Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: gemma
|
| 4 |
+
base_model: google/codegemma-7b
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: code-bench-CodeGemma-7B-cgv1-ds
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# code-bench-CodeGemma-7B-cgv1-ds
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [google/codegemma-7b](https://huggingface.co/google/codegemma-7b) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0947
|
| 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: 5e-05
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 3
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- gradient_accumulation_steps: 8
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 50 |
+
- num_epochs: 2
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 57 |
+
| 0.9203 | 0.0530 | 50 | 1.0306 |
|
| 58 |
+
| 0.551 | 0.1061 | 100 | 0.5383 |
|
| 59 |
+
| 0.4483 | 0.1591 | 150 | 0.4048 |
|
| 60 |
+
| 0.3469 | 0.2121 | 200 | 0.3013 |
|
| 61 |
+
| 0.2868 | 0.2652 | 250 | 0.2447 |
|
| 62 |
+
| 0.2307 | 0.3182 | 300 | 0.2061 |
|
| 63 |
+
| 0.1972 | 0.3713 | 350 | 0.1727 |
|
| 64 |
+
| 0.1716 | 0.4243 | 400 | 0.1525 |
|
| 65 |
+
| 0.1612 | 0.4773 | 450 | 0.1468 |
|
| 66 |
+
| 0.1631 | 0.5304 | 500 | 0.1400 |
|
| 67 |
+
| 0.1739 | 0.5834 | 550 | 0.1376 |
|
| 68 |
+
| 0.148 | 0.6364 | 600 | 0.1330 |
|
| 69 |
+
| 0.1413 | 0.6895 | 650 | 0.1274 |
|
| 70 |
+
| 0.1464 | 0.7425 | 700 | 0.1267 |
|
| 71 |
+
| 0.1376 | 0.7955 | 750 | 0.1240 |
|
| 72 |
+
| 0.1287 | 0.8486 | 800 | 0.1210 |
|
| 73 |
+
| 0.1402 | 0.9016 | 850 | 0.1198 |
|
| 74 |
+
| 0.1261 | 0.9547 | 900 | 0.1173 |
|
| 75 |
+
| 0.1195 | 1.0077 | 950 | 0.1145 |
|
| 76 |
+
| 0.1254 | 1.0607 | 1000 | 0.1133 |
|
| 77 |
+
| 0.1109 | 1.1138 | 1050 | 0.1119 |
|
| 78 |
+
| 0.1206 | 1.1668 | 1100 | 0.1093 |
|
| 79 |
+
| 0.1195 | 1.2198 | 1150 | 0.1084 |
|
| 80 |
+
| 0.1237 | 1.2729 | 1200 | 0.1073 |
|
| 81 |
+
| 0.1205 | 1.3259 | 1250 | 0.1064 |
|
| 82 |
+
| 0.1105 | 1.3789 | 1300 | 0.1048 |
|
| 83 |
+
| 0.1027 | 1.4320 | 1350 | 0.1038 |
|
| 84 |
+
| 0.1128 | 1.4850 | 1400 | 0.1035 |
|
| 85 |
+
| 0.1207 | 1.5381 | 1450 | 0.1030 |
|
| 86 |
+
| 0.1057 | 1.5911 | 1500 | 0.1013 |
|
| 87 |
+
| 0.1056 | 1.6441 | 1550 | 0.0996 |
|
| 88 |
+
| 0.1086 | 1.6972 | 1600 | 0.0985 |
|
| 89 |
+
| 0.1078 | 1.7502 | 1650 | 0.0982 |
|
| 90 |
+
| 0.0987 | 1.8032 | 1700 | 0.0968 |
|
| 91 |
+
| 0.1037 | 1.8563 | 1750 | 0.0960 |
|
| 92 |
+
| 0.1047 | 1.9093 | 1800 | 0.0957 |
|
| 93 |
+
| 0.1045 | 1.9623 | 1850 | 0.0947 |
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
### Framework versions
|
| 97 |
+
|
| 98 |
+
- PEFT 0.12.0
|
| 99 |
+
- Transformers 4.44.2
|
| 100 |
+
- Pytorch 2.5.1+cu121
|
| 101 |
+
- Datasets 2.21.0
|
| 102 |
+
- Tokenizers 0.19.1
|
runs/Sep10_18-53-35_m3h110/events.out.tfevents.1757495450.m3h110.2356734.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d33bf9793ffe67c5ac0b2f9ee361488a798020890886b5699a40fd4bc706bff8
|
| 3 |
+
size 39535
|