Training in progress, step 10000
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 484083951
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf4919861d4ccad97fae1071067d911686e64c5cc77f484bfa4b5cec4d30e90e
|
3 |
size 484083951
|
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 sha256:54b61cd064030bd425900beed8f1b2f0d1bc9425a31138817e896147af0cff57
|
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 sha256:6c2aff395de1e042f420e44ce149e165cdd8e788140e8479c307cc0e81bd4492
|
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:f31e111ce45b24bb4dd00df4effa8ae11169116c6b61584f2128dd8c7b4467db
|
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 sha256:697eba7592480ffb0e189ee34a39a2f526ba9f89c84a69e8fbca7dd532b29056
|
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": 3.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -367,11 +367,30 @@
|
|
367 |
"eval_samples_per_second": 54.524,
|
368 |
"eval_steps_per_second": 1.718,
|
369 |
"step": 9500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
370 |
}
|
371 |
],
|
372 |
"max_steps": 62500,
|
373 |
"num_train_epochs": 20,
|
374 |
-
"total_flos":
|
375 |
"trial_name": null,
|
376 |
"trial_params": null
|
377 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7238326668739319,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-10000",
|
4 |
+
"epoch": 3.2,
|
5 |
+
"global_step": 10000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
367 |
"eval_samples_per_second": 54.524,
|
368 |
"eval_steps_per_second": 1.718,
|
369 |
"step": 9500
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 3.2,
|
373 |
+
"learning_rate": 0.0004421305263157895,
|
374 |
+
"loss": 0.589,
|
375 |
+
"step": 10000
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 3.2,
|
379 |
+
"eval_bleu": 0.06509490313536258,
|
380 |
+
"eval_exact_match": 0.1005,
|
381 |
+
"eval_loss": 0.7238326668739319,
|
382 |
+
"eval_rouge1": 0.5044211940127038,
|
383 |
+
"eval_rouge2": 0.34197306671723443,
|
384 |
+
"eval_rougeL": 0.4906146460856744,
|
385 |
+
"eval_runtime": 35.0879,
|
386 |
+
"eval_samples_per_second": 57.0,
|
387 |
+
"eval_steps_per_second": 1.795,
|
388 |
+
"step": 10000
|
389 |
}
|
390 |
],
|
391 |
"max_steps": 62500,
|
392 |
"num_train_epochs": 20,
|
393 |
+
"total_flos": 4.184333715977011e+16,
|
394 |
"trial_name": null,
|
395 |
"trial_params": null
|
396 |
}
|
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 sha256:54b61cd064030bd425900beed8f1b2f0d1bc9425a31138817e896147af0cff57
|
3 |
size 242031355
|