Training in progress, step 44000
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:b1d0ff64be79e66f752abeb529f6881925a24d38fb21e2a097a15230affe13aa
|
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 sha256:1aab0623d473dd36456233114e9614da0e3e8e50401489de0babadab6591e82e
|
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 sha256:86690451b88ca7ec7946c433493bd67a3de5a6959d2993b8a282b34dedadf9dd
|
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:dfe9cd4b1870cc08c52a01526a50912b784c0d634c7d848108e06294afd36be5
|
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 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -468,11 +468,33 @@
|
|
468 |
"eval_samples_per_second": 60.796,
|
469 |
"eval_steps_per_second": 0.951,
|
470 |
"step": 42000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
471 |
}
|
472 |
],
|
473 |
"max_steps": 85840,
|
474 |
"num_train_epochs": 10,
|
475 |
-
"total_flos": 6.
|
476 |
"trial_name": null,
|
477 |
"trial_params": null
|
478 |
}
|
|
|
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": 5.125815470643057,
|
5 |
+
"global_step": 44000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
468 |
"eval_samples_per_second": 60.796,
|
469 |
"eval_steps_per_second": 0.951,
|
470 |
"step": 42000
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 5.13,
|
474 |
+
"learning_rate": 0.0005130720557217835,
|
475 |
+
"loss": 1.0571,
|
476 |
+
"step": 44000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 5.13,
|
480 |
+
"eval_accuracy": null,
|
481 |
+
"eval_bertscore_f1": 0.9361940296387629,
|
482 |
+
"eval_bleu": 0.42251404411209087,
|
483 |
+
"eval_f1": null,
|
484 |
+
"eval_loss": 1.7361332178115845,
|
485 |
+
"eval_rouge1": 0.623944320741679,
|
486 |
+
"eval_rouge2": 0.41785433009247724,
|
487 |
+
"eval_rougeL": 0.5665420760123123,
|
488 |
+
"eval_rougeLsum": 0.5687571348191405,
|
489 |
+
"eval_runtime": 164.5399,
|
490 |
+
"eval_samples_per_second": 59.815,
|
491 |
+
"eval_steps_per_second": 0.936,
|
492 |
+
"step": 44000
|
493 |
}
|
494 |
],
|
495 |
"max_steps": 85840,
|
496 |
"num_train_epochs": 10,
|
497 |
+
"total_flos": 6.649203110355149e+16,
|
498 |
"trial_name": null,
|
499 |
"trial_params": null
|
500 |
}
|
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 sha256:1aab0623d473dd36456233114e9614da0e3e8e50401489de0babadab6591e82e
|
3 |
size 307910149
|