Hugging Face's logo

CodeIsAbstract
/
HybridTimeScaleModel_conti3_

Transformers
Safetensors
hybrid_fourier_lm
Generated from Trainer
Model card Files
xet
 Community
CodeIsAbstract commited on
Commit
953eaac
·
verified ·
1 Parent(s): d47faa3

Training in progress, step 200

Browse files
Files changed (13) hide show
  1. README.md +79 -0
  2. best_model_streaming_cont/config.json +34 -0
  3. best_model_streaming_cont/generation_config.json +9 -0
  4. best_model_streaming_cont/model.safetensors +3 -0
  5. best_model_streaming_cont/tokenizer.json +0 -0
  6. best_model_streaming_cont/tokenizer_config.json +17 -0
  7. best_model_streaming_cont/training_args.bin +3 -0
  8. config.json +34 -0
  9. generation_config.json +9 -0
  10. model.safetensors +3 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +17 -0
  13. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: CodeIsAbstract/HybridTimeScaleModel_conti2
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: HybridTimeScaleModel_conti3
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # HybridTimeScaleModel_conti3
15
+
16
+ This model is a fine-tuned version of [CodeIsAbstract/HybridTimeScaleModel_conti2](https://huggingface.co/CodeIsAbstract/HybridTimeScaleModel_conti2) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 3.2616
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 2
39
+ - eval_batch_size: 2
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 16
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: constant_with_warmup
45
+ - lr_scheduler_warmup_steps: 10
46
+ - training_steps: 1000
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 3.1777 | 0.05 | 50 | 3.4269 |
53
+ | 3.1601 | 0.1 | 100 | 3.3961 |
54
+ | 3.1383 | 0.15 | 150 | 3.3838 |
55
+ | 3.0848 | 0.2 | 200 | 3.3661 |
56
+ | 3.0850 | 0.25 | 250 | 3.3512 |
57
+ | 3.0674 | 0.3 | 300 | 3.3399 |
58
+ | 3.0248 | 0.35 | 350 | 3.3282 |
59
+ | 3.0237 | 0.4 | 400 | 3.3229 |
60
+ | 3.0460 | 0.45 | 450 | 3.3178 |
61
+ | 3.0554 | 0.5 | 500 | 3.3105 |
62
+ | 3.0215 | 0.55 | 550 | 3.3045 |
63
+ | 3.0404 | 0.6 | 600 | 3.2980 |
64
+ | 3.0302 | 0.65 | 650 | 3.2929 |
65
+ | 3.0227 | 0.7 | 700 | 3.2861 |
66
+ | 2.9928 | 0.75 | 750 | 3.2805 |
67
+ | 3.0219 | 0.8 | 800 | 3.2757 |
68
+ | 2.9899 | 0.85 | 850 | 3.2712 |
69
+ | 2.9925 | 0.9 | 900 | 3.2690 |
70
+ | 2.9400 | 0.95 | 950 | 3.2654 |
71
+ | 2.9780 | 1.0 | 1000 | 3.2616 |
72
+
73
+
74
+ ### Framework versions
75
+
76
+ - Transformers 5.14.1
77
+ - Pytorch 2.8.0+cu128
78
+ - Datasets 5.0.1
79
+ - Tokenizers 0.22.2
best_model_streaming_cont/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HybridTimeScaleLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "chunk_size": 128,
7
+ "dropout": 0.05,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 2,
10
+ "latent_dim": 768,
11
+ "layer_types": [
12
+ "linear",
13
+ "linear",
14
+ "linear",
15
+ "softmax",
16
+ "linear",
17
+ "linear",
18
+ "linear",
19
+ "softmax",
20
+ "linear",
21
+ "linear",
22
+ "linear",
23
+ "softmax"
24
+ ],
25
+ "model_type": "hybrid_fourier_lm",
26
+ "num_layers": 12,
27
+ "num_modes": 64,
28
+ "pad_token_id": 2,
29
+ "tie_word_embeddings": true,
30
+ "time_scale": 128.0,
31
+ "transformers_version": "5.14.1",
32
+ "use_cache": false,
33
+ "vocab_size": 32768
34
+ }
best_model_streaming_cont/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": "5.14.1"
9
+ }
best_model_streaming_cont/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98d2fe0f6c71fc451029e15d3adda76c167de5a1de26fc9f1e9f7395acc07ef0
3
+ size 234681136
best_model_streaming_cont/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
best_model_streaming_cont/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_cont/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d533f720772e44e41a40b44f509f4cd172bfbbaa7e27d2a199c907bce81123b
3
+ size 5265
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HybridTimeScaleLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "chunk_size": 128,
7
+ "dropout": 0.05,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 2,
10
+ "latent_dim": 768,
11
+ "layer_types": [
12
+ "linear",
13
+ "linear",
14
+ "linear",
15
+ "softmax",
16
+ "linear",
17
+ "linear",
18
+ "linear",
19
+ "softmax",
20
+ "linear",
21
+ "linear",
22
+ "linear",
23
+ "softmax"
24
+ ],
25
+ "model_type": "hybrid_fourier_lm",
26
+ "num_layers": 12,
27
+ "num_modes": 64,
28
+ "pad_token_id": 2,
29
+ "tie_word_embeddings": true,
30
+ "time_scale": 128.0,
31
+ "transformers_version": "5.14.1",
32
+ "use_cache": false,
33
+ "vocab_size": 32768
34
+ }
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": "5.14.1"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07681faa1bfe71f19e3c13a7da1c21bac4fa91691aa81126db4fd7c58af0fcd8
3
+ size 234681136
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a70aabed0457e05b37f233610f4e2e52283700e304afecd170873a8550ff953
3
+ size 5265