Training in progress, step 11100, 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 sha256:2ec6b1daf0250d9d77617d0233c8adf78bac9d5776544fd8260e2d41eb9060eb
|
| 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 sha256:91e451b704f58a2593406968817911d9a12c0d0aefcd97a5c12a9f493eb2ff41
|
| 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 sha256:296712c92e91a4d4b7a29cca3c129cde147d58269454f4098d71d3cd83c9e656
|
| 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:fbe9bca9121a3c1fcc48538217e6315a3f948d9e0e6ec8e10ab73beb14ee868f
|
| 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":
|
| 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,
|
|
@@ -953,6 +953,13 @@
|
|
| 953 |
"eval_samples_per_second": 19.894,
|
| 954 |
"eval_steps_per_second": 2.488,
|
| 955 |
"step": 11000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 956 |
}
|
| 957 |
],
|
| 958 |
"logging_steps": 100,
|
|
@@ -972,7 +979,7 @@
|
|
| 972 |
"attributes": {}
|
| 973 |
}
|
| 974 |
},
|
| 975 |
-
"total_flos": 1.
|
| 976 |
"train_batch_size": 8,
|
| 977 |
"trial_name": null,
|
| 978 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 22.196531791907514,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 11100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 953 |
"eval_samples_per_second": 19.894,
|
| 954 |
"eval_steps_per_second": 2.488,
|
| 955 |
"step": 11000
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 22.196531791907514,
|
| 959 |
+
"grad_norm": 0.24070052802562714,
|
| 960 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 961 |
+
"loss": 1.2256,
|
| 962 |
+
"step": 11100
|
| 963 |
}
|
| 964 |
],
|
| 965 |
"logging_steps": 100,
|
|
|
|
| 979 |
"attributes": {}
|
| 980 |
}
|
| 981 |
},
|
| 982 |
+
"total_flos": 1.7324120350740447e+19,
|
| 983 |
"train_batch_size": 8,
|
| 984 |
"trial_name": null,
|
| 985 |
"trial_params": null
|