Training in progress, step 4000
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:ffbab0fc63ce00717c302547e84f82da5c6ee76fb3265174a8133ebdecef1a17
|
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 sha256:014b3be65b7ad8d2851782d7470f096709fe019b1add35f17e9f1ec11ff523c7
|
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:ccf5e1fa7cb0e64b9f7031f08d5a7607e164e6d95900975a7b4d6e0b968b2a28
|
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 sha256:0b61dc7ea15684027603ed37267a329167e46bc46091410e4d472ff753c910bd
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.7780297994613647,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-2000",
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -28,11 +28,33 @@
|
|
28 |
"eval_samples_per_second": 58.559,
|
29 |
"eval_steps_per_second": 0.916,
|
30 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
}
|
32 |
],
|
33 |
"max_steps": 85840,
|
34 |
"num_train_epochs": 10,
|
35 |
-
"total_flos":
|
36 |
"trial_name": null,
|
37 |
"trial_params": null
|
38 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.7780297994613647,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-2000",
|
4 |
+
"epoch": 0.4659832246039143,
|
5 |
+
"global_step": 4000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
28 |
"eval_samples_per_second": 58.559,
|
29 |
"eval_steps_per_second": 0.916,
|
30 |
"step": 2000
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.47,
|
34 |
+
"learning_rate": 0.0009319664492078286,
|
35 |
+
"loss": 1.4342,
|
36 |
+
"step": 4000
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 0.47,
|
40 |
+
"eval_accuracy": null,
|
41 |
+
"eval_bertscore_f1": 0.933153417701039,
|
42 |
+
"eval_bleu": 0.4002469468404885,
|
43 |
+
"eval_f1": null,
|
44 |
+
"eval_loss": 1.7909314632415771,
|
45 |
+
"eval_rouge1": 0.5975097321291585,
|
46 |
+
"eval_rouge2": 0.3847152683676083,
|
47 |
+
"eval_rougeL": 0.5420448625219438,
|
48 |
+
"eval_rougeLsum": 0.5439086899907004,
|
49 |
+
"eval_runtime": 163.5422,
|
50 |
+
"eval_samples_per_second": 60.18,
|
51 |
+
"eval_steps_per_second": 0.942,
|
52 |
+
"step": 4000
|
53 |
}
|
54 |
],
|
55 |
"max_steps": 85840,
|
56 |
"num_train_epochs": 10,
|
57 |
+
"total_flos": 6054128429826048.0,
|
58 |
"trial_name": null,
|
59 |
"trial_params": null
|
60 |
}
|
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 sha256:014b3be65b7ad8d2851782d7470f096709fe019b1add35f17e9f1ec11ff523c7
|
3 |
size 307910149
|