Epoch 0 - Val loss 1.7144
Browse files- config.json +1 -1
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -42,7 +42,7 @@
|
|
| 42 |
"rope_base": 1000000,
|
| 43 |
"seq_len": 8192,
|
| 44 |
"skip_stm": false,
|
| 45 |
-
"stm_batch_size":
|
| 46 |
"stm_size": 4096,
|
| 47 |
"tie_embeddings": true,
|
| 48 |
"training_cache": true,
|
|
|
|
| 42 |
"rope_base": 1000000,
|
| 43 |
"seq_len": 8192,
|
| 44 |
"skip_stm": false,
|
| 45 |
+
"stm_batch_size": 1,
|
| 46 |
"stm_size": 4096,
|
| 47 |
"tie_embeddings": true,
|
| 48 |
"training_cache": true,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3794621808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bed7631639411bbd1a24e1e5e53154eadd5b961b2cec80f9c462f655d9f766e1
|
| 3 |
size 3794621808
|