Training in progress, step 15500, 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 sha256:4a026e071b1e9ccf305886c9f4b0fd1b2ff3a0c6f479e54c91760927ffe8534b
|
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 sha256:6c8abbb5ace835107c998734168c52bca07dddaab2105fc321fdc2afa0796029
|
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:bb03875b0ff82321173ec7ebfdbb4756b9de0c0e7e17519178fc0be76b12441d
|
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 sha256:1820545852d3566a9453339979bf92f6e10cdd9f597f504847d317ad3ff68c77
|
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": 2.
|
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,
|
@@ -207,13 +207,19 @@
|
|
207 |
"learning_rate": 0.0005397483118477594,
|
208 |
"loss": 0.5289,
|
209 |
"step": 15000
|
|
|
|
|
|
|
|
|
|
|
|
|
210 |
}
|
211 |
],
|
212 |
"logging_steps": 500,
|
213 |
"max_steps": 32580,
|
214 |
"num_train_epochs": 5,
|
215 |
"save_steps": 500,
|
216 |
-
"total_flos":
|
217 |
"trial_name": null,
|
218 |
"trial_params": null
|
219 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.378759975445058,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 15500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
207 |
"learning_rate": 0.0005397483118477594,
|
208 |
"loss": 0.5289,
|
209 |
"step": 15000
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 2.38,
|
213 |
+
"learning_rate": 0.0005244014732965009,
|
214 |
+
"loss": 0.5321,
|
215 |
+
"step": 15500
|
216 |
}
|
217 |
],
|
218 |
"logging_steps": 500,
|
219 |
"max_steps": 32580,
|
220 |
"num_train_epochs": 5,
|
221 |
"save_steps": 500,
|
222 |
+
"total_flos": 8216994104475648.0,
|
223 |
"trial_name": null,
|
224 |
"trial_params": null
|
225 |
}
|