youdiniplays
commited on
Training in progress, step 22500, 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 sha256:05a33084b879a82540cb3edc4fb3256c0fe1c6fa4b3941680d6fed08b9519a1e
|
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 sha256:3f2f099fa29254d5fa0abebe2476734eebab9a8bbd6766b12469aadcc075f2cd
|
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:a6b32b541166e543f27f7315c34f487678689f44e697de630025ad54a269fadb
|
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 sha256:88fd94efeb6ba9dda0db69aa82b6c13e45b9ed92df96b2d00802396977ce49d9
|
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": 3.
|
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,
|
@@ -301,13 +301,19 @@
|
|
301 |
"learning_rate": 0.00032501534683855126,
|
302 |
"loss": 0.4906,
|
303 |
"step": 22000
|
|
|
|
|
|
|
|
|
|
|
|
|
304 |
}
|
305 |
],
|
306 |
"logging_steps": 500,
|
307 |
"max_steps": 32580,
|
308 |
"num_train_epochs": 5,
|
309 |
"save_steps": 500,
|
310 |
-
"total_flos": 1.
|
311 |
"trial_name": null,
|
312 |
"trial_params": null
|
313 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.453038674033149,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 22500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
301 |
"learning_rate": 0.00032501534683855126,
|
302 |
"loss": 0.4906,
|
303 |
"step": 22000
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 3.45,
|
307 |
+
"learning_rate": 0.0003096685082872928,
|
308 |
+
"loss": 0.4884,
|
309 |
+
"step": 22500
|
310 |
}
|
311 |
],
|
312 |
"logging_steps": 500,
|
313 |
"max_steps": 32580,
|
314 |
"num_train_epochs": 5,
|
315 |
"save_steps": 500,
|
316 |
+
"total_flos": 1.192505071632384e+16,
|
317 |
"trial_name": null,
|
318 |
"trial_params": null
|
319 |
}
|