End of training
Browse files- README.md +82 -0
- generation_config.json +6 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: Llama2-jp-123M
|
| 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 |
+
# Llama2-jp-123M
|
| 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: 2.6296
|
| 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: 0.0005
|
| 38 |
+
- train_batch_size: 156
|
| 39 |
+
- eval_batch_size: 156
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: cosine
|
| 43 |
+
- lr_scheduler_warmup_steps: 500
|
| 44 |
+
- num_epochs: 1
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 50 |
+
| 4.4744 | 0.04 | 1000 | 3.5915 |
|
| 51 |
+
| 3.4036 | 0.08 | 2000 | 3.2836 |
|
| 52 |
+
| 3.2088 | 0.12 | 3000 | 3.1575 |
|
| 53 |
+
| 3.1151 | 0.16 | 4000 | 3.0811 |
|
| 54 |
+
| 3.0471 | 0.2 | 5000 | 3.0247 |
|
| 55 |
+
| 3.0006 | 0.24 | 6000 | 2.9798 |
|
| 56 |
+
| 2.9581 | 0.28 | 7000 | 2.9409 |
|
| 57 |
+
| 2.9187 | 0.32 | 8000 | 2.9103 |
|
| 58 |
+
| 2.8899 | 0.36 | 9000 | 2.8805 |
|
| 59 |
+
| 2.8603 | 0.4 | 10000 | 2.8523 |
|
| 60 |
+
| 2.8329 | 0.44 | 11000 | 2.8259 |
|
| 61 |
+
| 2.8068 | 0.48 | 12000 | 2.8011 |
|
| 62 |
+
| 2.7825 | 0.52 | 13000 | 2.7782 |
|
| 63 |
+
| 2.7601 | 0.56 | 14000 | 2.7567 |
|
| 64 |
+
| 2.7384 | 0.6 | 15000 | 2.7362 |
|
| 65 |
+
| 2.7194 | 0.64 | 16000 | 2.7164 |
|
| 66 |
+
| 2.6986 | 0.68 | 17000 | 2.6973 |
|
| 67 |
+
| 2.683 | 0.72 | 18000 | 2.6810 |
|
| 68 |
+
| 2.667 | 0.76 | 19000 | 2.6664 |
|
| 69 |
+
| 2.6511 | 0.8 | 20000 | 2.6540 |
|
| 70 |
+
| 2.6421 | 0.84 | 21000 | 2.6441 |
|
| 71 |
+
| 2.6312 | 0.88 | 22000 | 2.6369 |
|
| 72 |
+
| 2.6286 | 0.92 | 23000 | 2.6322 |
|
| 73 |
+
| 2.6234 | 0.96 | 24000 | 2.6301 |
|
| 74 |
+
| 2.6216 | 1.0 | 25000 | 2.6296 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.38.2
|
| 80 |
+
- Pytorch 2.1.0+cu121
|
| 81 |
+
- Datasets 2.18.0
|
| 82 |
+
- 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 492151048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd6f01dfdb816075a3fb30e19e19cd4b1419265ddd2743a3e93d19bca199b7ce
|
| 3 |
size 492151048
|