Training in progress, step 11700, 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:f4f9f022bd865f30e57f5db3f26032b54e5d0a3288e6a73ab297bdb678b13eaf
|
| 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:c57aa65c84a15777a1928efbeeb57520ae429b9f06503f7659cf22eb55588906
|
| 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 sha256:40ef4a11b96067b992cf8afde7441d5bb4e1e029d276e66e4a189b2de033ce43
|
| 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 sha256:037287bc729b2fa86d80a430fb4fe83cf5198d8ba517f10314c41efc8f3e614d
|
| 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": 23.
|
| 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,
|
|
@@ -1003,6 +1003,13 @@
|
|
| 1003 |
"learning_rate": 2.2666666666666668e-05,
|
| 1004 |
"loss": 1.224,
|
| 1005 |
"step": 11600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1006 |
}
|
| 1007 |
],
|
| 1008 |
"logging_steps": 100,
|
|
@@ -1022,7 +1029,7 @@
|
|
| 1022 |
"attributes": {}
|
| 1023 |
}
|
| 1024 |
},
|
| 1025 |
-
"total_flos": 1.
|
| 1026 |
"train_batch_size": 8,
|
| 1027 |
"trial_name": null,
|
| 1028 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 23.396344321199813,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 11700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1003 |
"learning_rate": 2.2666666666666668e-05,
|
| 1004 |
"loss": 1.224,
|
| 1005 |
"step": 11600
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 23.396344321199813,
|
| 1009 |
+
"grad_norm": 0.23398549854755402,
|
| 1010 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 1011 |
+
"loss": 1.2218,
|
| 1012 |
+
"step": 11700
|
| 1013 |
}
|
| 1014 |
],
|
| 1015 |
"logging_steps": 100,
|
|
|
|
| 1029 |
"attributes": {}
|
| 1030 |
}
|
| 1031 |
},
|
| 1032 |
+
"total_flos": 1.8260561020999172e+19,
|
| 1033 |
"train_batch_size": 8,
|
| 1034 |
"trial_name": null,
|
| 1035 |
"trial_params": null
|