update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: Cerebras-GPT-1.3B-lora-s-t3000-v300-v1
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# Cerebras-GPT-1.3B-lora-s-t3000-v300-v1
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [cerebras/Cerebras-GPT-1.3B](https://huggingface.co/cerebras/Cerebras-GPT-1.3B) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 2.2409
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.0002
|
| 37 |
+
- train_batch_size: 4
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 4
|
| 41 |
+
- total_train_batch_size: 16
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_steps: 10
|
| 45 |
+
- training_steps: 1000
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| 2.4608 | 0.11 | 20 | 2.4030 |
|
| 53 |
+
| 2.2475 | 0.21 | 40 | 2.2757 |
|
| 54 |
+
| 2.2432 | 0.32 | 60 | 2.2579 |
|
| 55 |
+
| 2.3011 | 0.43 | 80 | 2.2467 |
|
| 56 |
+
| 2.2293 | 0.53 | 100 | 2.2478 |
|
| 57 |
+
| 2.1398 | 0.64 | 120 | 2.2436 |
|
| 58 |
+
| 2.2571 | 0.75 | 140 | 2.2413 |
|
| 59 |
+
| 2.1577 | 0.85 | 160 | 2.2349 |
|
| 60 |
+
| 2.2442 | 0.96 | 180 | 2.2371 |
|
| 61 |
+
| 2.2592 | 1.07 | 200 | 2.2342 |
|
| 62 |
+
| 2.2082 | 1.17 | 220 | 2.2352 |
|
| 63 |
+
| 2.1402 | 1.28 | 240 | 2.2345 |
|
| 64 |
+
| 2.1216 | 1.39 | 260 | 2.2345 |
|
| 65 |
+
| 2.1758 | 1.49 | 280 | 2.2320 |
|
| 66 |
+
| 2.1625 | 1.6 | 300 | 2.2329 |
|
| 67 |
+
| 2.1491 | 1.71 | 320 | 2.2311 |
|
| 68 |
+
| 2.2307 | 1.81 | 340 | 2.2286 |
|
| 69 |
+
| 2.1102 | 1.92 | 360 | 2.2300 |
|
| 70 |
+
| 2.2054 | 2.03 | 380 | 2.2278 |
|
| 71 |
+
| 2.157 | 2.13 | 400 | 2.2345 |
|
| 72 |
+
| 2.0643 | 2.24 | 420 | 2.2359 |
|
| 73 |
+
| 2.2134 | 2.35 | 440 | 2.2343 |
|
| 74 |
+
| 2.1296 | 2.45 | 460 | 2.2347 |
|
| 75 |
+
| 2.1001 | 2.56 | 480 | 2.2346 |
|
| 76 |
+
| 2.1401 | 2.67 | 500 | 2.2327 |
|
| 77 |
+
| 2.091 | 2.77 | 520 | 2.2328 |
|
| 78 |
+
| 2.1365 | 2.88 | 540 | 2.2359 |
|
| 79 |
+
| 2.1201 | 2.99 | 560 | 2.2295 |
|
| 80 |
+
| 2.1359 | 3.09 | 580 | 2.2338 |
|
| 81 |
+
| 2.0979 | 3.2 | 600 | 2.2427 |
|
| 82 |
+
| 2.2025 | 3.31 | 620 | 2.2345 |
|
| 83 |
+
| 2.1001 | 3.41 | 640 | 2.2368 |
|
| 84 |
+
| 2.0228 | 3.52 | 660 | 2.2350 |
|
| 85 |
+
| 2.1174 | 3.63 | 680 | 2.2362 |
|
| 86 |
+
| 2.0688 | 3.73 | 700 | 2.2372 |
|
| 87 |
+
| 2.0368 | 3.84 | 720 | 2.2328 |
|
| 88 |
+
| 2.1409 | 3.95 | 740 | 2.2341 |
|
| 89 |
+
| 2.0675 | 4.05 | 760 | 2.2377 |
|
| 90 |
+
| 2.1805 | 4.16 | 780 | 2.2392 |
|
| 91 |
+
| 2.0844 | 4.27 | 800 | 2.2417 |
|
| 92 |
+
| 2.0834 | 4.37 | 820 | 2.2395 |
|
| 93 |
+
| 2.1396 | 4.48 | 840 | 2.2400 |
|
| 94 |
+
| 2.1121 | 4.59 | 860 | 2.2394 |
|
| 95 |
+
| 2.0195 | 4.69 | 880 | 2.2391 |
|
| 96 |
+
| 2.0564 | 4.8 | 900 | 2.2391 |
|
| 97 |
+
| 1.9447 | 4.91 | 920 | 2.2396 |
|
| 98 |
+
| 2.2122 | 5.01 | 940 | 2.2384 |
|
| 99 |
+
| 2.0482 | 5.12 | 960 | 2.2404 |
|
| 100 |
+
| 2.051 | 5.23 | 980 | 2.2411 |
|
| 101 |
+
| 2.0345 | 5.33 | 1000 | 2.2409 |
|
| 102 |
+
|
| 103 |
+
|
| 104 |
+
### Framework versions
|
| 105 |
+
|
| 106 |
+
- Transformers 4.28.0.dev0
|
| 107 |
+
- Pytorch 1.13.1+cu116
|
| 108 |
+
- Datasets 2.11.0
|
| 109 |
+
- Tokenizers 0.13.2
|