Hugging Face's logo

abhi317
/
final_llama

PEFT
Safetensors
Generated from Trainer
Model card Files Community
abhi317 commited on
Commit
edd9507
•
1 Parent(s): 3d31b89

DONE

Browse files
Files changed (4) hide show
  1. README.md +158 -0
  2. adapter_config.json +29 -0
  3. adapter_model.safetensors +3 -0
  4. 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