Hugging Face's logo

ethansandbar
/
run_gemma-2-2b_20250507_202421

PEFT
Safetensors
Generated from Trainer
Model card Files Community
ethansandbar commited on
Commit
69d1c35
·
verified ·
1 Parent(s): 967c5ad

run_gemma-2-2b_20250507_202421-intent-cls

Browse files
Files changed (4) hide show
  1. README.md +86 -0
  2. adapter_config.json +40 -0
  3. adapter_model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: gemma
4
+ base_model: google/gemma-2-2b
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: run_gemma-2-2b_20250507_202421
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # run_gemma-2-2b_20250507_202421
18
+
19
+ This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.5589
22
+ - Accuracy: 0.7986
23
+ - Precision General: 0.7985
24
+ - Recall General: 0.9722
25
+ - F1 General: 0.8768
26
+ - Precision Memo: 0.8
27
+ - Recall Memo: 0.3333
28
+ - F1 Memo: 0.4706
29
+ - Precision Album: 0.0
30
+ - Recall Album: 0.0
31
+ - F1 Album: 0.0
32
+
33
+ ## Model description
34
+
35
+ More information needed
36
+
37
+ ## Intended uses & limitations
38
+
39
+ More information needed
40
+
41
+ ## Training and evaluation data
42
+
43
+ More information needed
44
+
45
+ ## Training procedure
46
+
47
+ ### Training hyperparameters
48
+
49
+ The following hyperparameters were used during training:
50
+ - learning_rate: 0.0001
51
+ - train_batch_size: 16
52
+ - eval_batch_size: 8
53
+ - seed: 42
54
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
55
+ - lr_scheduler_type: cosine
56
+ - lr_scheduler_warmup_ratio: 0.1
57
+ - num_epochs: 15
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision General | Recall General | F1 General | Precision Memo | Recall Memo | F1 Memo | Precision Album | Recall Album | F1 Album |
62
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------------:|:--------------:|:----------:|:--------------:|:-----------:|:-------:|:---------------:|:------------:|:--------:|
63
+ | 0.8016 | 1.0 | 147 | 1.0285 | 0.5274 | 0.816 | 0.4744 | 0.6 | 0.3114 | 0.7222 | 0.4351 | 0.0 | 0.0 | 0.0 |
64
+ | 0.5683 | 2.0 | 294 | 0.6889 | 0.75 | 0.8025 | 0.8884 | 0.8433 | 0.5185 | 0.3889 | 0.4444 | 0.0 | 0.0 | 0.0 |
65
+ | 0.5543 | 3.0 | 441 | 0.5514 | 0.7705 | 0.7891 | 0.9395 | 0.8577 | 0.6389 | 0.3194 | 0.4259 | 0.0 | 0.0 | 0.0 |
66
+ | 0.4472 | 4.0 | 588 | 0.5336 | 0.8151 | 0.8132 | 0.9721 | 0.8856 | 0.8286 | 0.4028 | 0.5421 | 0.0 | 0.0 | 0.0 |
67
+ | 0.4579 | 5.0 | 735 | 0.6379 | 0.75 | 0.8114 | 0.8605 | 0.8352 | 0.5312 | 0.4722 | 0.5 | 0.0 | 0.0 | 0.0 |
68
+ | 0.5291 | 6.0 | 882 | 0.6045 | 0.8048 | 0.8062 | 0.9674 | 0.8795 | 0.7941 | 0.375 | 0.5094 | 0.0 | 0.0 | 0.0 |
69
+ | 0.4397 | 7.0 | 1029 | 0.5941 | 0.8116 | 0.8293 | 0.9488 | 0.8850 | 0.7174 | 0.4583 | 0.5593 | 0.0 | 0.0 | 0.0 |
70
+ | 0.3478 | 8.0 | 1176 | 0.6598 | 0.8151 | 0.8061 | 0.9860 | 0.8870 | 0.8966 | 0.3611 | 0.5149 | 0.0 | 0.0 | 0.0 |
71
+ | 0.4765 | 9.0 | 1323 | 0.6486 | 0.8082 | 0.8069 | 0.9721 | 0.8819 | 0.8182 | 0.375 | 0.5143 | 0.0 | 0.0 | 0.0 |
72
+ | 0.3421 | 10.0 | 1470 | 0.6713 | 0.8082 | 0.8 | 0.9860 | 0.8833 | 0.8889 | 0.3333 | 0.4848 | 0.0 | 0.0 | 0.0 |
73
+ | 0.304 | 11.0 | 1617 | 0.6890 | 0.8048 | 0.8038 | 0.9721 | 0.88 | 0.8125 | 0.3611 | 0.5 | 0.0 | 0.0 | 0.0 |
74
+ | 0.3041 | 12.0 | 1764 | 0.6821 | 0.8014 | 0.8054 | 0.9628 | 0.8771 | 0.7714 | 0.375 | 0.5047 | 0.0 | 0.0 | 0.0 |
75
+ | 0.3565 | 13.0 | 1911 | 0.6882 | 0.8048 | 0.8086 | 0.9628 | 0.8790 | 0.7778 | 0.3889 | 0.5185 | 0.0 | 0.0 | 0.0 |
76
+ | 0.3987 | 14.0 | 2058 | 0.6888 | 0.8014 | 0.8054 | 0.9628 | 0.8771 | 0.7714 | 0.375 | 0.5047 | 0.0 | 0.0 | 0.0 |
77
+ | 0.338 | 15.0 | 2205 | 0.6909 | 0.8014 | 0.8054 | 0.9628 | 0.8771 | 0.7714 | 0.375 | 0.5047 | 0.0 | 0.0 | 0.0 |
78
+
79
+
80
+ ### Framework versions
81
+
82
+ - PEFT 0.15.0
83
+ - Transformers 4.50.0.dev0
84
+ - Pytorch 2.6.0+cu124
85
+ - Datasets 3.4.1
86
+ - Tokenizers 0.21.1
adapter_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "google/gemma-2-2b",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 32,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": [
22
+ "classifier",
23
+ "score"
24
+ ],
25
+ "peft_type": "LORA",
26
+ "r": 8,
27
+ "rank_pattern": {},
28
+ "revision": null,
29
+ "target_modules": [
30
+ "up_proj",
31
+ "q_proj",
32
+ "down_proj",
33
+ "v_proj",
34
+ "o_proj"
35
+ ],
36
+ "task_type": "SEQ_CLS",
37
+ "trainable_token_indices": null,
38
+ "use_dora": false,
39
+ "use_rslora": false
40
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad71579cfc45efe3d5af0b81e8c57249983e530d568d4855bd614aa01692065d
3
+ size 29241824
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f1deaafeac090b54b5473359df85a66f1e0600f923b20de5f11ac2440df74ec
3
+ size 5368