial_params": null
|
| 70 |
+
}
|