Training in progress, step 16, 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 sha256:30068b0b0922b30210f2b35c151ff3844cd2b8f68bc350a3a1bd8e06deaa7e10
|
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:a80ea0d2fcb5de2fb11891e897936e88df521e68f228c6d529d75261583df57e
|
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:ea7d2408b3a422851243030b42dda993dfe2492d0a051609097eef94f3c74fce
|
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,
|
@@ -169,6 +169,28 @@
|
|
169 |
"eval_samples_per_second": 4.187,
|
170 |
"eval_steps_per_second": 4.187,
|
171 |
"step": 14
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
172 |
}
|
173 |
],
|
174 |
"logging_steps": 1,
|
@@ -188,7 +210,7 @@
|
|
188 |
"attributes": {}
|
189 |
}
|
190 |
},
|
191 |
-
"total_flos":
|
192 |
"train_batch_size": 1,
|
193 |
"trial_name": null,
|
194 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00050093534020554,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 16,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
169 |
"eval_samples_per_second": 4.187,
|
170 |
"eval_steps_per_second": 4.187,
|
171 |
"step": 14
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.0004696268814426938,
|
175 |
+
"grad_norm": NaN,
|
176 |
+
"learning_rate": 0.00015000000000000001,
|
177 |
+
"loss": 0.0,
|
178 |
+
"step": 15
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.00050093534020554,
|
182 |
+
"grad_norm": NaN,
|
183 |
+
"learning_rate": 0.00013090169943749476,
|
184 |
+
"loss": 0.0,
|
185 |
+
"step": 16
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.00050093534020554,
|
189 |
+
"eval_loss": NaN,
|
190 |
+
"eval_runtime": 3323.0534,
|
191 |
+
"eval_samples_per_second": 4.047,
|
192 |
+
"eval_steps_per_second": 4.047,
|
193 |
+
"step": 16
|
194 |
}
|
195 |
],
|
196 |
"logging_steps": 1,
|
|
|
210 |
"attributes": {}
|
211 |
}
|
212 |
},
|
213 |
+
"total_flos": 1.1250071978901504e+16,
|
214 |
"train_batch_size": 1,
|
215 |
"trial_name": null,
|
216 |
"trial_params": null
|