Training in progress, step 11000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +39 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Jun06_11-48-52_7b05b18748ae/events.out.tfevents.1686052960.7b05b18748ae.5850.0 +3 -0
- training_args.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 2000137067
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:192130ea330c92335b4ec568d45b118ff74e35f0f6baf20efb9e7ae07f697212
|
3 |
size 2000137067
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1002469625
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9775edd7f74575a31ebea2cf97da1f9068612908d4b4f4ea3780076a453c56af
|
3 |
size 1002469625
|
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:e0b73b7b01670ed94b6a61c6719f8d173d02f028510cc157a5f436910c7fccc6
|
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 sha256:138d4c85d722f8a4d274dc6efcff89e360667260d179a09b851082c76dd02389
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -366,11 +366,47 @@
|
|
366 |
"eval_samples_per_second": 2.646,
|
367 |
"eval_steps_per_second": 0.336,
|
368 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
369 |
}
|
370 |
],
|
371 |
"max_steps": 11700,
|
372 |
"num_train_epochs": 300,
|
373 |
-
"total_flos":
|
374 |
"trial_name": null,
|
375 |
"trial_params": null
|
376 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 282.05128205128204,
|
5 |
+
"global_step": 11000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
366 |
"eval_samples_per_second": 2.646,
|
367 |
"eval_steps_per_second": 0.336,
|
368 |
"step": 10000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 269.23,
|
372 |
+
"learning_rate": 6.211340206185568e-06,
|
373 |
+
"loss": 0.0076,
|
374 |
+
"step": 10500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 269.23,
|
378 |
+
"eval_bleu": 96.5038,
|
379 |
+
"eval_em": 0.6283,
|
380 |
+
"eval_gen_len": 75.3453,
|
381 |
+
"eval_loss": 0.16782505810260773,
|
382 |
+
"eval_rm": 0.7482,
|
383 |
+
"eval_runtime": 181.3202,
|
384 |
+
"eval_samples_per_second": 2.3,
|
385 |
+
"eval_steps_per_second": 0.292,
|
386 |
+
"step": 10500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 282.05,
|
390 |
+
"learning_rate": 3.6340206185567013e-06,
|
391 |
+
"loss": 0.007,
|
392 |
+
"step": 11000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 282.05,
|
396 |
+
"eval_bleu": 96.7187,
|
397 |
+
"eval_em": 0.6355,
|
398 |
+
"eval_gen_len": 75.9281,
|
399 |
+
"eval_loss": 0.16688644886016846,
|
400 |
+
"eval_rm": 0.7458,
|
401 |
+
"eval_runtime": 181.4265,
|
402 |
+
"eval_samples_per_second": 2.298,
|
403 |
+
"eval_steps_per_second": 0.292,
|
404 |
+
"step": 11000
|
405 |
}
|
406 |
],
|
407 |
"max_steps": 11700,
|
408 |
"num_train_epochs": 300,
|
409 |
+
"total_flos": 8892915240118272.0,
|
410 |
"trial_name": null,
|
411 |
"trial_params": null
|
412 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4155
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0d52a1a038137cc46f5db4299babbc4af85f1acb9ee53a6a96c81b0f4cf8a6d
|
3 |
size 4155
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1002469625
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9775edd7f74575a31ebea2cf97da1f9068612908d4b4f4ea3780076a453c56af
|
3 |
size 1002469625
|
runs/Jun06_11-48-52_7b05b18748ae/events.out.tfevents.1686052960.7b05b18748ae.5850.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f39cea5328853dfbeb4ba210619b88a2716e732f2069f4545612ba4eb869e33
|
3 |
+
size 9829
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4155
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0d52a1a038137cc46f5db4299babbc4af85f1acb9ee53a6a96c81b0f4cf8a6d
|
3 |
size 4155
|