Commit
•
e7eb84f
1
Parent(s):
dbac49a
End of training
Browse files- all_results.json +12 -6
- eval_results.json +7 -6
- train_results.json +8 -0
- trainer_state.json +46 -0
all_results.json
CHANGED
|
@@ -1,9 +1,15 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
|
|
|
| 5 |
"eval_samples": 100,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"perplexity":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.08526422764227642,
|
| 4 |
+
"eval_loss": 0.205623060464859,
|
| 5 |
+
"eval_runtime": 2.1832,
|
| 6 |
"eval_samples": 100,
|
| 7 |
+
"eval_samples_per_second": 45.804,
|
| 8 |
+
"eval_steps_per_second": 1.832,
|
| 9 |
+
"perplexity": 1.2282901256155525,
|
| 10 |
+
"train_loss": 1.9150060657411814,
|
| 11 |
+
"train_runtime": 30.0037,
|
| 12 |
+
"train_samples": 1000,
|
| 13 |
+
"train_samples_per_second": 33.329,
|
| 14 |
+
"train_steps_per_second": 1.067
|
| 15 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
|
|
|
| 5 |
"eval_samples": 100,
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"perplexity":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.08526422764227642,
|
| 4 |
+
"eval_loss": 0.205623060464859,
|
| 5 |
+
"eval_runtime": 2.1832,
|
| 6 |
"eval_samples": 100,
|
| 7 |
+
"eval_samples_per_second": 45.804,
|
| 8 |
+
"eval_steps_per_second": 1.832,
|
| 9 |
+
"perplexity": 1.2282901256155525
|
| 10 |
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.9150060657411814,
|
| 4 |
+
"train_runtime": 30.0037,
|
| 5 |
+
"train_samples": 1000,
|
| 6 |
+
"train_samples_per_second": 33.329,
|
| 7 |
+
"train_steps_per_second": 1.067
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 32,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 5e-05,
|
| 13 |
+
"loss": 13.8997,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.78,
|
| 18 |
+
"learning_rate": 1.5625e-05,
|
| 19 |
+
"loss": 1.9481,
|
| 20 |
+
"step": 25
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.78,
|
| 24 |
+
"eval_accuracy": 0.08502032520325203,
|
| 25 |
+
"eval_loss": 0.215184286236763,
|
| 26 |
+
"eval_runtime": 1.9024,
|
| 27 |
+
"eval_samples_per_second": 52.566,
|
| 28 |
+
"eval_steps_per_second": 2.103,
|
| 29 |
+
"step": 25
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.0,
|
| 33 |
+
"step": 32,
|
| 34 |
+
"total_flos": 946476810240000.0,
|
| 35 |
+
"train_loss": 1.9150060657411814,
|
| 36 |
+
"train_runtime": 30.0037,
|
| 37 |
+
"train_samples_per_second": 33.329,
|
| 38 |
+
"train_steps_per_second": 1.067
|
| 39 |
+
}
|
| 40 |
+
],
|
| 41 |
+
"max_steps": 32,
|
| 42 |
+
"num_train_epochs": 1,
|
| 43 |
+
"total_flos": 946476810240000.0,
|
| 44 |
+
"trial_name": null,
|
| 45 |
+
"trial_params": null
|
| 46 |
+
}
|