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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:156f276758316a99af9908f873723249666a6343317cd60f4ce0c3f30c372763
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37965300
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a24df2cfafa8f843a944ed1b0f6c1542c007e823cc58b9e950690b3f095ffdf
|
3 |
size 37965300
|
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 sha256:3402faab675d6ce12c7f65f4a41ea9563097b3e01456d349846f69b226bf1713
|
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": 1.
|
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": 36.283,
|
248 |
"eval_steps_per_second": 4.751,
|
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": 1.6363636363636362,
|
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": 36.283,
|
248 |
"eval_steps_per_second": 4.751,
|
249 |
"step": 72
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 1.5151515151515151,
|
253 |
+
"grad_norm": 0.9272772073745728,
|
254 |
+
"learning_rate": 8.930309757836517e-06,
|
255 |
+
"loss": 1.9071,
|
256 |
+
"step": 75
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 1.5757575757575757,
|
260 |
+
"grad_norm": 1.047183871269226,
|
261 |
+
"learning_rate": 7.016504991533726e-06,
|
262 |
+
"loss": 2.116,
|
263 |
+
"step": 78
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 1.6363636363636362,
|
267 |
+
"grad_norm": 1.016968011856079,
|
268 |
+
"learning_rate": 5.299731159831953e-06,
|
269 |
+
"loss": 1.9271,
|
270 |
+
"step": 81
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 1.6363636363636362,
|
274 |
+
"eval_loss": 2.092479705810547,
|
275 |
+
"eval_runtime": 2.3272,
|
276 |
+
"eval_samples_per_second": 36.095,
|
277 |
+
"eval_steps_per_second": 4.727,
|
278 |
+
"step": 81
|
279 |
}
|
280 |
],
|
281 |
"logging_steps": 3,
|
|
|
295 |
"attributes": {}
|
296 |
}
|
297 |
},
|
298 |
+
"total_flos": 2.1153390976303104e+16,
|
299 |
"train_batch_size": 8,
|
300 |
"trial_name": null,
|
301 |
"trial_params": null
|