Training in progress, step 40000
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 sha256:8d193ff27c075191df41a8753d4124ffc0f8baafc06eba5ac95ed1ce740ce6ae
|
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 sha256:6f3a7514a95f28ef73934da27d69c294765e4e757a4eadd4ef8b4aaccaa4f62c
|
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 sha256:79279175f3892ebfce7af0172b34a9afeaad2767a70562f1818d2115e3caa401
|
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 sha256:38c67dd5200a0105c5f2b1b8243a1ce46093d418497c730f1ff3a6d23cd097af
|
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,
|
@@ -424,11 +424,33 @@
|
|
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":
|
432 |
"trial_name": null,
|
433 |
"trial_params": null
|
434 |
}
|
|
|
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": 4.659832246039143,
|
5 |
+
"global_step": 40000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
424 |
"eval_samples_per_second": 61.075,
|
425 |
"eval_steps_per_second": 0.956,
|
426 |
"step": 38000
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 4.66,
|
430 |
+
"learning_rate": 0.0005621229214695639,
|
431 |
+
"loss": 1.0817,
|
432 |
+
"step": 40000
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 4.66,
|
436 |
+
"eval_accuracy": null,
|
437 |
+
"eval_bertscore_f1": 0.9371525604679827,
|
438 |
+
"eval_bleu": 0.4290378828512276,
|
439 |
+
"eval_f1": null,
|
440 |
+
"eval_loss": 1.759724736213684,
|
441 |
+
"eval_rouge1": 0.6329216329529901,
|
442 |
+
"eval_rouge2": 0.428712988798996,
|
443 |
+
"eval_rougeL": 0.5766896544496578,
|
444 |
+
"eval_rougeLsum": 0.5786424518723892,
|
445 |
+
"eval_runtime": 164.8993,
|
446 |
+
"eval_samples_per_second": 59.685,
|
447 |
+
"eval_steps_per_second": 0.934,
|
448 |
+
"step": 40000
|
449 |
}
|
450 |
],
|
451 |
"max_steps": 85840,
|
452 |
"num_train_epochs": 10,
|
453 |
+
"total_flos": 6.045034099950797e+16,
|
454 |
"trial_name": null,
|
455 |
"trial_params": null
|
456 |
}
|
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 sha256:6f3a7514a95f28ef73934da27d69c294765e4e757a4eadd4ef8b4aaccaa4f62c
|
3 |
size 307910149
|