Training in progress, step 42000
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:c2a0fe598eece835bdfc830390e32a726c946f159920e4d6ab815379915272a9
|
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:ded81a002e988f86d8b0f7c4a0d00bb6d3c0dafcdaf2f8ac528ebeea35296986
|
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 sha256:153fa04f934a1013ab76c6fa68c7f1580aa638beb919287cafb51763657df2b6
|
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:cf6d9f4c1ec89d63c98b08543c58660f5818ed92d6babce2999c9131f7d6c72b
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-
|
4 |
-
"epoch": 4.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -446,11 +446,33 @@
|
|
446 |
"eval_samples_per_second": 80.383,
|
447 |
"eval_steps_per_second": 1.258,
|
448 |
"step": 40000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
449 |
}
|
450 |
],
|
451 |
"max_steps": 85840,
|
452 |
"num_train_epochs": 10,
|
453 |
-
"total_flos":
|
454 |
"trial_name": null,
|
455 |
"trial_params": null
|
456 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.718157410621643,
|
3 |
+
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-42000",
|
4 |
+
"epoch": 4.8928238583410995,
|
5 |
+
"global_step": 42000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
446 |
"eval_samples_per_second": 80.383,
|
447 |
"eval_steps_per_second": 1.258,
|
448 |
"step": 40000
|
449 |
+
},
|
450 |
+
{
|
451 |
+
"epoch": 4.89,
|
452 |
+
"learning_rate": 0.0005375974885956737,
|
453 |
+
"loss": 1.1674,
|
454 |
+
"step": 42000
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 4.89,
|
458 |
+
"eval_accuracy": null,
|
459 |
+
"eval_bertscore_f1": 0.9342498932154143,
|
460 |
+
"eval_bleu": 0.4057773557512404,
|
461 |
+
"eval_f1": null,
|
462 |
+
"eval_loss": 1.718157410621643,
|
463 |
+
"eval_rouge1": 0.6173759208611083,
|
464 |
+
"eval_rouge2": 0.4116919174551955,
|
465 |
+
"eval_rougeL": 0.5609282546294716,
|
466 |
+
"eval_rougeLsum": 0.5629408116210994,
|
467 |
+
"eval_runtime": 126.5334,
|
468 |
+
"eval_samples_per_second": 77.782,
|
469 |
+
"eval_steps_per_second": 1.217,
|
470 |
+
"step": 42000
|
471 |
}
|
472 |
],
|
473 |
"max_steps": 85840,
|
474 |
"num_train_epochs": 10,
|
475 |
+
"total_flos": 4.194163310818099e+16,
|
476 |
"trial_name": null,
|
477 |
"trial_params": null
|
478 |
}
|
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:ded81a002e988f86d8b0f7c4a0d00bb6d3c0dafcdaf2f8ac528ebeea35296986
|
3 |
size 242071641
|