Training in progress, step 63, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e51e563e316add60af860ed4c649cf9be7db912fe546a36df80026a14206ea1
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37965300
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7a4f2b5e058d8a303d88189b19a825022f6bfca9ed038a8724e38bcaa4757e3
|
3 |
size 37965300
|
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 sha256:325ac916028333cff48d1655ec49518bb3508c9da4047901b750b21ad73910fb
|
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 sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
|
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": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -189,6 +189,35 @@
|
|
189 |
"eval_samples_per_second": 36.237,
|
190 |
"eval_steps_per_second": 4.745,
|
191 |
"step": 54
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 3,
|
@@ -208,7 +237,7 @@
|
|
208 |
"attributes": {}
|
209 |
}
|
210 |
},
|
211 |
-
"total_flos": 1.
|
212 |
"train_batch_size": 8,
|
213 |
"trial_name": null,
|
214 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.2727272727272727,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 63,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
189 |
"eval_samples_per_second": 36.237,
|
190 |
"eval_steps_per_second": 4.745,
|
191 |
"step": 54
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.1515151515151516,
|
195 |
+
"grad_norm": 0.9968785047531128,
|
196 |
+
"learning_rate": 2.3256088156396868e-05,
|
197 |
+
"loss": 2.2676,
|
198 |
+
"step": 57
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.2121212121212122,
|
202 |
+
"grad_norm": 1.0607465505599976,
|
203 |
+
"learning_rate": 2.0658795558326743e-05,
|
204 |
+
"loss": 2.2769,
|
205 |
+
"step": 60
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.2727272727272727,
|
209 |
+
"grad_norm": 1.071947693824768,
|
210 |
+
"learning_rate": 1.8109066104575023e-05,
|
211 |
+
"loss": 2.1025,
|
212 |
+
"step": 63
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.2727272727272727,
|
216 |
+
"eval_loss": 2.20631742477417,
|
217 |
+
"eval_runtime": 2.3202,
|
218 |
+
"eval_samples_per_second": 36.203,
|
219 |
+
"eval_steps_per_second": 4.741,
|
220 |
+
"step": 63
|
221 |
}
|
222 |
],
|
223 |
"logging_steps": 3,
|
|
|
237 |
"attributes": {}
|
238 |
}
|
239 |
},
|
240 |
+
"total_flos": 1.645082316374016e+16,
|
241 |
"train_batch_size": 8,
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|