Hugging Face's logo

Codemaster67
/
OLmo-chebl_domain_adaption

Text Generation
Transformers
Safetensors
olmo
Generated from Trainer
Model card Files
xet
 Community
Codemaster67 commited on
Commit
3e735e3
·
verified ·
1 Parent(s): 81ee958

Model save

Browse files
Files changed (7) hide show
  1. README.md +90 -0
  2. config.json +30 -0
  3. generation_config.json +9 -0
  4. model.safetensors +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +19 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: allenai/OLMo-7B-hf
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: OLmo-chebl_domain_adaption
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
+ # OLmo-chebl_domain_adaption
16
+
17
+ This model is a fine-tuned version of [allenai/OLMo-7B-hf](https://huggingface.co/allenai/OLMo-7B-hf) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.3516
20
+ - Model Preparation Time: 0.0043
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: 0.0001
40
+ - train_batch_size: 4
41
+ - eval_batch_size: 4
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 8
45
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: cosine
47
+ - lr_scheduler_warmup_steps: 0.05
48
+ - num_epochs: 2
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
53
+ |:-------------:|:------:|:----:|:---------------:|:----------------------:|
54
+ | 6.3473 | 0.0710 | 50 | 6.2448 | 0.0043 |
55
+ | 4.8393 | 0.1419 | 100 | 4.6801 | 0.0043 |
56
+ | 3.2501 | 0.2129 | 150 | 3.2598 | 0.0043 |
57
+ | 2.7432 | 0.2839 | 200 | 2.8011 | 0.0043 |
58
+ | 2.4688 | 0.3549 | 250 | 2.4233 | 0.0043 |
59
+ | 2.2724 | 0.4258 | 300 | 2.2580 | 0.0043 |
60
+ | 2.1390 | 0.4968 | 350 | 2.1196 | 0.0043 |
61
+ | 1.9718 | 0.5678 | 400 | 2.0202 | 0.0043 |
62
+ | 1.8871 | 0.6388 | 450 | 1.9191 | 0.0043 |
63
+ | 1.8967 | 0.7097 | 500 | 1.8318 | 0.0043 |
64
+ | 1.7147 | 0.7807 | 550 | 1.7578 | 0.0043 |
65
+ | 1.7526 | 0.8517 | 600 | 1.7118 | 0.0043 |
66
+ | 1.6391 | 0.9226 | 650 | 1.6556 | 0.0043 |
67
+ | 1.5693 | 0.9936 | 700 | 1.6024 | 0.0043 |
68
+ | 1.4872 | 1.0639 | 750 | 1.5712 | 0.0043 |
69
+ | 1.4543 | 1.1348 | 800 | 1.5263 | 0.0043 |
70
+ | 1.4862 | 1.2058 | 850 | 1.4896 | 0.0043 |
71
+ | 1.3994 | 1.2768 | 900 | 1.4550 | 0.0043 |
72
+ | 1.2903 | 1.3478 | 950 | 1.4253 | 0.0043 |
73
+ | 1.2909 | 1.4187 | 1000 | 1.4001 | 0.0043 |
74
+ | 1.2847 | 1.4897 | 1050 | 1.3812 | 0.0043 |
75
+ | 1.2536 | 1.5607 | 1100 | 1.3681 | 0.0043 |
76
+ | 1.2414 | 1.6317 | 1150 | 1.3592 | 0.0043 |
77
+ | 1.3003 | 1.7026 | 1200 | 1.3541 | 0.0043 |
78
+ | 1.3042 | 1.7736 | 1250 | 1.3523 | 0.0043 |
79
+ | 1.3176 | 1.8446 | 1300 | 1.3517 | 0.0043 |
80
+ | 1.2306 | 1.9155 | 1350 | 1.3516 | 0.0043 |
81
+ | 1.2716 | 1.9865 | 1400 | 1.3515 | 0.0043 |
82
+ | 1.3064 | 2.0 | 1410 | 1.3516 | 0.0043 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 5.9.0
88
+ - Pytorch 2.8.0+cu128
89
+ - Datasets 4.8.5
90
+ - Tokenizers 0.22.2
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "OlmoForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": null,
8
+ "clip_qkv": null,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 50279,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 11008,
15
+ "max_position_embeddings": 2048,
16
+ "model_type": "olmo",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 32,
20
+ "pad_token_id": 1,
21
+ "pretraining_tp": 1,
22
+ "rope_parameters": {
23
+ "rope_theta": 10000.0,
24
+ "rope_type": "default"
25
+ },
26
+ "tie_word_embeddings": false,
27
+ "transformers_version": "5.9.0",
28
+ "use_cache": false,
29
+ "vocab_size": 51407
30
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 50279,
5
+ 0
6
+ ],
7
+ "pad_token_id": 1,
8
+ "transformers_version": "5.9.0"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:449e2a62fe5844e6adde3eda3ec90f4f060c23094c5588a50b7663b9d8aaf589
3
+ size 13794289512
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": true,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|start_of_smiles|>",
10
+ "<|end_of_smiles|>"
11
+ ],
12
+ "is_local": false,
13
+ "local_files_only": false,
14
+ "model_max_length": 1000000000000000019884624838656,
15
+ "pad_token": "<|padding|>",
16
+ "tokenizer_class": "GPTNeoXTokenizer",
17
+ "trim_offsets": true,
18
+ "unk_token": null
19
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b57b41c03ea7ba370ad9e5d08cf80f3dd9792d6c525059511f6be6cb194fd86b
3
+ size 5329