Training in progress, step 48000
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1135685
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19495f29b8b6391126862396073e55ac97780140fe143b53b5642eef2b98c172
|
3 |
size 1135685
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 307910149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1071cc6351bd8ef0f1a7e18cfd72334a4e9f844291b3a7c9eefac96ecaade01
|
3 |
size 307910149
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50d326174c95407f971ae90220382f4be662d03843ac04078e3118cb26948332
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc33e2c8cf4a5789b202db8aa3fd1e34917bf5bb69c22ecf597bcc4377ce99dc
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.6879340410232544,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-28000",
|
4 |
-
"epoch": 5.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -512,11 +512,33 @@
|
|
512 |
"eval_samples_per_second": 60.882,
|
513 |
"eval_steps_per_second": 0.953,
|
514 |
"step": 46000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
515 |
}
|
516 |
],
|
517 |
"max_steps": 85840,
|
518 |
"num_train_epochs": 10,
|
519 |
-
"total_flos":
|
520 |
"trial_name": null,
|
521 |
"trial_params": null
|
522 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.6879340410232544,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-28000",
|
4 |
+
"epoch": 5.591798695246971,
|
5 |
+
"global_step": 48000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
512 |
"eval_samples_per_second": 60.882,
|
513 |
"eval_steps_per_second": 0.953,
|
514 |
"step": 46000
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 5.59,
|
518 |
+
"learning_rate": 0.00046402118997400306,
|
519 |
+
"loss": 1.0474,
|
520 |
+
"step": 48000
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 5.59,
|
524 |
+
"eval_accuracy": null,
|
525 |
+
"eval_bertscore_f1": 0.9365723418816394,
|
526 |
+
"eval_bleu": 0.4240621501677298,
|
527 |
+
"eval_f1": null,
|
528 |
+
"eval_loss": 1.7373207807540894,
|
529 |
+
"eval_rouge1": 0.6282821742967474,
|
530 |
+
"eval_rouge2": 0.4224469238177527,
|
531 |
+
"eval_rougeL": 0.5726173107138908,
|
532 |
+
"eval_rougeLsum": 0.5746977682346076,
|
533 |
+
"eval_runtime": 161.3334,
|
534 |
+
"eval_samples_per_second": 61.004,
|
535 |
+
"eval_steps_per_second": 0.955,
|
536 |
+
"step": 48000
|
537 |
}
|
538 |
],
|
539 |
"max_steps": 85840,
|
540 |
"num_train_epochs": 10,
|
541 |
+
"total_flos": 7.254987734347162e+16,
|
542 |
"trial_name": null,
|
543 |
"trial_params": null
|
544 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 307910149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1071cc6351bd8ef0f1a7e18cfd72334a4e9f844291b3a7c9eefac96ecaade01
|
3 |
size 307910149
|