End of training
Browse files- README.md +18 -18
- adapter_model.bin +1 -1
README.md
CHANGED
|
@@ -26,7 +26,7 @@ is_llama_derived_model: true
|
|
| 26 |
hub_model_id: noeloco/camel-lora
|
| 27 |
|
| 28 |
load_in_8bit: false
|
| 29 |
-
load_in_4bit:
|
| 30 |
strict: false
|
| 31 |
|
| 32 |
datasets:
|
|
@@ -44,7 +44,7 @@ sequence_len: 2048
|
|
| 44 |
sample_packing: false
|
| 45 |
pad_to_sequence_len: true
|
| 46 |
|
| 47 |
-
adapter:
|
| 48 |
lora_model_dir:
|
| 49 |
lora_r: 16
|
| 50 |
lora_alpha: 8
|
|
@@ -98,9 +98,9 @@ special_tokens:
|
|
| 98 |
|
| 99 |
# camel-lora
|
| 100 |
|
| 101 |
-
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on
|
| 102 |
It achieves the following results on the evaluation set:
|
| 103 |
-
- Loss: 0.
|
| 104 |
|
| 105 |
## Model description
|
| 106 |
|
|
@@ -134,20 +134,20 @@ The following hyperparameters were used during training:
|
|
| 134 |
|
| 135 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 136 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 137 |
-
| 1.
|
| 138 |
-
| 1.
|
| 139 |
-
| 1.
|
| 140 |
-
| 0.
|
| 141 |
-
| 0.
|
| 142 |
-
| 0.
|
| 143 |
-
| 0.
|
| 144 |
-
| 0.
|
| 145 |
-
| 0.
|
| 146 |
-
| 0.
|
| 147 |
-
| 0.
|
| 148 |
-
| 0.
|
| 149 |
-
| 0.
|
| 150 |
-
| 0.
|
| 151 |
|
| 152 |
|
| 153 |
### Framework versions
|
|
|
|
| 26 |
hub_model_id: noeloco/camel-lora
|
| 27 |
|
| 28 |
load_in_8bit: false
|
| 29 |
+
load_in_4bit: false
|
| 30 |
strict: false
|
| 31 |
|
| 32 |
datasets:
|
|
|
|
| 44 |
sample_packing: false
|
| 45 |
pad_to_sequence_len: true
|
| 46 |
|
| 47 |
+
adapter: lora
|
| 48 |
lora_model_dir:
|
| 49 |
lora_r: 16
|
| 50 |
lora_alpha: 8
|
|
|
|
| 98 |
|
| 99 |
# camel-lora
|
| 100 |
|
| 101 |
+
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on the None dataset.
|
| 102 |
It achieves the following results on the evaluation set:
|
| 103 |
+
- Loss: 0.0383
|
| 104 |
|
| 105 |
## Model description
|
| 106 |
|
|
|
|
| 134 |
|
| 135 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 136 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 137 |
+
| 1.7285 | 0.06 | 1 | 2.5189 |
|
| 138 |
+
| 1.8487 | 0.29 | 5 | 2.4980 |
|
| 139 |
+
| 1.4443 | 0.57 | 10 | 1.9379 |
|
| 140 |
+
| 0.7471 | 0.86 | 15 | 1.0148 |
|
| 141 |
+
| 0.561 | 1.14 | 20 | 0.5721 |
|
| 142 |
+
| 0.2245 | 1.43 | 25 | 0.3640 |
|
| 143 |
+
| 0.3456 | 1.71 | 30 | 0.1683 |
|
| 144 |
+
| 0.2138 | 2.0 | 35 | 0.1051 |
|
| 145 |
+
| 0.1145 | 2.29 | 40 | 0.0834 |
|
| 146 |
+
| 0.1193 | 2.57 | 45 | 0.0526 |
|
| 147 |
+
| 0.1083 | 2.86 | 50 | 0.0436 |
|
| 148 |
+
| 0.1388 | 3.14 | 55 | 0.0387 |
|
| 149 |
+
| 0.1102 | 3.43 | 60 | 0.0385 |
|
| 150 |
+
| 0.0628 | 3.71 | 65 | 0.0383 |
|
| 151 |
|
| 152 |
|
| 153 |
### Framework versions
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 80115914
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b66e19266959041f6863e2ae34bc5aee2db2a88b45bac11641d5327b69dc9df
|
| 3 |
size 80115914
|