End of training
Browse files- README.md +100 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- unsloth
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
base_model: Qwen/Qwen2-7B
|
| 8 |
+
model-index:
|
| 9 |
+
- name: qwen2_Magiccoder_evol_10k_reverse
|
| 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 |
+
# qwen2_Magiccoder_evol_10k_reverse
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.8272
|
| 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: 2
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 32
|
| 44 |
+
- total_train_batch_size: 64
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_steps: 0.02
|
| 48 |
+
- num_epochs: 1
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 0.8303 | 0.0261 | 4 | 0.8571 |
|
| 55 |
+
| 0.8267 | 0.0522 | 8 | 0.8449 |
|
| 56 |
+
| 0.8201 | 0.0784 | 12 | 0.8389 |
|
| 57 |
+
| 0.8002 | 0.1045 | 16 | 0.8436 |
|
| 58 |
+
| 0.8491 | 0.1306 | 20 | 0.8414 |
|
| 59 |
+
| 0.7448 | 0.1567 | 24 | 0.8434 |
|
| 60 |
+
| 0.7606 | 0.1828 | 28 | 0.8459 |
|
| 61 |
+
| 0.9214 | 0.2089 | 32 | 0.8474 |
|
| 62 |
+
| 0.8071 | 0.2351 | 36 | 0.8466 |
|
| 63 |
+
| 0.8353 | 0.2612 | 40 | 0.8479 |
|
| 64 |
+
| 0.8762 | 0.2873 | 44 | 0.8473 |
|
| 65 |
+
| 0.8544 | 0.3134 | 48 | 0.8475 |
|
| 66 |
+
| 0.7855 | 0.3395 | 52 | 0.8482 |
|
| 67 |
+
| 0.7725 | 0.3656 | 56 | 0.8467 |
|
| 68 |
+
| 0.8044 | 0.3918 | 60 | 0.8470 |
|
| 69 |
+
| 0.8282 | 0.4179 | 64 | 0.8446 |
|
| 70 |
+
| 0.853 | 0.4440 | 68 | 0.8449 |
|
| 71 |
+
| 0.8047 | 0.4701 | 72 | 0.8439 |
|
| 72 |
+
| 0.8145 | 0.4962 | 76 | 0.8431 |
|
| 73 |
+
| 0.8063 | 0.5223 | 80 | 0.8411 |
|
| 74 |
+
| 0.8782 | 0.5485 | 84 | 0.8395 |
|
| 75 |
+
| 0.7944 | 0.5746 | 88 | 0.8395 |
|
| 76 |
+
| 0.8728 | 0.6007 | 92 | 0.8370 |
|
| 77 |
+
| 0.7882 | 0.6268 | 96 | 0.8363 |
|
| 78 |
+
| 0.8999 | 0.6529 | 100 | 0.8354 |
|
| 79 |
+
| 0.7857 | 0.6790 | 104 | 0.8341 |
|
| 80 |
+
| 0.8258 | 0.7052 | 108 | 0.8331 |
|
| 81 |
+
| 0.7877 | 0.7313 | 112 | 0.8317 |
|
| 82 |
+
| 0.7686 | 0.7574 | 116 | 0.8305 |
|
| 83 |
+
| 0.7422 | 0.7835 | 120 | 0.8299 |
|
| 84 |
+
| 0.8229 | 0.8096 | 124 | 0.8292 |
|
| 85 |
+
| 0.7577 | 0.8357 | 128 | 0.8285 |
|
| 86 |
+
| 0.8811 | 0.8619 | 132 | 0.8278 |
|
| 87 |
+
| 0.8243 | 0.8880 | 136 | 0.8277 |
|
| 88 |
+
| 0.8243 | 0.9141 | 140 | 0.8275 |
|
| 89 |
+
| 0.8096 | 0.9402 | 144 | 0.8275 |
|
| 90 |
+
| 0.8476 | 0.9663 | 148 | 0.8274 |
|
| 91 |
+
| 0.8154 | 0.9925 | 152 | 0.8272 |
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
### Framework versions
|
| 95 |
+
|
| 96 |
+
- PEFT 0.7.1
|
| 97 |
+
- Transformers 4.40.2
|
| 98 |
+
- Pytorch 2.3.0+cu121
|
| 99 |
+
- Datasets 2.19.1
|
| 100 |
+
- 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 80792096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e7dc02c70773750b3f2985751f02b562faa292978d54830e881158e09814349
|
| 3 |
size 80792096
|