Training in progress, step 1500, 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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aab4573c0a3c2d0999e56cb9fe328f031d48d260eb80427c3949bf99f592728
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfbed8a95e8003076d385c5a7d2a54fffd5599ffaf1b5f5b18c6e41662a6be13
|
3 |
size 18902665
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84c42f02805f05255b8fcfb4fa3b8e8ef15f6edcb5701c96a5484d4d1911b2fc
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -203,13 +203,27 @@
|
|
203 |
"eval_samples_per_second": 30.324,
|
204 |
"eval_steps_per_second": 3.794,
|
205 |
"step": 1400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
206 |
}
|
207 |
],
|
208 |
"logging_steps": 100,
|
209 |
"max_steps": 4116,
|
210 |
"num_train_epochs": 3,
|
211 |
"save_steps": 100,
|
212 |
-
"total_flos": 4.
|
213 |
"trial_name": null,
|
214 |
"trial_params": null
|
215 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.293931484222412,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1500",
|
4 |
+
"epoch": 1.092896174863388,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
203 |
"eval_samples_per_second": 30.324,
|
204 |
"eval_steps_per_second": 3.794,
|
205 |
"step": 1400
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.09,
|
209 |
+
"learning_rate": 0.0002,
|
210 |
+
"loss": 2.2619,
|
211 |
+
"step": 1500
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 1.09,
|
215 |
+
"eval_loss": 2.293931484222412,
|
216 |
+
"eval_runtime": 207.4615,
|
217 |
+
"eval_samples_per_second": 30.242,
|
218 |
+
"eval_steps_per_second": 3.784,
|
219 |
+
"step": 1500
|
220 |
}
|
221 |
],
|
222 |
"logging_steps": 100,
|
223 |
"max_steps": 4116,
|
224 |
"num_train_epochs": 3,
|
225 |
"save_steps": 100,
|
226 |
+
"total_flos": 4.384226881972224e+16,
|
227 |
"trial_name": null,
|
228 |
"trial_params": null
|
229 |
}
|