Training in progress, step 50, 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 341314196
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b58078a3a2952f646161894c34305d56d807fba87283b6d29c907f881bad429e
|
3 |
size 341314196
|
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 sha256:41d5ad601748b21a266dee44090f0c2517e7480ff1324ca0d841123be04408ed
|
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:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -192,6 +192,21 @@
|
|
192 |
"eval_samples_per_second": 13.629,
|
193 |
"eval_steps_per_second": 1.704,
|
194 |
"step": 45
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
195 |
}
|
196 |
],
|
197 |
"logging_steps": 3,
|
@@ -206,12 +221,12 @@
|
|
206 |
"should_evaluate": false,
|
207 |
"should_log": false,
|
208 |
"should_save": true,
|
209 |
-
"should_training_stop":
|
210 |
},
|
211 |
"attributes": {}
|
212 |
}
|
213 |
},
|
214 |
-
"total_flos":
|
215 |
"train_batch_size": 8,
|
216 |
"trial_name": null,
|
217 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0033668333249162502,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
192 |
"eval_samples_per_second": 13.629,
|
193 |
"eval_steps_per_second": 1.704,
|
194 |
"step": 45
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.0032321599919196,
|
198 |
+
"grad_norm": NaN,
|
199 |
+
"learning_rate": 6.15582970243117e-07,
|
200 |
+
"loss": 0.0,
|
201 |
+
"step": 48
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.0033668333249162502,
|
205 |
+
"eval_loss": NaN,
|
206 |
+
"eval_runtime": 1835.6612,
|
207 |
+
"eval_samples_per_second": 13.626,
|
208 |
+
"eval_steps_per_second": 1.703,
|
209 |
+
"step": 50
|
210 |
}
|
211 |
],
|
212 |
"logging_steps": 3,
|
|
|
221 |
"should_evaluate": false,
|
222 |
"should_log": false,
|
223 |
"should_save": true,
|
224 |
+
"should_training_stop": true
|
225 |
},
|
226 |
"attributes": {}
|
227 |
}
|
228 |
},
|
229 |
+
"total_flos": 7.693419251603866e+16,
|
230 |
"train_batch_size": 8,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|