Training in progress, step 400, 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 sha256:850a0780811b7e944d82012ca6c61a0f12d4f19e5e11a3d768ff77378417df3e
|
| 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 sha256:7b4b307af65eb907a3afe1e2c916d795d29627b628955b23b72bdfc57d57f658
|
| 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 sha256:24cf931618f4f7ceb21beb676f434312c3b214f3f1474068e69b596f961b47a9
|
| 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:cd036b10b8d5375fd193c0c61ce0f3c488671f8caba167559ea82531d6e0d4f6
|
| 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": 0.
|
| 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,
|
|
@@ -28,6 +28,13 @@
|
|
| 28 |
"learning_rate": 9.8e-05,
|
| 29 |
"loss": 1.4002,
|
| 30 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
}
|
| 32 |
],
|
| 33 |
"logging_steps": 100,
|
|
@@ -47,7 +54,7 @@
|
|
| 47 |
"attributes": {}
|
| 48 |
}
|
| 49 |
},
|
| 50 |
-
"total_flos":
|
| 51 |
"train_batch_size": 8,
|
| 52 |
"trial_name": null,
|
| 53 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7998750195281987,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 28 |
"learning_rate": 9.8e-05,
|
| 29 |
"loss": 1.4002,
|
| 30 |
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.7998750195281987,
|
| 34 |
+
"grad_norm": 0.0898224264383316,
|
| 35 |
+
"learning_rate": 9.733333333333335e-05,
|
| 36 |
+
"loss": 1.3804,
|
| 37 |
+
"step": 400
|
| 38 |
}
|
| 39 |
],
|
| 40 |
"logging_steps": 100,
|
|
|
|
| 54 |
"attributes": {}
|
| 55 |
}
|
| 56 |
},
|
| 57 |
+
"total_flos": 6.242998847526666e+17,
|
| 58 |
"train_batch_size": 8,
|
| 59 |
"trial_name": null,
|
| 60 |
"trial_params": null
|