Commit
•
48bdc3b
1
Parent(s):
921f84f
End of training
Browse files- all_results.json +28 -0
- eval_results.json +13 -0
- generated_predictions.txt +0 -0
- predict_results.json +12 -0
- train_results.json +8 -0
- trainer_state.json +25 -0
all_results.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.01,
|
| 3 |
+
"eval_gen_len": 42.787333333333336,
|
| 4 |
+
"eval_loss": 2.5066428184509277,
|
| 5 |
+
"eval_rouge1": 23.6554,
|
| 6 |
+
"eval_rouge2": 7.5413,
|
| 7 |
+
"eval_rougeL": 17.4259,
|
| 8 |
+
"eval_rougeLsum": 20.6655,
|
| 9 |
+
"eval_runtime": 186.4899,
|
| 10 |
+
"eval_samples": 1500,
|
| 11 |
+
"eval_samples_per_second": 8.043,
|
| 12 |
+
"eval_steps_per_second": 0.804,
|
| 13 |
+
"predict_gen_len": 42.516,
|
| 14 |
+
"predict_loss": 2.4928014278411865,
|
| 15 |
+
"predict_rouge1": 24.233,
|
| 16 |
+
"predict_rouge2": 7.7785,
|
| 17 |
+
"predict_rougeL": 17.6919,
|
| 18 |
+
"predict_rougeLsum": 21.0741,
|
| 19 |
+
"predict_runtime": 186.2282,
|
| 20 |
+
"predict_samples": 1500,
|
| 21 |
+
"predict_samples_per_second": 8.055,
|
| 22 |
+
"predict_steps_per_second": 0.805,
|
| 23 |
+
"train_loss": 2.8345144271850584,
|
| 24 |
+
"train_runtime": 8.6661,
|
| 25 |
+
"train_samples": 7000,
|
| 26 |
+
"train_samples_per_second": 11.539,
|
| 27 |
+
"train_steps_per_second": 1.154
|
| 28 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.01,
|
| 3 |
+
"eval_gen_len": 42.787333333333336,
|
| 4 |
+
"eval_loss": 2.5066428184509277,
|
| 5 |
+
"eval_rouge1": 23.6554,
|
| 6 |
+
"eval_rouge2": 7.5413,
|
| 7 |
+
"eval_rougeL": 17.4259,
|
| 8 |
+
"eval_rougeLsum": 20.6655,
|
| 9 |
+
"eval_runtime": 186.4899,
|
| 10 |
+
"eval_samples": 1500,
|
| 11 |
+
"eval_samples_per_second": 8.043,
|
| 12 |
+
"eval_steps_per_second": 0.804
|
| 13 |
+
}
|
generated_predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
predict_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_gen_len": 42.516,
|
| 3 |
+
"predict_loss": 2.4928014278411865,
|
| 4 |
+
"predict_rouge1": 24.233,
|
| 5 |
+
"predict_rouge2": 7.7785,
|
| 6 |
+
"predict_rougeL": 17.6919,
|
| 7 |
+
"predict_rougeLsum": 21.0741,
|
| 8 |
+
"predict_runtime": 186.2282,
|
| 9 |
+
"predict_samples": 1500,
|
| 10 |
+
"predict_samples_per_second": 8.055,
|
| 11 |
+
"predict_steps_per_second": 0.805
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.01,
|
| 3 |
+
"train_loss": 2.8345144271850584,
|
| 4 |
+
"train_runtime": 8.6661,
|
| 5 |
+
"train_samples": 7000,
|
| 6 |
+
"train_samples_per_second": 11.539,
|
| 7 |
+
"train_steps_per_second": 1.154
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.014285714285714285,
|
| 5 |
+
"global_step": 10,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"step": 10,
|
| 13 |
+
"total_flos": 52873081651200.0,
|
| 14 |
+
"train_loss": 2.8345144271850584,
|
| 15 |
+
"train_runtime": 8.6661,
|
| 16 |
+
"train_samples_per_second": 11.539,
|
| 17 |
+
"train_steps_per_second": 1.154
|
| 18 |
+
}
|
| 19 |
+
],
|
| 20 |
+
"max_steps": 10,
|
| 21 |
+
"num_train_epochs": 1,
|
| 22 |
+
"total_flos": 52873081651200.0,
|
| 23 |
+
"trial_name": null,
|
| 24 |
+
"trial_params": null
|
| 25 |
+
}
|