Training in progress, step 25, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a737b0c1e8fb72cb6c054968e4e28f2c59bcc3f54b017f98ce2cc8b1944d126
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 168149074
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63369e7533c00096bf3b040d65870dbd61a2f52ca17821398030c19e5fce1e37
|
3 |
size 168149074
|
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 sha256:6f3a13c121a1722ff730d0b2ff62a8da8014f7d106b7c698bc4e323f6369265d
|
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 sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
|
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": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -247,6 +247,13 @@
|
|
247 |
"eval_samples_per_second": 8.196,
|
248 |
"eval_steps_per_second": 8.196,
|
249 |
"step": 24
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
250 |
}
|
251 |
],
|
252 |
"logging_steps": 1,
|
@@ -261,12 +268,12 @@
|
|
261 |
"should_evaluate": false,
|
262 |
"should_log": false,
|
263 |
"should_save": true,
|
264 |
-
"should_training_stop":
|
265 |
},
|
266 |
"attributes": {}
|
267 |
}
|
268 |
},
|
269 |
-
"total_flos":
|
270 |
"train_batch_size": 1,
|
271 |
"trial_name": null,
|
272 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0833333333333335,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 25,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
247 |
"eval_samples_per_second": 8.196,
|
248 |
"eval_steps_per_second": 8.196,
|
249 |
"step": 24
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 2.0833333333333335,
|
253 |
+
"grad_norm": 0.06670382618904114,
|
254 |
+
"learning_rate": 0.0,
|
255 |
+
"loss": 0.0044,
|
256 |
+
"step": 25
|
257 |
}
|
258 |
],
|
259 |
"logging_steps": 1,
|
|
|
268 |
"should_evaluate": false,
|
269 |
"should_log": false,
|
270 |
"should_save": true,
|
271 |
+
"should_training_stop": true
|
272 |
},
|
273 |
"attributes": {}
|
274 |
}
|
275 |
},
|
276 |
+
"total_flos": 9247821240729600.0,
|
277 |
"train_batch_size": 1,
|
278 |
"trial_name": null,
|
279 |
"trial_params": null
|