Training in progress, step 64, 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 97728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb4bbb5372f29a6caf128538be1b6f05973475bb5e1a9806bcb4c94754837795
|
3 |
size 97728
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 212298
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bef68d4704428cd2075b9af0de2c4a7528e31bdc93d8faac3410566b8b58c44
|
3 |
size 212298
|
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 sha256:344338431e33a6e2f5674878a19c239f840bfbb7767463e4bb420c416a152c1a
|
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 sha256:9f5fef290c2d601f702708df10bf5f98083660f03273309905f9ee205d8b58af
|
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":
|
5 |
"eval_steps": 8,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -197,6 +197,35 @@
|
|
197 |
"eval_samples_per_second": 134.919,
|
198 |
"eval_steps_per_second": 68.155,
|
199 |
"step": 56
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
200 |
}
|
201 |
],
|
202 |
"logging_steps": 3,
|
@@ -216,7 +245,7 @@
|
|
216 |
"attributes": {}
|
217 |
}
|
218 |
},
|
219 |
-
"total_flos":
|
220 |
"train_batch_size": 2,
|
221 |
"trial_name": null,
|
222 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.273522975929978,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 64,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
197 |
"eval_samples_per_second": 134.919,
|
198 |
"eval_steps_per_second": 68.155,
|
199 |
"step": 56
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 2.0284463894967177,
|
203 |
+
"grad_norm": 0.2121211737394333,
|
204 |
+
"learning_rate": 8.107487556395901e-05,
|
205 |
+
"loss": 13.6014,
|
206 |
+
"step": 57
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.1334792122538295,
|
210 |
+
"grad_norm": 0.11470862478017807,
|
211 |
+
"learning_rate": 6.729320366825784e-05,
|
212 |
+
"loss": 10.2428,
|
213 |
+
"step": 60
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 2.238512035010941,
|
217 |
+
"grad_norm": 0.0803636685013771,
|
218 |
+
"learning_rate": 5.417734782725896e-05,
|
219 |
+
"loss": 10.1202,
|
220 |
+
"step": 63
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 2.273522975929978,
|
224 |
+
"eval_loss": 10.290419578552246,
|
225 |
+
"eval_runtime": 0.7218,
|
226 |
+
"eval_samples_per_second": 134.394,
|
227 |
+
"eval_steps_per_second": 67.89,
|
228 |
+
"step": 64
|
229 |
}
|
230 |
],
|
231 |
"logging_steps": 3,
|
|
|
245 |
"attributes": {}
|
246 |
}
|
247 |
},
|
248 |
+
"total_flos": 27451748253696.0,
|
249 |
"train_batch_size": 2,
|
250 |
"trial_name": null,
|
251 |
"trial_params": null
|