Filtered Corpus Training
Collection
All models from the paper "Filtered Corpus Training (FiCT) Shows...". Naming convention: `{filter}-{model}-{seed}`. • 47 items • Updated
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("CLMBR/full-transformer-1")
model = AutoModelForCausalLM.from_pretrained("CLMBR/full-transformer-1")Quick Links
full2-transformer-1
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.8575
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 1
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 3052726
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.2215 | 0.03 | 76320 | 4.1935 |
| 4.0184 | 1.03 | 152640 | 4.0250 |
| 3.9089 | 0.03 | 228960 | 3.9513 |
| 3.8437 | 1.03 | 305280 | 3.9104 |
| 3.7912 | 0.03 | 381600 | 3.8856 |
| 3.7513 | 0.03 | 457920 | 3.8687 |
| 3.722 | 1.03 | 534240 | 3.8590 |
| 3.6915 | 0.03 | 610560 | 3.8514 |
| 3.6647 | 1.03 | 686880 | 3.8469 |
| 3.6384 | 0.03 | 763200 | 3.8437 |
| 3.6155 | 0.03 | 839520 | 3.8417 |
| 3.5932 | 1.03 | 915840 | 3.8412 |
| 3.5776 | 0.03 | 992160 | 3.8405 |
| 3.56 | 1.03 | 1068480 | 3.8412 |
| 3.5407 | 0.03 | 1144800 | 3.8419 |
| 3.5278 | 1.03 | 1221120 | 3.8412 |
| 3.509 | 0.03 | 1297440 | 3.8432 |
| 3.4952 | 1.03 | 1373760 | 3.8440 |
| 3.4796 | 0.03 | 1450080 | 3.8456 |
| 3.4729 | 0.03 | 1526400 | 3.8466 |
| 3.4662 | 1.03 | 1602720 | 3.8462 |
| 3.4547 | 0.03 | 1679040 | 3.8487 |
| 3.4501 | 1.03 | 1755360 | 3.8488 |
| 3.4412 | 0.03 | 1831680 | 3.8505 |
| 3.4263 | 0.03 | 1908000 | 3.8518 |
| 3.4148 | 1.03 | 1984320 | 3.8530 |
| 3.403 | 0.03 | 2060640 | 3.8536 |
| 3.3917 | 1.03 | 2136960 | 3.8543 |
| 3.3844 | 0.03 | 2213280 | 3.8566 |
| 3.374 | 1.03 | 2289600 | 3.8571 |
| 3.3612 | 0.03 | 2365920 | 3.8569 |
| 3.3518 | 0.03 | 2442240 | 3.8590 |
| 3.3394 | 1.03 | 2518560 | 3.8593 |
| 3.3304 | 0.03 | 2594880 | 3.8589 |
| 3.3182 | 1.03 | 2671200 | 3.8600 |
| 3.3153 | 0.03 | 2747520 | 3.8600 |
| 3.3098 | 1.03 | 2823840 | 3.8598 |
| 3.3034 | 0.03 | 2900160 | 3.8589 |
| 3.3014 | 1.03 | 2976480 | 3.8586 |
| 3.2952 | 0.02 | 3052726 | 3.8575 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 276
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CLMBR/full-transformer-1")