Model save
Browse files- README.md +97 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- llama-factory
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: meta-llama/Meta-Llama-3-70B-Instruct
|
| 8 |
+
model-index:
|
| 9 |
+
- name: llama3-70B-lora-pretrain_v2
|
| 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 |
+
# llama3-70B-lora-pretrain_v2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.9383
|
| 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: 0.0001
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 2
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- total_eval_batch_size: 2
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_steps: 500
|
| 51 |
+
- num_epochs: 3.0
|
| 52 |
+
- mixed_precision_training: Native AMP
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
+
| 2.6995 | 0.0939 | 100 | 2.6305 |
|
| 59 |
+
| 2.4199 | 0.1877 | 200 | 2.3979 |
|
| 60 |
+
| 2.2722 | 0.2816 | 300 | 2.2180 |
|
| 61 |
+
| 2.0762 | 0.3754 | 400 | 2.1251 |
|
| 62 |
+
| 1.9652 | 0.4693 | 500 | 2.0858 |
|
| 63 |
+
| 2.1893 | 0.5631 | 600 | 2.0629 |
|
| 64 |
+
| 2.0153 | 0.6570 | 700 | 2.0473 |
|
| 65 |
+
| 1.9911 | 0.7508 | 800 | 2.0318 |
|
| 66 |
+
| 2.1041 | 0.8447 | 900 | 2.0198 |
|
| 67 |
+
| 2.0488 | 0.9385 | 1000 | 2.0117 |
|
| 68 |
+
| 1.897 | 1.0324 | 1100 | 2.0018 |
|
| 69 |
+
| 2.0298 | 1.1262 | 1200 | 1.9952 |
|
| 70 |
+
| 2.0989 | 1.2201 | 1300 | 1.9890 |
|
| 71 |
+
| 1.8695 | 1.3139 | 1400 | 1.9838 |
|
| 72 |
+
| 2.1573 | 1.4078 | 1500 | 1.9764 |
|
| 73 |
+
| 2.0183 | 1.5016 | 1600 | 1.9713 |
|
| 74 |
+
| 1.9229 | 1.5955 | 1700 | 1.9672 |
|
| 75 |
+
| 1.9732 | 1.6893 | 1800 | 1.9617 |
|
| 76 |
+
| 1.6835 | 1.7832 | 1900 | 1.9574 |
|
| 77 |
+
| 1.9874 | 1.8771 | 2000 | 1.9539 |
|
| 78 |
+
| 1.7607 | 1.9709 | 2100 | 1.9512 |
|
| 79 |
+
| 1.9459 | 2.0648 | 2200 | 1.9480 |
|
| 80 |
+
| 1.7611 | 2.1586 | 2300 | 1.9463 |
|
| 81 |
+
| 1.8491 | 2.2525 | 2400 | 1.9441 |
|
| 82 |
+
| 1.9121 | 2.3463 | 2500 | 1.9427 |
|
| 83 |
+
| 1.8849 | 2.4402 | 2600 | 1.9413 |
|
| 84 |
+
| 2.0679 | 2.5340 | 2700 | 1.9400 |
|
| 85 |
+
| 1.9908 | 2.6279 | 2800 | 1.9394 |
|
| 86 |
+
| 1.9557 | 2.7217 | 2900 | 1.9388 |
|
| 87 |
+
| 1.9627 | 2.8156 | 3000 | 1.9384 |
|
| 88 |
+
| 1.8339 | 2.9094 | 3100 | 1.9383 |
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
### Framework versions
|
| 92 |
+
|
| 93 |
+
- PEFT 0.10.0
|
| 94 |
+
- Transformers 4.40.0
|
| 95 |
+
- Pytorch 2.2.1
|
| 96 |
+
- Datasets 2.18.0
|
| 97 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 65578776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ad3c783879a72cd5fc04d23dc065dea599f3ad10f9d50c4abcfc8f7a7e80e83
|
| 3 |
size 65578776
|