Training in progress, step 500

README.md

@@ -1,11 +1,9 @@
 ---
 library_name: transformers
 license: mit
-base_model: SumanNazir/highlight_summary_model_trained_on_reduced_data
+base_model: facebook/bart-large-xsum
 tags:
 - generated_from_trainer
-metrics:
-- rouge
 model-index:
 - name: highlight_summary_model_trained_on_reduced_data
   results: []
@@ -16,14 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # highlight_summary_model_trained_on_reduced_data
 
-This model is a fine-tuned version of [SumanNazir/highlight_summary_model_trained_on_reduced_data](https://huggingface.co/SumanNazir/highlight_summary_model_trained_on_reduced_data) on an unknown dataset.
+This model is a fine-tuned version of [facebook/bart-large-xsum](https://huggingface.co/facebook/bart-large-xsum) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.7393
-- Rouge1: 0.4167
-- Rouge2: 0.1684
-- Rougel: 0.3095
-- Rougelsum: 0.3088
-- Generated Length: 38.5758
+- Loss: 1.7400
 
 ## Model description
 
@@ -43,8 +36,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- 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
@@ -53,15 +46,15 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Generated Length |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------------:|
-| No log        | 1.0   | 263  | 4.6745          | 0.4127 | 0.1629 | 0.3115 | 0.3119    | 38.0909          |
-| 0.0309        | 2.0   | 526  | 4.7393          | 0.4167 | 0.1684 | 0.3095 | 0.3088    | 38.5758          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 274  | 1.7445          |
+| 1.6984        | 2.0   | 548  | 1.7400          |
 
 
 ### Framework versions
 
-- Transformers 4.45.1
+- Transformers 4.44.2
 - Pytorch 2.4.1+cu121
 - Datasets 3.0.1
-- Tokenizers 0.20.0
+- Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "SumanNazir/highlight_summary_model_trained_on_reduced_data",
+  "_name_or_path": "facebook/bart-large-xsum",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "gelu",
@@ -19,7 +19,7 @@
   "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "early_stopping": null,
+  "early_stopping": true,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
@@ -42,14 +42,14 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "max_length": null,
+  "max_length": 62,
   "max_position_embeddings": 1024,
-  "min_length": null,
+  "min_length": 11,
   "model_type": "bart",
-  "no_repeat_ngram_size": null,
+  "no_repeat_ngram_size": 3,
   "normalize_before": false,
   "normalize_embedding": true,
-  "num_beams": null,
+  "num_beams": 6,
   "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 1,
@@ -61,7 +61,7 @@
   "student_encoder_layers": null,
   "task_specific_params": {},
   "torch_dtype": "float32",
-  "transformers_version": "4.45.1",
+  "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 50264
 }

generation_config.json

@@ -1,4 +1,5 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 0,
   "decoder_start_token_id": 2,
   "early_stopping": true,
@@ -9,5 +10,5 @@
   "no_repeat_ngram_size": 3,
   "num_beams": 6,
   "pad_token_id": 1,
-  "transformers_version": "4.45.1"
+  "transformers_version": "4.44.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dae807a36ab2a73745aa6a8774bf07f05777b341764cb7cf949a7ec82109c834
+oid sha256:ec831245c1c44fa9b8c40b10528656362ca2657d808f466ae3e07000a3b39745
 size 1625422896

runs/Sep30_20-26-55_13959885f477/events.out.tfevents.1727728016.13959885f477.218.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65fb1689147f1aab9cb9d31dc3605174ac98acf95cb2a8541048e02ceba39e10
+size 6300

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

@@ -48,14 +48,10 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
-  "max_length": 128,
   "model_max_length": 1024,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "stride": 0,
   "tokenizer_class": "BartTokenizer",
   "trim_offsets": true,
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040a829b06db162606556c2f6239102a308d4530eaa19d03f1bf19f978ba81dd
-size 5432
+oid sha256:6582dc6f594bf01c19035f3963975b4f785d0bc02bdc2f50ec12495118b5d2af
+size 5368