TrevorJS commited on
Commit
30315d8
·
verified ·
1 Parent(s): 5680db4

TrevorJS/check-amount-deverbalizer-smollm2-mk2

Browse files
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: HuggingFaceTB/SmolLM2-135M-Instruct
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: check-amount-deverbalizer-smollm2
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # check-amount-deverbalizer-smollm2
16
+
17
+ This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.1520
20
+ - Json Parse Rate: 0.96
21
+ - Dollar Accuracy: 0.96
22
+ - Cents Accuracy: 0.96
23
+ - Digit Count Accuracy: 0.96
24
+ - Perfect Match: 0.96
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 5e-05
44
+ - train_batch_size: 128
45
+ - eval_batch_size: 2
46
+ - seed: 42
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 100
50
+ - num_epochs: 3
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Json Parse Rate | Dollar Accuracy | Cents Accuracy | Digit Count Accuracy | Perfect Match |
55
+ |:-------------:|:------:|:----:|:---------------:|:---------------:|:---------------:|:--------------:|:--------------------:|:-------------:|
56
+ | 0.1588 | 0.2128 | 200 | 0.1580 | 0.9571 | 0.9271 | 0.9529 | 0.95 | 0.9186 |
57
+ | 0.1576 | 0.4255 | 400 | 0.1549 | 0.96 | 0.9557 | 0.96 | 0.96 | 0.9557 |
58
+ | 0.1546 | 0.6383 | 600 | 0.1539 | 0.96 | 0.9571 | 0.96 | 0.96 | 0.9571 |
59
+ | 0.154 | 0.8511 | 800 | 0.1541 | 0.9586 | 0.95 | 0.9586 | 0.9586 | 0.95 |
60
+ | 0.1539 | 1.0638 | 1000 | 0.1536 | 0.96 | 0.9557 | 0.96 | 0.96 | 0.9557 |
61
+ | 0.1544 | 1.2766 | 1200 | 0.1524 | 0.96 | 0.96 | 0.96 | 0.96 | 0.96 |
62
+ | 0.1535 | 1.4894 | 1400 | 0.1529 | 0.96 | 0.9571 | 0.96 | 0.96 | 0.9571 |
63
+ | 0.1537 | 1.7021 | 1600 | 0.1525 | 0.96 | 0.9586 | 0.96 | 0.96 | 0.9586 |
64
+ | 0.1548 | 1.9149 | 1800 | 0.1527 | 0.96 | 0.9586 | 0.96 | 0.96 | 0.9586 |
65
+ | 0.1545 | 2.1277 | 2000 | 0.1524 | 0.96 | 0.96 | 0.96 | 0.96 | 0.96 |
66
+ | 0.1534 | 2.3404 | 2200 | 0.1526 | 0.96 | 0.96 | 0.96 | 0.96 | 0.96 |
67
+ | 0.1533 | 2.5532 | 2400 | 0.1522 | 0.96 | 0.96 | 0.96 | 0.96 | 0.96 |
68
+ | 0.1524 | 2.7660 | 2600 | 0.1521 | 0.96 | 0.96 | 0.96 | 0.96 | 0.96 |
69
+ | 0.1527 | 2.9787 | 2800 | 0.1520 | 0.96 | 0.96 | 0.96 | 0.96 | 0.96 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.48.2
75
+ - Pytorch 2.5.1+cu124
76
+ - Datasets 3.2.0
77
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 576,
13
+ "initializer_range": 0.041666666666666664,
14
+ "intermediate_size": 1536,
15
+ "is_llama_config": true,
16
+ "max_position_embeddings": 8192,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 9,
20
+ "num_hidden_layers": 30,
21
+ "num_key_value_heads": 3,
22
+ "pad_token_id": 2,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_interleaved": false,
26
+ "rope_scaling": null,
27
+ "rope_theta": 100000,
28
+ "tie_word_embeddings": true,
29
+ "torch_dtype": "float32",
30
+ "transformers.js_config": {
31
+ "kv_cache_dtype": {
32
+ "fp16": "float16",
33
+ "q4f16": "float16"
34
+ }
35
+ },
36
+ "transformers_version": "4.48.2",
37
+ "use_cache": true,
38
+ "vocab_size": 49152
39
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 2,
6
+ "transformers_version": "4.48.2"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e6c8d044765a2fcb3dcb0cbdc8313ff3b1f59fc6b487ce3cbb45e7fad01436b
3
+ size 538090408
runs/Feb13_20-25-01_8384fb57439c/events.out.tfevents.1739478468.8384fb57439c.21274.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8221c4142627a347b67f49f65a15941e73925f7b901f0529d301777230e3e785
3
+ size 5459
runs/Feb13_20-34-45_8384fb57439c/events.out.tfevents.1739478916.8384fb57439c.23935.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea598a286928c686c0ac4c9bb1261fcdaa1d263acb9525c0d42556386092eb0
3
+ size 4184
runs/Feb13_20-36-43_8384fb57439c/events.out.tfevents.1739479023.8384fb57439c.24649.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b2b751f0c66dbb0bd2c17806332d4c47f5b898c90f568828eed651750d99388
3
+ size 9631
runs/Feb13_20-55-09_8384fb57439c/events.out.tfevents.1739480119.8384fb57439c.29918.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a4ce357758fa16b4551cb90bdcfed0728b98c6290d924747711d7caca879c6b
3
+ size 5459
runs/Feb13_21-03-14_8384fb57439c/events.out.tfevents.1739480619.8384fb57439c.32345.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77ea15690166b5672c3f95593b676b9b5f846758dde9c15f0cf73686e22659c2
3
+ size 4184
runs/Feb13_21-05-42_8384fb57439c/events.out.tfevents.1739480774.8384fb57439c.33196.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f14926ddf35bc8ec663f102e46779e5eca10196152aaef89679b6baeeee4ee06
3
+ size 9631
runs/Feb13_21-11-39_8384fb57439c/events.out.tfevents.1739481119.8384fb57439c.35000.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca3b04831793a815a41991a299301146d1b640cbdb8e3daba963f31e158f97e
3
+ size 9629
runs/Feb13_21-33-49_8384fb57439c/events.out.tfevents.1739482448.8384fb57439c.41153.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f8df462afc8f7be5461548d735505d19ca865e593c8ee9a19f2d5d8199926f3
3
+ size 9631
runs/Feb13_21-39-14_8384fb57439c/events.out.tfevents.1739482773.8384fb57439c.42634.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b2a1fb4a98494aef42d2e6acc84768eda27d688c2e4cacf59da6552ea17761a
3
+ size 73219
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|im_start|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
+ },
141
+ "additional_special_tokens": [
142
+ "<|im_start|>",
143
+ "<|im_end|>"
144
+ ],
145
+ "bos_token": "<|im_start|>",
146
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
147
+ "clean_up_tokenization_spaces": false,
148
+ "eos_token": "<|im_end|>",
149
+ "extra_special_tokens": {},
150
+ "model_max_length": 8192,
151
+ "pad_token": "<|im_end|>",
152
+ "tokenizer_class": "GPT2Tokenizer",
153
+ "unk_token": "<|endoftext|>",
154
+ "vocab_size": 49152
155
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07132bb19fc405cbe2eeb5b9c40933863e5af26a79f04ce6466723ca239432f0
3
+ size 5432
vocab.json ADDED
The diff for this file is too large to render. See raw diff