Training in progress, step 68000
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 839365
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15b1e74906e1203b005a6b9bca50dcf589c8b30846aa79dfec8c137eff613d9f
|
3 |
size 839365
|
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:ad824fce4bfcd606ebbf2ed65caf347577d0868c7d73632c081faf9703ce969d
|
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 sha256:523a3ffeeab3e366f445bf190b238928854b06c29003bb23dbb5942608806919
|
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:e60a1f34fa32a8230677171306ced8f04fe6a2d25580582a3cb989139e4be411
|
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,
|
@@ -732,11 +732,33 @@
|
|
732 |
"eval_samples_per_second": 69.221,
|
733 |
"eval_steps_per_second": 1.083,
|
734 |
"step": 66000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
735 |
}
|
736 |
],
|
737 |
"max_steps": 85840,
|
738 |
"num_train_epochs": 10,
|
739 |
-
"total_flos": 6.
|
740 |
"trial_name": null,
|
741 |
"trial_params": null
|
742 |
}
|
|
|
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": 7.921714818266542,
|
5 |
+
"global_step": 68000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
732 |
"eval_samples_per_second": 69.221,
|
733 |
"eval_steps_per_second": 1.083,
|
734 |
"step": 66000
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 7.92,
|
738 |
+
"learning_rate": 0.0002187668612351008,
|
739 |
+
"loss": 1.0751,
|
740 |
+
"step": 68000
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 7.92,
|
744 |
+
"eval_accuracy": null,
|
745 |
+
"eval_bertscore_f1": 0.9340490757014009,
|
746 |
+
"eval_bleu": 0.40620204839955465,
|
747 |
+
"eval_f1": null,
|
748 |
+
"eval_loss": 1.7554686069488525,
|
749 |
+
"eval_rouge1": 0.6164376145373307,
|
750 |
+
"eval_rouge2": 0.40876980632820026,
|
751 |
+
"eval_rougeL": 0.5595624559170196,
|
752 |
+
"eval_rougeLsum": 0.5614936851444701,
|
753 |
+
"eval_runtime": 141.9779,
|
754 |
+
"eval_samples_per_second": 69.321,
|
755 |
+
"eval_steps_per_second": 1.085,
|
756 |
+
"step": 68000
|
757 |
}
|
758 |
],
|
759 |
"max_steps": 85840,
|
760 |
"num_train_epochs": 10,
|
761 |
+
"total_flos": 6.790982897575526e+16,
|
762 |
"trial_name": null,
|
763 |
"trial_params": null
|
764 |
}
|
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:ad824fce4bfcd606ebbf2ed65caf347577d0868c7d73632c081faf9703ce969d
|
3 |
size 242071641
|