Hugging Face's logo

DaijobuAI
/
smol-finetuned-SC

Safetensors
llama
Generated from Trainer
Model card Files Community
DaijobuAI commited on
Commit
747a38b
•
1 Parent(s): e5fce57

DaijobuAI/ScopeAnalyzer-2

Browse files
Files changed (4) hide show
  1. README.md +103 -0
  2. config.json +41 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: smol-finetuned-SC
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # smol-finetuned-SC
13
+
14
+ This model was trained from scratch on an unknown dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 0.7200
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 5
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - gradient_accumulation_steps: 8
40
+ - total_train_batch_size: 40
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 4
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:------:|:----:|:---------------:|
49
+ | No log | 0.0846 | 100 | 0.8014 |
50
+ | No log | 0.1691 | 200 | 0.8304 |
51
+ | No log | 0.2537 | 300 | 0.7394 |
52
+ | No log | 0.3382 | 400 | 0.8970 |
53
+ | 0.7898 | 0.4228 | 500 | 0.7392 |
54
+ | 0.7898 | 0.5073 | 600 | 0.7310 |
55
+ | 0.7898 | 0.5919 | 700 | 0.8090 |
56
+ | 0.7898 | 0.6765 | 800 | 0.7245 |
57
+ | 0.7898 | 0.7610 | 900 | 0.7344 |
58
+ | 0.7284 | 0.8456 | 1000 | 0.7322 |
59
+ | 0.7284 | 0.9301 | 1100 | 0.7280 |
60
+ | 0.7284 | 1.0147 | 1200 | 0.7254 |
61
+ | 0.7284 | 1.0992 | 1300 | 0.7273 |
62
+ | 0.7284 | 1.1838 | 1400 | 0.7366 |
63
+ | 0.7173 | 1.2684 | 1500 | 0.7314 |
64
+ | 0.7173 | 1.3529 | 1600 | 0.7186 |
65
+ | 0.7173 | 1.4375 | 1700 | 0.7164 |
66
+ | 0.7173 | 1.5220 | 1800 | 0.7190 |
67
+ | 0.7173 | 1.6066 | 1900 | 0.7159 |
68
+ | 0.7196 | 1.6912 | 2000 | 0.7262 |
69
+ | 0.7196 | 1.7757 | 2100 | 0.7288 |
70
+ | 0.7196 | 1.8603 | 2200 | 0.7892 |
71
+ | 0.7196 | 1.9448 | 2300 | 0.7237 |
72
+ | 0.7196 | 2.0294 | 2400 | 0.7182 |
73
+ | 0.7166 | 2.1139 | 2500 | 0.7238 |
74
+ | 0.7166 | 2.1985 | 2600 | 0.7181 |
75
+ | 0.7166 | 2.2831 | 2700 | 0.7149 |
76
+ | 0.7166 | 2.3676 | 2800 | 0.7224 |
77
+ | 0.7166 | 2.4522 | 2900 | 0.7151 |
78
+ | 0.7047 | 2.5367 | 3000 | 0.7209 |
79
+ | 0.7047 | 2.6213 | 3100 | 0.7171 |
80
+ | 0.7047 | 2.7058 | 3200 | 0.7155 |
81
+ | 0.7047 | 2.7904 | 3300 | 0.7157 |
82
+ | 0.7047 | 2.8750 | 3400 | 0.7175 |
83
+ | 0.7081 | 2.9595 | 3500 | 0.7194 |
84
+ | 0.7081 | 3.0441 | 3600 | 0.7164 |
85
+ | 0.7081 | 3.1286 | 3700 | 0.7179 |
86
+ | 0.7081 | 3.2132 | 3800 | 0.7186 |
87
+ | 0.7081 | 3.2977 | 3900 | 0.7223 |
88
+ | 0.694 | 3.3823 | 4000 | 0.7195 |
89
+ | 0.694 | 3.4669 | 4100 | 0.7209 |
90
+ | 0.694 | 3.5514 | 4200 | 0.7181 |
91
+ | 0.694 | 3.6360 | 4300 | 0.7194 |
92
+ | 0.694 | 3.7205 | 4400 | 0.7184 |
93
+ | 0.6989 | 3.8051 | 4500 | 0.7203 |
94
+ | 0.6989 | 3.8897 | 4600 | 0.7192 |
95
+ | 0.6989 | 3.9742 | 4700 | 0.7200 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.43.3
101
+ - Pytorch 2.1.0+cu118
102
+ - Datasets 2.14.5
103
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./smol-finetuned-SC/checkpoint-1200",
3
+ "architectures": [
4
+ "LlamaForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 960,
12
+ "id2label": {
13
+ "0": "LOOSE",
14
+ "1": "NOT_IN_SCOPE",
15
+ "2": "STRICT"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 2560,
19
+ "label2id": {
20
+ "LOOSE": 0,
21
+ "NOT_IN_SCOPE": 1,
22
+ "STRICT": 2
23
+ },
24
+ "max_position_embeddings": 2048,
25
+ "mlp_bias": false,
26
+ "model_type": "llama",
27
+ "num_attention_heads": 15,
28
+ "num_hidden_layers": 32,
29
+ "num_key_value_heads": 5,
30
+ "pad_token_id": 49152,
31
+ "pretraining_tp": 1,
32
+ "problem_type": "single_label_classification",
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": null,
35
+ "rope_theta": 10000.0,
36
+ "tie_word_embeddings": true,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.43.3",
39
+ "use_cache": true,
40
+ "vocab_size": 49159
41
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fe354e1da6aab8b1c8e7deb59a261774b0c954568a8a03f89795d70a9715788
3
+ size 1447355568
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc11760d981b09a36a7b5903e4fcf80003e7110a27b1850df8095392c2b0fac6
3
+ size 5240