Training in progress, step 22, 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 27024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:994a6c1ec3dcc1a5db23088000de14b21b89c2b42f8184f6c205cb6e0fb92541
|
3 |
size 27024
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 63974
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:966b5efc886d7597a65c3d0119ab91d4beaf99e8e9d77cfe0e8c341359f42811
|
3 |
size 63974
|
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 sha256:8ed09bfe734c9814025ec917462737624591264937583c93cb36af9436c63d48
|
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 sha256:1565387b96ec5f770ad7b2f4817988cb2fc09f94ceb911096ae3c468010baf3d
|
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": 6,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -165,6 +165,34 @@
|
|
165 |
"eval_samples_per_second": 464.759,
|
166 |
"eval_steps_per_second": 232.379,
|
167 |
"step": 18
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
168 |
}
|
169 |
],
|
170 |
"logging_steps": 1,
|
@@ -179,12 +207,12 @@
|
|
179 |
"should_evaluate": false,
|
180 |
"should_log": false,
|
181 |
"should_save": true,
|
182 |
-
"should_training_stop":
|
183 |
},
|
184 |
"attributes": {}
|
185 |
}
|
186 |
},
|
187 |
-
"total_flos":
|
188 |
"train_batch_size": 2,
|
189 |
"trial_name": null,
|
190 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0445103857566767,
|
5 |
"eval_steps": 6,
|
6 |
+
"global_step": 22,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
165 |
"eval_samples_per_second": 464.759,
|
166 |
"eval_steps_per_second": 232.379,
|
167 |
"step": 18
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.9020771513353115,
|
171 |
+
"grad_norm": 0.10974813997745514,
|
172 |
+
"learning_rate": 1.4644660940672627e-05,
|
173 |
+
"loss": 10.3813,
|
174 |
+
"step": 19
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.9495548961424333,
|
178 |
+
"grad_norm": 0.11267790198326111,
|
179 |
+
"learning_rate": 6.698729810778065e-06,
|
180 |
+
"loss": 10.3783,
|
181 |
+
"step": 20
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.9970326409495549,
|
185 |
+
"grad_norm": 0.10685980319976807,
|
186 |
+
"learning_rate": 1.70370868554659e-06,
|
187 |
+
"loss": 10.3776,
|
188 |
+
"step": 21
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.0445103857566767,
|
192 |
+
"grad_norm": 0.26596400141716003,
|
193 |
+
"learning_rate": 0.0,
|
194 |
+
"loss": 20.1393,
|
195 |
+
"step": 22
|
196 |
}
|
197 |
],
|
198 |
"logging_steps": 1,
|
|
|
207 |
"should_evaluate": false,
|
208 |
"should_log": false,
|
209 |
"should_save": true,
|
210 |
+
"should_training_stop": true
|
211 |
},
|
212 |
"attributes": {}
|
213 |
}
|
214 |
},
|
215 |
+
"total_flos": 1765068963840.0,
|
216 |
"train_batch_size": 2,
|
217 |
"trial_name": null,
|
218 |
"trial_params": null
|