Commit
•
a914641
1
Parent(s):
8ec9bf1
End of training
Browse files- all_results.json +11 -0
- eval_nbest_predictions.json +2 -2
- eval_predictions.json +0 -0
- eval_results.json +6 -0
- runs/Oct04_20-01-42_g3010/events.out.tfevents.1664939451.g3010.91199.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +37 -0
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 33.33,
|
| 3 |
+
"eval_exact_match": 3.6140018921475874,
|
| 4 |
+
"eval_f1": 12.691344244805641,
|
| 5 |
+
"eval_samples": 10793,
|
| 6 |
+
"train_loss": 2.1091724014282227,
|
| 7 |
+
"train_runtime": 92.0933,
|
| 8 |
+
"train_samples": 64,
|
| 9 |
+
"train_samples_per_second": 26.061,
|
| 10 |
+
"train_steps_per_second": 2.172
|
| 11 |
+
}
|
eval_nbest_predictions.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99de290c2eef100d365624d4ccdbede6124a0225081ccf9e535556c2bd9563e7
|
| 3 |
+
size 52918557
|
eval_predictions.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 33.33,
|
| 3 |
+
"eval_exact_match": 3.6140018921475874,
|
| 4 |
+
"eval_f1": 12.691344244805641,
|
| 5 |
+
"eval_samples": 10793
|
| 6 |
+
}
|
runs/Oct04_20-01-42_g3010/events.out.tfevents.1664939451.g3010.91199.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:115ff278a5a7f02da9a2c30b8ca47ac38571a3095bde8c032e0af6e785079d54
|
| 3 |
+
size 191
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 33.33,
|
| 3 |
+
"train_loss": 2.1091724014282227,
|
| 4 |
+
"train_runtime": 92.0933,
|
| 5 |
+
"train_samples": 64,
|
| 6 |
+
"train_samples_per_second": 26.061,
|
| 7 |
+
"train_steps_per_second": 2.172
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 33.333333333333336,
|
| 5 |
+
"global_step": 200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 16.67,
|
| 12 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 13 |
+
"loss": 3.8103,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 33.33,
|
| 18 |
+
"learning_rate": 0.0,
|
| 19 |
+
"loss": 0.4081,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 33.33,
|
| 24 |
+
"step": 200,
|
| 25 |
+
"total_flos": 346463168384640.0,
|
| 26 |
+
"train_loss": 2.1091724014282227,
|
| 27 |
+
"train_runtime": 92.0933,
|
| 28 |
+
"train_samples_per_second": 26.061,
|
| 29 |
+
"train_steps_per_second": 2.172
|
| 30 |
+
}
|
| 31 |
+
],
|
| 32 |
+
"max_steps": 200,
|
| 33 |
+
"num_train_epochs": 34,
|
| 34 |
+
"total_flos": 346463168384640.0,
|
| 35 |
+
"trial_name": null,
|
| 36 |
+
"trial_params": null
|
| 37 |
+
}
|