Training in progress, step 34000
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:f9111aa92a20d8e82f0e9b1600ef48208474c3e572326ca0d83cea91e6dfbaf9
|
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:a4271cda2eff451a0ede900aca21f95457d5b189342d020f2338e721f86f5ac9
|
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:e29be3b2f57cd6981a40f41fa2578943874b0037dd459fcf689f3cdcaccd1d10
|
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 sha256:292bbc3eea567b7064818bfea393d6857515280efa4e423c4a2bf4ccb9a3aaa2
|
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": 3.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -358,11 +358,33 @@
|
|
358 |
"eval_samples_per_second": 59.06,
|
359 |
"eval_steps_per_second": 0.924,
|
360 |
"step": 32000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
361 |
}
|
362 |
],
|
363 |
"max_steps": 85840,
|
364 |
"num_train_epochs": 10,
|
365 |
-
"total_flos":
|
366 |
"trial_name": null,
|
367 |
"trial_params": null
|
368 |
}
|
|
|
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": 3.960857409133271,
|
5 |
+
"global_step": 34000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
358 |
"eval_samples_per_second": 59.06,
|
359 |
"eval_steps_per_second": 0.924,
|
360 |
"step": 32000
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 3.96,
|
364 |
+
"learning_rate": 0.0006356992200912346,
|
365 |
+
"loss": 1.1249,
|
366 |
+
"step": 34000
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 3.96,
|
370 |
+
"eval_accuracy": null,
|
371 |
+
"eval_bertscore_f1": 0.935824385111566,
|
372 |
+
"eval_bleu": 0.42158432020818837,
|
373 |
+
"eval_f1": null,
|
374 |
+
"eval_loss": 1.717002511024475,
|
375 |
+
"eval_rouge1": 0.626629100727167,
|
376 |
+
"eval_rouge2": 0.41890429908455223,
|
377 |
+
"eval_rougeL": 0.5695943813788329,
|
378 |
+
"eval_rougeLsum": 0.5715380718252487,
|
379 |
+
"eval_runtime": 163.4292,
|
380 |
+
"eval_samples_per_second": 60.222,
|
381 |
+
"eval_steps_per_second": 0.942,
|
382 |
+
"step": 34000
|
383 |
}
|
384 |
],
|
385 |
"max_steps": 85840,
|
386 |
"num_train_epochs": 10,
|
387 |
+
"total_flos": 5.138717210930995e+16,
|
388 |
"trial_name": null,
|
389 |
"trial_params": null
|
390 |
}
|
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:a4271cda2eff451a0ede900aca21f95457d5b189342d020f2338e721f86f5ac9
|
3 |
size 307910149
|