Training in progress, step 50000
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 1135685
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7f13b93c89ec168901e580f05867aa8adb01769c2617972a196313798e4182e
|
3 |
size 1135685
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 307910149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd8043109b4f4db22c6a1b67e6f518831b5d450f8470c2d5600f8de929e6fd5f
|
3 |
size 307910149
|
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:a36e9fd029a2a17d01d953bbe5298320c8d2b52748ab966f769554a706c56603
|
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 sha256:257f08b3c7ea6b7917dfcfe4ee59477480ad5f789e6c05f1e16bdb5501dec5b8
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.6879340410232544,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-28000",
|
4 |
-
"epoch": 5.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -534,11 +534,33 @@
|
|
534 |
"eval_samples_per_second": 61.004,
|
535 |
"eval_steps_per_second": 0.955,
|
536 |
"step": 48000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
537 |
}
|
538 |
],
|
539 |
"max_steps": 85840,
|
540 |
"num_train_epochs": 10,
|
541 |
-
"total_flos": 7.
|
542 |
"trial_name": null,
|
543 |
"trial_params": null
|
544 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.6879340410232544,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-28000",
|
4 |
+
"epoch": 5.824790307548929,
|
5 |
+
"global_step": 50000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
534 |
"eval_samples_per_second": 61.004,
|
535 |
"eval_steps_per_second": 0.955,
|
536 |
"step": 48000
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 5.82,
|
540 |
+
"learning_rate": 0.0004394957571001128,
|
541 |
+
"loss": 1.0452,
|
542 |
+
"step": 50000
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 5.82,
|
546 |
+
"eval_accuracy": null,
|
547 |
+
"eval_bertscore_f1": 0.9367801601858649,
|
548 |
+
"eval_bleu": 0.42680714988492996,
|
549 |
+
"eval_f1": null,
|
550 |
+
"eval_loss": 1.7337367534637451,
|
551 |
+
"eval_rouge1": 0.6314115131516205,
|
552 |
+
"eval_rouge2": 0.4278669646141474,
|
553 |
+
"eval_rougeL": 0.5750403719188825,
|
554 |
+
"eval_rougeLsum": 0.5770931885025077,
|
555 |
+
"eval_runtime": 161.292,
|
556 |
+
"eval_samples_per_second": 61.02,
|
557 |
+
"eval_steps_per_second": 0.955,
|
558 |
+
"step": 50000
|
559 |
}
|
560 |
],
|
561 |
"max_steps": 85840,
|
562 |
"num_train_epochs": 10,
|
563 |
+
"total_flos": 7.557485029020672e+16,
|
564 |
"trial_name": null,
|
565 |
"trial_params": null
|
566 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 307910149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd8043109b4f4db22c6a1b67e6f518831b5d450f8470c2d5600f8de929e6fd5f
|
3 |
size 307910149
|