amphora commited on
Commit
cbcd9d1
·
verified ·
1 Parent(s): fa56027

Training in progress, step 68

Browse files
Files changed (4) hide show
  1. config.json +1 -1
  2. debug.log +0 -0
  3. model.safetensors +1 -1
  4. training_args.bin +2 -2
config.json CHANGED
@@ -40,7 +40,7 @@
40
  "full_attention",
41
  "full_attention"
42
  ],
43
- "max_position_embeddings": 65536,
44
  "max_window_layers": 21,
45
  "model_type": "qwen2",
46
  "num_attention_heads": 12,
 
40
  "full_attention",
41
  "full_attention"
42
  ],
43
+ "max_position_embeddings": 32768,
44
  "max_window_layers": 21,
45
  "model_type": "qwen2",
46
  "num_attention_heads": 12,
debug.log CHANGED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:accdf7bde886ac707c6dc607c66cb3a5ab3898e5b8b6601c6cbbef5318957020
3
  size 7108390424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d177e2e9fc08f0fd5d7c0b43ec3574bd4ffc9f5e6319f76dfd8d9b7073a4be9
3
  size 7108390424
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7b4ef651f69241b5deabe76f9c1c72e102899b5eede74caae1f82573f8d47c5
3
- size 9809
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee589dda58f55b7e70e26f353767835722c41336f1ea4962185f386af134140
3
+ size 9745