Training in progress, step 99, 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 35237104
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea2eb84da3fdbfecc6109c8431d5e3f2f27a4dc7932ef15726ef6b02dfa8d546
|
3 |
size 35237104
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18810036
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:180029b15d0aa3129226a1543622f30dc1e06958e2198d027caa30ec9d729438
|
3 |
size 18810036
|
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 sha256:50d971102200e053e5ee4e90c91d13b967e2459d373d2afdd68fe0eadbca64ff
|
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 sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
|
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,
|
@@ -305,6 +305,35 @@
|
|
305 |
"eval_samples_per_second": 65.207,
|
306 |
"eval_steps_per_second": 8.156,
|
307 |
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
308 |
}
|
309 |
],
|
310 |
"logging_steps": 3,
|
@@ -324,7 +353,7 @@
|
|
324 |
"attributes": {}
|
325 |
}
|
326 |
},
|
327 |
-
"total_flos":
|
328 |
"train_batch_size": 8,
|
329 |
"trial_name": null,
|
330 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.033423362592842676,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 99,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
305 |
"eval_samples_per_second": 65.207,
|
306 |
"eval_steps_per_second": 8.156,
|
307 |
"step": 90
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.03139770425388251,
|
311 |
+
"grad_norm": 2.6511683464050293,
|
312 |
+
"learning_rate": 7.426068431000882e-07,
|
313 |
+
"loss": 2.1854,
|
314 |
+
"step": 93
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.03241053342336259,
|
318 |
+
"grad_norm": 2.4693081378936768,
|
319 |
+
"learning_rate": 2.4329828146074095e-07,
|
320 |
+
"loss": 2.0594,
|
321 |
+
"step": 96
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.033423362592842676,
|
325 |
+
"grad_norm": 2.277552366256714,
|
326 |
+
"learning_rate": 1.522932452260595e-08,
|
327 |
+
"loss": 1.9894,
|
328 |
+
"step": 99
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.033423362592842676,
|
332 |
+
"eval_loss": 2.008247137069702,
|
333 |
+
"eval_runtime": 76.5121,
|
334 |
+
"eval_samples_per_second": 65.205,
|
335 |
+
"eval_steps_per_second": 8.156,
|
336 |
+
"step": 99
|
337 |
}
|
338 |
],
|
339 |
"logging_steps": 3,
|
|
|
353 |
"attributes": {}
|
354 |
}
|
355 |
},
|
356 |
+
"total_flos": 7137447578173440.0,
|
357 |
"train_batch_size": 8,
|
358 |
"trial_name": null,
|
359 |
"trial_params": null
|