Training in progress, step 63, 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 1001465824
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:906d89c73a29ae5fbdab0bccaab839653cd2b21a62aa9bce4b0f92aabee18bb9
|
3 |
size 1001465824
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 509176980
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cca5e1bed11b97f60ffab38e8ddf3d42527147fa7577c8cd93c566d10be62de2
|
3 |
size 509176980
|
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 sha256:68562acc50572f6cb365f5d14b11accf166d4aa6a44cf504f5e5b802c9d1c19f
|
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:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
|
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,
|
@@ -189,6 +189,35 @@
|
|
189 |
"eval_samples_per_second": 7.77,
|
190 |
"eval_steps_per_second": 1.963,
|
191 |
"step": 54
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 3,
|
@@ -208,7 +237,7 @@
|
|
208 |
"attributes": {}
|
209 |
}
|
210 |
},
|
211 |
-
"total_flos":
|
212 |
"train_batch_size": 4,
|
213 |
"trial_name": null,
|
214 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5575221238938053,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 63,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
189 |
"eval_samples_per_second": 7.77,
|
190 |
"eval_steps_per_second": 1.963,
|
191 |
"step": 54
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.504424778761062,
|
195 |
+
"grad_norm": 4.16663424402941e-05,
|
196 |
+
"learning_rate": 4.6512176312793736e-05,
|
197 |
+
"loss": 0.0,
|
198 |
+
"step": 57
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.5309734513274337,
|
202 |
+
"grad_norm": 3.846506660920568e-05,
|
203 |
+
"learning_rate": 4.131759111665349e-05,
|
204 |
+
"loss": 0.0,
|
205 |
+
"step": 60
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.5575221238938053,
|
209 |
+
"grad_norm": 5.5511947721242905e-05,
|
210 |
+
"learning_rate": 3.6218132209150045e-05,
|
211 |
+
"loss": 0.0,
|
212 |
+
"step": 63
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.5575221238938053,
|
216 |
+
"eval_loss": 2.6978867140314833e-07,
|
217 |
+
"eval_runtime": 12.2104,
|
218 |
+
"eval_samples_per_second": 7.78,
|
219 |
+
"eval_steps_per_second": 1.966,
|
220 |
+
"step": 63
|
221 |
}
|
222 |
],
|
223 |
"logging_steps": 3,
|
|
|
237 |
"attributes": {}
|
238 |
}
|
239 |
},
|
240 |
+
"total_flos": 9.112767072043008e+16,
|
241 |
"train_batch_size": 4,
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|