youdiniplays
commited on
Training in progress, step 31000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7e29eb21b28d9a4635f6391e41f77edef0083a50dd8b4b5ada35cc25d56747c
|
3 |
size 242041896
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484163514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb496a59806696fa7140a2c2813245e5fcec35b56e894e79d6db03b567bfd25b
|
3 |
size 484163514
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e55b8a5848de3264050c8013765de1560baaee850bf1ad3dbe34acf32ad69c8
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4209dfe93068dcc657ee5aed80708653f32fd354859faa8ee0651e94dd4d100
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 4.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -413,13 +413,19 @@
|
|
413 |
"learning_rate": 6.424186617556783e-05,
|
414 |
"loss": 0.4495,
|
415 |
"step": 30500
|
|
|
|
|
|
|
|
|
|
|
|
|
416 |
}
|
417 |
],
|
418 |
"logging_steps": 500,
|
419 |
"max_steps": 32580,
|
420 |
"num_train_epochs": 5,
|
421 |
"save_steps": 500,
|
422 |
-
"total_flos": 1.
|
423 |
"trial_name": null,
|
424 |
"trial_params": null
|
425 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.757519950890116,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 31000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
413 |
"learning_rate": 6.424186617556783e-05,
|
414 |
"loss": 0.4495,
|
415 |
"step": 30500
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 4.76,
|
419 |
+
"learning_rate": 4.8895027624309394e-05,
|
420 |
+
"loss": 0.4555,
|
421 |
+
"step": 31000
|
422 |
}
|
423 |
],
|
424 |
"logging_steps": 500,
|
425 |
"max_steps": 32580,
|
426 |
"num_train_epochs": 5,
|
427 |
"save_steps": 500,
|
428 |
+
"total_flos": 1.6437266018205696e+16,
|
429 |
"trial_name": null,
|
430 |
"trial_params": null
|
431 |
}
|