eddieman78 commited on
Commit
2ff35c6
1 Parent(s): 30b7c35
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ base_model: bert-base-uncased
9
+ model-index:
10
+ - name: test-sent-classifier-qlora
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
+ # test-sent-classifier-qlora
18
+
19
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.2813
22
+ - Accuracy: 0.9197
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.001
42
+ - train_batch_size: 32
43
+ - eval_batch_size: 32
44
+ - seed: 42
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 3
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 0.2345 | 1.0 | 2105 | 0.2690 | 0.9037 |
54
+ | 0.1808 | 2.0 | 4210 | 0.2797 | 0.9128 |
55
+ | 0.1367 | 3.0 | 6315 | 0.2813 | 0.9197 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - PEFT 0.10.1.dev0
61
+ - Transformers 4.40.0.dev0
62
+ - Pytorch 2.2.1+cu121
63
+ - Datasets 2.18.0
64
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bert-base-uncased",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "query",
24
+ "value"
25
+ ],
26
+ "task_type": "SEQ_CLS",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c69771baec6f27e46966ca97604f762b2370a5f6aff8cb43c94a0fe094eba926
3
+ size 1192672
runs/Mar25_09-59-18_06e9b6116acd/events.out.tfevents.1711360831.06e9b6116acd.1659.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e5eded92d0b2bbc9d88ddc27b9f3423c441f9dae9c4867e86e0a334b1d35a1d
3
+ size 5106
runs/Mar25_10-03-50_06e9b6116acd/events.out.tfevents.1711361090.06e9b6116acd.4758.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e4ebad98b9449db465ba73e8a1a2891ed699ed819fb1bf40bf46becfc8c86b2
3
+ size 5106
runs/Mar25_10-05-37_06e9b6116acd/events.out.tfevents.1711361144.06e9b6116acd.4758.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1c209c513076a6d318b97eedc7a8a1e2d74aa26f2a966d356059889b5ce476f
3
+ size 4184
runs/Mar25_10-07-15_06e9b6116acd/events.out.tfevents.1711361240.06e9b6116acd.4758.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fc51fb9ac2f1963a883a8f5a4e24a0fb84f59dc2dae914587d6b35b6c48ad3d
3
+ size 4184
runs/Mar25_10-09-41_06e9b6116acd/events.out.tfevents.1711361391.06e9b6116acd.6068.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cdccb0b024d6cf4dd4ad34c4d2b923118034e78ec7ec0f4ab9840daab8abdfa
3
+ size 5105
runs/Mar25_10-21-37_06e9b6116acd/events.out.tfevents.1711362139.06e9b6116acd.7568.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fbfe045bb6a2f1b09be540ef3a91504a641980c6fd430c3d7c1138f6614fa13
3
+ size 5951
runs/Mar25_10-32-08_06e9b6116acd/events.out.tfevents.1711362739.06e9b6116acd.7568.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82dd9b2a742a7e32868bcc62915bec82a9eec0676e39d297967557c2b30c65ba
3
+ size 8962
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a1cbb7e484dc2ccb2fd6beabc15535d77ed20f280a257c1bfb11d1844443a64
3
+ size 4920
vocab.txt ADDED
The diff for this file is too large to render. See raw diff