Hugging Face's logo

CodeIsAbstract
/
HybridModelScratch_lightn_Conti

Transformers
Safetensors
hybrid_fourier_lm
Generated from Trainer
Model card Files
xet
 Community
CodeIsAbstract commited on
Commit
88c7aeb
·
verified ·
1 Parent(s): 5f63d8a

Model save

Browse files
Files changed (8) hide show
  1. README.md +109 -0
  2. best_model_streaming/config.json +33 -0
  3. best_model_streaming/model.safetensors +3 -0
  4. best_model_streaming/tokenizer.json +0 -0
  5. best_model_streaming/tokenizer_config.json +14 -0
  6. best_model_streaming/training_args.bin +3 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +14 -0
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: HybridModelScratch_lightn_Conti
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
+ # HybridModelScratch_lightn_Conti
16
+
17
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 3.2749
20
+ - Accuracy: 0.3848
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.001
40
+ - train_batch_size: 120
41
+ - eval_batch_size: 16
42
+ - seed: 42
43
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
44
+ - lr_scheduler_type: cosine
45
+ - lr_scheduler_warmup_steps: 150
46
+ - training_steps: 50000
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
51
+ |:-------------:|:-----:|:-----:|:--------:|:---------------:|
52
+ | 4.5799 | 0.02 | 1000 | 0.2697 | 4.5051 |
53
+ | 4.1703 | 0.04 | 2000 | 0.3056 | 4.1036 |
54
+ | 4.0044 | 0.06 | 3000 | 0.3195 | 3.9451 |
55
+ | 3.8638 | 0.08 | 4000 | 0.3281 | 3.8499 |
56
+ | 3.7991 | 0.1 | 5000 | 0.3350 | 3.7702 |
57
+ | 3.6996 | 0.12 | 6000 | 0.3414 | 3.7112 |
58
+ | 3.6319 | 0.14 | 7000 | 0.3448 | 3.6666 |
59
+ | 3.6062 | 0.16 | 8000 | 0.3476 | 3.6405 |
60
+ | 3.6643 | 0.18 | 9000 | 0.3498 | 3.6175 |
61
+ | 3.5992 | 0.2 | 10000 | 0.3535 | 3.5797 |
62
+ | 3.5671 | 0.22 | 11000 | 0.3559 | 3.5543 |
63
+ | 3.5230 | 0.24 | 12000 | 0.3578 | 3.5308 |
64
+ | 3.5930 | 0.26 | 13000 | 0.3593 | 3.5190 |
65
+ | 3.5475 | 0.28 | 14000 | 0.3616 | 3.4961 |
66
+ | 3.5220 | 0.3 | 15000 | 0.3633 | 3.4778 |
67
+ | 3.5050 | 0.32 | 16000 | 0.3644 | 3.4654 |
68
+ | 3.4776 | 0.34 | 17000 | 0.3666 | 3.4458 |
69
+ | 3.4829 | 0.36 | 18000 | 0.3674 | 3.4346 |
70
+ | 3.4483 | 0.38 | 19000 | 0.3694 | 3.4189 |
71
+ | 3.4418 | 0.4 | 20000 | 0.3704 | 3.4063 |
72
+ | 3.4183 | 0.42 | 21000 | 0.3720 | 3.3956 |
73
+ | 3.3858 | 0.44 | 22000 | 0.3725 | 3.3870 |
74
+ | 3.3654 | 0.46 | 23000 | 0.3728 | 3.3824 |
75
+ | 3.3943 | 0.48 | 24000 | 0.3734 | 3.3756 |
76
+ | 3.3957 | 0.5 | 25000 | 0.3757 | 3.3548 |
77
+ | 3.3787 | 0.52 | 26000 | 0.3769 | 3.3452 |
78
+ | 3.3605 | 0.54 | 27000 | 0.3777 | 3.3393 |
79
+ | 3.3707 | 0.56 | 28000 | 0.3787 | 3.3302 |
80
+ | 3.3508 | 0.58 | 29000 | 0.3793 | 3.3221 |
81
+ | 3.3566 | 0.6 | 30000 | 0.3802 | 3.3148 |
82
+ | 3.3441 | 0.62 | 31000 | 0.3809 | 3.3054 |
83
+ | 3.3268 | 0.64 | 32000 | 0.3814 | 3.3028 |
84
+ | 3.0620 | 0.02 | 33000 | 3.3109 | 0.3804 |
85
+ | 3.0159 | 0.04 | 34000 | 3.3074 | 0.3810 |
86
+ | 3.0230 | 0.06 | 35000 | 3.3025 | 0.3815 |
87
+ | 3.0335 | 0.08 | 36000 | 3.2988 | 0.3821 |
88
+ | 3.0098 | 0.1 | 37000 | 3.2959 | 0.3826 |
89
+ | 3.0096 | 0.12 | 38000 | 3.2932 | 0.3826 |
90
+ | 2.9760 | 0.14 | 39000 | 3.2904 | 0.3831 |
91
+ | 2.9701 | 0.16 | 40000 | 3.2869 | 0.3832 |
92
+ | 2.9654 | 0.18 | 41000 | 3.2847 | 0.3837 |
93
+ | 2.9752 | 0.2 | 42000 | 3.2823 | 0.3839 |
94
+ | 2.9480 | 0.22 | 43000 | 3.2810 | 0.3840 |
95
+ | 2.9637 | 0.24 | 44000 | 3.2790 | 0.3842 |
96
+ | 2.9721 | 0.26 | 45000 | 3.2772 | 0.3843 |
97
+ | 2.9694 | 0.28 | 46000 | 3.2765 | 0.3847 |
98
+ | 2.9577 | 0.3 | 47000 | 3.2756 | 0.3847 |
99
+ | 2.9573 | 0.32 | 48000 | 3.2751 | 0.3847 |
100
+ | 2.9537 | 0.34 | 49000 | 3.2749 | 0.3848 |
101
+ | 2.9677 | 0.36 | 50000 | 3.2749 | 0.3848 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 5.13.0
107
+ - Pytorch 2.8.0+cu128
108
+ - Datasets 5.0.0
109
+ - Tokenizers 0.22.2
best_model_streaming/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HybridFourierLM"
4
+ ],
5
+ "bos_token_id": 0,
6
+ "dropout": 0.05,
7
+ "dtype": "float32",
8
+ "eos_token_id": 0,
9
+ "latent_dim": 768,
10
+ "layer_types": [
11
+ "linear",
12
+ "linear",
13
+ "linear",
14
+ "softmax",
15
+ "linear",
16
+ "linear",
17
+ "linear",
18
+ "softmax",
19
+ "linear",
20
+ "linear",
21
+ "linear",
22
+ "softmax"
23
+ ],
24
+ "model_type": "hybrid_fourier_lm",
25
+ "num_layers": 12,
26
+ "num_modes": 64,
27
+ "pad_token_id": 1,
28
+ "tie_word_embeddings": true,
29
+ "time_scale": 128.0,
30
+ "transformers_version": "5.13.0",
31
+ "use_cache": false,
32
+ "vocab_size": 50277
33
+ }
best_model_streaming/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:820ce0664e8dd374150850bdca06f989fd53e07c16e17ed8101206c3e35d8c6e
3
+ size 579824888
best_model_streaming/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
best_model_streaming/tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1000000000,
10
+ "pad_token": "<|padding|>",
11
+ "tokenizer_class": "GPTNeoXTokenizer",
12
+ "trim_offsets": true,
13
+ "unk_token": "<|endoftext|>"
14
+ }
best_model_streaming/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651f72844ade54f1175bd507f2f69a0c1cdeae4fb980af8775a3f4647e063e4d
3
+ size 5265
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1000000000,
10
+ "pad_token": "<|padding|>",
11
+ "tokenizer_class": "GPTNeoXTokenizer",
12
+ "trim_offsets": true,
13
+ "unk_token": "<|endoftext|>"
14
+ }