Model save
Browse files- README.md +12 -6
- config.json +3 -3
- model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Loss: 3.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -44,11 +44,17 @@ The following hyperparameters were used during training:
|
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
-
| Training Loss | Epoch
|
| 48 |
-
|
| 49 |
-
| 3.
|
| 50 |
-
| 3.
|
| 51 |
-
| 3.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
|
| 53 |
|
| 54 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 3.3881
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 49 |
+
| 3.8906 | 0.1067 | 5000 | 3.8169 |
|
| 50 |
+
| 3.7452 | 0.2133 | 10000 | 3.6688 |
|
| 51 |
+
| 3.6584 | 0.32 | 15000 | 3.5842 |
|
| 52 |
+
| 3.6004 | 0.4267 | 20000 | 3.5230 |
|
| 53 |
+
| 3.5443 | 0.5333 | 25000 | 3.4647 |
|
| 54 |
+
| 3.5011 | 0.64 | 30000 | 3.4239 |
|
| 55 |
+
| 3.4836 | 0.7467 | 35000 | 3.4020 |
|
| 56 |
+
| 3.4549 | 0.8533 | 40000 | 3.3917 |
|
| 57 |
+
| 3.4606 | 0.96 | 45000 | 3.3881 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
config.json
CHANGED
|
@@ -33,10 +33,10 @@
|
|
| 33 |
"full_attention"
|
| 34 |
],
|
| 35 |
"linear_conv_kernel_dim": 4,
|
| 36 |
-
"linear_key_head_dim":
|
| 37 |
"linear_num_key_heads": 8,
|
| 38 |
-
"linear_num_value_heads":
|
| 39 |
-
"linear_value_head_dim":
|
| 40 |
"max_position_embeddings": 512,
|
| 41 |
"model_type": "neollm",
|
| 42 |
"num_attention_heads": 8,
|
|
|
|
| 33 |
"full_attention"
|
| 34 |
],
|
| 35 |
"linear_conv_kernel_dim": 4,
|
| 36 |
+
"linear_key_head_dim": 32,
|
| 37 |
"linear_num_key_heads": 8,
|
| 38 |
+
"linear_num_value_heads": 16,
|
| 39 |
+
"linear_value_head_dim": 32,
|
| 40 |
"max_position_embeddings": 512,
|
| 41 |
"model_type": "neollm",
|
| 42 |
"num_attention_heads": 8,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f14b10de44faaa69ef479a457dd75c927d920e17189ae8dae55f72437960e89
|
| 3 |
+
size 245234560
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5521
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d73ddd42d104db05486ea8abf270ee84a6d551ab624552e075f5f3a06e239b63
|
| 3 |
size 5521
|