Training in progress, step 81, 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 335604696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:160429ba22b04fdbad7986d3afa68476d7c662fd7a918ab53b902b2e11e43a96
|
3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 671466706
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55fae3faf0e97152f1535d44bb7cd537b1b90ea36c196f3303a58e63422b4a5d
|
3 |
size 671466706
|
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 sha256:9db0a36de4bb96902a948897c32d08fcc8f52ec7148136028a54d1ab041188bd
|
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 sha256:4967fab956f007beafd6b8bc5c5dee4d86950ea055e4ab46c9a7cdc66a69112d
|
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": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -247,6 +247,35 @@
|
|
247 |
"eval_samples_per_second": 8.989,
|
248 |
"eval_steps_per_second": 4.494,
|
249 |
"step": 72
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
250 |
}
|
251 |
],
|
252 |
"logging_steps": 3,
|
@@ -266,7 +295,7 @@
|
|
266 |
"attributes": {}
|
267 |
}
|
268 |
},
|
269 |
-
"total_flos": 4.
|
270 |
"train_batch_size": 2,
|
271 |
"trial_name": null,
|
272 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.011352786075317325,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 81,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
247 |
"eval_samples_per_second": 8.989,
|
248 |
"eval_steps_per_second": 4.494,
|
249 |
"step": 72
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.010511838958627154,
|
253 |
+
"grad_norm": 0.9212751984596252,
|
254 |
+
"learning_rate": 4.444297669803981e-05,
|
255 |
+
"loss": 1.3108,
|
256 |
+
"step": 75
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.01093231251697224,
|
260 |
+
"grad_norm": 0.8381961584091187,
|
261 |
+
"learning_rate": 3.5055195166981645e-05,
|
262 |
+
"loss": 1.3383,
|
263 |
+
"step": 78
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.011352786075317325,
|
267 |
+
"grad_norm": 0.8427872657775879,
|
268 |
+
"learning_rate": 2.6567749056431467e-05,
|
269 |
+
"loss": 1.3653,
|
270 |
+
"step": 81
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.011352786075317325,
|
274 |
+
"eval_loss": 1.324036717414856,
|
275 |
+
"eval_runtime": 2673.9575,
|
276 |
+
"eval_samples_per_second": 8.988,
|
277 |
+
"eval_steps_per_second": 4.494,
|
278 |
+
"step": 81
|
279 |
}
|
280 |
],
|
281 |
"logging_steps": 3,
|
|
|
295 |
"attributes": {}
|
296 |
}
|
297 |
},
|
298 |
+
"total_flos": 4.83414773002666e+17,
|
299 |
"train_batch_size": 2,
|
300 |
"trial_name": null,
|
301 |
"trial_params": null
|