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 125918320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a69f467bae445edb83cdc93110ee1d39380676f28a114d0280ed3c40cc00dcdb
|
3 |
size 125918320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 64683604
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6921e1855b9b87d250af8c258829c3aa968408b7edacb36d411edd29d8fc6d57
|
3 |
size 64683604
|
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 sha256:8de9f15cb7cf16a613c75ae673fe065d6d3ea271f16870a12211dedaaf4137b6
|
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 sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
|
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": 7.859,
|
248 |
"eval_steps_per_second": 0.984,
|
249 |
"step": 72
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
250 |
}
|
251 |
],
|
252 |
"logging_steps": 3,
|
@@ -266,7 +295,7 @@
|
|
266 |
"attributes": {}
|
267 |
}
|
268 |
},
|
269 |
-
"total_flos":
|
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": 0.03071090047393365,
|
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": 7.859,
|
248 |
"eval_steps_per_second": 0.984,
|
249 |
"step": 72
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.02843601895734597,
|
253 |
+
"grad_norm": 4.369206428527832,
|
254 |
+
"learning_rate": 1.7860619515673033e-05,
|
255 |
+
"loss": 2.1532,
|
256 |
+
"step": 75
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.02957345971563981,
|
260 |
+
"grad_norm": 4.181845664978027,
|
261 |
+
"learning_rate": 1.4033009983067452e-05,
|
262 |
+
"loss": 2.0465,
|
263 |
+
"step": 78
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.03071090047393365,
|
267 |
+
"grad_norm": 4.068225383758545,
|
268 |
+
"learning_rate": 1.0599462319663905e-05,
|
269 |
+
"loss": 1.9805,
|
270 |
+
"step": 81
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.03071090047393365,
|
274 |
+
"eval_loss": 0.48237505555152893,
|
275 |
+
"eval_runtime": 565.3076,
|
276 |
+
"eval_samples_per_second": 7.858,
|
277 |
+
"eval_steps_per_second": 0.984,
|
278 |
+
"step": 81
|
279 |
}
|
280 |
],
|
281 |
"logging_steps": 3,
|
|
|
295 |
"attributes": {}
|
296 |
}
|
297 |
},
|
298 |
+
"total_flos": 2.1634795839474893e+17,
|
299 |
"train_batch_size": 8,
|
300 |
"trial_name": null,
|
301 |
"trial_params": null
|