Training in progress, step 10900, 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 sha256:54954af78d21501178aa62df97e4be776d44dff55739ccefcf53cd7aa892ad26
|
| 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 sha256:50c0891fae01c1d6432579b2b936d4b0012c9b7ac7ea43bb5023b807960238aa
|
| 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:b862f636711227d7ee569cee2e33728ccc9fbbf65bc11cd093eb1d516eb0a06e
|
| 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 sha256:6d45e2a529ec73c259dc8a505fb5d678af9533763a932c892160c698a82dd89e
|
| 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": 21.
|
| 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,
|
|
@@ -931,6 +931,13 @@
|
|
| 931 |
"learning_rate": 2.8000000000000003e-05,
|
| 932 |
"loss": 1.2222,
|
| 933 |
"step": 10800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 934 |
}
|
| 935 |
],
|
| 936 |
"logging_steps": 100,
|
|
@@ -950,7 +957,7 @@
|
|
| 950 |
"attributes": {}
|
| 951 |
}
|
| 952 |
},
|
| 953 |
-
"total_flos": 1.
|
| 954 |
"train_batch_size": 8,
|
| 955 |
"trial_name": null,
|
| 956 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 21.796594282143417,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 10900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 931 |
"learning_rate": 2.8000000000000003e-05,
|
| 932 |
"loss": 1.2222,
|
| 933 |
"step": 10800
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 21.796594282143417,
|
| 937 |
+
"grad_norm": 0.2397545576095581,
|
| 938 |
+
"learning_rate": 2.733333333333333e-05,
|
| 939 |
+
"loss": 1.2294,
|
| 940 |
+
"step": 10900
|
| 941 |
}
|
| 942 |
],
|
| 943 |
"logging_steps": 100,
|
|
|
|
| 957 |
"attributes": {}
|
| 958 |
}
|
| 959 |
},
|
| 960 |
+
"total_flos": 1.701197956523439e+19,
|
| 961 |
"train_batch_size": 8,
|
| 962 |
"trial_name": null,
|
| 963 |
"trial_params": null
|