Training in progress, step 18, 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 335922386
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3aad4cf4bed4efe12d4cf18d8ebf4121a8a0454f9c8a7b06b2d84c185513a665
|
3 |
size 335922386
|
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:e84fa95b0a9b7043e1894cd756d8a04df512926621e069da3953953ea057c218
|
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 sha256:7f8e3d30c4f47a519421ea0a44735662bdb9869afd75e3f7738f31c9ef193e41
|
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": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -191,6 +191,28 @@
|
|
191 |
"eval_samples_per_second": 4.047,
|
192 |
"eval_steps_per_second": 4.047,
|
193 |
"step": 16
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
194 |
}
|
195 |
],
|
196 |
"logging_steps": 1,
|
@@ -210,7 +232,7 @@
|
|
210 |
"attributes": {}
|
211 |
}
|
212 |
},
|
213 |
-
"total_flos": 1.
|
214 |
"train_batch_size": 1,
|
215 |
"trial_name": null,
|
216 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0005635522577312326,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 18,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
191 |
"eval_samples_per_second": 4.047,
|
192 |
"eval_steps_per_second": 4.047,
|
193 |
"step": 16
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.0005322437989683863,
|
197 |
+
"grad_norm": NaN,
|
198 |
+
"learning_rate": 0.00011045284632676536,
|
199 |
+
"loss": 0.0,
|
200 |
+
"step": 17
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.0005635522577312326,
|
204 |
+
"grad_norm": NaN,
|
205 |
+
"learning_rate": 8.954715367323468e-05,
|
206 |
+
"loss": 0.0,
|
207 |
+
"step": 18
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.0005635522577312326,
|
211 |
+
"eval_loss": NaN,
|
212 |
+
"eval_runtime": 3266.4933,
|
213 |
+
"eval_samples_per_second": 4.117,
|
214 |
+
"eval_steps_per_second": 4.117,
|
215 |
+
"step": 18
|
216 |
}
|
217 |
],
|
218 |
"logging_steps": 1,
|
|
|
232 |
"attributes": {}
|
233 |
}
|
234 |
},
|
235 |
+
"total_flos": 1.2656330976264192e+16,
|
236 |
"train_batch_size": 1,
|
237 |
"trial_name": null,
|
238 |
"trial_params": null
|