Training in progress, step 36, 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 180385008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9818f655e1059b45078cc4ddfe3d5e4eeab2975b6c25126258bafb955f5539c7
|
3 |
size 180385008
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 91850362
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21c0c48c561db65eceed91ed55aa8db2b299cfe00e4a016c83079c5fd9af7109
|
3 |
size 91850362
|
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 sha256:6d1cd64c191938a7d7b164994e250edb51d9a674767ad279d977dab6b9b2f77d
|
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 sha256:28651c349f447d90467a1ab072123a42ef3fcd558c7e8a7b853a87ba29324613
|
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":
|
5 |
"eval_steps": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -180,6 +180,21 @@
|
|
180 |
"eval_samples_per_second": 47.827,
|
181 |
"eval_steps_per_second": 7.174,
|
182 |
"step": 33
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
183 |
}
|
184 |
],
|
185 |
"logging_steps": 3,
|
@@ -194,12 +209,12 @@
|
|
194 |
"should_evaluate": false,
|
195 |
"should_log": false,
|
196 |
"should_save": true,
|
197 |
-
"should_training_stop":
|
198 |
},
|
199 |
"attributes": {}
|
200 |
}
|
201 |
},
|
202 |
-
"total_flos":
|
203 |
"train_batch_size": 8,
|
204 |
"trial_name": null,
|
205 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0638297872340425,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 36,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
180 |
"eval_samples_per_second": 47.827,
|
181 |
"eval_steps_per_second": 7.174,
|
182 |
"step": 33
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 3.0638297872340425,
|
186 |
+
"grad_norm": 2.7310924530029297,
|
187 |
+
"learning_rate": 0.0,
|
188 |
+
"loss": 2.3388,
|
189 |
+
"step": 36
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 3.0638297872340425,
|
193 |
+
"eval_loss": 2.7303249835968018,
|
194 |
+
"eval_runtime": 0.4199,
|
195 |
+
"eval_samples_per_second": 47.631,
|
196 |
+
"eval_steps_per_second": 7.145,
|
197 |
+
"step": 36
|
198 |
}
|
199 |
],
|
200 |
"logging_steps": 3,
|
|
|
209 |
"should_evaluate": false,
|
210 |
"should_log": false,
|
211 |
"should_save": true,
|
212 |
+
"should_training_stop": true
|
213 |
},
|
214 |
"attributes": {}
|
215 |
}
|
216 |
},
|
217 |
+
"total_flos": 7206952438333440.0,
|
218 |
"train_batch_size": 8,
|
219 |
"trial_name": null,
|
220 |
"trial_params": null
|