End of training
Browse files- README.md +84 -0
- generation_config.json +6 -0
- 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-test-1
|
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-test-1
|
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: 10.6136
|
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: 0.0024
|
38 |
+
- train_batch_size: 48
|
39 |
+
- eval_batch_size: 48
|
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: 500
|
44 |
+
- num_epochs: 1
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 7.3834 | 0.04 | 200 | 6.5397 |
|
51 |
+
| 6.8679 | 0.07 | 400 | 9.8549 |
|
52 |
+
| 10.2542 | 0.11 | 600 | 10.3642 |
|
53 |
+
| 10.3959 | 0.14 | 800 | 10.4168 |
|
54 |
+
| 10.4303 | 0.18 | 1000 | 10.4429 |
|
55 |
+
| 10.4527 | 0.22 | 1200 | 10.4638 |
|
56 |
+
| 10.4744 | 0.25 | 1400 | 10.4837 |
|
57 |
+
| 10.4907 | 0.29 | 1600 | 10.4981 |
|
58 |
+
| 10.5032 | 0.32 | 1800 | 10.5069 |
|
59 |
+
| 10.5134 | 0.36 | 2000 | 10.5165 |
|
60 |
+
| 10.5208 | 0.4 | 2200 | 10.5264 |
|
61 |
+
| 10.5284 | 0.43 | 2400 | 10.5324 |
|
62 |
+
| 10.535 | 0.47 | 2600 | 10.5372 |
|
63 |
+
| 10.541 | 0.51 | 2800 | 10.5445 |
|
64 |
+
| 10.5472 | 0.54 | 3000 | 10.5498 |
|
65 |
+
| 10.5532 | 0.58 | 3200 | 10.5561 |
|
66 |
+
| 10.5588 | 0.61 | 3400 | 10.5614 |
|
67 |
+
| 10.5647 | 0.65 | 3600 | 10.5672 |
|
68 |
+
| 10.5698 | 0.69 | 3800 | 10.5727 |
|
69 |
+
| 10.5753 | 0.72 | 4000 | 10.5760 |
|
70 |
+
| 10.5809 | 0.76 | 4200 | 10.5834 |
|
71 |
+
| 10.5864 | 0.79 | 4400 | 10.5892 |
|
72 |
+
| 10.5919 | 0.83 | 4600 | 10.5946 |
|
73 |
+
| 10.5971 | 0.87 | 4800 | 10.5995 |
|
74 |
+
| 10.6027 | 0.9 | 5000 | 10.6047 |
|
75 |
+
| 10.6076 | 0.94 | 5200 | 10.6105 |
|
76 |
+
| 10.6126 | 0.97 | 5400 | 10.6136 |
|
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:
|
3 |
size 511344824
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7591282a89e9ecfc853c3369022cffc6b00b6a411df143dd4caba336c7284d59
|
3 |
size 511344824
|