End of training
Browse files- README.md +10 -10
- adapter_config.json +4 -3
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 1.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -52,17 +52,17 @@ The following hyperparameters were used during training:
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
|
61 |
|
62 |
### Framework versions
|
63 |
|
64 |
-
- PEFT 0.
|
65 |
-
- Transformers 4.
|
66 |
-
- Pytorch 2.
|
67 |
-
- Datasets
|
68 |
- Tokenizers 0.19.1
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.6392
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| 0.561 | 1.0 | 394 | 1.5800 |
|
56 |
+
| 0.5974 | 2.0 | 788 | 1.5667 |
|
57 |
+
| 0.5388 | 3.0 | 1182 | 1.5681 |
|
58 |
+
| 0.496 | 4.0 | 1576 | 1.5996 |
|
59 |
+
| 0.4139 | 5.0 | 1970 | 1.6392 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
63 |
|
64 |
+
- PEFT 0.12.1.dev0
|
65 |
+
- Transformers 4.45.0.dev0
|
66 |
+
- Pytorch 2.4.1+cu121
|
67 |
+
- Datasets 3.0.0
|
68 |
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -10,17 +10,18 @@
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
-
"lora_alpha":
|
14 |
"lora_dropout": 0.05,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
-
"r":
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
|
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM",
|
26 |
"use_dora": false,
|
|
|
10 |
"layers_pattern": null,
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
"lora_dropout": 0.05,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
+
"r": 8,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
+
"o_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
adapter_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 sha256:653c17a00f1b1b83258a5941869da3e55c043965851913b1b193ffe68a4f9b33
|
3 |
+
size 2128659168
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3f9c4081453a7ff67aa451b1b5484e84eb9bda7980f390466844f515273b467
|
3 |
size 5432
|