Commit
·
0d56eee
1
Parent(s):
6ef7df1
Training in progress, step 300, checkpoint
Browse files
last-checkpoint/adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 369214349
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5107c1e3e4f20ae2d01a00b3177144426b219e54afd7614b9d02e74c2f3ab6c
|
| 3 |
size 369214349
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 369142184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e782e84e692f02fbda556cdbd0b56b2a3476ed6be137830fbce02e8d2ddd8f0
|
| 3 |
size 369142184
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 738393861
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c958eb1a8503f4eae4085bedb0c3056eb4754c9d3f629842f1aaa1c94f086b2e
|
| 3 |
size 738393861
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:862164832507ca0755143b19a96acb896b1f394e94065e94a7857cbe9c8453dc
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
|
| 3 |
size 627
|
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,
|
|
@@ -73,13 +73,19 @@
|
|
| 73 |
"learning_rate": 0.0002,
|
| 74 |
"loss": 1.0453,
|
| 75 |
"step": 275
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
}
|
| 77 |
],
|
| 78 |
"logging_steps": 25,
|
| 79 |
"max_steps": 728,
|
| 80 |
"num_train_epochs": 1,
|
| 81 |
"save_steps": 25,
|
| 82 |
-
"total_flos":
|
| 83 |
"trial_name": null,
|
| 84 |
"trial_params": null
|
| 85 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.41208791208791207,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 73 |
"learning_rate": 0.0002,
|
| 74 |
"loss": 1.0453,
|
| 75 |
"step": 275
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.41,
|
| 79 |
+
"learning_rate": 0.0002,
|
| 80 |
+
"loss": 0.7793,
|
| 81 |
+
"step": 300
|
| 82 |
}
|
| 83 |
],
|
| 84 |
"logging_steps": 25,
|
| 85 |
"max_steps": 728,
|
| 86 |
"num_train_epochs": 1,
|
| 87 |
"save_steps": 25,
|
| 88 |
+
"total_flos": 2899555803168768.0,
|
| 89 |
"trial_name": null,
|
| 90 |
"trial_params": null
|
| 91 |
}
|