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 121155320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a74979803968791bcb9814ef083e4a1c424717889d2a2a288066d8e0f756d90a
|
3 |
size 121155320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 61896852
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:557d9787dbd12e67252aaeb47a72c4d9828515e26ba7442922b3dea6437d69f8
|
3 |
size 61896852
|
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 sha256:57978914a5378a38dc2ef208f398a1e86dd5ab917242be26cd4b3d1e2f9e2e57
|
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 sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
|
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": 1.
|
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": 64.019,
|
306 |
"eval_steps_per_second": 8.442,
|
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": 1.8465116279069766,
|
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": 64.019,
|
306 |
"eval_steps_per_second": 8.442,
|
307 |
"step": 90
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 1.7348837209302326,
|
311 |
+
"grad_norm": 2.3214516639709473,
|
312 |
+
"learning_rate": 1.4852136862001764e-06,
|
313 |
+
"loss": 3.6552,
|
314 |
+
"step": 93
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.7906976744186047,
|
318 |
+
"grad_norm": 2.328660726547241,
|
319 |
+
"learning_rate": 4.865965629214819e-07,
|
320 |
+
"loss": 3.671,
|
321 |
+
"step": 96
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.8465116279069766,
|
325 |
+
"grad_norm": 2.30373477935791,
|
326 |
+
"learning_rate": 3.04586490452119e-08,
|
327 |
+
"loss": 3.5648,
|
328 |
+
"step": 99
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.8465116279069766,
|
332 |
+
"eval_loss": 3.7725934982299805,
|
333 |
+
"eval_runtime": 1.4221,
|
334 |
+
"eval_samples_per_second": 63.991,
|
335 |
+
"eval_steps_per_second": 8.438,
|
336 |
+
"step": 99
|
337 |
}
|
338 |
],
|
339 |
"logging_steps": 3,
|
|
|
353 |
"attributes": {}
|
354 |
}
|
355 |
},
|
356 |
+
"total_flos": 6592188603432960.0,
|
357 |
"train_batch_size": 8,
|
358 |
"trial_name": null,
|
359 |
"trial_params": null
|