Training in progress, step 4100, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2d0d2ee106556697ee5bb319a5c66f7da60fdefc5b2294aedef91b2d4c90622
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93fc1a43b3c79274a76d45363da8217224dd9ed74fe13aaac3588c46f683bda9
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dfbdf22163bd5ea80a653a007f051d613da79be7b41af651245f6aba2f9024c
|
| 3 |
size 15006
|
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 sha256:7c96e4de7567585305fbb3c5ce22247da92426eac792079c558bbf8ec5b548f2
|
| 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":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -351,6 +351,13 @@
|
|
| 351 |
"eval_samples_per_second": 19.85,
|
| 352 |
"eval_steps_per_second": 2.482,
|
| 353 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 354 |
}
|
| 355 |
],
|
| 356 |
"logging_steps": 100,
|
|
@@ -370,7 +377,7 @@
|
|
| 370 |
"attributes": {}
|
| 371 |
}
|
| 372 |
},
|
| 373 |
-
"total_flos": 6.
|
| 374 |
"train_batch_size": 8,
|
| 375 |
"trial_name": null,
|
| 376 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.198718950164038,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 4100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 351 |
"eval_samples_per_second": 19.85,
|
| 352 |
"eval_steps_per_second": 2.482,
|
| 353 |
"step": 4000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 8.198718950164038,
|
| 357 |
+
"grad_norm": 0.18043838441371918,
|
| 358 |
+
"learning_rate": 7.266666666666667e-05,
|
| 359 |
+
"loss": 1.2639,
|
| 360 |
+
"step": 4100
|
| 361 |
}
|
| 362 |
],
|
| 363 |
"logging_steps": 100,
|
|
|
|
| 377 |
"attributes": {}
|
| 378 |
}
|
| 379 |
},
|
| 380 |
+
"total_flos": 6.399000563752632e+18,
|
| 381 |
"train_batch_size": 8,
|
| 382 |
"trial_name": null,
|
| 383 |
"trial_params": null
|