Training in progress, step 11300, 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 sha256:4a2df2fd9d3388bbfe3a42680062628915566ff1afd8993455f99f35524ca58c
|
| 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 sha256:6c5d73b7bdcd0b3a89fd01492d599234ebde6bc0f8b6a384ee86568ee13773b1
|
| 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 sha256:2e2d3c2211d761da3b1cbff084d541301a3ebdbf40d15cb7e7692d1ca4561797
|
| 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 sha256:979f21377f7bfec8e2e5caddaea769a924497f2f7c446c6418878672779b3a12
|
| 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,
|
|
@@ -967,6 +967,13 @@
|
|
| 967 |
"learning_rate": 2.5333333333333337e-05,
|
| 968 |
"loss": 1.2206,
|
| 969 |
"step": 11200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 970 |
}
|
| 971 |
],
|
| 972 |
"logging_steps": 100,
|
|
@@ -986,7 +993,7 @@
|
|
| 986 |
"attributes": {}
|
| 987 |
}
|
| 988 |
},
|
| 989 |
-
"total_flos": 1.
|
| 990 |
"train_batch_size": 8,
|
| 991 |
"trial_name": null,
|
| 992 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 22.596469301671615,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 11300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 967 |
"learning_rate": 2.5333333333333337e-05,
|
| 968 |
"loss": 1.2206,
|
| 969 |
"step": 11200
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 22.596469301671615,
|
| 973 |
+
"grad_norm": 0.22408048808574677,
|
| 974 |
+
"learning_rate": 2.466666666666667e-05,
|
| 975 |
+
"loss": 1.2219,
|
| 976 |
+
"step": 11300
|
| 977 |
}
|
| 978 |
],
|
| 979 |
"logging_steps": 100,
|
|
|
|
| 993 |
"attributes": {}
|
| 994 |
}
|
| 995 |
},
|
| 996 |
+
"total_flos": 1.763627029311678e+19,
|
| 997 |
"train_batch_size": 8,
|
| 998 |
"trial_name": null,
|
| 999 |
"trial_params": null
|