Hugging Face's logo

Rafaelrosendo1
/
llama-3-8b-local-definitivo

Safetensors
trl
sft
Generated from Trainer
Model card Files Community
Rafaelrosendo1 commited on
Commit
52bfc63
•
1 Parent(s): 2fbbe3c

Rafaelrosendo1/llama

Browse files
Files changed (5) hide show
  1. README.md +39 -39
  2. adapter_config.json +5 -5
  3. adapter_model.bin +1 -1
  4. adapter_model.safetensors +1 -1
  5. training_args.bin +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.4658
21
 
22
  ## Model description
23
 
@@ -51,44 +51,44 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
- | 1.893 | 0.03 | 25 | 1.7774 |
55
- | 1.714 | 0.05 | 50 | 1.7412 |
56
- | 1.7498 | 0.08 | 75 | 1.7188 |
57
- | 1.6899 | 0.1 | 100 | 1.7036 |
58
- | 1.7176 | 0.13 | 125 | 1.6906 |
59
- | 1.7198 | 0.15 | 150 | 1.6782 |
60
- | 1.7086 | 0.18 | 175 | 1.6694 |
61
- | 1.7236 | 0.21 | 200 | 1.6559 |
62
- | 1.7616 | 0.23 | 225 | 1.6457 |
63
- | 1.6756 | 0.26 | 250 | 1.6341 |
64
- | 1.7199 | 0.28 | 275 | 1.6236 |
65
- | 1.7121 | 0.31 | 300 | 1.6175 |
66
- | 1.7542 | 0.34 | 325 | 1.6071 |
67
- | 1.6884 | 0.36 | 350 | 1.5967 |
68
- | 1.6089 | 0.39 | 375 | 1.5892 |
69
- | 1.6556 | 0.41 | 400 | 1.5821 |
70
- | 1.5784 | 0.44 | 425 | 1.5745 |
71
- | 1.6317 | 0.46 | 450 | 1.5636 |
72
- | 1.6375 | 0.49 | 475 | 1.5571 |
73
- | 1.6772 | 0.52 | 500 | 1.5498 |
74
- | 1.5775 | 0.54 | 525 | 1.5408 |
75
- | 1.6307 | 0.57 | 550 | 1.5335 |
76
- | 1.6938 | 0.59 | 575 | 1.5304 |
77
- | 1.5764 | 0.62 | 600 | 1.5211 |
78
- | 1.5834 | 0.64 | 625 | 1.5164 |
79
- | 1.5483 | 0.67 | 650 | 1.5090 |
80
- | 1.5883 | 0.7 | 675 | 1.5013 |
81
- | 1.6268 | 0.72 | 700 | 1.4993 |
82
- | 1.5515 | 0.75 | 725 | 1.4919 |
83
- | 1.665 | 0.77 | 750 | 1.4882 |
84
- | 1.6557 | 0.8 | 775 | 1.4848 |
85
- | 1.635 | 0.83 | 800 | 1.4829 |
86
- | 1.6689 | 0.85 | 825 | 1.4782 |
87
- | 1.6995 | 0.88 | 850 | 1.4742 |
88
- | 1.6312 | 0.9 | 875 | 1.4714 |
89
- | 1.6465 | 0.93 | 900 | 1.4689 |
90
- | 1.51 | 0.95 | 925 | 1.4667 |
91
- | 1.5953 | 0.98 | 950 | 1.4658 |
92
 
93
 
94
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.4655
21
 
22
  ## Model description
23
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | 1.8917 | 0.03 | 25 | 1.7768 |
55
+ | 1.7137 | 0.05 | 50 | 1.7402 |
56
+ | 1.7492 | 0.08 | 75 | 1.7194 |
57
+ | 1.6895 | 0.1 | 100 | 1.7036 |
58
+ | 1.7168 | 0.13 | 125 | 1.6899 |
59
+ | 1.7184 | 0.15 | 150 | 1.6784 |
60
+ | 1.7081 | 0.18 | 175 | 1.6700 |
61
+ | 1.7245 | 0.21 | 200 | 1.6555 |
62
+ | 1.7603 | 0.23 | 225 | 1.6453 |
63
+ | 1.6707 | 0.26 | 250 | 1.6344 |
64
+ | 1.7224 | 0.28 | 275 | 1.6233 |
65
+ | 1.7112 | 0.31 | 300 | 1.6178 |
66
+ | 1.7531 | 0.34 | 325 | 1.6067 |
67
+ | 1.6894 | 0.36 | 350 | 1.5967 |
68
+ | 1.609 | 0.39 | 375 | 1.5895 |
69
+ | 1.6563 | 0.41 | 400 | 1.5818 |
70
+ | 1.5761 | 0.44 | 425 | 1.5744 |
71
+ | 1.6282 | 0.46 | 450 | 1.5630 |
72
+ | 1.637 | 0.49 | 475 | 1.5567 |
73
+ | 1.6759 | 0.52 | 500 | 1.5497 |
74
+ | 1.577 | 0.54 | 525 | 1.5402 |
75
+ | 1.6314 | 0.57 | 550 | 1.5334 |
76
+ | 1.6907 | 0.59 | 575 | 1.5297 |
77
+ | 1.5755 | 0.62 | 600 | 1.5207 |
78
+ | 1.5822 | 0.64 | 625 | 1.5163 |
79
+ | 1.549 | 0.67 | 650 | 1.5088 |
80
+ | 1.5865 | 0.7 | 675 | 1.5012 |
81
+ | 1.6242 | 0.72 | 700 | 1.4994 |
82
+ | 1.5511 | 0.75 | 725 | 1.4916 |
83
+ | 1.6663 | 0.77 | 750 | 1.4880 |
84
+ | 1.6563 | 0.8 | 775 | 1.4847 |
85
+ | 1.6347 | 0.83 | 800 | 1.4826 |
86
+ | 1.6682 | 0.85 | 825 | 1.4779 |
87
+ | 1.6995 | 0.88 | 850 | 1.4738 |
88
+ | 1.6295 | 0.9 | 875 | 1.4711 |
89
+ | 1.6469 | 0.93 | 900 | 1.4686 |
90
+ | 1.5073 | 0.95 | 925 | 1.4663 |
91
+ | 1.5953 | 0.98 | 950 | 1.4655 |
92
 
93
 
94
  ### Framework versions
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "q_proj",
24
- "up_proj",
25
- "v_proj",
26
- "gate_proj",
27
  "down_proj",
 
 
28
  "k_proj",
29
- "o_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
 
23
  "down_proj",
24
+ "v_proj",
25
+ "o_proj",
26
  "k_proj",
27
+ "q_proj",
28
+ "gate_proj",
29
+ "up_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d617ba54d6e56b0c8b5039a53088fb47ecf366386dea9383cb627c3fc055360
3
  size 160069834
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700effb22b53a3f30e54619e427e20fd87f5ead8f4e5a22d149f29468a28e8dc
3
  size 160069834
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0411a43ae1658296cc5d5e661745d2a53b5be55aa0380f188a7253ae21055d19
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:442e2d866c34ace4ef12db90ebb19d6ca20a9e8267a8dd42a683bd4f8a90f470
3
  size 159967880
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6248506603f85d9811e1ea2245951537528766be6c3f96806aa05b38998cbd12
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2285842db349531677bd37c2a080d9fec0cb345057599110dfe597d9b51f564
3
  size 4536