End of training
Browse files- README.md +84 -0
- config.json +34 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/flan-t5-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: models
|
| 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 |
+
# models
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.1902
|
| 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: 2e-05
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 2
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
| 49 |
+
| 0.3389 | 0.0699 | 500 | 0.2668 |
|
| 50 |
+
| 0.2719 | 0.1398 | 1000 | 0.2524 |
|
| 51 |
+
| 0.2612 | 0.2097 | 1500 | 0.2381 |
|
| 52 |
+
| 0.2634 | 0.2796 | 2000 | 0.2313 |
|
| 53 |
+
| 0.2403 | 0.3495 | 2500 | 0.2260 |
|
| 54 |
+
| 0.2433 | 0.4193 | 3000 | 0.2190 |
|
| 55 |
+
| 0.2351 | 0.4892 | 3500 | 0.2168 |
|
| 56 |
+
| 0.2424 | 0.5591 | 4000 | 0.2109 |
|
| 57 |
+
| 0.2198 | 0.6290 | 4500 | 0.2071 |
|
| 58 |
+
| 0.2313 | 0.6989 | 5000 | 0.2062 |
|
| 59 |
+
| 0.226 | 0.7688 | 5500 | 0.2058 |
|
| 60 |
+
| 0.2195 | 0.8387 | 6000 | 0.2030 |
|
| 61 |
+
| 0.2173 | 0.9086 | 6500 | 0.2009 |
|
| 62 |
+
| 0.2359 | 0.9785 | 7000 | 0.1969 |
|
| 63 |
+
| 0.2055 | 1.0484 | 7500 | 0.1961 |
|
| 64 |
+
| 0.2074 | 1.1183 | 8000 | 0.1980 |
|
| 65 |
+
| 0.2066 | 1.1881 | 8500 | 0.1938 |
|
| 66 |
+
| 0.2077 | 1.2580 | 9000 | 0.1937 |
|
| 67 |
+
| 0.196 | 1.3279 | 9500 | 0.1948 |
|
| 68 |
+
| 0.2027 | 1.3978 | 10000 | 0.1931 |
|
| 69 |
+
| 0.2001 | 1.4677 | 10500 | 0.1922 |
|
| 70 |
+
| 0.1925 | 1.5376 | 11000 | 0.1932 |
|
| 71 |
+
| 0.1933 | 1.6075 | 11500 | 0.1900 |
|
| 72 |
+
| 0.2038 | 1.6774 | 12000 | 0.1921 |
|
| 73 |
+
| 0.1892 | 1.7473 | 12500 | 0.1914 |
|
| 74 |
+
| 0.1956 | 1.8172 | 13000 | 0.1904 |
|
| 75 |
+
| 0.1956 | 1.8871 | 13500 | 0.1898 |
|
| 76 |
+
| 0.1925 | 1.9569 | 14000 | 0.1902 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- Transformers 4.40.2
|
| 82 |
+
- Pytorch 2.1.2
|
| 83 |
+
- Datasets 2.18.0
|
| 84 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2816,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 1024,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"max_length": 1024,
|
| 20 |
+
"model_type": "t5",
|
| 21 |
+
"n_positions": 512,
|
| 22 |
+
"num_decoder_layers": 24,
|
| 23 |
+
"num_heads": 16,
|
| 24 |
+
"num_layers": 24,
|
| 25 |
+
"output_past": true,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"relative_attention_max_distance": 128,
|
| 28 |
+
"relative_attention_num_buckets": 32,
|
| 29 |
+
"tie_word_embeddings": false,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.40.2",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 32128
|
| 34 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"early_stopping": true,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"num_beams": 5,
|
| 6 |
+
"pad_token": 0,
|
| 7 |
+
"transformers_version": "4.40.2"
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:068999492671fd651558d5976dcb4cc6e7f2fea53b6d8cc7b1193658d86ef22b
|
| 3 |
+
size 3132668808
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23c95f1fceb4f180948543f6f5ce1f21afe6fa42cde40c7292ab85bc62d9324e
|
| 3 |
+
size 6648
|