Training in progress, step 81, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1342555602
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d0dd053508affbbad72b89388a95b6bc780bb4d8f659dd9238713d9a5942a01
|
3 |
size 1342555602
|
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 sha256:8e5deaa005da3f37ac047220efed89711e9e0f7a3bbfe87c152d5792af35f64e
|
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 sha256:09ab64d5ace66796aa9c2fa2fc4e0206d69a1eb4ef03f574f85ee8eb16a64b71
|
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,
|
@@ -177,6 +177,28 @@
|
|
177 |
"eval_samples_per_second": 10.199,
|
178 |
"eval_steps_per_second": 1.276,
|
179 |
"step": 72
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
180 |
}
|
181 |
],
|
182 |
"logging_steps": 5,
|
@@ -196,7 +218,7 @@
|
|
196 |
"attributes": {}
|
197 |
}
|
198 |
},
|
199 |
-
"total_flos": 2.
|
200 |
"train_batch_size": 8,
|
201 |
"trial_name": null,
|
202 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.04310230145004656,
|
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,
|
|
|
177 |
"eval_samples_per_second": 10.199,
|
178 |
"eval_steps_per_second": 1.276,
|
179 |
"step": 72
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.03990953837967274,
|
183 |
+
"grad_norm": NaN,
|
184 |
+
"learning_rate": 3.333223252352985e-05,
|
185 |
+
"loss": 0.0,
|
186 |
+
"step": 75
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.042570174271650926,
|
190 |
+
"grad_norm": NaN,
|
191 |
+
"learning_rate": 2.1966991411008938e-05,
|
192 |
+
"loss": 0.0,
|
193 |
+
"step": 80
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.04310230145004656,
|
197 |
+
"eval_loss": NaN,
|
198 |
+
"eval_runtime": 654.9321,
|
199 |
+
"eval_samples_per_second": 10.203,
|
200 |
+
"eval_steps_per_second": 1.276,
|
201 |
+
"step": 81
|
202 |
}
|
203 |
],
|
204 |
"logging_steps": 5,
|
|
|
218 |
"attributes": {}
|
219 |
}
|
220 |
},
|
221 |
+
"total_flos": 2.2891693557468365e+17,
|
222 |
"train_batch_size": 8,
|
223 |
"trial_name": null,
|
224 |
"trial_params": null
|