Hugging Face's logo

Lalith16
/
Genpro_Llama3-8b

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
Lalith16 commited on
Commit
07e9628
•
1 Parent(s): b302807

End of training

Browse files
Files changed (4) hide show
  1. README.md +80 -17
  2. adapter_config.json +4 -4
  3. adapter_model.safetensors +1 -1
  4. 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](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6683
22
 
23
  ## Model description
24
 
@@ -44,27 +44,90 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: constant
46
  - lr_scheduler_warmup_ratio: 0.03
47
- - num_epochs: 1
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
- | 1.3225 | 0.0634 | 100 | 1.3185 |
54
- | 1.1249 | 0.1267 | 200 | 1.1062 |
55
- | 1.0249 | 0.1901 | 300 | 1.0177 |
56
- | 1.025 | 0.2535 | 400 | 0.9535 |
57
- | 0.9842 | 0.3169 | 500 | 0.9055 |
58
- | 0.9721 | 0.3802 | 600 | 0.8475 |
59
- | 0.9047 | 0.4436 | 700 | 0.8295 |
60
- | 0.8861 | 0.5070 | 800 | 0.7987 |
61
- | 0.7792 | 0.5703 | 900 | 0.7721 |
62
- | 0.8329 | 0.6337 | 1000 | 0.7541 |
63
- | 0.7882 | 0.6971 | 1100 | 0.7305 |
64
- | 0.8286 | 0.7605 | 1200 | 0.7095 |
65
- | 0.7418 | 0.8238 | 1300 | 0.6927 |
66
- | 0.7594 | 0.8872 | 1400 | 0.6725 |
67
- | 0.7717 | 0.9506 | 1500 | 0.6683 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
 
69
 
70
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5784
22
 
23
  ## Model description
24
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: constant
46
  - lr_scheduler_warmup_ratio: 0.03
47
+ - num_epochs: 5
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
+ | 1.3266 | 0.0634 | 100 | 1.3260 |
54
+ | 1.123 | 0.1267 | 200 | 1.1090 |
55
+ | 1.0242 | 0.1901 | 300 | 1.0121 |
56
+ | 1.0228 | 0.2535 | 400 | 0.9520 |
57
+ | 0.9834 | 0.3169 | 500 | 0.9037 |
58
+ | 0.9726 | 0.3802 | 600 | 0.8456 |
59
+ | 0.9003 | 0.4436 | 700 | 0.8270 |
60
+ | 0.8862 | 0.5070 | 800 | 0.7967 |
61
+ | 0.7788 | 0.5703 | 900 | 0.7715 |
62
+ | 0.831 | 0.6337 | 1000 | 0.7528 |
63
+ | 0.7875 | 0.6971 | 1100 | 0.7319 |
64
+ | 0.8284 | 0.7605 | 1200 | 0.7097 |
65
+ | 0.7387 | 0.8238 | 1300 | 0.6927 |
66
+ | 0.7573 | 0.8872 | 1400 | 0.6735 |
67
+ | 0.7744 | 0.9506 | 1500 | 0.6668 |
68
+ | 0.5684 | 1.0139 | 1600 | 0.6487 |
69
+ | 0.5606 | 1.0773 | 1700 | 0.6378 |
70
+ | 0.5268 | 1.1407 | 1800 | 0.6363 |
71
+ | 0.5727 | 1.2041 | 1900 | 0.6269 |
72
+ | 0.5456 | 1.2674 | 2000 | 0.6196 |
73
+ | 0.5174 | 1.3308 | 2100 | 0.6146 |
74
+ | 0.499 | 1.3942 | 2200 | 0.6055 |
75
+ | 0.5831 | 1.4575 | 2300 | 0.5984 |
76
+ | 0.4884 | 1.5209 | 2400 | 0.5952 |
77
+ | 0.5538 | 1.5843 | 2500 | 0.5829 |
78
+ | 0.5302 | 1.6477 | 2600 | 0.5805 |
79
+ | 0.5506 | 1.7110 | 2700 | 0.5758 |
80
+ | 0.5509 | 1.7744 | 2800 | 0.5708 |
81
+ | 0.5249 | 1.8378 | 2900 | 0.5597 |
82
+ | 0.5249 | 1.9011 | 3000 | 0.5601 |
83
+ | 0.4597 | 1.9645 | 3100 | 0.5585 |
84
+ | 0.383 | 2.0279 | 3200 | 0.5643 |
85
+ | 0.4115 | 2.0913 | 3300 | 0.5666 |
86
+ | 0.3928 | 2.1546 | 3400 | 0.5737 |
87
+ | 0.4634 | 2.2180 | 3500 | 0.5587 |
88
+ | 0.4093 | 2.2814 | 3600 | 0.5615 |
89
+ | 0.3724 | 2.3447 | 3700 | 0.5529 |
90
+ | 0.3846 | 2.4081 | 3800 | 0.5604 |
91
+ | 0.4206 | 2.4715 | 3900 | 0.5539 |
92
+ | 0.4803 | 2.5349 | 4000 | 0.5422 |
93
+ | 0.4319 | 2.5982 | 4100 | 0.5452 |
94
+ | 0.3762 | 2.6616 | 4200 | 0.5523 |
95
+ | 0.4472 | 2.7250 | 4300 | 0.5319 |
96
+ | 0.4048 | 2.7883 | 4400 | 0.5370 |
97
+ | 0.4227 | 2.8517 | 4500 | 0.5401 |
98
+ | 0.4407 | 2.9151 | 4600 | 0.5294 |
99
+ | 0.3998 | 2.9785 | 4700 | 0.5282 |
100
+ | 0.336 | 3.0418 | 4800 | 0.5504 |
101
+ | 0.3022 | 3.1052 | 4900 | 0.5608 |
102
+ | 0.3323 | 3.1686 | 5000 | 0.5584 |
103
+ | 0.3306 | 3.2319 | 5100 | 0.5560 |
104
+ | 0.3557 | 3.2953 | 5200 | 0.5478 |
105
+ | 0.3475 | 3.3587 | 5300 | 0.5656 |
106
+ | 0.3515 | 3.4221 | 5400 | 0.5520 |
107
+ | 0.3236 | 3.4854 | 5500 | 0.5479 |
108
+ | 0.3886 | 3.5488 | 5600 | 0.5436 |
109
+ | 0.339 | 3.6122 | 5700 | 0.5408 |
110
+ | 0.3509 | 3.6755 | 5800 | 0.5499 |
111
+ | 0.3651 | 3.7389 | 5900 | 0.5447 |
112
+ | 0.3707 | 3.8023 | 6000 | 0.5340 |
113
+ | 0.3122 | 3.8657 | 6100 | 0.5360 |
114
+ | 0.3613 | 3.9290 | 6200 | 0.5326 |
115
+ | 0.364 | 3.9924 | 6300 | 0.5315 |
116
+ | 0.2418 | 4.0558 | 6400 | 0.5719 |
117
+ | 0.2349 | 4.1191 | 6500 | 0.5686 |
118
+ | 0.2366 | 4.1825 | 6600 | 0.5750 |
119
+ | 0.2433 | 4.2459 | 6700 | 0.5739 |
120
+ | 0.2566 | 4.3093 | 6800 | 0.5664 |
121
+ | 0.2524 | 4.3726 | 6900 | 0.5798 |
122
+ | 0.2667 | 4.4360 | 7000 | 0.5570 |
123
+ | 0.2528 | 4.4994 | 7100 | 0.5573 |
124
+ | 0.2348 | 4.5627 | 7200 | 0.5723 |
125
+ | 0.2629 | 4.6261 | 7300 | 0.5742 |
126
+ | 0.2705 | 4.6895 | 7400 | 0.5743 |
127
+ | 0.2893 | 4.7529 | 7500 | 0.5560 |
128
+ | 0.2371 | 4.8162 | 7600 | 0.5652 |
129
+ | 0.287 | 4.8796 | 7700 | 0.5436 |
130
+ | 0.2725 | 4.9430 | 7800 | 0.5784 |
131
 
132
 
133
  ### Framework versions
adapter_config.json CHANGED
@@ -20,14 +20,14 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
 
23
  "up_proj",
24
- "q_proj",
25
  "lm_head",
26
- "gate_proj",
27
  "o_proj",
28
  "k_proj",
29
- "down_proj",
30
- "v_proj"
31
  ],
32
  "task_type": "CAUSAL_LM",
33
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "down_proj",
24
+ "gate_proj",
25
+ "v_proj",
26
  "up_proj",
 
27
  "lm_head",
 
28
  "o_proj",
29
  "k_proj",
30
+ "q_proj"
 
31
  ],
32
  "task_type": "CAUSAL_LM",
33
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99f7c88cc73040f518547cd4a1d0ae4e9d4d85d445658df9d5cbb74373544eca
3
  size 2277650904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:041412b19ec0e2c43f0bab7a109c3b2e34e0713a55584bc6ecc886d06168a262
3
  size 2277650904
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c8c6824d374f7ff7467829a3c55bcf3fa4e3097d534cc6e0695a633b8e70562
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b3352f6543e0fd3ad260b5fd9613cd3964ac111f93c6c78d7ba636d9d5ad785
3
  size 5112