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 50624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb87d0790dd07e691f04066b63b75e48ac0cdcc40f6a5c544a6d40d3c2584c86
|
3 |
size 50624
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 111142
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f3d3ae5ca90940b1211d42fffd7c61fdb8c365d6a4520479043a802d56ae9a2
|
3 |
size 111142
|
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 sha256:2fc879f5666d75c721d421ad7c5c129fa846443e68d782ad1d52ba9244ab8801
|
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": 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": 388.34,
|
306 |
"eval_steps_per_second": 48.564,
|
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": 0.07240811848601207,
|
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": 388.34,
|
306 |
"eval_steps_per_second": 48.564,
|
307 |
"step": 90
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.06801974766867801,
|
311 |
+
"grad_norm": 0.05691976100206375,
|
312 |
+
"learning_rate": 1.4852136862001764e-06,
|
313 |
+
"loss": 10.3571,
|
314 |
+
"step": 93
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.07021393307734504,
|
318 |
+
"grad_norm": 0.06406902521848679,
|
319 |
+
"learning_rate": 4.865965629214819e-07,
|
320 |
+
"loss": 10.3567,
|
321 |
+
"step": 96
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.07240811848601207,
|
325 |
+
"grad_norm": 0.05502088740468025,
|
326 |
+
"learning_rate": 3.04586490452119e-08,
|
327 |
+
"loss": 10.354,
|
328 |
+
"step": 99
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.07240811848601207,
|
332 |
+
"eval_loss": 10.355634689331055,
|
333 |
+
"eval_runtime": 5.8887,
|
334 |
+
"eval_samples_per_second": 391.09,
|
335 |
+
"eval_steps_per_second": 48.908,
|
336 |
+
"step": 99
|
337 |
}
|
338 |
],
|
339 |
"logging_steps": 3,
|
|
|
353 |
"attributes": {}
|
354 |
}
|
355 |
},
|
356 |
+
"total_flos": 14801592385536.0,
|
357 |
"train_batch_size": 8,
|
358 |
"trial_name": null,
|
359 |
"trial_params": null
|