Training in progress, step 56, 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 97728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e99d093626ee59249ef6a651400719dc92cda3d23205108e8c0ed1d1f467de95
|
3 |
size 97728
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 212298
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f441a5bbf6bd228867549861adab261f2f188ce88f7c3fa4b87682af7a8e6bf0
|
3 |
size 212298
|
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:c2ccd39fda0bf0ecc3227ac1a7a11b99683295c5148b14a2c9b0f8e73bbf6887
|
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 sha256:54fd3d743640bd98861785afa48759ae85e753ebdc3bb34f138e5c40ed09d555
|
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": 1.
|
5 |
"eval_steps": 8,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -175,6 +175,28 @@
|
|
175 |
"eval_samples_per_second": 134.448,
|
176 |
"eval_steps_per_second": 67.917,
|
177 |
"step": 48
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
178 |
}
|
179 |
],
|
180 |
"logging_steps": 3,
|
@@ -194,7 +216,7 @@
|
|
194 |
"attributes": {}
|
195 |
}
|
196 |
},
|
197 |
-
"total_flos":
|
198 |
"train_batch_size": 2,
|
199 |
"trial_name": null,
|
200 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9770240700218817,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 56,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
175 |
"eval_samples_per_second": 134.448,
|
176 |
"eval_steps_per_second": 67.917,
|
177 |
"step": 48
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.8019693654266957,
|
181 |
+
"grad_norm": 0.11578352749347687,
|
182 |
+
"learning_rate": 0.00010950560433041826,
|
183 |
+
"loss": 10.223,
|
184 |
+
"step": 51
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.9070021881838075,
|
188 |
+
"grad_norm": 0.10895143449306488,
|
189 |
+
"learning_rate": 9.524180841762577e-05,
|
190 |
+
"loss": 10.258,
|
191 |
+
"step": 54
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.9770240700218817,
|
195 |
+
"eval_loss": 10.293498039245605,
|
196 |
+
"eval_runtime": 0.719,
|
197 |
+
"eval_samples_per_second": 134.919,
|
198 |
+
"eval_steps_per_second": 68.155,
|
199 |
+
"step": 56
|
200 |
}
|
201 |
],
|
202 |
"logging_steps": 3,
|
|
|
216 |
"attributes": {}
|
217 |
}
|
218 |
},
|
219 |
+
"total_flos": 24030303485952.0,
|
220 |
"train_batch_size": 2,
|
221 |
"trial_name": null,
|
222 |
"trial_params": null
|