Training in progress, step 88, 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 sha256:768db4d21385826b525ded38563713ad67afaf060bd313b935d5d55d323538b6
|
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 sha256:1cd2ee98ef0299a10a7e1bd426de675a5958b0827775c524e33f14b14fcebb01
|
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:fd0f16ba53ff18dd96e0c7bcdd0d6d91883558662e2adf70806364bb3a367ccc
|
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 sha256:01a4e7013bdf0cfef44b18348c4082377d680816016af2638e8995bf0bb3c8d9
|
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":
|
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,
|
@@ -277,6 +277,35 @@
|
|
277 |
"eval_samples_per_second": 7.505,
|
278 |
"eval_steps_per_second": 3.766,
|
279 |
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
280 |
}
|
281 |
],
|
282 |
"logging_steps": 3,
|
@@ -296,7 +325,7 @@
|
|
296 |
"attributes": {}
|
297 |
}
|
298 |
},
|
299 |
-
"total_flos":
|
300 |
"train_batch_size": 2,
|
301 |
"trial_name": null,
|
302 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0703154694032686,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 88,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
277 |
"eval_samples_per_second": 7.505,
|
278 |
"eval_steps_per_second": 3.766,
|
279 |
"step": 80
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.9851767388825542,
|
283 |
+
"grad_norm": 0.6385733485221863,
|
284 |
+
"learning_rate": 8.047222744854943e-06,
|
285 |
+
"loss": 1.2547,
|
286 |
+
"step": 81
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.0216647662485747,
|
290 |
+
"grad_norm": 0.5922430157661438,
|
291 |
+
"learning_rate": 3.6037139304146762e-06,
|
292 |
+
"loss": 1.4369,
|
293 |
+
"step": 84
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.0581527936145951,
|
297 |
+
"grad_norm": 0.5931403040885925,
|
298 |
+
"learning_rate": 9.0502382320653e-07,
|
299 |
+
"loss": 1.0506,
|
300 |
+
"step": 87
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 1.0703154694032686,
|
304 |
+
"eval_loss": 1.2342017889022827,
|
305 |
+
"eval_runtime": 36.8829,
|
306 |
+
"eval_samples_per_second": 7.51,
|
307 |
+
"eval_steps_per_second": 3.769,
|
308 |
+
"step": 88
|
309 |
}
|
310 |
],
|
311 |
"logging_steps": 3,
|
|
|
325 |
"attributes": {}
|
326 |
}
|
327 |
},
|
328 |
+
"total_flos": 6.141531047445135e+17,
|
329 |
"train_batch_size": 2,
|
330 |
"trial_name": null,
|
331 |
"trial_params": null
|