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 2373352
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5a696e0e329b408e34b3e0e49a12540360b34e90e1cca73235f44fa28ee9b1f
|
3 |
size 2373352
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4830714
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ab4d99c29bd607a5557d149dbd7610c0e221e3fd623289aeabe89368e8c4076
|
3 |
size 4830714
|
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 sha256:17c043cdd871b6398c8be79e7333b68b3d681731bc55d24ea9f6ec3f3c6dabfd
|
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": 134.166,
|
193 |
"eval_steps_per_second": 16.812,
|
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": 0.029476787030213707,
|
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": 134.166,
|
193 |
"eval_steps_per_second": 16.812,
|
194 |
"step": 45
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.02829771554900516,
|
198 |
+
"grad_norm": 0.27372610569000244,
|
199 |
+
"learning_rate": 6.15582970243117e-07,
|
200 |
+
"loss": 11.8696,
|
201 |
+
"step": 48
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.029476787030213707,
|
205 |
+
"eval_loss": 11.87025260925293,
|
206 |
+
"eval_runtime": 21.3042,
|
207 |
+
"eval_samples_per_second": 134.105,
|
208 |
+
"eval_steps_per_second": 16.804,
|
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": 55089561600000.0,
|
230 |
"train_batch_size": 8,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|