<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
mini_molformer_gsf_6epochs
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6470
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: 0.0006
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.7953 | 0.1 | 1000 | 1.0871 |
| 1.0284 | 0.19 | 2000 | 0.9575 |
| 0.9463 | 0.29 | 3000 | 0.9099 |
| 0.9048 | 0.39 | 4000 | 0.8758 |
| 0.877 | 0.48 | 5000 | 0.8517 |
| 0.8573 | 0.58 | 6000 | 0.8323 |
| 0.8399 | 0.68 | 7000 | 0.8176 |
| 0.8276 | 0.77 | 8000 | 0.8127 |
| 0.8164 | 0.87 | 9000 | 0.8037 |
| 0.8071 | 0.97 | 10000 | 0.7889 |
| 0.7969 | 1.07 | 11000 | 0.7815 |
| 0.7901 | 1.16 | 12000 | 0.7742 |
| 0.7844 | 1.26 | 13000 | 0.7710 |
| 0.778 | 1.36 | 14000 | 0.7633 |
| 0.7732 | 1.45 | 15000 | 0.7605 |
| 0.7695 | 1.55 | 16000 | 0.7567 |
| 0.7646 | 1.65 | 17000 | 0.7486 |
| 0.7606 | 1.74 | 18000 | 0.7462 |
| 0.7576 | 1.84 | 19000 | 0.7434 |
| 0.7539 | 1.94 | 20000 | 0.7376 |
| 0.7484 | 2.03 | 21000 | 0.7343 |
| 0.7423 | 2.13 | 22000 | 0.7318 |
| 0.7403 | 2.23 | 23000 | 0.7270 |
| 0.7364 | 2.32 | 24000 | 0.7274 |
| 0.7341 | 2.42 | 25000 | 0.7206 |
| 0.7321 | 2.52 | 26000 | 0.7204 |
| 0.728 | 2.61 | 27000 | 0.7152 |
| 0.7253 | 2.71 | 28000 | 0.7131 |
| 0.7224 | 2.81 | 29000 | 0.7099 |
| 0.7198 | 2.91 | 30000 | 0.7073 |
| 0.7166 | 3.0 | 31000 | 0.7039 |
| 0.7079 | 3.1 | 32000 | 0.7009 |
| 0.7074 | 3.2 | 33000 | 0.6980 |
| 0.7051 | 3.29 | 34000 | 0.6951 |
| 0.703 | 3.39 | 35000 | 0.6924 |
| 0.7008 | 3.49 | 36000 | 0.6895 |
| 0.6971 | 3.58 | 37000 | 0.6873 |
| 0.6943 | 3.68 | 38000 | 0.6854 |
| 0.6931 | 3.78 | 39000 | 0.6814 |
| 0.6899 | 3.87 | 40000 | 0.6799 |
| 0.6874 | 3.97 | 41000 | 0.6770 |
| 0.6805 | 4.07 | 42000 | 0.6740 |
| 0.6762 | 4.16 | 43000 | 0.6722 |
| 0.6753 | 4.26 | 44000 | 0.6689 |
| 0.6721 | 4.36 | 45000 | 0.6668 |
| 0.671 | 4.45 | 46000 | 0.6643 |
| 0.6686 | 4.55 | 47000 | 0.6627 |
| 0.6664 | 4.65 | 48000 | 0.6604 |
| 0.6654 | 4.75 | 49000 | 0.6581 |
| 0.6635 | 4.84 | 50000 | 0.6565 |
| 0.6617 | 4.94 | 51000 | 0.6548 |
| 0.6577 | 5.04 | 52000 | 0.6532 |
| 0.6527 | 5.13 | 53000 | 0.6522 |
| 0.6514 | 5.23 | 54000 | 0.6508 |
| 0.6501 | 5.33 | 55000 | 0.6498 |
| 0.6494 | 5.42 | 56000 | 0.6489 |
| 0.6484 | 5.52 | 57000 | 0.6483 |
| 0.6484 | 5.62 | 58000 | 0.6477 |
| 0.6474 | 5.71 | 59000 | 0.6473 |
| 0.6478 | 5.81 | 60000 | 0.6471 |
| 0.6474 | 5.91 | 61000 | 0.6470 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
