Training in progress, step 192, 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 3380768360
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87f6f5e2ebebe7cbd36c7fc47902b762d5204ac5267047a39ffe3bae1f31820b
|
3 |
size 3380768360
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1757899449
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3c5065690d7c3ac23c095dccfa8c8f644a2710e0edbe735a2a8dc943a9da737
|
3 |
size 1757899449
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1465
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:378cb8caa1753a27e13f72b6f9313442152b34dacda281ba328c9e010c1b29ab
|
3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
@@ -2,9 +2,9 @@
|
|
2 |
"best_global_step": null,
|
3 |
"best_metric": null,
|
4 |
"best_model_checkpoint": null,
|
5 |
-
"epoch":
|
6 |
"eval_steps": 30,
|
7 |
-
"global_step":
|
8 |
"is_hyper_param_search": false,
|
9 |
"is_local_process_zero": true,
|
10 |
"is_world_process_zero": true,
|
@@ -315,6 +315,20 @@
|
|
315 |
"eval_samples_per_second": 0.291,
|
316 |
"eval_steps_per_second": 0.073,
|
317 |
"step": 180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
318 |
}
|
319 |
],
|
320 |
"logging_steps": 5,
|
@@ -329,12 +343,12 @@
|
|
329 |
"should_evaluate": false,
|
330 |
"should_log": false,
|
331 |
"should_save": true,
|
332 |
-
"should_training_stop":
|
333 |
},
|
334 |
"attributes": {}
|
335 |
}
|
336 |
},
|
337 |
-
"total_flos": 1.
|
338 |
"train_batch_size": 8,
|
339 |
"trial_name": null,
|
340 |
"trial_params": null
|
|
|
2 |
"best_global_step": null,
|
3 |
"best_metric": null,
|
4 |
"best_model_checkpoint": null,
|
5 |
+
"epoch": 2.0,
|
6 |
"eval_steps": 30,
|
7 |
+
"global_step": 192,
|
8 |
"is_hyper_param_search": false,
|
9 |
"is_local_process_zero": true,
|
10 |
"is_world_process_zero": true,
|
|
|
315 |
"eval_samples_per_second": 0.291,
|
316 |
"eval_steps_per_second": 0.073,
|
317 |
"step": 180
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.9303135888501743,
|
321 |
+
"grad_norm": 0.10959440469741821,
|
322 |
+
"learning_rate": 4.55756592088058e-07,
|
323 |
+
"loss": 0.2618,
|
324 |
+
"step": 185
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 1.9825783972125435,
|
328 |
+
"grad_norm": 0.07039328664541245,
|
329 |
+
"learning_rate": 6.417464144736208e-08,
|
330 |
+
"loss": 0.2559,
|
331 |
+
"step": 190
|
332 |
}
|
333 |
],
|
334 |
"logging_steps": 5,
|
|
|
343 |
"should_evaluate": false,
|
344 |
"should_log": false,
|
345 |
"should_save": true,
|
346 |
+
"should_training_stop": true
|
347 |
},
|
348 |
"attributes": {}
|
349 |
}
|
350 |
},
|
351 |
+
"total_flos": 1.2340088273817969e+18,
|
352 |
"train_batch_size": 8,
|
353 |
"trial_name": null,
|
354 |
"trial_params": null
|