Training in progress, step 70000
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 sha256:4863ad0f4e0c09f1e8909d09892687a2e09f414f9cd1a6813c8d448c02e82f8c
|
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 sha256:2431b10f7045fc14c6eb0f669737dc9d954c34f68c4c2de94213851f18188e13
|
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 sha256:81f2c495a34c011b5456e526592b0203671d6e3631adc2ba8e1ad0716038e478
|
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 sha256:85dfcba34f09680e32437898336c10dc8b742264ee7085cf82e7d66a51be9f6d
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -754,11 +754,33 @@
|
|
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.
|
762 |
"trial_name": null,
|
763 |
"trial_params": null
|
764 |
}
|
|
|
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": 8.154706430568499,
|
5 |
+
"global_step": 70000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
754 |
"eval_samples_per_second": 69.321,
|
755 |
"eval_steps_per_second": 1.085,
|
756 |
"step": 68000
|
757 |
+
},
|
758 |
+
{
|
759 |
+
"epoch": 8.15,
|
760 |
+
"learning_rate": 0.0001942414283612106,
|
761 |
+
"loss": 1.053,
|
762 |
+
"step": 70000
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 8.15,
|
766 |
+
"eval_accuracy": null,
|
767 |
+
"eval_bertscore_f1": 0.9347367377463842,
|
768 |
+
"eval_bleu": 0.4099625767370798,
|
769 |
+
"eval_f1": null,
|
770 |
+
"eval_loss": 1.767859935760498,
|
771 |
+
"eval_rouge1": 0.6194533859109013,
|
772 |
+
"eval_rouge2": 0.4117428622305384,
|
773 |
+
"eval_rougeL": 0.5620848425359636,
|
774 |
+
"eval_rougeLsum": 0.5640752528686849,
|
775 |
+
"eval_runtime": 142.9599,
|
776 |
+
"eval_samples_per_second": 68.844,
|
777 |
+
"eval_steps_per_second": 1.077,
|
778 |
+
"step": 70000
|
779 |
}
|
780 |
],
|
781 |
"max_steps": 85840,
|
782 |
"num_train_epochs": 10,
|
783 |
+
"total_flos": 6.989213408251085e+16,
|
784 |
"trial_name": null,
|
785 |
"trial_params": null
|
786 |
}
|
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 sha256:2431b10f7045fc14c6eb0f669737dc9d954c34f68c4c2de94213851f18188e13
|
3 |
size 242071641
|