add model
Browse files- README.md +81 -0
- config.json +66 -0
- tf_model.h5 +3 -0
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_keras_callback
|
| 5 |
+
model-index:
|
| 6 |
+
- name: codet5-kormath
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 11 |
+
probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# codet5-kormath
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [Salesforce/codet5-base](https://huggingface.co/Salesforce/codet5-base) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Train Loss: 0.1967
|
| 18 |
+
- Validation Loss: 0.4570
|
| 19 |
+
- Epoch: 28
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- optimizer: {'name': 'Adam', 'learning_rate': 0.001, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
|
| 39 |
+
- training_precision: mixed_bfloat16
|
| 40 |
+
|
| 41 |
+
### Training results
|
| 42 |
+
|
| 43 |
+
| Train Loss | Validation Loss | Epoch |
|
| 44 |
+
|:----------:|:---------------:|:-----:|
|
| 45 |
+
| 5.0517 | 2.2426 | 0 |
|
| 46 |
+
| 1.9413 | 1.3583 | 1 |
|
| 47 |
+
| 1.7250 | 1.3015 | 2 |
|
| 48 |
+
| 1.2929 | 1.1497 | 3 |
|
| 49 |
+
| 1.1521 | 1.0543 | 4 |
|
| 50 |
+
| 1.0552 | 0.9923 | 5 |
|
| 51 |
+
| 0.9877 | 0.9358 | 6 |
|
| 52 |
+
| 0.9393 | 0.8962 | 7 |
|
| 53 |
+
| 0.8904 | 0.8435 | 8 |
|
| 54 |
+
| 0.8369 | 0.7710 | 9 |
|
| 55 |
+
| 0.7724 | 0.7054 | 10 |
|
| 56 |
+
| 0.6976 | 0.6604 | 11 |
|
| 57 |
+
| 0.6317 | 0.5938 | 12 |
|
| 58 |
+
| 0.5702 | 0.5463 | 13 |
|
| 59 |
+
| 0.5198 | 0.5138 | 14 |
|
| 60 |
+
| 0.4856 | 0.5757 | 15 |
|
| 61 |
+
| 0.5134 | 0.5152 | 16 |
|
| 62 |
+
| 0.4554 | 0.4839 | 17 |
|
| 63 |
+
| 0.4111 | 0.4755 | 18 |
|
| 64 |
+
| 0.3778 | 0.4571 | 19 |
|
| 65 |
+
| 0.3484 | 0.4375 | 20 |
|
| 66 |
+
| 0.3246 | 0.4363 | 21 |
|
| 67 |
+
| 0.3097 | 0.4382 | 22 |
|
| 68 |
+
| 0.2871 | 0.4213 | 23 |
|
| 69 |
+
| 0.2677 | 0.4334 | 24 |
|
| 70 |
+
| 0.2473 | 0.4261 | 25 |
|
| 71 |
+
| 0.2291 | 0.4301 | 26 |
|
| 72 |
+
| 0.2132 | 0.4296 | 27 |
|
| 73 |
+
| 0.1967 | 0.4570 | 28 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.19.2
|
| 79 |
+
- TensorFlow 2.8.0
|
| 80 |
+
- Datasets 2.2.1
|
| 81 |
+
- Tokenizers 0.12.1
|
config.json
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Salesforce/codet5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 2,
|
| 13 |
+
"feed_forward_proj": "relu",
|
| 14 |
+
"gradient_checkpointing": false,
|
| 15 |
+
"id2label": {
|
| 16 |
+
"0": "LABEL_0"
|
| 17 |
+
},
|
| 18 |
+
"initializer_factor": 1.0,
|
| 19 |
+
"is_encoder_decoder": true,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"LABEL_0": 0
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_epsilon": 1e-06,
|
| 24 |
+
"model_type": "t5",
|
| 25 |
+
"n_positions": 512,
|
| 26 |
+
"num_decoder_layers": 12,
|
| 27 |
+
"num_heads": 12,
|
| 28 |
+
"num_layers": 12,
|
| 29 |
+
"output_past": true,
|
| 30 |
+
"pad_token_id": 0,
|
| 31 |
+
"relative_attention_max_distance": 128,
|
| 32 |
+
"relative_attention_num_buckets": 32,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"summarization": {
|
| 35 |
+
"early_stopping": true,
|
| 36 |
+
"length_penalty": 2.0,
|
| 37 |
+
"max_length": 200,
|
| 38 |
+
"min_length": 30,
|
| 39 |
+
"no_repeat_ngram_size": 3,
|
| 40 |
+
"num_beams": 4,
|
| 41 |
+
"prefix": "summarize: "
|
| 42 |
+
},
|
| 43 |
+
"translation_en_to_de": {
|
| 44 |
+
"early_stopping": true,
|
| 45 |
+
"max_length": 300,
|
| 46 |
+
"num_beams": 4,
|
| 47 |
+
"prefix": "translate English to German: "
|
| 48 |
+
},
|
| 49 |
+
"translation_en_to_fr": {
|
| 50 |
+
"early_stopping": true,
|
| 51 |
+
"max_length": 300,
|
| 52 |
+
"num_beams": 4,
|
| 53 |
+
"prefix": "translate English to French: "
|
| 54 |
+
},
|
| 55 |
+
"translation_en_to_ro": {
|
| 56 |
+
"early_stopping": true,
|
| 57 |
+
"max_length": 300,
|
| 58 |
+
"num_beams": 4,
|
| 59 |
+
"prefix": "translate English to Romanian: "
|
| 60 |
+
}
|
| 61 |
+
},
|
| 62 |
+
"torch_dtype": "float32",
|
| 63 |
+
"transformers_version": "4.19.2",
|
| 64 |
+
"use_cache": true,
|
| 65 |
+
"vocab_size": 32100
|
| 66 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8c26aa9390ca19dd341d6ec22f9f5ef77e4369bd7ac122fd65979a4ec243a2b
|
| 3 |
+
size 892059032
|