Training in progress, step 54000
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 sha256:0b488ce34771ef3fcea1f84e722e8f47605458e7f0ad282cd51d4d98668c6c8d
|
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 sha256:36b28ef0b817ea7d7bbb5a9b95bd9e4ee39413d48889ced7efce95b4e41363fa
|
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:cfa7f89f8cc912a448ceaeddf99e51ca0f292f3436c7ea8781e2790a62419d9f
|
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 sha256:9d2947289c2e0b804edc84d9006dd6cc9446a008db92d3236a5dcb9a0d596e1b
|
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": 6.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -578,11 +578,33 @@
|
|
578 |
"eval_samples_per_second": 69.625,
|
579 |
"eval_steps_per_second": 1.089,
|
580 |
"step": 52000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
581 |
}
|
582 |
],
|
583 |
"max_steps": 85840,
|
584 |
"num_train_epochs": 10,
|
585 |
-
"total_flos": 5.
|
586 |
"trial_name": null,
|
587 |
"trial_params": null
|
588 |
}
|
|
|
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": 6.290773532152842,
|
5 |
+
"global_step": 54000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
578 |
"eval_samples_per_second": 69.625,
|
579 |
"eval_steps_per_second": 1.089,
|
580 |
"step": 52000
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 6.29,
|
584 |
+
"learning_rate": 0.0003904448913523324,
|
585 |
+
"loss": 1.099,
|
586 |
+
"step": 54000
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 6.29,
|
590 |
+
"eval_accuracy": null,
|
591 |
+
"eval_bertscore_f1": 0.9344165326315463,
|
592 |
+
"eval_bleu": 0.4117161078695893,
|
593 |
+
"eval_f1": null,
|
594 |
+
"eval_loss": 1.7616441249847412,
|
595 |
+
"eval_rouge1": 0.6196071982260033,
|
596 |
+
"eval_rouge2": 0.41061524172454117,
|
597 |
+
"eval_rougeL": 0.5611350900753369,
|
598 |
+
"eval_rougeLsum": 0.5630504417819058,
|
599 |
+
"eval_runtime": 140.5199,
|
600 |
+
"eval_samples_per_second": 70.04,
|
601 |
+
"eval_steps_per_second": 1.096,
|
602 |
+
"step": 54000
|
603 |
}
|
604 |
],
|
605 |
"max_steps": 85840,
|
606 |
"num_train_epochs": 10,
|
607 |
+
"total_flos": 5.393002563796992e+16,
|
608 |
"trial_name": null,
|
609 |
"trial_params": null
|
610 |
}
|
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 sha256:36b28ef0b817ea7d7bbb5a9b95bd9e4ee39413d48889ced7efce95b4e41363fa
|
3 |
size 242071641
|