Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
base_model: ai-forever/rugpt3large_based_on_gpt2
|
| 6 |
+
model-index:
|
| 7 |
+
- name: rugpt3large_5epoch_withval
|
| 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 |
+
# rugpt3large_5epoch_withval
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [ai-forever/rugpt3large_based_on_gpt2](https://huggingface.co/ai-forever/rugpt3large_based_on_gpt2) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 3.6271
|
| 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: 0.0002
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 3
|
| 42 |
+
- total_train_batch_size: 24
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 5
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:------:|:------:|:---------------:|
|
| 52 |
+
| 3.738 | 1.0000 | 24244 | 3.6641 |
|
| 53 |
+
| 3.7271 | 2.0000 | 48488 | 3.6466 |
|
| 54 |
+
| 3.7072 | 3.0 | 72733 | 3.6372 |
|
| 55 |
+
| 3.6851 | 4.0000 | 96977 | 3.6301 |
|
| 56 |
+
| 3.6827 | 4.9999 | 121220 | 3.6271 |
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
### Framework versions
|
| 60 |
+
|
| 61 |
+
- PEFT 0.11.2.dev0
|
| 62 |
+
- Transformers 4.42.0.dev0
|
| 63 |
+
- Pytorch 2.0.1+cu118
|
| 64 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4724728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf8e89e4068ccb8646f187cbc3a01e19281db9905d81267ecf04e7dbf729cb13
|
| 3 |
size 4724728
|
runs/Jun27_10-09-39_l-624519da-6f8f-4d3b-9b3b-e8e21f677653/events.out.tfevents.1719482980.l-624519da-6f8f-4d3b-9b3b-e8e21f677653.16792.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56bfd1f9d1032ff1e6e555f61115c0070913ef0128ce8db6b0ca64e03eb6e02c
|
| 3 |
+
size 59219
|