Commit
•
fc55371
1
Parent(s):
6f52d8f
End of training
Browse files- README.md +95 -0
- generation_config.json +7 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: facebook/opt-350m
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: opt-history-gen2
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# opt-history-gen2
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.8025
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-05
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 8
|
| 42 |
+
- total_train_batch_size: 32
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 500
|
| 46 |
+
- num_epochs: 6
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 3.1245 | 0.1693 | 100 | 3.0013 |
|
| 54 |
+
| 2.9473 | 0.3386 | 200 | 2.9180 |
|
| 55 |
+
| 2.9014 | 0.5078 | 300 | 2.8787 |
|
| 56 |
+
| 2.873 | 0.6771 | 400 | 2.8646 |
|
| 57 |
+
| 2.8631 | 0.8464 | 500 | 2.8631 |
|
| 58 |
+
| 2.8366 | 1.0157 | 600 | 2.8451 |
|
| 59 |
+
| 2.64 | 1.1849 | 700 | 2.8380 |
|
| 60 |
+
| 2.6295 | 1.3542 | 800 | 2.8202 |
|
| 61 |
+
| 2.6272 | 1.5235 | 900 | 2.7987 |
|
| 62 |
+
| 2.6327 | 1.6928 | 1000 | 2.7971 |
|
| 63 |
+
| 2.626 | 1.8620 | 1100 | 2.7739 |
|
| 64 |
+
| 2.5237 | 2.0313 | 1200 | 2.7829 |
|
| 65 |
+
| 2.3242 | 2.2006 | 1300 | 2.7812 |
|
| 66 |
+
| 2.319 | 2.3699 | 1400 | 2.7727 |
|
| 67 |
+
| 2.3314 | 2.5391 | 1500 | 2.7668 |
|
| 68 |
+
| 2.3579 | 2.7084 | 1600 | 2.7561 |
|
| 69 |
+
| 2.307 | 2.8777 | 1700 | 2.7586 |
|
| 70 |
+
| 2.2612 | 3.0470 | 1800 | 2.7795 |
|
| 71 |
+
| 2.056 | 3.2163 | 1900 | 2.7801 |
|
| 72 |
+
| 2.0802 | 3.3855 | 2000 | 2.7670 |
|
| 73 |
+
| 2.1104 | 3.5548 | 2100 | 2.7708 |
|
| 74 |
+
| 2.1115 | 3.7241 | 2200 | 2.7629 |
|
| 75 |
+
| 2.0828 | 3.8934 | 2300 | 2.7606 |
|
| 76 |
+
| 1.996 | 4.0626 | 2400 | 2.7849 |
|
| 77 |
+
| 1.8701 | 4.2319 | 2500 | 2.7938 |
|
| 78 |
+
| 1.92 | 4.4012 | 2600 | 2.7928 |
|
| 79 |
+
| 1.8844 | 4.5705 | 2700 | 2.7846 |
|
| 80 |
+
| 1.9058 | 4.7397 | 2800 | 2.7840 |
|
| 81 |
+
| 1.901 | 4.9090 | 2900 | 2.7821 |
|
| 82 |
+
| 1.8418 | 5.0783 | 3000 | 2.8017 |
|
| 83 |
+
| 1.757 | 5.2476 | 3100 | 2.8055 |
|
| 84 |
+
| 1.7503 | 5.4168 | 3200 | 2.8095 |
|
| 85 |
+
| 1.7606 | 5.5861 | 3300 | 2.8065 |
|
| 86 |
+
| 1.7316 | 5.7554 | 3400 | 2.8043 |
|
| 87 |
+
| 1.7632 | 5.9247 | 3500 | 2.8025 |
|
| 88 |
+
|
| 89 |
+
|
| 90 |
+
### Framework versions
|
| 91 |
+
|
| 92 |
+
- Transformers 4.42.4
|
| 93 |
+
- Pytorch 2.3.1+cu121
|
| 94 |
+
- Datasets 2.21.0
|
| 95 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 1,
|
| 6 |
+
"transformers_version": "4.42.4"
|
| 7 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1324830880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1825597db8f9a84fc820aa2628784eb2d6a21fc550132e5f7e26d2e313505d3
|
| 3 |
size 1324830880
|