End of training

README.md

@@ -1,11 +1,9 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: sshleifer/distilbart-cnn-12-6
+base_model: facebook/bart-base
 tags:
 - generated_from_trainer
-metrics:
-- rouge
 model-index:
 - name: cleaned_ds
   results: []
@@ -16,14 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # cleaned_ds
 
-This model is a fine-tuned version of [sshleifer/distilbart-cnn-12-6](https://huggingface.co/sshleifer/distilbart-cnn-12-6) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 4.2803
-- Rouge1: 0.2705
-- Rouge2: 0.0363
-- Rougel: 0.1609
-- Rougelsum: 0.1609
-- Generated Length: 113.0
+This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
 
 ## Model description
 
@@ -48,21 +39,11 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Generated Length |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------------:|
-| No log        | 1.0   | 1    | 4.5060          | 0.2826 | 0.0384 | 0.1694 | 0.1694    | 95.0             |
-| No log        | 2.0   | 2    | 4.3368          | 0.2832 | 0.0333 | 0.1701 | 0.1701    | 82.0             |
-| No log        | 3.0   | 3    | 4.2803          | 0.2705 | 0.0363 | 0.1609 | 0.1609    | 113.0            |
-
-
 ### Framework versions
 
 - Transformers 4.44.2
 - Pytorch 2.4.1+cu121
-- Datasets 3.0.1
 - Tokenizers 0.19.1

config.json

@@ -1,32 +1,29 @@
 {
-  "_name_or_path": "sshleifer/distilbart-cnn-12-6",
-  "_num_labels": 3,
-  "activation_dropout": 0.0,
+  "_name_or_path": "facebook/bart-base",
+  "activation_dropout": 0.1,
   "activation_function": "gelu",
   "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
     "BartForConditionalGeneration"
   ],
-  "attention_dropout": 0.0,
+  "attention_dropout": 0.1,
   "bos_token_id": 0,
-  "classif_dropout": 0.0,
+  "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
   "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_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 12,
+  "encoder_layers": 6,
   "eos_token_id": 2,
-  "extra_pos_embeddings": 2,
-  "force_bos_token_to_be_generated": true,
   "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
@@ -42,36 +39,37 @@
     "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,
   "normalize_embedding": true,
   "num_beams": 4,
-  "num_hidden_layers": 12,
-  "output_past": true,
+  "num_hidden_layers": 6,
   "pad_token_id": 1,
-  "prefix": " ",
-  "replacing_rate": 0,
   "scale_embedding": false,
-  "static_position_embeddings": false,
-  "student_decoder_layers": null,
-  "student_encoder_layers": null,
   "task_specific_params": {
     "summarization": {
-      "early_stopping": true,
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
       "length_penalty": 2.0,
       "max_length": 142,
       "min_length": 56,
-      "no_repeat_ngram_size": 3,
       "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
     }
   },
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
   "use_cache": true,
-  "vocab_size": 50264
+  "vocab_size": 50265
 }

generation_config.json

@@ -5,9 +5,6 @@
   "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,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be9c99e0b130daaa46d4ce297668b4848422976475aaaedb840de68d638f1b13
-size 1222284056
+oid sha256:6760e7333f73bb63205c02d5677a52e254fc4090ddc70a302c5c441c50742eae
+size 557912620

runs/Oct02_19-55-33_640012623f1f/events.out.tfevents.1727898934.640012623f1f.384.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d651e20f4049b135793cd5a3598cee40d274929746963583101f1c5550eb07ee
+size 6537

special_tokens_map.json

@@ -1,25 +1,7 @@
 {
-  "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
-  },
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -27,25 +9,7 @@
     "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
-  }
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -48,7 +48,7 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
-  "model_max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "tokenizer_class": "BartTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbc967df72e2cc8222a72307c72bb2902573db98a04d0e70e950111ced8c7043
+oid sha256:84f73c7e2b1bbbbf948cca365efe87a01c9cf1fea2dddd08c2db03927df1c094
 size 5304