Training in progress, step 5800, 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:acec6603804e5a2f0bec297d1d770d35519ef72741151abe5b5bff745c3fe294
|
| 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 sha256:41d63612197149c4816d263640cf586f3286832cb12cc93fb250dce62b89e430
|
| 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:daccf081cb23259d16827272caeca5846785397dc7686b421ede20374cf93802
|
| 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 sha256:722511f8f2b00af89e38aa14648bcef3f994f331197ea37cab0026a523fec0b9
|
| 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": 11.
|
| 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,
|
|
@@ -494,6 +494,13 @@
|
|
| 494 |
"learning_rate": 6.2e-05,
|
| 495 |
"loss": 1.2485,
|
| 496 |
"step": 5700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 497 |
}
|
| 498 |
],
|
| 499 |
"logging_steps": 100,
|
|
@@ -513,7 +520,7 @@
|
|
| 513 |
"attributes": {}
|
| 514 |
}
|
| 515 |
},
|
| 516 |
-
"total_flos":
|
| 517 |
"train_batch_size": 8,
|
| 518 |
"trial_name": null,
|
| 519 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 11.598187783158881,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 5800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 494 |
"learning_rate": 6.2e-05,
|
| 495 |
"loss": 1.2485,
|
| 496 |
"step": 5700
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 11.598187783158881,
|
| 500 |
+
"grad_norm": 0.20710080862045288,
|
| 501 |
+
"learning_rate": 6.133333333333334e-05,
|
| 502 |
+
"loss": 1.2441,
|
| 503 |
+
"step": 5800
|
| 504 |
}
|
| 505 |
],
|
| 506 |
"logging_steps": 100,
|
|
|
|
| 520 |
"attributes": {}
|
| 521 |
}
|
| 522 |
},
|
| 523 |
+
"total_flos": 9.05224760334064e+18,
|
| 524 |
"train_batch_size": 8,
|
| 525 |
"trial_name": null,
|
| 526 |
"trial_params": null
|