Training in progress, step 36000
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 sha256:88830563c9930fc43398c8c295082fff228092e25ccb022a9b1675bc042f973c
|
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 sha256:2c631692db5d74b5b0a51901a78f382169c96c7a2d5c58d6c235c73af67f2ff4
|
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 sha256:4b7edabd23499c9a6b6838e62eb59c7722e2e05f3a710e532ca9b4287feb3f82
|
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:afcf5db00c35362054255eb91304101b5889a34325096006adc3589ac1645575
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -380,11 +380,33 @@
|
|
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.
|
388 |
"trial_name": null,
|
389 |
"trial_params": null
|
390 |
}
|
|
|
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": 4.193849021435228,
|
5 |
+
"global_step": 36000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
380 |
"eval_samples_per_second": 60.222,
|
381 |
"eval_steps_per_second": 0.942,
|
382 |
"step": 34000
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 4.19,
|
386 |
+
"learning_rate": 0.0006111737872173444,
|
387 |
+
"loss": 1.081,
|
388 |
+
"step": 36000
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 4.19,
|
392 |
+
"eval_accuracy": null,
|
393 |
+
"eval_bertscore_f1": 0.9366190056446194,
|
394 |
+
"eval_bleu": 0.4235289371475263,
|
395 |
+
"eval_f1": null,
|
396 |
+
"eval_loss": 1.7053654193878174,
|
397 |
+
"eval_rouge1": 0.6275525594646458,
|
398 |
+
"eval_rouge2": 0.4228795682628885,
|
399 |
+
"eval_rougeL": 0.5724176993561514,
|
400 |
+
"eval_rougeLsum": 0.5744128212816374,
|
401 |
+
"eval_runtime": 161.6199,
|
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": 5.439019436459213e+16,
|
410 |
"trial_name": null,
|
411 |
"trial_params": null
|
412 |
}
|
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 sha256:2c631692db5d74b5b0a51901a78f382169c96c7a2d5c58d6c235c73af67f2ff4
|
3 |
size 307910149
|