End of training

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model: sshleifer/distilbart-xsum-12-6
+tags:
+- generated_from_trainer
+model-index:
+- name: bart-abs-1509-0313-lr-0.0003-bs-4-maxep-10
+  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-abs-1509-0313-lr-0.0003-bs-4-maxep-10
+
+This model is a fine-tuned version of [sshleifer/distilbart-xsum-12-6](https://huggingface.co/sshleifer/distilbart-xsum-12-6) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.7482
+- Rouge/rouge1: 0.4015
+- Rouge/rouge2: 0.1493
+- Rouge/rougel: 0.329
+- Rouge/rougelsum: 0.3294
+- Bertscore/bertscore-precision: 0.8894
+- Bertscore/bertscore-recall: 0.8807
+- Bertscore/bertscore-f1: 0.8849
+- Meteor: 0.3397
+- Gen Len: 33.2
+
+## 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: 0.0003
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge/rouge1 | Rouge/rouge2 | Rouge/rougel | Rouge/rougelsum | Bertscore/bertscore-precision | Bertscore/bertscore-recall | Bertscore/bertscore-f1 | Meteor | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-----------------------------:|:--------------------------:|:----------------------:|:------:|:-------:|
+| 1.722         | 1.0   | 217  | 2.6756          | 0.4274       | 0.1866       | 0.3588       | 0.3592          | 0.8936                        | 0.884                      | 0.8886                 | 0.3527 | 32.9545 |
+| 1.7652        | 2.0   | 434  | 2.7321          | 0.416        | 0.1726       | 0.3511       | 0.3521          | 0.8944                        | 0.8818                     | 0.888                  | 0.3352 | 31.5909 |
+| 1.135         | 3.0   | 651  | 2.9372          | 0.3752       | 0.1441       | 0.3163       | 0.3158          | 0.8968                        | 0.8736                     | 0.8849                 | 0.2976 | 26.4    |
+| 0.9762        | 4.0   | 868  | 3.1311          | 0.3959       | 0.1535       | 0.3344       | 0.3353          | 0.8893                        | 0.8777                     | 0.8833                 | 0.3296 | 33.1273 |
+| 0.7207        | 5.0   | 1085 | 3.3741          | 0.4028       | 0.1562       | 0.3388       | 0.3389          | 0.8889                        | 0.8818                     | 0.8852                 | 0.3324 | 34.3273 |
+| 0.3986        | 6.0   | 1302 | 3.4504          | 0.4245       | 0.1689       | 0.3493       | 0.3501          | 0.892                         | 0.8834                     | 0.8876                 | 0.351  | 34.4727 |
+| 0.2471        | 7.0   | 1519 | 3.8316          | 0.4096       | 0.1536       | 0.3384       | 0.3389          | 0.8922                        | 0.8814                     | 0.8867                 | 0.3376 | 32.7909 |
+| 0.1613        | 8.0   | 1736 | 4.2439          | 0.4201       | 0.1621       | 0.346        | 0.347           | 0.8921                        | 0.8815                     | 0.8866                 | 0.3503 | 33.3    |
+| 0.0989        | 9.0   | 1953 | 4.4784          | 0.4115       | 0.1499       | 0.3394       | 0.3408          | 0.8904                        | 0.8825                     | 0.8863                 | 0.3409 | 34.0    |
+| 0.0644        | 10.0  | 2170 | 4.7482          | 0.4015       | 0.1493       | 0.329        | 0.3294          | 0.8894                        | 0.8807                     | 0.8849                 | 0.3397 | 33.2    |
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 2.4.0
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "sshleifer/distilbart-xsum-12-6",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "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": 6,
+  "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,
+  "eos_token_ids": [
+    2
+  ],
+  "extra_pos_embeddings": 2,
+  "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": 0.5,
+  "max_length": 62,
+  "max_position_embeddings": 1024,
+  "min_length": 11,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 6,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "replacing_rate": 0,
+  "save_step": 58,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "student_decoder_layers": null,
+  "student_encoder_layers": null,
+  "task_specific_params": {},
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "length_penalty": 0.5,
+  "max_length": 62,
+  "min_length": 11,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 6,
+  "pad_token_id": 1,
+  "transformers_version": "4.44.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d39bbc493d9bba839048b199bab2d526096b3b6e7fb9a59533cb8691b7d51cb
+size 1222284056

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 +1,57 @@
+{
+  "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": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc513bfa7011a7071a46c0d4f094f02506606c7075d40d30ca7d11ac7dc4ed8e
+size 5432