Model save
Browse files- README.md +106 -0
- generation_config.json +7 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: EleutherAI/pythia-1b-deduped
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: sft-pythia-1b-deduped-tldr-preference-sft-trl-style-20241031-202104
|
| 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 |
+
# sft-pythia-1b-deduped-tldr-preference-sft-trl-style-20241031-202104
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [EleutherAI/pythia-1b-deduped](https://huggingface.co/EleutherAI/pythia-1b-deduped) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.4606
|
| 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: 1.41e-05
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 16
|
| 45 |
+
- total_train_batch_size: 128
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 1.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 2.5542 | 0.0221 | 20 | 2.5166 |
|
| 55 |
+
| 2.5232 | 0.0441 | 40 | 2.4990 |
|
| 56 |
+
| 2.5299 | 0.0662 | 60 | 2.4913 |
|
| 57 |
+
| 2.5028 | 0.0883 | 80 | 2.4865 |
|
| 58 |
+
| 2.4449 | 0.1104 | 100 | 2.4829 |
|
| 59 |
+
| 2.4787 | 0.1324 | 120 | 2.4799 |
|
| 60 |
+
| 2.4927 | 0.1545 | 140 | 2.4778 |
|
| 61 |
+
| 2.4421 | 0.1766 | 160 | 2.4759 |
|
| 62 |
+
| 2.4821 | 0.1986 | 180 | 2.4743 |
|
| 63 |
+
| 2.4504 | 0.2207 | 200 | 2.4728 |
|
| 64 |
+
| 2.4284 | 0.2428 | 220 | 2.4716 |
|
| 65 |
+
| 2.4677 | 0.2649 | 240 | 2.4704 |
|
| 66 |
+
| 2.4817 | 0.2869 | 260 | 2.4692 |
|
| 67 |
+
| 2.4607 | 0.3090 | 280 | 2.4683 |
|
| 68 |
+
| 2.4314 | 0.3311 | 300 | 2.4675 |
|
| 69 |
+
| 2.4429 | 0.3532 | 320 | 2.4668 |
|
| 70 |
+
| 2.4618 | 0.3752 | 340 | 2.4661 |
|
| 71 |
+
| 2.4372 | 0.3973 | 360 | 2.4655 |
|
| 72 |
+
| 2.444 | 0.4194 | 380 | 2.4649 |
|
| 73 |
+
| 2.467 | 0.4414 | 400 | 2.4644 |
|
| 74 |
+
| 2.4718 | 0.4635 | 420 | 2.4640 |
|
| 75 |
+
| 2.452 | 0.4856 | 440 | 2.4635 |
|
| 76 |
+
| 2.4283 | 0.5077 | 460 | 2.4632 |
|
| 77 |
+
| 2.4349 | 0.5297 | 480 | 2.4628 |
|
| 78 |
+
| 2.42 | 0.5518 | 500 | 2.4626 |
|
| 79 |
+
| 2.4291 | 0.5739 | 520 | 2.4623 |
|
| 80 |
+
| 2.4285 | 0.5959 | 540 | 2.4620 |
|
| 81 |
+
| 2.4648 | 0.6180 | 560 | 2.4618 |
|
| 82 |
+
| 2.4195 | 0.6401 | 580 | 2.4616 |
|
| 83 |
+
| 2.4958 | 0.6622 | 600 | 2.4614 |
|
| 84 |
+
| 2.4378 | 0.6842 | 620 | 2.4613 |
|
| 85 |
+
| 2.4647 | 0.7063 | 640 | 2.4611 |
|
| 86 |
+
| 2.4334 | 0.7284 | 660 | 2.4611 |
|
| 87 |
+
| 2.4399 | 0.7504 | 680 | 2.4609 |
|
| 88 |
+
| 2.4598 | 0.7725 | 700 | 2.4608 |
|
| 89 |
+
| 2.4149 | 0.7946 | 720 | 2.4607 |
|
| 90 |
+
| 2.4319 | 0.8167 | 740 | 2.4607 |
|
| 91 |
+
| 2.4581 | 0.8387 | 760 | 2.4606 |
|
| 92 |
+
| 2.4439 | 0.8608 | 780 | 2.4606 |
|
| 93 |
+
| 2.4645 | 0.8829 | 800 | 2.4606 |
|
| 94 |
+
| 2.5149 | 0.9050 | 820 | 2.4606 |
|
| 95 |
+
| 2.482 | 0.9270 | 840 | 2.4606 |
|
| 96 |
+
| 2.473 | 0.9491 | 860 | 2.4605 |
|
| 97 |
+
| 2.4648 | 0.9712 | 880 | 2.4605 |
|
| 98 |
+
| 2.4516 | 0.9932 | 900 | 2.4606 |
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
### Framework versions
|
| 102 |
+
|
| 103 |
+
- Transformers 4.44.2
|
| 104 |
+
- Pytorch 2.4.0+cu121
|
| 105 |
+
- Datasets 2.14.6
|
| 106 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.44.2",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2023586384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08ef93deda297b8777c00b9abc6a1106420cea6cd9ab21029beee21e0275841d
|
| 3 |
size 2023586384
|