Hugging Face's logo

CodeIsAbstract
/
HybridTimeScaleModel

Transformers
Safetensors
hybrid_fourier_lm
Generated from Trainer
Model card Files
xet
 Community
CodeIsAbstract commited on
Commit
3d14d9f
·
verified ·
1 Parent(s): ebc7090

Model save

Browse files
Files changed (9) hide show
  1. README.md +133 -0
  2. best_model_streaming/config.json +33 -0
  3. best_model_streaming/generation_config.json +9 -0
  4. best_model_streaming/model.safetensors +3 -0
  5. best_model_streaming/tokenizer.json +0 -0
  6. best_model_streaming/tokenizer_config.json +17 -0
  7. best_model_streaming/training_args.bin +3 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +17 -0
README.md ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: HybridTimeScaleModel
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # HybridTimeScaleModel
14
+
15
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 3.0226
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 1e-06
37
+ - train_batch_size: 22
38
+ - eval_batch_size: 4
39
+ - seed: 42
40
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
+ - lr_scheduler_type: cosine
42
+ - lr_scheduler_warmup_steps: 150
43
+ - training_steps: 77000
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:------:|:-----:|:---------------:|
49
+ | 4.1200 | 0.0091 | 1000 | 4.3751 |
50
+ | 3.5707 | 0.0182 | 2000 | 3.8969 |
51
+ | 3.3944 | 0.0273 | 3000 | 3.7320 |
52
+ | 3.2534 | 0.0364 | 4000 | 3.6268 |
53
+ | 3.2178 | 0.0455 | 5000 | 3.5597 |
54
+ | 3.1700 | 0.0545 | 6000 | 3.4946 |
55
+ | 3.1400 | 0.0636 | 7000 | 3.4605 |
56
+ | 3.0755 | 0.0727 | 8000 | 3.4183 |
57
+ | 3.0527 | 0.0818 | 9000 | 3.3907 |
58
+ | 3.0213 | 0.0909 | 10000 | 3.3656 |
59
+ | 3.0590 | 0.1 | 11000 | 3.3479 |
60
+ | 2.9770 | 0.1091 | 12000 | 3.3242 |
61
+ | 2.9614 | 0.1182 | 13000 | 3.3102 |
62
+ | 2.9506 | 0.1273 | 14000 | 3.2945 |
63
+ | 2.9333 | 0.1364 | 15000 | 3.2715 |
64
+ | 2.8988 | 0.1455 | 16000 | 3.2674 |
65
+ | 2.9117 | 0.1545 | 17000 | 3.2496 |
66
+ | 2.8933 | 0.1636 | 18000 | 3.2416 |
67
+ | 2.8866 | 0.1727 | 19000 | 3.2224 |
68
+ | 2.9030 | 0.1818 | 20000 | 3.2188 |
69
+ | 2.9004 | 0.1909 | 21000 | 3.2108 |
70
+ | 2.8540 | 0.2 | 22000 | 3.1956 |
71
+ | 2.8207 | 0.2091 | 23000 | 3.1900 |
72
+ | 2.8272 | 0.2182 | 24000 | 3.1836 |
73
+ | 2.8192 | 0.2273 | 25000 | 3.1781 |
74
+ | 2.7933 | 0.2364 | 26000 | 3.1706 |
75
+ | 2.8126 | 0.2455 | 27000 | 3.1654 |
76
+ | 2.8480 | 0.2545 | 28000 | 3.1647 |
77
+ | 2.7938 | 0.2636 | 29000 | 3.1548 |
78
+ | 2.7823 | 0.2727 | 30000 | 3.1496 |
79
+ | 2.7479 | 0.2818 | 31000 | 3.1456 |
80
+ | 2.7778 | 0.2909 | 32000 | 3.1463 |
81
+ | 2.7698 | 0.0091 | 33000 | 3.1402 |
82
+ | 2.7731 | 0.0182 | 34000 | 3.1313 |
83
+ | 2.7693 | 0.0273 | 35000 | 3.1262 |
84
+ | 2.7321 | 0.0364 | 36000 | 3.1245 |
85
+ | 2.6874 | 0.0091 | 37000 | 3.1317 |
86
+ | 2.6970 | 0.0182 | 38000 | 3.1285 |
87
+ | 2.6958 | 0.0273 | 39000 | 3.1291 |
88
+ | 2.6649 | 0.0364 | 40000 | 3.1292 |
89
+ | 2.7598 | 0.0455 | 41000 | 3.1212 |
90
+ | 2.7124 | 0.0545 | 42000 | 3.1164 |
91
+ | 2.7572 | 0.0636 | 43000 | 3.1164 |
92
+ | 2.7247 | 0.0727 | 44000 | 3.1065 |
93
+ | 2.7101 | 0.0818 | 45000 | 3.1004 |
94
+ | 2.6942 | 0.0909 | 46000 | 3.0926 |
95
+ | 2.7299 | 0.1 | 47000 | 3.0938 |
96
+ | 2.7021 | 0.1091 | 48000 | 3.0897 |
97
+ | 2.6787 | 0.1182 | 49000 | 3.0872 |
98
+ | 2.6781 | 0.1273 | 50000 | 3.0828 |
99
+ | 2.7094 | 0.1364 | 51000 | 3.0797 |
100
+ | 2.7144 | 0.1455 | 52000 | 3.0822 |
101
+ | 2.6800 | 0.1545 | 53000 | 3.0733 |
102
+ | 2.6689 | 0.1636 | 54000 | 3.0703 |
103
+ | 2.6780 | 0.1727 | 55000 | 3.0706 |
104
+ | 2.6806 | 0.1818 | 56000 | 3.0680 |
105
+ | 2.7088 | 0.1909 | 57000 | 3.0626 |
106
+ | 2.6277 | 0.2 | 58000 | 3.0661 |
107
+ | 2.6540 | 0.2091 | 59000 | 3.0577 |
108
+ | 2.6756 | 0.2182 | 60000 | 3.0541 |
109
+ | 2.6778 | 0.2273 | 61000 | 3.0542 |
110
+ | 2.6535 | 0.2364 | 62000 | 3.0504 |
111
+ | 2.6557 | 0.2455 | 63000 | 3.0508 |
112
+ | 2.6445 | 0.2545 | 64000 | 3.0473 |
113
+ | 2.6488 | 0.2636 | 65000 | 3.0462 |
114
+ | 2.6457 | 0.2727 | 66000 | 3.0442 |
115
+ | 2.6479 | 0.2818 | 67000 | 3.0378 |
116
+ | 2.6303 | 0.2909 | 68000 | 3.0449 |
117
+ | 2.6089 | 0.3 | 69000 | 3.0342 |
118
+ | 2.5966 | 0.3091 | 70000 | 3.0347 |
119
+ | 2.6226 | 0.3182 | 71000 | 3.0347 |
120
+ | 2.6174 | 0.3273 | 72000 | 3.0310 |
121
+ | 2.6171 | 0.3364 | 73000 | 3.0339 |
122
+ | 2.6139 | 0.3455 | 74000 | 3.0277 |
123
+ | 2.5904 | 0.3545 | 75000 | 3.0259 |
124
+ | 2.5940 | 0.3636 | 76000 | 3.0242 |
125
+ | 2.5818 | 0.0130 | 77000 | 3.0226 |
126
+
127
+
128
+ ### Framework versions
129
+
130
+ - Transformers 5.13.1
131
+ - Pytorch 2.8.0+cu128
132
+ - Datasets 5.0.0
133
+ - Tokenizers 0.22.2
best_model_streaming/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HybridFourierLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "dropout": 0.05,
7
+ "dtype": "float32",
8
+ "eos_token_id": 2,
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": 2,
28
+ "tie_word_embeddings": true,
29
+ "time_scale": 128.0,
30
+ "transformers_version": "5.13.1",
31
+ "use_cache": false,
32
+ "vocab_size": 32768
33
+ }
best_model_streaming/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 2,
8
+ "transformers_version": "5.13.1"
9
+ }
best_model_streaming/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f64707cb242aae96a30c6b449fcc99592355f500c9224203686d1d890be2992
3
+ size 469337272
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 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "is_local": false,
8
+ "legacy": false,
9
+ "local_files_only": false,
10
+ "model_max_length": 1000000000,
11
+ "pad_token": "</s>",
12
+ "sp_model_kwargs": {},
13
+ "spaces_between_special_tokens": false,
14
+ "tokenizer_class": "TokenizersBackend",
15
+ "unk_token": "<unk>",
16
+ "use_default_system_prompt": false
17
+ }
best_model_streaming/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de39541c4d3c2c8cd3db89cc5a7ea96a1526b7e8be52cafa957494d7daabed0f
3
+ size 5201
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "is_local": false,
8
+ "legacy": false,
9
+ "local_files_only": false,
10
+ "model_max_length": 1000000000,
11
+ "pad_token": "</s>",
12
+ "sp_model_kwargs": {},
13
+ "spaces_between_special_tokens": false,
14
+ "tokenizer_class": "TokenizersBackend",
15
+ "unk_token": "<unk>",
16
+ "use_default_system_prompt": false
17
+ }