Hugging Face's logo

rishavranaut
/
QWEN_FACT_updates

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
rishavranaut commited on
Commit
53c6bbf
·
verified ·
1 Parent(s): 35b64d1

rishavranaut/QWEN_FACT_updates

Browse files
Files changed (5) hide show
  1. README.md +22 -22
  2. adapter_config.json +1 -1
  3. adapter_model.safetensors +1 -1
  4. runs/Jun28_21-18-33_iit-p/events.out.tfevents.1719589714.iit-p +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -18,20 +18,20 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.5057
22
- - Balanced Accuracy: 0.7773
23
- - Accuracy: 0.7980
24
- - Micro F1: 0.7980
25
- - Macro F1: 0.7368
26
- - Weighted F1: 0.8096
27
  - Classification Report: precision recall f1-score support
28
 
29
  0 0.92 0.81 0.86 857
30
- 1 0.52 0.74 0.61 232
31
 
32
  accuracy 0.80 1089
33
  macro avg 0.72 0.78 0.74 1089
34
- weighted avg 0.83 0.80 0.81 1089
35
 
36
 
37
  ## Model description
@@ -61,9 +61,9 @@ The following hyperparameters were used during training:
61
 
62
  ### Training results
63
 
64
- | Training Loss | Epoch | Step | Validation Loss | Balanced Accuracy | Accuracy | Micro F1 | Macro F1 | Weighted F1 | Classification Report |
65
- |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------:|:--------:|:--------:|:-----------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
66
- | 0.6846 | 1.0 | 391 | 0.5173 | 0.7553 | 0.7980 | 0.7980 | 0.7278 | 0.8071 | precision recall f1-score support
67
 
68
  0 0.91 0.83 0.87 857
69
  1 0.52 0.68 0.59 232
@@ -71,8 +71,8 @@ The following hyperparameters were used during training:
71
  accuracy 0.80 1089
72
  macro avg 0.71 0.76 0.73 1089
73
  weighted avg 0.82 0.80 0.81 1089
74
- |
75
- | 0.5021 | 2.0 | 782 | 0.4834 | 0.7673 | 0.8044 | 0.8044 | 0.7374 | 0.8135 | precision recall f1-score support
76
 
77
  0 0.91 0.83 0.87 857
78
  1 0.53 0.70 0.60 232
@@ -80,8 +80,8 @@ weighted avg 0.82 0.80 0.81 1089
80
  accuracy 0.80 1089
81
  macro avg 0.72 0.77 0.74 1089
82
  weighted avg 0.83 0.80 0.81 1089
83
- |
84
- | 0.408 | 3.0 | 1173 | 0.4296 | 0.7667 | 0.8356 | 0.8356 | 0.7605 | 0.8375 | precision recall f1-score support
85
 
86
  0 0.90 0.89 0.89 857
87
  1 0.61 0.65 0.63 232
@@ -89,8 +89,8 @@ weighted avg 0.83 0.80 0.81 1089
89
  accuracy 0.84 1089
90
  macro avg 0.75 0.77 0.76 1089
91
  weighted avg 0.84 0.84 0.84 1089
92
- |
93
- | 0.3032 | 4.0 | 1564 | 0.5927 | 0.7712 | 0.7511 | 0.7511 | 0.7015 | 0.7714 | precision recall f1-score support
94
 
95
  0 0.93 0.74 0.82 857
96
  1 0.45 0.81 0.58 232
@@ -98,16 +98,16 @@ weighted avg 0.84 0.84 0.84 1089
98
  accuracy 0.75 1089
99
  macro avg 0.69 0.77 0.70 1089
100
  weighted avg 0.83 0.75 0.77 1089
101
- |
102
- | 0.2434 | 5.0 | 1955 | 0.5057 | 0.7773 | 0.7980 | 0.7980 | 0.7368 | 0.8096 | precision recall f1-score support
103
 
104
  0 0.92 0.81 0.86 857
105
- 1 0.52 0.74 0.61 232
106
 
107
  accuracy 0.80 1089
108
  macro avg 0.72 0.78 0.74 1089
109
- weighted avg 0.83 0.80 0.81 1089
110
- |
111
 
112
 
113
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5144
22
+ - Balanced Accuracy: 0.7801
23
+ - Accuracy: 0.7998
24
+ - Micro F1: 0.7998
25
+ - Macro F1: 0.7392
26
+ - Weighted F1: 0.8114
27
  - Classification Report: precision recall f1-score support
28
 
29
  0 0.92 0.81 0.86 857
30
+ 1 0.52 0.75 0.61 232
31
 
32
  accuracy 0.80 1089
33
  macro avg 0.72 0.78 0.74 1089
34
+ weighted avg 0.84 0.80 0.81 1089
35
 
36
 
37
  ## Model description
 
61
 
62
  ### Training results
63
 
64
+ | Training Loss | Epoch | Step | Accuracy | Balanced Accuracy | Classification Report | Validation Loss | Macro F1 | Micro F1 | Weighted F1 |
65
+ |:-------------:|:-----:|:----:|:--------:|:-----------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------:|:--------:|:--------:|:-----------:|
66
+ | 0.6846 | 1.0 | 391 | 0.7980 | 0.7553 | precision recall f1-score support
67
 
68
  0 0.91 0.83 0.87 857
69
  1 0.52 0.68 0.59 232
 
71
  accuracy 0.80 1089
72
  macro avg 0.71 0.76 0.73 1089
73
  weighted avg 0.82 0.80 0.81 1089
74
+ | 0.5173 | 0.7278 | 0.7980 | 0.8071 |
75
+ | 0.5021 | 2.0 | 782 | 0.8044 | 0.7673 | precision recall f1-score support
76
 
77
  0 0.91 0.83 0.87 857
78
  1 0.53 0.70 0.60 232
 
80
  accuracy 0.80 1089
81
  macro avg 0.72 0.77 0.74 1089
82
  weighted avg 0.83 0.80 0.81 1089
83
+ | 0.4834 | 0.7374 | 0.8044 | 0.8135 |
84
+ | 0.408 | 3.0 | 1173 | 0.8356 | 0.7667 | precision recall f1-score support
85
 
86
  0 0.90 0.89 0.89 857
87
  1 0.61 0.65 0.63 232
 
89
  accuracy 0.84 1089
90
  macro avg 0.75 0.77 0.76 1089
91
  weighted avg 0.84 0.84 0.84 1089
92
+ | 0.4296 | 0.7605 | 0.8356 | 0.8375 |
93
+ | 0.3032 | 4.0 | 1564 | 0.7511 | 0.7712 | precision recall f1-score support
94
 
95
  0 0.93 0.74 0.82 857
96
  1 0.45 0.81 0.58 232
 
98
  accuracy 0.75 1089
99
  macro avg 0.69 0.77 0.70 1089
100
  weighted avg 0.83 0.75 0.77 1089
101
+ | 0.5927 | 0.7015 | 0.7511 | 0.7714 |
102
+ | 0.234 | 5.0 | 1955 | 0.5144 | 0.7801 | 0.7998 | 0.7998 | 0.7392 | 0.8114 | precision recall f1-score support
103
 
104
  0 0.92 0.81 0.86 857
105
+ 1 0.52 0.75 0.61 232
106
 
107
  accuracy 0.80 1089
108
  macro avg 0.72 0.78 0.74 1089
109
+ weighted avg 0.84 0.80 0.81 1089
110
+ |
111
 
112
 
113
  ### Framework versions
adapter_config.json CHANGED
@@ -25,8 +25,8 @@
25
  "revision": null,
26
  "target_modules": [
27
  "o_proj",
28
- "v_proj",
29
  "q_proj",
 
30
  "k_proj"
31
  ],
32
  "task_type": "SEQ_CLS",
 
25
  "revision": null,
26
  "target_modules": [
27
  "o_proj",
 
28
  "q_proj",
29
+ "v_proj",
30
  "k_proj"
31
  ],
32
  "task_type": "SEQ_CLS",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed5349b8842ccd5365f33924c16ba9805c0a9b9f613b012d166ae4cad715501d
3
  size 40428968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de15a3a4e32ab6a3e5079a5e89ee159367313e211ab2a2238d8b29b4877834bd
3
  size 40428968
runs/Jun28_21-18-33_iit-p/events.out.tfevents.1719589714.iit-p ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2acf16c82f81480320e5f16395b4086d3f003380f0ccc4623ac874eb137d52eb
3
+ size 6516
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9da80e3a0c4c6707719a75f48a9b9ab14f42bc07d5088d36b355b83bb45776d2
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:102953a21584cc33046ebfdb457e15723918084eb46df83bbee9772144002c4f
3
  size 5176