End of training
Browse files- README.md +66 -0
- generation_config.json +14 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/blenderbot-400M-distill
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- rouge
|
| 9 |
+
model-index:
|
| 10 |
+
- name: newest
|
| 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 |
+
# newest
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [facebook/blenderbot-400M-distill](https://huggingface.co/facebook/blenderbot-400M-distill) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.3335
|
| 22 |
+
- Rouge1: 0.3426
|
| 23 |
+
- Rouge2: 0.0596
|
| 24 |
+
- Rougel: 0.1740
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 5e-05
|
| 44 |
+
- train_batch_size: 4
|
| 45 |
+
- eval_batch_size: 4
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 3
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|
|
| 56 |
+
| 2.7821 | 1.0 | 789 | 2.6726 | 0.3439 | 0.0600 | 0.1742 |
|
| 57 |
+
| 2.1263 | 2.0 | 1578 | 2.4068 | 0.3421 | 0.0596 | 0.1747 |
|
| 58 |
+
| 1.7148 | 3.0 | 2367 | 2.3335 | 0.3426 | 0.0596 | 0.1740 |
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
### Framework versions
|
| 62 |
+
|
| 63 |
+
- Transformers 4.48.2
|
| 64 |
+
- Pytorch 2.5.1+cu124
|
| 65 |
+
- Datasets 3.2.0
|
| 66 |
+
- Tokenizers 0.21.0
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"encoder_no_repeat_ngram_size": 3,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_eos_token_id": 2,
|
| 7 |
+
"length_penalty": 0.65,
|
| 8 |
+
"max_length": 60,
|
| 9 |
+
"min_length": 20,
|
| 10 |
+
"no_repeat_ngram_size": 3,
|
| 11 |
+
"num_beams": 10,
|
| 12 |
+
"pad_token_id": 2,
|
| 13 |
+
"transformers_version": "4.48.2"
|
| 14 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1459283800
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abf4c3e56edda689416d2068ba80f8e82277f306439330220af260de2c6b3216
|
| 3 |
size 1459283800
|