Training in progress, step 81, 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 72396376
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f073ddbdf47ba2068025701aa32d5c54ebd60dcbb4d960803dc3e16859db7f3
|
3 |
size 72396376
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37134420
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:768952480bd95e80c37bf8c00bf129fcf0e57b1e2713a64a0d1dee54a0123901
|
3 |
size 37134420
|
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 sha256:323bb1f1205a74bebd0f0bd9a8964d7b506928f6ead84ee656ba46045c26e2aa
|
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:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
|
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": 0.
|
5 |
"eval_steps": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -247,6 +247,35 @@
|
|
247 |
"eval_samples_per_second": 34.511,
|
248 |
"eval_steps_per_second": 4.371,
|
249 |
"step": 72
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
250 |
}
|
251 |
],
|
252 |
"logging_steps": 3,
|
@@ -266,7 +295,7 @@
|
|
266 |
"attributes": {}
|
267 |
}
|
268 |
},
|
269 |
-
"total_flos": 2.
|
270 |
"train_batch_size": 8,
|
271 |
"trial_name": null,
|
272 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3036551077788191,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 81,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
247 |
"eval_samples_per_second": 34.511,
|
248 |
"eval_steps_per_second": 4.371,
|
249 |
"step": 72
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.28116213683223995,
|
253 |
+
"grad_norm": 0.26518431305885315,
|
254 |
+
"learning_rate": 8.930309757836517e-06,
|
255 |
+
"loss": 1.9598,
|
256 |
+
"step": 75
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.2924086223055295,
|
260 |
+
"grad_norm": 0.2572343051433563,
|
261 |
+
"learning_rate": 7.016504991533726e-06,
|
262 |
+
"loss": 1.9719,
|
263 |
+
"step": 78
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.3036551077788191,
|
267 |
+
"grad_norm": 0.2520810067653656,
|
268 |
+
"learning_rate": 5.299731159831953e-06,
|
269 |
+
"loss": 1.9132,
|
270 |
+
"step": 81
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.3036551077788191,
|
274 |
+
"eval_loss": 1.9208440780639648,
|
275 |
+
"eval_runtime": 12.9817,
|
276 |
+
"eval_samples_per_second": 34.664,
|
277 |
+
"eval_steps_per_second": 4.391,
|
278 |
+
"step": 81
|
279 |
}
|
280 |
],
|
281 |
"logging_steps": 3,
|
|
|
295 |
"attributes": {}
|
296 |
}
|
297 |
},
|
298 |
+
"total_flos": 2.649947204537549e+16,
|
299 |
"train_batch_size": 8,
|
300 |
"trial_name": null,
|
301 |
"trial_params": null
|