Training in progress, step 4900, 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 sha256:6d6bb0b2cec7dc64f0af46afa2b02f194aa462b8988801e2e4745f8fa2534d1b
|
| 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:af7cc39daabd7a9b6cf9547dc9f2e67fcdcaee859f2ffd9a5951bff5ee807e77
|
| 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 sha256:4a760749fd116630cde5751ade399c8fc4db67179112bf0943279a27fabe50d0
|
| 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 sha256:38266f6cb5deecc74eba12934513eb63bf16beecebcaf6118d632bda28a37867
|
| 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": 9.
|
| 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,
|
|
@@ -415,6 +415,13 @@
|
|
| 415 |
"learning_rate": 6.800000000000001e-05,
|
| 416 |
"loss": 1.2519,
|
| 417 |
"step": 4800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 418 |
}
|
| 419 |
],
|
| 420 |
"logging_steps": 100,
|
|
@@ -434,7 +441,7 @@
|
|
| 434 |
"attributes": {}
|
| 435 |
}
|
| 436 |
},
|
| 437 |
-
"total_flos": 7.
|
| 438 |
"train_batch_size": 8,
|
| 439 |
"trial_name": null,
|
| 440 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.798468989220435,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 4900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 415 |
"learning_rate": 6.800000000000001e-05,
|
| 416 |
"loss": 1.2519,
|
| 417 |
"step": 4800
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 9.798468989220435,
|
| 421 |
+
"grad_norm": 0.18754470348358154,
|
| 422 |
+
"learning_rate": 6.733333333333333e-05,
|
| 423 |
+
"loss": 1.2581,
|
| 424 |
+
"step": 4900
|
| 425 |
}
|
| 426 |
],
|
| 427 |
"logging_steps": 100,
|
|
|
|
| 441 |
"attributes": {}
|
| 442 |
}
|
| 443 |
},
|
| 444 |
+
"total_flos": 7.64759117638769e+18,
|
| 445 |
"train_batch_size": 8,
|
| 446 |
"trial_name": null,
|
| 447 |
"trial_params": null
|