Hugging Face's logo

HachiML
/
myBit-Llama2-jp-127M-test-7

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
HachiML commited on
Commit
c8be05c
•
1 Parent(s): 0f0adb1

End of training

Browse files
Files changed (3) hide show
  1. README.md +84 -0
  2. generation_config.json +6 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: myBit-Llama2-jp-127M-7
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
+ # myBit-Llama2-jp-127M-7
15
+
16
+ This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 10.6539
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: 0.00024
38
+ - train_batch_size: 96
39
+ - eval_batch_size: 96
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: polynomial
43
+ - lr_scheduler_warmup_steps: 250
44
+ - num_epochs: 1
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | 9.0536 | 0.04 | 100 | 7.4802 |
51
+ | 6.8962 | 0.07 | 200 | 6.5875 |
52
+ | 6.3685 | 0.11 | 300 | 6.1149 |
53
+ | 5.8698 | 0.15 | 400 | 5.6208 |
54
+ | 5.6334 | 0.18 | 500 | 6.1096 |
55
+ | 8.8705 | 0.22 | 600 | 10.3915 |
56
+ | 10.5174 | 0.26 | 700 | 10.5752 |
57
+ | 10.5929 | 0.29 | 800 | 10.6066 |
58
+ | 10.6128 | 0.33 | 900 | 10.6187 |
59
+ | 10.6218 | 0.37 | 1000 | 10.6255 |
60
+ | 10.6274 | 0.4 | 1100 | 10.6302 |
61
+ | 10.6312 | 0.44 | 1200 | 10.6335 |
62
+ | 10.6343 | 0.48 | 1300 | 10.6363 |
63
+ | 10.6369 | 0.51 | 1400 | 10.6384 |
64
+ | 10.6391 | 0.55 | 1500 | 10.6404 |
65
+ | 10.6408 | 0.59 | 1600 | 10.6422 |
66
+ | 10.6426 | 0.62 | 1700 | 10.6438 |
67
+ | 10.6441 | 0.66 | 1800 | 10.6451 |
68
+ | 10.6454 | 0.7 | 1900 | 10.6464 |
69
+ | 10.6467 | 0.73 | 2000 | 10.6477 |
70
+ | 10.6479 | 0.77 | 2100 | 10.6486 |
71
+ | 10.649 | 0.81 | 2200 | 10.6496 |
72
+ | 10.6499 | 0.84 | 2300 | 10.6506 |
73
+ | 10.6508 | 0.88 | 2400 | 10.6515 |
74
+ | 10.6516 | 0.92 | 2500 | 10.6522 |
75
+ | 10.6524 | 0.95 | 2600 | 10.6531 |
76
+ | 10.6534 | 0.99 | 2700 | 10.6539 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.38.2
82
+ - Pytorch 2.1.0+cu121
83
+ - Datasets 2.18.0
84
+ - Tokenizers 0.15.2
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.38.2"
6
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce4e27bfc6a1d1298a6c2187606a09a6afedd8b3be80296273814f36ea3558d9
3
  size 511344824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae9a611bb2fe0e004cea44557c082f2492739169ef8e5243be036273d6d02e3
3
  size 511344824