Training in progress, step 11200, 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:aff08074dd96e5edcd66c7b80b3d5a774494af4637153a00c7f21af1277475c7
|
| 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 sha256:77cdc285e571ad5532e203a25c52b53286dd461fb8f226d2060997cac20be791
|
| 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:f0d656649ff18c4d86ce2423ca37c912c7cc371c10e36c210c3d55e7e58579f8
|
| 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 sha256:11fb3dae59763a6c87c8721f79c6bf92881dc4dfecb018111062e39aaf3a935b
|
| 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": 22.
|
| 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,
|
|
@@ -960,6 +960,13 @@
|
|
| 960 |
"learning_rate": 2.6000000000000002e-05,
|
| 961 |
"loss": 1.2256,
|
| 962 |
"step": 11100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 963 |
}
|
| 964 |
],
|
| 965 |
"logging_steps": 100,
|
|
@@ -979,7 +986,7 @@
|
|
| 979 |
"attributes": {}
|
| 980 |
}
|
| 981 |
},
|
| 982 |
-
"total_flos": 1.
|
| 983 |
"train_batch_size": 8,
|
| 984 |
"trial_name": null,
|
| 985 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 22.396500546789564,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 11200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 960 |
"learning_rate": 2.6000000000000002e-05,
|
| 961 |
"loss": 1.2256,
|
| 962 |
"step": 11100
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 22.396500546789564,
|
| 966 |
+
"grad_norm": 0.24903209507465363,
|
| 967 |
+
"learning_rate": 2.5333333333333337e-05,
|
| 968 |
+
"loss": 1.2206,
|
| 969 |
+
"step": 11200
|
| 970 |
}
|
| 971 |
],
|
| 972 |
"logging_steps": 100,
|
|
|
|
| 986 |
"attributes": {}
|
| 987 |
}
|
| 988 |
},
|
| 989 |
+
"total_flos": 1.7480195321928614e+19,
|
| 990 |
"train_batch_size": 8,
|
| 991 |
"trial_name": null,
|
| 992 |
"trial_params": null
|