MohamedAhmedAE
commited on
Commit
•
dc7c654
1
Parent(s):
e05b7dd
Training in progress, step 215800, 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 1715561468
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27e5940bc93f7cff15956075e09a7ca10ff525d1b7c9454eb76d35a49ab214d0
|
3 |
size 1715561468
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3431474364
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cd2491474ec7e902135dfb582471eb48d09d9194e1783a1a027f37f00e527d0
|
3 |
size 3431474364
|
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:b7be69f4f5a92bd2333e98a6ee6690d48a2a8d1f1f78465c4960abc5c608a82c
|
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": 21.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -9273,6 +9273,13 @@
|
|
9273 |
"learning_rate": 3.0338827527763924e-05,
|
9274 |
"loss": 0.3548,
|
9275 |
"step": 215600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9276 |
}
|
9277 |
],
|
9278 |
"logging_steps": 200,
|
@@ -9292,7 +9299,7 @@
|
|
9292 |
"attributes": {}
|
9293 |
}
|
9294 |
},
|
9295 |
-
"total_flos": 3.
|
9296 |
"train_batch_size": 6,
|
9297 |
"trial_name": null,
|
9298 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 21.595116581607126,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 215800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
9273 |
"learning_rate": 3.0338827527763924e-05,
|
9274 |
"loss": 0.3548,
|
9275 |
"step": 215600
|
9276 |
+
},
|
9277 |
+
{
|
9278 |
+
"epoch": 21.595116581607126,
|
9279 |
+
"grad_norm": 2.6156089305877686,
|
9280 |
+
"learning_rate": 3.030811030135342e-05,
|
9281 |
+
"loss": 0.3513,
|
9282 |
+
"step": 215800
|
9283 |
}
|
9284 |
],
|
9285 |
"logging_steps": 200,
|
|
|
9299 |
"attributes": {}
|
9300 |
}
|
9301 |
},
|
9302 |
+
"total_flos": 3.0937185381113856e+18,
|
9303 |
"train_batch_size": 6,
|
9304 |
"trial_name": null,
|
9305 |
"trial_params": null
|