Training in progress, step 30, 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 97307544
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7c25e36ef1bea88e955b04a392995659ce2efa2958e9a824de856926f2f78b2
|
3 |
size 97307544
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 49846260
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc69a4cb3de67ebaa3a95161b888f3e6a62143841950ec7d93681c428ce896bf
|
3 |
size 49846260
|
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 sha256:5e8303210a87e6366e53f9d2ad1dc5984114aa017ddbff7d118553d8efe51202
|
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 sha256:4a73e1ff9beffc13aa54f4adf4df9ed4ad8819cc503c53ddfd100ef74e91d520
|
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": 386,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -190,6 +190,41 @@
|
|
190 |
"learning_rate": 5e-05,
|
191 |
"loss": 1.4606,
|
192 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
193 |
}
|
194 |
],
|
195 |
"logging_steps": 1,
|
@@ -209,7 +244,7 @@
|
|
209 |
"attributes": {}
|
210 |
}
|
211 |
},
|
212 |
-
"total_flos":
|
213 |
"train_batch_size": 4,
|
214 |
"trial_name": null,
|
215 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.038822387576835975,
|
5 |
"eval_steps": 386,
|
6 |
+
"global_step": 30,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
190 |
"learning_rate": 5e-05,
|
191 |
"loss": 1.4606,
|
192 |
"step": 25
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.033646069233257844,
|
196 |
+
"grad_norm": 1.5480064153671265,
|
197 |
+
"learning_rate": 5.2000000000000004e-05,
|
198 |
+
"loss": 1.5027,
|
199 |
+
"step": 26
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.034940148819152375,
|
203 |
+
"grad_norm": 1.6736445426940918,
|
204 |
+
"learning_rate": 5.4000000000000005e-05,
|
205 |
+
"loss": 1.2426,
|
206 |
+
"step": 27
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.03623422840504691,
|
210 |
+
"grad_norm": 1.7392551898956299,
|
211 |
+
"learning_rate": 5.6000000000000006e-05,
|
212 |
+
"loss": 1.4703,
|
213 |
+
"step": 28
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.037528307990941444,
|
217 |
+
"grad_norm": 1.6173359155654907,
|
218 |
+
"learning_rate": 5.8e-05,
|
219 |
+
"loss": 1.4546,
|
220 |
+
"step": 29
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.038822387576835975,
|
224 |
+
"grad_norm": 1.3955802917480469,
|
225 |
+
"learning_rate": 6e-05,
|
226 |
+
"loss": 1.3808,
|
227 |
+
"step": 30
|
228 |
}
|
229 |
],
|
230 |
"logging_steps": 1,
|
|
|
244 |
"attributes": {}
|
245 |
}
|
246 |
},
|
247 |
+
"total_flos": 3.353811515080704e+16,
|
248 |
"train_batch_size": 4,
|
249 |
"trial_name": null,
|
250 |
"trial_params": null
|