Training in progress, step 46000
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 sha256:8145237037b5109c78d1a5879e0cf8763fea748e20db6e1e3356f13ed2496aaf
|
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:d9f01996f68af324691688e6700648fd0411bc37adbbcd72a8ac176b1499aef7
|
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 sha256:0d19410c708bc31c995020055a1459e71a8a188db526cdf704166b8aae36b035
|
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 sha256:1e7f7dbcc6af1af2997ab49eaf245404b3ca605cb402cb0c5a0a5319ced2d65e
|
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,
|
@@ -490,11 +490,33 @@
|
|
490 |
"eval_samples_per_second": 59.815,
|
491 |
"eval_steps_per_second": 0.936,
|
492 |
"step": 44000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
493 |
}
|
494 |
],
|
495 |
"max_steps": 85840,
|
496 |
"num_train_epochs": 10,
|
497 |
-
"total_flos": 6.
|
498 |
"trial_name": null,
|
499 |
"trial_params": null
|
500 |
}
|
|
|
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": 5.358807082945014,
|
5 |
+
"global_step": 46000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
490 |
"eval_samples_per_second": 59.815,
|
491 |
"eval_steps_per_second": 0.936,
|
492 |
"step": 44000
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 5.36,
|
496 |
+
"learning_rate": 0.0004885466228478932,
|
497 |
+
"loss": 1.0369,
|
498 |
+
"step": 46000
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 5.36,
|
502 |
+
"eval_accuracy": null,
|
503 |
+
"eval_bertscore_f1": 0.9371138367619463,
|
504 |
+
"eval_bleu": 0.4294131133171002,
|
505 |
+
"eval_f1": null,
|
506 |
+
"eval_loss": 1.7538217306137085,
|
507 |
+
"eval_rouge1": 0.6345686935597785,
|
508 |
+
"eval_rouge2": 0.428714304925809,
|
509 |
+
"eval_rougeL": 0.5771767322931747,
|
510 |
+
"eval_rougeLsum": 0.5792294306188093,
|
511 |
+
"eval_runtime": 161.6565,
|
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": 6.952690271966208e+16,
|
520 |
"trial_name": null,
|
521 |
"trial_params": null
|
522 |
}
|
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:d9f01996f68af324691688e6700648fd0411bc37adbbcd72a8ac176b1499aef7
|
3 |
size 307910149
|