Training complete

README.md

@@ -0,0 +1,62 @@
+---
+license: mit
+base_model: facebook/bart-large-cnn
+tags:
+- Code Generation
+- generated_from_trainer
+model-index:
+- name: bart-finetuned-cXg-nl-to-code
+ results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# bart-finetuned-cXg-nl-to-code
+
+This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 3.9866
+- eval_rouge1: 0.0521
+- eval_rouge2: 0.0051
+- eval_rougeL: 0.0444
+- eval_bleu: 0.5881
+- eval_meteor: 0.0687
+- eval_codebleu: 0.2509
+- eval_runtime: 145.8637
+- eval_samples_per_second: 0.069
+- eval_steps_per_second: 0.007
+- step: 0
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,70 @@
+{
+ "_name_or_path": "facebook/bart-large-cnn",
+ "_num_labels": 3,
+ "activation_dropout": 0.0,
+ "activation_function": "gelu",
+ "add_final_layer_norm": false,
+ "architectures": [
+ "BartForConditionalGeneration"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 0,
+ "classif_dropout": 0.0,
+ "classifier_dropout": 0.0,
+ "d_model": 1024,
+ "decoder_attention_heads": 16,
+ "decoder_ffn_dim": 4096,
+ "decoder_layerdrop": 0.0,
+ "decoder_layers": 12,
+ "decoder_start_token_id": 2,
+ "dropout": 0.1,
+ "early_stopping": true,
+ "encoder_attention_heads": 16,
+ "encoder_ffn_dim": 4096,
+ "encoder_layerdrop": 0.0,
+ "encoder_layers": 12,
+ "eos_token_id": 2,
+ "force_bos_token_to_be_generated": true,
+ "forced_bos_token_id": 0,
+ "forced_eos_token_id": 2,
+ "gradient_checkpointing": false,
+ "id2label": {
+ "0": "LABEL_0",
+ "1": "LABEL_1",
+ "2": "LABEL_2"
+ },
+ "init_std": 0.02,
+ "is_encoder_decoder": true,
+ "label2id": {
+ "LABEL_0": 0,
+ "LABEL_1": 1,
+ "LABEL_2": 2
+ },
+ "length_penalty": 2.0,
+ "max_length": 142,
+ "max_position_embeddings": 1024,
+ "min_length": 56,
+ "model_type": "bart",
+ "no_repeat_ngram_size": 3,
+ "normalize_before": false,
+ "num_beams": 4,
+ "num_hidden_layers": 12,
+ "output_past": true,
+ "pad_token_id": 1,
+ "prefix": " ",
+ "scale_embedding": false,
+ "task_specific_params": {
+ "summarization": {
+ "early_stopping": true,
+ "length_penalty": 2.0,
+ "max_length": 142,
+ "min_length": 56,
+ "no_repeat_ngram_size": 3,
+ "num_beams": 4
+ }
+ },
+ "torch_dtype": "float32",
+ "transformers_version": "4.42.4",
+ "use_cache": true,
+ "vocab_size": 50264
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+ "bos_token_id": 0,
+ "decoder_start_token_id": 2,
+ "early_stopping": true,
+ "eos_token_id": 2,
+ "forced_bos_token_id": 0,
+ "forced_eos_token_id": 2,
+ "length_penalty": 2.0,
+ "max_length": 142,
+ "min_length": 56,
+ "no_repeat_ngram_size": 3,
+ "num_beams": 4,
+ "pad_token_id": 1,
+ "transformers_version": "4.42.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ab761cb3d97ddaa8efd72d8ba9ea5f46773f43ee83377cf6f14178860e20faf
+size 1625422896

runs/Jul24_11-55-43_ba56a2514472/events.out.tfevents.1721822290.ba56a2514472.135.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a206d6d9924c68c1d2c77d0d7359051eb189292e9a826f4701f3c010b34d3193
+size 579

special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "cls_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "mask_token": {
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "</s>",
+ "sep_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<pad>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "3": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "50264": {
+ "content": "<mask>",
+ "lstrip": true,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<s>",
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "errors": "replace",
+ "mask_token": "<mask>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "</s>",
+ "sep_token": "</s>",
+ "tokenizer_class": "BartTokenizer",
+ "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55109b5b92b8bdcc7983329f32034371b125f1689dced5287c6480c924ac042
+size 5304