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 335604696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c6900fd766177592ad05c0fb77157c4cff53902e9b7f003a7509208d22dab4c
|
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:b281f3decd631695e13c505e5fb203021190d0e0c18bee430c11eea836f4b599
|
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 sha256:5a00629bf05750b086240b2e21c50e8524f7626a411f0470f03ec27820c2d92b
|
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 sha256:7041fa0be7432c15ac468c1425bc3b5d595e4b5b769cfa7728743ab80ef12291
|
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": 8.968,
|
306 |
"eval_steps_per_second": 4.509,
|
307 |
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
308 |
}
|
309 |
],
|
310 |
"logging_steps": 3,
|
@@ -324,7 +353,7 @@
|
|
324 |
"attributes": {}
|
325 |
}
|
326 |
},
|
327 |
-
"total_flos": 5.
|
328 |
"train_batch_size": 2,
|
329 |
"trial_name": null,
|
330 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.89247311827957,
|
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": 8.968,
|
306 |
"eval_steps_per_second": 4.509,
|
307 |
"step": 90
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 1.7777777777777777,
|
311 |
+
"grad_norm": 1.6190431118011475,
|
312 |
+
"learning_rate": 3.7544763546352834e-06,
|
313 |
+
"loss": 1.2655,
|
314 |
+
"step": 93
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.8351254480286738,
|
318 |
+
"grad_norm": 1.7480906248092651,
|
319 |
+
"learning_rate": 1.231165940486234e-06,
|
320 |
+
"loss": 1.374,
|
321 |
+
"step": 96
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.89247311827957,
|
325 |
+
"grad_norm": 1.9425756931304932,
|
326 |
+
"learning_rate": 7.709637592770991e-08,
|
327 |
+
"loss": 1.2715,
|
328 |
+
"step": 99
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.89247311827957,
|
332 |
+
"eval_loss": 1.8266067504882812,
|
333 |
+
"eval_runtime": 19.7351,
|
334 |
+
"eval_samples_per_second": 8.969,
|
335 |
+
"eval_steps_per_second": 4.51,
|
336 |
+
"step": 99
|
337 |
}
|
338 |
],
|
339 |
"logging_steps": 3,
|
|
|
353 |
"attributes": {}
|
354 |
}
|
355 |
},
|
356 |
+
"total_flos": 5.908402781143695e+17,
|
357 |
"train_batch_size": 2,
|
358 |
"trial_name": null,
|
359 |
"trial_params": null
|