Training in progress, step 58000
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 sha256:21a9fdfe33aace60a7130d9cfd543c08affbbbf333d0aeb43eb22d0281c0b5c8
|
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 sha256:369cee498bed779b6cf6cb205a3fc9ba757a7286c36a91eebc554711e5dc1b27
|
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:f98121e4e538d45fa41f11d3c6832e4fd62b5f5e345c1960351801e577a63576
|
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 sha256:7514021e04110a02e65d512afd0fc5e309873ca18823657b4dfb91c5272acc79
|
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,
|
@@ -622,11 +622,33 @@
|
|
622 |
"eval_samples_per_second": 68.281,
|
623 |
"eval_steps_per_second": 1.068,
|
624 |
"step": 56000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
625 |
}
|
626 |
],
|
627 |
"max_steps": 85840,
|
628 |
"num_train_epochs": 10,
|
629 |
-
"total_flos": 5.
|
630 |
"trial_name": null,
|
631 |
"trial_params": null
|
632 |
}
|
|
|
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": 6.756756756756757,
|
5 |
+
"global_step": 58000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
622 |
"eval_samples_per_second": 68.281,
|
623 |
"eval_steps_per_second": 1.068,
|
624 |
"step": 56000
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 6.76,
|
628 |
+
"learning_rate": 0.0003413940256045519,
|
629 |
+
"loss": 1.1021,
|
630 |
+
"step": 58000
|
631 |
+
},
|
632 |
+
{
|
633 |
+
"epoch": 6.76,
|
634 |
+
"eval_accuracy": null,
|
635 |
+
"eval_bertscore_f1": 0.9347718441130257,
|
636 |
+
"eval_bleu": 0.4145601483938376,
|
637 |
+
"eval_f1": null,
|
638 |
+
"eval_loss": 1.7501702308654785,
|
639 |
+
"eval_rouge1": 0.6220518407228575,
|
640 |
+
"eval_rouge2": 0.41616106256237295,
|
641 |
+
"eval_rougeL": 0.5653493806262004,
|
642 |
+
"eval_rougeLsum": 0.5674926448995362,
|
643 |
+
"eval_runtime": 143.3032,
|
644 |
+
"eval_samples_per_second": 68.68,
|
645 |
+
"eval_steps_per_second": 1.075,
|
646 |
+
"step": 58000
|
647 |
}
|
648 |
],
|
649 |
"max_steps": 85840,
|
650 |
"num_train_epochs": 10,
|
651 |
+
"total_flos": 5.792203357873766e+16,
|
652 |
"trial_name": null,
|
653 |
"trial_params": null
|
654 |
}
|
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 sha256:369cee498bed779b6cf6cb205a3fc9ba757a7286c36a91eebc554711e5dc1b27
|
3 |
size 242071641
|