Training in progress, step 13500
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +24 -5
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484085807
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b21e41e67212eae8e1332f8e4c172ca9bdb2ea653ad09fefcfbc367de7bfa50b
|
3 |
size 484085807
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242031355
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99f72175fbc7586aab4b1820d13bf580e9a6df9aa7e116750402184faf0580c4
|
3 |
size 242031355
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87ef3e7d31ff357becc518ac8be9b55a4dab0e0a48d2fb3dced427d51de9cc56
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15a0f07f0e3d1e04502b206a2a1c6a8c5f48911a16dd2a6af0ff3fcfd7f96ff4
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1529048a87702aab8bb6e007f632aca8b97213dd5b76e31af16debc8df92bba9
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-
|
4 |
-
"epoch": 4.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -500,11 +500,30 @@
|
|
500 |
"eval_samples_per_second": 77.029,
|
501 |
"eval_steps_per_second": 2.426,
|
502 |
"step": 13000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
503 |
}
|
504 |
],
|
505 |
"max_steps": 62500,
|
506 |
"num_train_epochs": 20,
|
507 |
-
"total_flos": 5.
|
508 |
"trial_name": null,
|
509 |
"trial_params": null
|
510 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.700024425983429,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-13500",
|
4 |
+
"epoch": 4.32,
|
5 |
+
"global_step": 13500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
500 |
"eval_samples_per_second": 77.029,
|
501 |
"eval_steps_per_second": 2.426,
|
502 |
"step": 13000
|
503 |
+
},
|
504 |
+
{
|
505 |
+
"epoch": 4.32,
|
506 |
+
"learning_rate": 0.0004126736842105263,
|
507 |
+
"loss": 0.5303,
|
508 |
+
"step": 13500
|
509 |
+
},
|
510 |
+
{
|
511 |
+
"epoch": 4.32,
|
512 |
+
"eval_bleu": 0.06674010593523277,
|
513 |
+
"eval_exact_match": 0.1,
|
514 |
+
"eval_loss": 0.700024425983429,
|
515 |
+
"eval_rouge1": 0.5072383570011582,
|
516 |
+
"eval_rouge2": 0.35252886838350916,
|
517 |
+
"eval_rougeL": 0.49584290875564585,
|
518 |
+
"eval_runtime": 25.9074,
|
519 |
+
"eval_samples_per_second": 77.198,
|
520 |
+
"eval_steps_per_second": 2.432,
|
521 |
+
"step": 13500
|
522 |
}
|
523 |
],
|
524 |
"max_steps": 62500,
|
525 |
"num_train_epochs": 20,
|
526 |
+
"total_flos": 5.648322598954598e+16,
|
527 |
"trial_name": null,
|
528 |
"trial_params": null
|
529 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242031355
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99f72175fbc7586aab4b1820d13bf580e9a6df9aa7e116750402184faf0580c4
|
3 |
size 242031355
|