Training in progress, step 64000
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 839109
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:027f6abc6b8bc27d990af08026a6ad6b3296f97d13f5998a2a65b508aa812d29
|
3 |
size 839109
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242071641
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fbb0f493d2d6d8af0fbf7af6dcdd5002f9456febdf6cdb49f13de7755b489e9
|
3 |
size 242071641
|
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:fe4a9dd2db357b6cc8e728bd9c7780d94aaeba618ff5db15904e71fd73552176
|
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:be58087d50e4040c3e2ec78d4704cf0d7602fc8726059d52b3c64ffc0ad057da
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.7131295204162598,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-52000",
|
4 |
-
"epoch": 7.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -688,11 +688,33 @@
|
|
688 |
"eval_samples_per_second": 67.126,
|
689 |
"eval_steps_per_second": 1.05,
|
690 |
"step": 62000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
691 |
}
|
692 |
],
|
693 |
"max_steps": 85840,
|
694 |
"num_train_epochs": 10,
|
695 |
-
"total_flos": 6.
|
696 |
"trial_name": null,
|
697 |
"trial_params": null
|
698 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.7131295204162598,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-52000",
|
4 |
+
"epoch": 7.4557315936626285,
|
5 |
+
"global_step": 64000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
688 |
"eval_samples_per_second": 67.126,
|
689 |
"eval_steps_per_second": 1.05,
|
690 |
"step": 62000
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 7.46,
|
694 |
+
"learning_rate": 0.0002678177269828813,
|
695 |
+
"loss": 1.0755,
|
696 |
+
"step": 64000
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 7.46,
|
700 |
+
"eval_accuracy": null,
|
701 |
+
"eval_bertscore_f1": 0.9339887901089875,
|
702 |
+
"eval_bleu": 0.4076539996327793,
|
703 |
+
"eval_f1": null,
|
704 |
+
"eval_loss": 1.752874732017517,
|
705 |
+
"eval_rouge1": 0.6144795036298025,
|
706 |
+
"eval_rouge2": 0.4050923100648689,
|
707 |
+
"eval_rougeL": 0.5573353646470276,
|
708 |
+
"eval_rougeLsum": 0.5593645460867931,
|
709 |
+
"eval_runtime": 141.9841,
|
710 |
+
"eval_samples_per_second": 69.318,
|
711 |
+
"eval_steps_per_second": 1.085,
|
712 |
+
"step": 64000
|
713 |
}
|
714 |
],
|
715 |
"max_steps": 85840,
|
716 |
"num_train_epochs": 10,
|
717 |
+
"total_flos": 6.391807480086528e+16,
|
718 |
"trial_name": null,
|
719 |
"trial_params": null
|
720 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242071641
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fbb0f493d2d6d8af0fbf7af6dcdd5002f9456febdf6cdb49f13de7755b489e9
|
3 |
size 242071641
|