Epoch 4: train_loss=3.3821, val_loss=3.5047
Browse files
best_model/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 912354791
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7934d606e5584787df1c1066453bb630836dd4b5f98dc20317561d8a8baee333
|
| 3 |
size 912354791
|
best_model/training_info.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 3.
|
| 4 |
-
"val_loss": 3.
|
| 5 |
"router_type": "hash",
|
| 6 |
"num_experts": 8,
|
| 7 |
"use_lora_experts": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4,
|
| 3 |
+
"train_loss": 3.3820994957210324,
|
| 4 |
+
"val_loss": 3.5047283063211583,
|
| 5 |
"router_type": "hash",
|
| 6 |
"num_experts": 8,
|
| 7 |
"use_lora_experts": false,
|