ysr/deepseek-rust-1.3b-lora-32
Browse files- README.md +20 -12
- adapter_config.json +4 -4
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -39,7 +39,7 @@ More information needed
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
-
- learning_rate: 0.
|
43 |
- train_batch_size: 1
|
44 |
- eval_batch_size: 1
|
45 |
- seed: 42
|
@@ -48,27 +48,35 @@ The following hyperparameters were used during training:
|
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: cosine
|
50 |
- lr_scheduler_warmup_ratio: 0.05
|
51 |
-
- lr_scheduler_warmup_steps:
|
52 |
- num_epochs: 5
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
|
67 |
|
68 |
### Framework versions
|
69 |
|
70 |
- PEFT 0.10.0
|
71 |
-
- Transformers 4.39.
|
72 |
- Pytorch 2.2.1
|
73 |
- Datasets 2.18.0
|
74 |
- Tokenizers 0.15.2
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-1.3b-base](https://huggingface.co/deepseek-ai/deepseek-coder-1.3b-base) on the generator dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.4301
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 0.0003
|
43 |
- train_batch_size: 1
|
44 |
- eval_batch_size: 1
|
45 |
- seed: 42
|
|
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: cosine
|
50 |
- lr_scheduler_warmup_ratio: 0.05
|
51 |
+
- lr_scheduler_warmup_steps: 20
|
52 |
- num_epochs: 5
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|
|
58 |
+
| 0.8205 | 0.3 | 25 | 0.5577 |
|
59 |
+
| 0.5013 | 0.59 | 50 | 0.4856 |
|
60 |
+
| 0.4588 | 0.89 | 75 | 0.4663 |
|
61 |
+
| 0.4503 | 1.18 | 100 | 0.4556 |
|
62 |
+
| 0.4319 | 1.48 | 125 | 0.4482 |
|
63 |
+
| 0.4293 | 1.77 | 150 | 0.4429 |
|
64 |
+
| 0.4272 | 2.07 | 175 | 0.4387 |
|
65 |
+
| 0.4153 | 2.37 | 200 | 0.4365 |
|
66 |
+
| 0.4111 | 2.66 | 225 | 0.4343 |
|
67 |
+
| 0.4031 | 2.96 | 250 | 0.4322 |
|
68 |
+
| 0.406 | 3.25 | 275 | 0.4317 |
|
69 |
+
| 0.3996 | 3.55 | 300 | 0.4309 |
|
70 |
+
| 0.3959 | 3.84 | 325 | 0.4303 |
|
71 |
+
| 0.3989 | 4.14 | 350 | 0.4302 |
|
72 |
+
| 0.4035 | 4.43 | 375 | 0.4303 |
|
73 |
+
| 0.3929 | 4.73 | 400 | 0.4301 |
|
74 |
|
75 |
|
76 |
### Framework versions
|
77 |
|
78 |
- PEFT 0.10.0
|
79 |
+
- Transformers 4.39.3
|
80 |
- Pytorch 2.2.1
|
81 |
- Datasets 2.18.0
|
82 |
- Tokenizers 0.15.2
|
adapter_config.json
CHANGED
@@ -16,14 +16,14 @@
|
|
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 |
-
"o_proj",
|
25 |
"k_proj",
|
26 |
-
"
|
|
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
|
|
16 |
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
|
|
24 |
"k_proj",
|
25 |
+
"v_proj",
|
26 |
+
"o_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"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 sha256:84a723e022024cdfece83514750f0c6efcf4dc33aefc626f199a1553a4a60f8d
|
3 |
+
size 25191728
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b08e1878e76116da9d989483eca71f784ccf29c23ca5c4fb9e809222fcba214
|
3 |
size 4920
|