Commit
·
7017cf9
1
Parent(s):
8345dff
Training in progress, step 40, 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 125248064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94227d74def4392cb0858dec5cc79f10f016d6d4cd0918860f43d17e963e6838
|
3 |
size 125248064
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 63350356
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:316ade94b6d96eda4bd7e177d6826e75c49fc70e0c9fa9e20ae11e4acc88a7d7
|
3 |
size 63350356
|
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 sha256:8f4a56d3eaf05ae5f699ef13189e24ddd5fcf425cc9cf8207ad6e0944d73bf35
|
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 sha256:610e491c82604b1b591117150d7c6581358cc6593f7a436345f16444653cc75d
|
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": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -217,13 +217,43 @@
|
|
217 |
"learning_rate": 0.00015646258503401362,
|
218 |
"loss": 1.8159,
|
219 |
"step": 35
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
220 |
}
|
221 |
],
|
222 |
"logging_steps": 1,
|
223 |
"max_steps": 150,
|
224 |
"num_train_epochs": 1,
|
225 |
"save_steps": 5,
|
226 |
-
"total_flos":
|
227 |
"trial_name": null,
|
228 |
"trial_params": null
|
229 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.016,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 40,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
217 |
"learning_rate": 0.00015646258503401362,
|
218 |
"loss": 1.8159,
|
219 |
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.01,
|
223 |
+
"learning_rate": 0.00015510204081632654,
|
224 |
+
"loss": 1.6081,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.01,
|
229 |
+
"learning_rate": 0.00015374149659863945,
|
230 |
+
"loss": 1.5529,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.02,
|
235 |
+
"learning_rate": 0.00015238095238095237,
|
236 |
+
"loss": 1.5456,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.02,
|
241 |
+
"learning_rate": 0.0001510204081632653,
|
242 |
+
"loss": 2.1016,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.02,
|
247 |
+
"learning_rate": 0.00014965986394557826,
|
248 |
+
"loss": 1.4394,
|
249 |
+
"step": 40
|
250 |
}
|
251 |
],
|
252 |
"logging_steps": 1,
|
253 |
"max_steps": 150,
|
254 |
"num_train_epochs": 1,
|
255 |
"save_steps": 5,
|
256 |
+
"total_flos": 4574768524247040.0,
|
257 |
"trial_name": null,
|
258 |
"trial_params": null
|
259 |
}
|