Training in progress, step 50, 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 191968
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a04257ba48c65bae1ce9e5e4ad7ea432f8f9ee7c122ff380ff01fdd1dca06c9d
|
3 |
size 191968
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 253144
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97eaf88d27b9b3477d4af630a383127cd5eb081cdd68cb9e9ba392e91fc26b0f
|
3 |
size 253144
|
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:edb5c36704e3b6ab500ab7d15a735dfa01cbe4172126713b690f4768758ad502
|
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": 456.26,
|
193 |
"eval_steps_per_second": 57.033,
|
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": 0.0350938761186173,
|
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": 456.26,
|
193 |
"eval_steps_per_second": 57.033,
|
194 |
"step": 45
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.033690121073872606,
|
198 |
+
"grad_norm": 0.2071637362241745,
|
199 |
+
"learning_rate": 6.15582970243117e-07,
|
200 |
+
"loss": 10.3603,
|
201 |
+
"step": 48
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.0350938761186173,
|
205 |
+
"eval_loss": 10.35882568359375,
|
206 |
+
"eval_runtime": 5.2405,
|
207 |
+
"eval_samples_per_second": 457.969,
|
208 |
+
"eval_steps_per_second": 57.246,
|
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": 5828522016768.0,
|
230 |
"train_batch_size": 8,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|