Training in progress, step 24, 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 sha256:7218447982eff110f849b470233fc4a6d276fed4f1c7ddac27d3905dc8dc40cf
|
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 70922
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc0b81dc68d12bd72222a18ddd1d7ff6e0c3c13f2afdc5364d487a263591e3bb
|
3 |
size 70922
|
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:ab594e810d8ab32046a6e307046228ac632e78669c4e55927f43fe5185a83078
|
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 sha256:9be43866b7a112efbf8125d7bbc11610819a4fb8c7f205bdfffb33dc32734ab8
|
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": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -218,6 +218,35 @@
|
|
218 |
"eval_samples_per_second": 135.217,
|
219 |
"eval_steps_per_second": 135.217,
|
220 |
"step": 21
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
221 |
}
|
222 |
],
|
223 |
"logging_steps": 1,
|
@@ -237,7 +266,7 @@
|
|
237 |
"attributes": {}
|
238 |
}
|
239 |
},
|
240 |
-
"total_flos":
|
241 |
"train_batch_size": 1,
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0017012227538543328,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 24,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
218 |
"eval_samples_per_second": 135.217,
|
219 |
"eval_steps_per_second": 135.217,
|
220 |
"step": 21
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.0015594541910331384,
|
224 |
+
"grad_norm": 0.11468103528022766,
|
225 |
+
"learning_rate": 1.9098300562505266e-05,
|
226 |
+
"loss": 10.3818,
|
227 |
+
"step": 22
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.0016303384724437357,
|
231 |
+
"grad_norm": 0.10616473853588104,
|
232 |
+
"learning_rate": 8.645454235739903e-06,
|
233 |
+
"loss": 10.3837,
|
234 |
+
"step": 23
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.0017012227538543328,
|
238 |
+
"grad_norm": 0.10667341947555542,
|
239 |
+
"learning_rate": 2.1852399266194314e-06,
|
240 |
+
"loss": 10.3874,
|
241 |
+
"step": 24
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.0017012227538543328,
|
245 |
+
"eval_loss": 10.382101058959961,
|
246 |
+
"eval_runtime": 23.3378,
|
247 |
+
"eval_samples_per_second": 127.262,
|
248 |
+
"eval_steps_per_second": 127.262,
|
249 |
+
"step": 24
|
250 |
}
|
251 |
],
|
252 |
"logging_steps": 1,
|
|
|
266 |
"attributes": {}
|
267 |
}
|
268 |
},
|
269 |
+
"total_flos": 620683591680.0,
|
270 |
"train_batch_size": 1,
|
271 |
"trial_name": null,
|
272 |
"trial_params": null
|