DONE
Browse files- README.md +158 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
7 |
+
model-index:
|
8 |
+
- name: final_llama
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# final_llama
|
16 |
+
|
17 |
+
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.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 3.4315
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 2e-05
|
39 |
+
- train_batch_size: 4
|
40 |
+
- eval_batch_size: 4
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 100
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 20.3519 | 1.0 | 1 | 20.2665 |
|
51 |
+
| 20.3519 | 2.0 | 2 | 20.1486 |
|
52 |
+
| 20.3519 | 3.0 | 3 | 20.0148 |
|
53 |
+
| 20.3519 | 4.0 | 4 | 19.8717 |
|
54 |
+
| 20.3519 | 5.0 | 5 | 19.7162 |
|
55 |
+
| 20.3519 | 6.0 | 6 | 19.5484 |
|
56 |
+
| 20.3519 | 7.0 | 7 | 19.3671 |
|
57 |
+
| 20.3519 | 8.0 | 8 | 19.1726 |
|
58 |
+
| 20.3519 | 9.0 | 9 | 18.9658 |
|
59 |
+
| 20.3519 | 10.0 | 10 | 18.7509 |
|
60 |
+
| 20.3519 | 11.0 | 11 | 18.5206 |
|
61 |
+
| 20.3519 | 12.0 | 12 | 18.2873 |
|
62 |
+
| 20.3519 | 13.0 | 13 | 18.0473 |
|
63 |
+
| 20.3519 | 14.0 | 14 | 17.8122 |
|
64 |
+
| 20.3519 | 15.0 | 15 | 17.5813 |
|
65 |
+
| 20.3519 | 16.0 | 16 | 17.3524 |
|
66 |
+
| 20.3519 | 17.0 | 17 | 17.1373 |
|
67 |
+
| 20.3519 | 18.0 | 18 | 16.9325 |
|
68 |
+
| 20.3519 | 19.0 | 19 | 16.7373 |
|
69 |
+
| 20.3519 | 20.0 | 20 | 16.5515 |
|
70 |
+
| 20.3519 | 21.0 | 21 | 16.3717 |
|
71 |
+
| 20.3519 | 22.0 | 22 | 16.1991 |
|
72 |
+
| 20.3519 | 23.0 | 23 | 16.0269 |
|
73 |
+
| 20.3519 | 24.0 | 24 | 15.8545 |
|
74 |
+
| 20.3519 | 25.0 | 25 | 15.6744 |
|
75 |
+
| 20.3519 | 26.0 | 26 | 15.4867 |
|
76 |
+
| 20.3519 | 27.0 | 27 | 15.2966 |
|
77 |
+
| 20.3519 | 28.0 | 28 | 15.0983 |
|
78 |
+
| 20.3519 | 29.0 | 29 | 14.8900 |
|
79 |
+
| 20.3519 | 30.0 | 30 | 14.6800 |
|
80 |
+
| 20.3519 | 31.0 | 31 | 14.4623 |
|
81 |
+
| 20.3519 | 32.0 | 32 | 14.2411 |
|
82 |
+
| 20.3519 | 33.0 | 33 | 14.0190 |
|
83 |
+
| 20.3519 | 34.0 | 34 | 13.7946 |
|
84 |
+
| 20.3519 | 35.0 | 35 | 13.5692 |
|
85 |
+
| 20.3519 | 36.0 | 36 | 13.3422 |
|
86 |
+
| 20.3519 | 37.0 | 37 | 13.1188 |
|
87 |
+
| 20.3519 | 38.0 | 38 | 12.8947 |
|
88 |
+
| 20.3519 | 39.0 | 39 | 12.6666 |
|
89 |
+
| 20.3519 | 40.0 | 40 | 12.4454 |
|
90 |
+
| 20.3519 | 41.0 | 41 | 12.2206 |
|
91 |
+
| 20.3519 | 42.0 | 42 | 11.9955 |
|
92 |
+
| 20.3519 | 43.0 | 43 | 11.7648 |
|
93 |
+
| 20.3519 | 44.0 | 44 | 11.5387 |
|
94 |
+
| 20.3519 | 45.0 | 45 | 11.3104 |
|
95 |
+
| 20.3519 | 46.0 | 46 | 11.0794 |
|
96 |
+
| 20.3519 | 47.0 | 47 | 10.8506 |
|
97 |
+
| 20.3519 | 48.0 | 48 | 10.6189 |
|
98 |
+
| 20.3519 | 49.0 | 49 | 10.3891 |
|
99 |
+
| 20.3519 | 50.0 | 50 | 10.1577 |
|
100 |
+
| 20.3519 | 51.0 | 51 | 9.9252 |
|
101 |
+
| 20.3519 | 52.0 | 52 | 9.6967 |
|
102 |
+
| 20.3519 | 53.0 | 53 | 9.4668 |
|
103 |
+
| 20.3519 | 54.0 | 54 | 9.2420 |
|
104 |
+
| 20.3519 | 55.0 | 55 | 9.0153 |
|
105 |
+
| 20.3519 | 56.0 | 56 | 8.7923 |
|
106 |
+
| 20.3519 | 57.0 | 57 | 8.5711 |
|
107 |
+
| 20.3519 | 58.0 | 58 | 8.3488 |
|
108 |
+
| 20.3519 | 59.0 | 59 | 8.1307 |
|
109 |
+
| 20.3519 | 60.0 | 60 | 7.9147 |
|
110 |
+
| 20.3519 | 61.0 | 61 | 7.7034 |
|
111 |
+
| 20.3519 | 62.0 | 62 | 7.4925 |
|
112 |
+
| 20.3519 | 63.0 | 63 | 7.2867 |
|
113 |
+
| 20.3519 | 64.0 | 64 | 7.0867 |
|
114 |
+
| 20.3519 | 65.0 | 65 | 6.8855 |
|
115 |
+
| 20.3519 | 66.0 | 66 | 6.6916 |
|
116 |
+
| 20.3519 | 67.0 | 67 | 6.5061 |
|
117 |
+
| 20.3519 | 68.0 | 68 | 6.3185 |
|
118 |
+
| 20.3519 | 69.0 | 69 | 6.1380 |
|
119 |
+
| 20.3519 | 70.0 | 70 | 5.9656 |
|
120 |
+
| 20.3519 | 71.0 | 71 | 5.7981 |
|
121 |
+
| 20.3519 | 72.0 | 72 | 5.6359 |
|
122 |
+
| 20.3519 | 73.0 | 73 | 5.4777 |
|
123 |
+
| 20.3519 | 74.0 | 74 | 5.3250 |
|
124 |
+
| 20.3519 | 75.0 | 75 | 5.1813 |
|
125 |
+
| 20.3519 | 76.0 | 76 | 5.0366 |
|
126 |
+
| 20.3519 | 77.0 | 77 | 4.9050 |
|
127 |
+
| 20.3519 | 78.0 | 78 | 4.7747 |
|
128 |
+
| 20.3519 | 79.0 | 79 | 4.6546 |
|
129 |
+
| 20.3519 | 80.0 | 80 | 4.5398 |
|
130 |
+
| 20.3519 | 81.0 | 81 | 4.4281 |
|
131 |
+
| 20.3519 | 82.0 | 82 | 4.3260 |
|
132 |
+
| 20.3519 | 83.0 | 83 | 4.2277 |
|
133 |
+
| 20.3519 | 84.0 | 84 | 4.1377 |
|
134 |
+
| 20.3519 | 85.0 | 85 | 4.0487 |
|
135 |
+
| 20.3519 | 86.0 | 86 | 3.9703 |
|
136 |
+
| 20.3519 | 87.0 | 87 | 3.8984 |
|
137 |
+
| 20.3519 | 88.0 | 88 | 3.8298 |
|
138 |
+
| 20.3519 | 89.0 | 89 | 3.7664 |
|
139 |
+
| 20.3519 | 90.0 | 90 | 3.7087 |
|
140 |
+
| 20.3519 | 91.0 | 91 | 3.6577 |
|
141 |
+
| 20.3519 | 92.0 | 92 | 3.6108 |
|
142 |
+
| 20.3519 | 93.0 | 93 | 3.5709 |
|
143 |
+
| 20.3519 | 94.0 | 94 | 3.5354 |
|
144 |
+
| 20.3519 | 95.0 | 95 | 3.5040 |
|
145 |
+
| 20.3519 | 96.0 | 96 | 3.4798 |
|
146 |
+
| 20.3519 | 97.0 | 97 | 3.4595 |
|
147 |
+
| 20.3519 | 98.0 | 98 | 3.4442 |
|
148 |
+
| 20.3519 | 99.0 | 99 | 3.4354 |
|
149 |
+
| 10.6394 | 100.0 | 100 | 3.4315 |
|
150 |
+
|
151 |
+
|
152 |
+
### Framework versions
|
153 |
+
|
154 |
+
- PEFT 0.11.1
|
155 |
+
- Transformers 4.41.2
|
156 |
+
- Pytorch 2.1.2
|
157 |
+
- Datasets 2.19.2
|
158 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.1,
|
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 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a3926bc9c8444ce270bdd83063cb6e50db90a365a1c5b24a22fd726eb975b73
|
3 |
+
size 13648432
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56330400c72607d2f0a1b411d0955a11120e91128b78fdf39f65f16df8f3ca99
|
3 |
+
size 5048
|