Hugging Face's logo

abhi317
/
ps

PEFT
Safetensors
t5
Generated from Trainer
Model card Files Community
abhi317 commited on
Commit
6e4277c
•
1 Parent(s): c452ece

DONE

Browse files
Files changed (4) hide show
  1. README.md +15 -107
  2. adapter_config.json +1 -1
  3. adapter_model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,7 +1,9 @@
1
  ---
2
- base_model: abhi317/results_2
 
3
  tags:
4
  - generated_from_trainer
 
5
  model-index:
6
  - name: ps
7
  results: []
@@ -12,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
12
 
13
  # ps
14
 
15
- This model is a fine-tuned version of [abhi317/results_2](https://huggingface.co/abhi317/results_2) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.8012
18
 
19
  ## Model description
20
 
@@ -34,122 +36,28 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 2e-05
37
- - train_batch_size: 8
38
- - eval_batch_size: 8
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
- - num_epochs: 100
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | 3.9667 | 1.0 | 1 | 3.2203 |
49
- | 3.9667 | 2.0 | 2 | 3.1776 |
50
- | 3.9667 | 3.0 | 3 | 3.1302 |
51
- | 3.9667 | 4.0 | 4 | 3.0774 |
52
- | 3.9667 | 5.0 | 5 | 3.0206 |
53
- | 3.9667 | 6.0 | 6 | 2.9620 |
54
- | 3.9667 | 7.0 | 7 | 2.9025 |
55
- | 3.9667 | 8.0 | 8 | 2.8303 |
56
- | 3.9667 | 9.0 | 9 | 2.7513 |
57
- | 3.9667 | 10.0 | 10 | 2.6685 |
58
- | 3.9667 | 11.0 | 11 | 2.5901 |
59
- | 3.9667 | 12.0 | 12 | 2.5100 |
60
- | 3.9667 | 13.0 | 13 | 2.4258 |
61
- | 3.9667 | 14.0 | 14 | 2.3446 |
62
- | 3.9667 | 15.0 | 15 | 2.2655 |
63
- | 3.9667 | 16.0 | 16 | 2.1921 |
64
- | 3.9667 | 17.0 | 17 | 2.1228 |
65
- | 3.9667 | 18.0 | 18 | 2.0600 |
66
- | 3.9667 | 19.0 | 19 | 2.0048 |
67
- | 3.9667 | 20.0 | 20 | 1.9579 |
68
- | 3.9667 | 21.0 | 21 | 1.9125 |
69
- | 3.9667 | 22.0 | 22 | 1.8690 |
70
- | 3.9667 | 23.0 | 23 | 1.8311 |
71
- | 3.9667 | 24.0 | 24 | 1.7907 |
72
- | 3.9667 | 25.0 | 25 | 1.7512 |
73
- | 3.9667 | 26.0 | 26 | 1.7272 |
74
- | 3.9667 | 27.0 | 27 | 1.7020 |
75
- | 3.9667 | 28.0 | 28 | 1.6785 |
76
- | 3.9667 | 29.0 | 29 | 1.6482 |
77
- | 3.9667 | 30.0 | 30 | 1.6108 |
78
- | 3.9667 | 31.0 | 31 | 1.5778 |
79
- | 3.9667 | 32.0 | 32 | 1.5455 |
80
- | 3.9667 | 33.0 | 33 | 1.5059 |
81
- | 3.9667 | 34.0 | 34 | 1.4684 |
82
- | 3.9667 | 35.0 | 35 | 1.4343 |
83
- | 3.9667 | 36.0 | 36 | 1.3967 |
84
- | 3.9667 | 37.0 | 37 | 1.3623 |
85
- | 3.9667 | 38.0 | 38 | 1.3328 |
86
- | 3.9667 | 39.0 | 39 | 1.3074 |
87
- | 3.9667 | 40.0 | 40 | 1.2830 |
88
- | 3.9667 | 41.0 | 41 | 1.2600 |
89
- | 3.9667 | 42.0 | 42 | 1.2419 |
90
- | 3.9667 | 43.0 | 43 | 1.2293 |
91
- | 3.9667 | 44.0 | 44 | 1.2184 |
92
- | 3.9667 | 45.0 | 45 | 1.2097 |
93
- | 3.9667 | 46.0 | 46 | 1.2001 |
94
- | 3.9667 | 47.0 | 47 | 1.1898 |
95
- | 3.9667 | 48.0 | 48 | 1.1794 |
96
- | 3.9667 | 49.0 | 49 | 1.1679 |
97
- | 3.9667 | 50.0 | 50 | 1.1534 |
98
- | 3.9667 | 51.0 | 51 | 1.1407 |
99
- | 3.9667 | 52.0 | 52 | 1.1269 |
100
- | 3.9667 | 53.0 | 53 | 1.1130 |
101
- | 3.9667 | 54.0 | 54 | 1.0979 |
102
- | 3.9667 | 55.0 | 55 | 1.0840 |
103
- | 3.9667 | 56.0 | 56 | 1.0725 |
104
- | 3.9667 | 57.0 | 57 | 1.0626 |
105
- | 3.9667 | 58.0 | 58 | 1.0536 |
106
- | 3.9667 | 59.0 | 59 | 1.0447 |
107
- | 3.9667 | 60.0 | 60 | 1.0377 |
108
- | 3.9667 | 61.0 | 61 | 1.0330 |
109
- | 3.9667 | 62.0 | 62 | 1.0267 |
110
- | 3.9667 | 63.0 | 63 | 1.0243 |
111
- | 3.9667 | 64.0 | 64 | 1.0188 |
112
- | 3.9667 | 65.0 | 65 | 1.0114 |
113
- | 3.9667 | 66.0 | 66 | 1.0058 |
114
- | 3.9667 | 67.0 | 67 | 0.9979 |
115
- | 3.9667 | 68.0 | 68 | 0.9849 |
116
- | 3.9667 | 69.0 | 69 | 0.9685 |
117
- | 3.9667 | 70.0 | 70 | 0.9535 |
118
- | 3.9667 | 71.0 | 71 | 0.9384 |
119
- | 3.9667 | 72.0 | 72 | 0.9272 |
120
- | 3.9667 | 73.0 | 73 | 0.9154 |
121
- | 3.9667 | 74.0 | 74 | 0.9060 |
122
- | 3.9667 | 75.0 | 75 | 0.8956 |
123
- | 3.9667 | 76.0 | 76 | 0.8864 |
124
- | 3.9667 | 77.0 | 77 | 0.8766 |
125
- | 3.9667 | 78.0 | 78 | 0.8688 |
126
- | 3.9667 | 79.0 | 79 | 0.8624 |
127
- | 3.9667 | 80.0 | 80 | 0.8556 |
128
- | 3.9667 | 81.0 | 81 | 0.8493 |
129
- | 3.9667 | 82.0 | 82 | 0.8439 |
130
- | 3.9667 | 83.0 | 83 | 0.8397 |
131
- | 3.9667 | 84.0 | 84 | 0.8363 |
132
- | 3.9667 | 85.0 | 85 | 0.8338 |
133
- | 3.9667 | 86.0 | 86 | 0.8304 |
134
- | 3.9667 | 87.0 | 87 | 0.8272 |
135
- | 3.9667 | 88.0 | 88 | 0.8233 |
136
- | 3.9667 | 89.0 | 89 | 0.8200 |
137
- | 3.9667 | 90.0 | 90 | 0.8166 |
138
- | 3.9667 | 91.0 | 91 | 0.8130 |
139
- | 3.9667 | 92.0 | 92 | 0.8100 |
140
- | 3.9667 | 93.0 | 93 | 0.8078 |
141
- | 3.9667 | 94.0 | 94 | 0.8055 |
142
- | 3.9667 | 95.0 | 95 | 0.8041 |
143
- | 3.9667 | 96.0 | 96 | 0.8029 |
144
- | 3.9667 | 97.0 | 97 | 0.8020 |
145
- | 3.9667 | 98.0 | 98 | 0.8016 |
146
- | 3.9667 | 99.0 | 99 | 0.8013 |
147
- | 2.3542 | 100.0 | 100 | 0.8012 |
148
 
149
 
150
  ### Framework versions
151
 
 
152
  - Transformers 4.39.3
153
  - Pytorch 2.1.2
154
  - Datasets 2.18.0
155
- - Tokenizers 0.15.2
 
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: ps
9
  results: []
 
14
 
15
  # ps
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: 19.4910
20
 
21
  ## Model description
22
 
 
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: 5
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 19.9084 | 1.0 | 1 | 19.7991 |
51
+ | 19.9084 | 2.0 | 2 | 19.6841 |
52
+ | 19.9084 | 3.0 | 3 | 19.5861 |
53
+ | 19.9084 | 4.0 | 4 | 19.5192 |
54
+ | 19.9084 | 5.0 | 5 | 19.4910 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
58
 
59
+ - PEFT 0.11.1
60
  - Transformers 4.39.3
61
  - Pytorch 2.1.2
62
  - Datasets 2.18.0
63
+ - Tokenizers 0.15.2
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
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,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": null,
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f001832a9e6b8ae9ba7f37737066c123df0fc14376a8e6e4e454ebecf1d3d54
3
- size 13648432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fe1bedebf8b0b6aaa62557c64d72a9a58bc686f84f813f0266acdb0aa71658f
3
+ size 13650608
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2982d9f9d57ba77591a7b69f587290e663ed86ad8451cdaed738c2134d103b02
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff451ee64846e34c441e6dddb4538e307417605b3e4d995e95598f3148592f03
3
  size 4856