Training in progress, step 20, 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 40036040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac387f4394cdc5049c943f63366b756f67480945f4fbc1392f65d94c92bd45c7
|
3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20814996
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cae910e682fb0da26584caaf627ed14a4eafa8a54a8abaac8498075f51d0ad6c
|
3 |
size 20814996
|
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:f1132930fd0ce88e1675be111a60ba3f2297312d1bafabf3a0aaf192acb36070
|
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 sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
|
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": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -213,6 +213,28 @@
|
|
213 |
"eval_samples_per_second": 3.757,
|
214 |
"eval_steps_per_second": 3.757,
|
215 |
"step": 18
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
216 |
}
|
217 |
],
|
218 |
"logging_steps": 1,
|
@@ -227,12 +249,12 @@
|
|
227 |
"should_evaluate": false,
|
228 |
"should_log": false,
|
229 |
"should_save": true,
|
230 |
-
"should_training_stop":
|
231 |
},
|
232 |
"attributes": {}
|
233 |
}
|
234 |
},
|
235 |
-
"total_flos":
|
236 |
"train_batch_size": 1,
|
237 |
"trial_name": null,
|
238 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.029665337906739593,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
213 |
"eval_samples_per_second": 3.757,
|
214 |
"eval_steps_per_second": 3.757,
|
215 |
"step": 18
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.028182071011402614,
|
219 |
+
"grad_norm": 34.15607452392578,
|
220 |
+
"learning_rate": 4.8943483704846475e-06,
|
221 |
+
"loss": 6.5006,
|
222 |
+
"step": 19
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 0.029665337906739593,
|
226 |
+
"grad_norm": 30.67697525024414,
|
227 |
+
"learning_rate": 0.0,
|
228 |
+
"loss": 5.968,
|
229 |
+
"step": 20
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 0.029665337906739593,
|
233 |
+
"eval_loss": 0.3306680917739868,
|
234 |
+
"eval_runtime": 151.2525,
|
235 |
+
"eval_samples_per_second": 3.755,
|
236 |
+
"eval_steps_per_second": 3.755,
|
237 |
+
"step": 20
|
238 |
}
|
239 |
],
|
240 |
"logging_steps": 1,
|
|
|
249 |
"should_evaluate": false,
|
250 |
"should_log": false,
|
251 |
"should_save": true,
|
252 |
+
"should_training_stop": true
|
253 |
},
|
254 |
"attributes": {}
|
255 |
}
|
256 |
},
|
257 |
+
"total_flos": 3252586115235840.0,
|
258 |
"train_batch_size": 1,
|
259 |
"trial_name": null,
|
260 |
"trial_params": null
|