Training in progress, step 30000
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 sha256:8d84430446db4d99c3febcd7069c01b881fdf59602a6b2f386c6aa6f6088e31c
|
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 sha256:99d2e4c5815635fa81968b10f073c84d641b574540c97062b58e265dfd90d2cf
|
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 sha256:8b562ad0fe42141b4131900487ab29531dae5f3b66e799e44aa1bac6297445f4
|
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:c253821127e6e97cecd3e16899e80bf0898ae3dcd40b71b5a507f5ae44245fdf
|
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,
|
@@ -314,11 +314,33 @@
|
|
314 |
"eval_samples_per_second": 61.009,
|
315 |
"eval_steps_per_second": 0.955,
|
316 |
"step": 28000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
317 |
}
|
318 |
],
|
319 |
"max_steps": 85840,
|
320 |
"num_train_epochs": 10,
|
321 |
-
"total_flos": 4.
|
322 |
"trial_name": null,
|
323 |
"trial_params": null
|
324 |
}
|
|
|
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": 3.494874184529357,
|
5 |
+
"global_step": 30000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
314 |
"eval_samples_per_second": 61.009,
|
315 |
"eval_steps_per_second": 0.955,
|
316 |
"step": 28000
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 3.49,
|
320 |
+
"learning_rate": 0.0006847500858390151,
|
321 |
+
"loss": 1.121,
|
322 |
+
"step": 30000
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 3.49,
|
326 |
+
"eval_accuracy": null,
|
327 |
+
"eval_bertscore_f1": 0.9367988150164839,
|
328 |
+
"eval_bleu": 0.42462787525751705,
|
329 |
+
"eval_f1": null,
|
330 |
+
"eval_loss": 1.7076311111450195,
|
331 |
+
"eval_rouge1": 0.6318247622031307,
|
332 |
+
"eval_rouge2": 0.42560950906924944,
|
333 |
+
"eval_rougeL": 0.5726212713576446,
|
334 |
+
"eval_rougeLsum": 0.5746959557098454,
|
335 |
+
"eval_runtime": 159.1906,
|
336 |
+
"eval_samples_per_second": 61.825,
|
337 |
+
"eval_steps_per_second": 0.967,
|
338 |
+
"step": 30000
|
339 |
}
|
340 |
],
|
341 |
"max_steps": 85840,
|
342 |
"num_train_epochs": 10,
|
343 |
+
"total_flos": 4.532149523187917e+16,
|
344 |
"trial_name": null,
|
345 |
"trial_params": null
|
346 |
}
|
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 sha256:99d2e4c5815635fa81968b10f073c84d641b574540c97062b58e265dfd90d2cf
|
3 |
size 307910149
|