add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: mbarthez-davide_articles-copy_enhanced
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 36.548
+---
+
+<!-- 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. -->
+
+# mbarthez-davide_articles-copy_enhanced
+
+This model is a fine-tuned version of [moussaKam/mbarthez](https://huggingface.co/moussaKam/mbarthez) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4905
+- Rouge1: 36.548
+- Rouge2: 19.6282
+- Rougel: 30.2513
+- Rougelsum: 30.2765
+- Gen Len: 25.7238
+
+## 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: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 1.6706        | 1.0   | 33552  | 1.5690          | 31.2477 | 16.5455 | 26.9855 | 26.9754   | 18.6217 |
+| 1.3446        | 2.0   | 67104  | 1.5060          | 32.1108 | 17.1408 | 27.7833 | 27.7703   | 18.9115 |
+| 1.3245        | 3.0   | 100656 | 1.4905          | 32.9084 | 17.7027 | 28.2912 | 28.2975   | 18.9801 |
+
+
+### Framework versions
+
+- Transformers 4.10.2
+- Pytorch 1.7.1+cu110
+- Datasets 1.11.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 25.7238,
+    "eval_loss": 1.4905033111572266,
+    "eval_rouge1": 36.548,
+    "eval_rouge2": 19.6282,
+    "eval_rougeL": 30.2513,
+    "eval_rougeLsum": 30.2765,
+    "eval_runtime": 530.3745,
+    "eval_samples": 2712,
+    "eval_samples_per_second": 5.113,
+    "eval_steps_per_second": 0.639,
+    "train_loss": 1.5143268576412658,
+    "train_runtime": 40494.9096,
+    "train_samples": 268414,
+    "train_samples_per_second": 19.885,
+    "train_steps_per_second": 2.486
+}

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "moussaKam/mbarthez",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartCopyEnhanced"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "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,
+  "dim_proj": 1024,
+  "do_blenderbot_90_layernorm": false,
+  "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,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "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
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "tokenizer_class": "BarthezTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 101122
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 25.7238,
+    "eval_loss": 1.4905033111572266,
+    "eval_rouge1": 36.548,
+    "eval_rouge2": 19.6282,
+    "eval_rougeL": 30.2513,
+    "eval_rougeLsum": 30.2765,
+    "eval_runtime": 530.3745,
+    "eval_samples": 2712,
+    "eval_samples_per_second": 5.113,
+    "eval_steps_per_second": 0.639
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8499db984189f64dc103cc07d6913f7ad2dd079518881565271140390bfc671
+size 1834120283

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7fff580d02c71f72575747fdc1dffa5698f8a88a02dfafa25c0a63df6dbe967
+size 1966695

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "moussaKam/mbarthez", "tokenizer_class": "BarthezTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.5143268576412658,
+    "train_runtime": 40494.9096,
+    "train_samples": 268414,
+    "train_samples_per_second": 19.885,
+    "train_steps_per_second": 2.486
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3c2f68a6d422960ca5a47f11fddaadcf1280c8d5bbb30a2650521d6a5e0a7d
+size 2927