Model save
Browse files- README.md +98 -0
- generation_config.json +6 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: BEE-spoke-data/smol_llama-101M-GQA
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: smol_llama-101M-GQA-midjourney-messages-cleaned-1024-vN
|
| 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 |
+
# smol_llama-101M-GQA-midjourney-messages-cleaned-1024-vN
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [BEE-spoke-data/smol_llama-101M-GQA](https://huggingface.co/BEE-spoke-data/smol_llama-101M-GQA) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.8431
|
| 21 |
+
- Accuracy: 0.4682
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.00025
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 4
|
| 43 |
+
- seed: 17056
|
| 44 |
+
- gradient_accumulation_steps: 16
|
| 45 |
+
- total_train_batch_size: 64
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: inverse_sqrt
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 49 |
+
- num_epochs: 1.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
+
| 3.3031 | 0.03 | 200 | 3.2643 | 0.4169 |
|
| 56 |
+
| 3.1762 | 0.06 | 400 | 3.1674 | 0.4247 |
|
| 57 |
+
| 3.0914 | 0.08 | 600 | 3.0850 | 0.4359 |
|
| 58 |
+
| 3.0384 | 0.11 | 800 | 3.0371 | 0.4419 |
|
| 59 |
+
| 3.0235 | 0.14 | 1000 | 3.0057 | 0.4467 |
|
| 60 |
+
| 2.9874 | 0.17 | 1200 | 2.9816 | 0.4496 |
|
| 61 |
+
| 2.9708 | 0.19 | 1400 | 2.9650 | 0.4518 |
|
| 62 |
+
| 2.9796 | 0.22 | 1600 | 2.9487 | 0.4541 |
|
| 63 |
+
| 2.9371 | 0.25 | 1800 | 2.9364 | 0.4560 |
|
| 64 |
+
| 2.932 | 0.28 | 2000 | 2.9265 | 0.4571 |
|
| 65 |
+
| 2.9272 | 0.3 | 2200 | 2.9175 | 0.4580 |
|
| 66 |
+
| 2.935 | 0.33 | 2400 | 2.9115 | 0.4591 |
|
| 67 |
+
| 2.9074 | 0.36 | 2600 | 2.9038 | 0.4600 |
|
| 68 |
+
| 2.9404 | 0.39 | 2800 | 2.8986 | 0.4611 |
|
| 69 |
+
| 2.8896 | 0.41 | 3000 | 2.8938 | 0.4617 |
|
| 70 |
+
| 2.8946 | 0.44 | 3200 | 2.8893 | 0.4624 |
|
| 71 |
+
| 2.9183 | 0.47 | 3400 | 2.8855 | 0.4623 |
|
| 72 |
+
| 2.887 | 0.5 | 3600 | 2.8813 | 0.4638 |
|
| 73 |
+
| 2.8823 | 0.52 | 3800 | 2.8780 | 0.4638 |
|
| 74 |
+
| 2.9171 | 0.55 | 4000 | 2.8744 | 0.4642 |
|
| 75 |
+
| 2.8884 | 0.58 | 4200 | 2.8718 | 0.4646 |
|
| 76 |
+
| 2.8875 | 0.61 | 4400 | 2.8700 | 0.4651 |
|
| 77 |
+
| 2.9121 | 0.63 | 4600 | 2.8668 | 0.4653 |
|
| 78 |
+
| 2.8653 | 0.66 | 4800 | 2.8639 | 0.4658 |
|
| 79 |
+
| 2.8603 | 0.69 | 5000 | 2.8625 | 0.4659 |
|
| 80 |
+
| 2.8489 | 0.72 | 5200 | 2.8598 | 0.4661 |
|
| 81 |
+
| 2.8674 | 0.74 | 5400 | 2.8577 | 0.4666 |
|
| 82 |
+
| 2.884 | 0.77 | 5600 | 2.8554 | 0.4669 |
|
| 83 |
+
| 2.857 | 0.8 | 5800 | 2.8535 | 0.4672 |
|
| 84 |
+
| 2.8747 | 0.83 | 6000 | 2.8516 | 0.4673 |
|
| 85 |
+
| 2.8809 | 0.86 | 6200 | 2.8501 | 0.4672 |
|
| 86 |
+
| 2.8832 | 0.88 | 6400 | 2.8482 | 0.4679 |
|
| 87 |
+
| 2.8817 | 0.91 | 6600 | 2.8472 | 0.4681 |
|
| 88 |
+
| 2.8813 | 0.94 | 6800 | 2.8457 | 0.4684 |
|
| 89 |
+
| 2.8493 | 0.97 | 7000 | 2.8444 | 0.4677 |
|
| 90 |
+
| 2.8455 | 0.99 | 7200 | 2.8431 | 0.4682 |
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
### Framework versions
|
| 94 |
+
|
| 95 |
+
- Transformers 4.36.0.dev0
|
| 96 |
+
- Pytorch 2.1.0
|
| 97 |
+
- Datasets 2.15.0
|
| 98 |
+
- Tokenizers 0.15.0
|
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": "4.36.0.dev0"
|
| 6 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 202532568
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cffcb432a2884fda08bf8ce40fd712b1bc61259ec9ce6de00c1b27e0a1cb315
|
| 3 |
size 202532568
|