hlillemark commited on
Commit
acb2bf9
·
verified ·
1 Parent(s): a37a9e9

Model save

Browse files
Files changed (2) hide show
  1. README.md +77 -0
  2. generation_config.json +12 -0
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: llama3
4
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: all_tasks_combined_8b_sft
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # all_tasks_combined_8b_sft
17
+
18
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.0667
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: 1e-05
40
+ - train_batch_size: 2
41
+ - eval_batch_size: 2
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 4
45
+ - gradient_accumulation_steps: 2
46
+ - total_train_batch_size: 16
47
+ - total_eval_batch_size: 8
48
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 10.0
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:------:|:----:|:---------------:|
57
+ | 0.7504 | 0.7463 | 50 | 0.7051 |
58
+ | 0.6328 | 1.4925 | 100 | 0.6948 |
59
+ | 0.2823 | 2.2388 | 150 | 0.8329 |
60
+ | 0.3349 | 2.9851 | 200 | 0.8282 |
61
+ | 0.2069 | 3.7313 | 250 | 0.7403 |
62
+ | 0.0942 | 4.4776 | 300 | 0.8360 |
63
+ | 0.0553 | 5.2239 | 350 | 0.8743 |
64
+ | 0.0774 | 5.9701 | 400 | 0.8344 |
65
+ | 0.0352 | 6.7164 | 450 | 0.9773 |
66
+ | 0.0176 | 7.4627 | 500 | 0.9961 |
67
+ | 0.0083 | 8.2090 | 550 | 1.0166 |
68
+ | 0.0075 | 8.9552 | 600 | 1.0438 |
69
+ | 0.0028 | 9.7015 | 650 | 1.0667 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.49.0
75
+ - Pytorch 2.5.1+cu124
76
+ - Datasets 3.2.0
77
+ - Tokenizers 0.21.0
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128009
7
+ ],
8
+ "max_length": 4096,
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.49.0"
12
+ }