Training in progress, step 9500
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 sha256:7a2dd38a0cccc43d47914cb567f6a657a8e753386c74d23079e2ba5c427670b6
|
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:eb324b7538e9487d07219feb70fc2572eb3ca9bafdedd05d4a5da34aba5a75c2
|
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 sha256:1051255e2fdf5d296c97bbfdc55cf71c864c5ebce20a858becd7c2ae86d42157
|
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 sha256:91ed0cd028941c6bb5d5dd41c046243d92bfedf223801da9bf634ce367f77e5e
|
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:eb2cc4edf5bb335b4a3d327cdd00678796932a01847274adadc3b23b4d3ab1f3
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -348,11 +348,30 @@
|
|
348 |
"eval_samples_per_second": 53.491,
|
349 |
"eval_steps_per_second": 1.685,
|
350 |
"step": 9000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
351 |
}
|
352 |
],
|
353 |
"max_steps": 62500,
|
354 |
"num_train_epochs": 20,
|
355 |
-
"total_flos": 3.
|
356 |
"trial_name": null,
|
357 |
"trial_params": null
|
358 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7321618795394897,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-9500",
|
4 |
+
"epoch": 3.04,
|
5 |
+
"global_step": 9500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
348 |
"eval_samples_per_second": 53.491,
|
349 |
"eval_steps_per_second": 1.685,
|
350 |
"step": 9000
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 3.04,
|
354 |
+
"learning_rate": 0.000446341052631579,
|
355 |
+
"loss": 0.6008,
|
356 |
+
"step": 9500
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 3.04,
|
360 |
+
"eval_bleu": 0.06461231818263671,
|
361 |
+
"eval_exact_match": 0.101,
|
362 |
+
"eval_loss": 0.7321618795394897,
|
363 |
+
"eval_rouge1": 0.5033575057087202,
|
364 |
+
"eval_rouge2": 0.3421619427853616,
|
365 |
+
"eval_rougeL": 0.4902835308639695,
|
366 |
+
"eval_runtime": 36.6808,
|
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": 3.975969937293312e+16,
|
375 |
"trial_name": null,
|
376 |
"trial_params": null
|
377 |
}
|
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:eb324b7538e9487d07219feb70fc2572eb3ca9bafdedd05d4a5da34aba5a75c2
|
3 |
size 242031355
|