Training in progress, step 38000
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:b94a27445fb507a46d388e538e08e23b176277f9ace7b3b7c13ca71d00bf9b7e
|
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:a0e49b0eab33b9539d5954a9a379dcb893c591083001ba531e4332b2580c9ed9
|
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 sha256:77dae9ea08add14bb0142a4d5fc8c0f93707db1b293b0745f4336805b89fc61b
|
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:ffeb963729db1b612e93f14e73acb438b741837a1b73c63cbf77406a43c96611
|
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": 4.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -402,11 +402,33 @@
|
|
402 |
"eval_samples_per_second": 60.896,
|
403 |
"eval_steps_per_second": 0.953,
|
404 |
"step": 36000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
405 |
}
|
406 |
],
|
407 |
"max_steps": 85840,
|
408 |
"num_train_epochs": 10,
|
409 |
-
"total_flos": 5.
|
410 |
"trial_name": null,
|
411 |
"trial_params": null
|
412 |
}
|
|
|
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": 4.426840633737186,
|
5 |
+
"global_step": 38000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
402 |
"eval_samples_per_second": 60.896,
|
403 |
"eval_steps_per_second": 0.953,
|
404 |
"step": 36000
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 4.43,
|
408 |
+
"learning_rate": 0.0005866483543434542,
|
409 |
+
"loss": 1.0775,
|
410 |
+
"step": 38000
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 4.43,
|
414 |
+
"eval_accuracy": null,
|
415 |
+
"eval_bertscore_f1": 0.9358997231175613,
|
416 |
+
"eval_bleu": 0.42469208733709635,
|
417 |
+
"eval_f1": null,
|
418 |
+
"eval_loss": 1.7025026082992554,
|
419 |
+
"eval_rouge1": 0.624191647944516,
|
420 |
+
"eval_rouge2": 0.4156753967572323,
|
421 |
+
"eval_rougeL": 0.5654439558669471,
|
422 |
+
"eval_rougeLsum": 0.5676313065358018,
|
423 |
+
"eval_runtime": 161.1453,
|
424 |
+
"eval_samples_per_second": 61.075,
|
425 |
+
"eval_steps_per_second": 0.956,
|
426 |
+
"step": 38000
|
427 |
}
|
428 |
],
|
429 |
"max_steps": 85840,
|
430 |
"num_train_epochs": 10,
|
431 |
+
"total_flos": 5.742276558570701e+16,
|
432 |
"trial_name": null,
|
433 |
"trial_params": null
|
434 |
}
|
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:a0e49b0eab33b9539d5954a9a379dcb893c591083001ba531e4332b2580c9ed9
|
3 |
size 307910149
|