Bollywood-Summary-Generator

README.md

@@ -1,19 +1,19 @@
 ---
-license: apache-2.0
-base_model: facebook/bart-large
+license: mit
+base_model: gpt2
 tags:
 - generated_from_trainer
 model-index:
-- name: results
+- name: Bollywood-Summary-Generator
   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. -->
 
-# results
+# Bollywood-Summary-Generator
 
-This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 
 ## Model description
 
@@ -33,12 +33,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 5
+- eval_batch_size: 5
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 

config.json

@@ -1,75 +1,41 @@
 {
-  "_name_or_path": "facebook/bart-large",
-  "activation_dropout": 0.1,
-  "activation_function": "gelu",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
   "architectures": [
-    "BartForCausalLM"
+    "GPT2LMHeadModel"
   ],
-  "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,
-  "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,
-  "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_decoder": true,
-  "is_encoder_decoder": false,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_position_embeddings": 1024,
-  "model_type": "bart",
-  "no_repeat_ngram_size": 3,
-  "normalize_before": false,
-  "num_beams": 4,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "scale_embedding": false,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "do_sample": true,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_length": 50,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
   "task_specific_params": {
-    "summarization": {
-      "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,
-      "num_beams": 4
-    },
-    "summarization_xsum": {
-      "length_penalty": 1.0,
-      "max_length": 62,
-      "min_length": 11,
-      "num_beams": 6
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
     }
   },
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 50257
 }

generation_config.json

@@ -1,13 +1,9 @@
 {
   "_from_model_config": true,
-  "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,
-  "no_repeat_ngram_size": 3,
-  "num_beams": 4,
-  "pad_token_id": 1,
+  "bos_token_id": 50256,
+  "do_sample": true,
+  "eos_token_id": 50256,
+  "max_length": 50,
+  "pad_token_id": 50256,
   "transformers_version": "4.41.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c1cae3c74ea63fa0e46e589e4ef5e9f08f590484782b27250cc460035598c2
-size 1016373744
+oid sha256:1dd4f9ba6e8eba80fe8ebbbe80760ec96af2ba2b57cdff8d1466175319518d9a
+size 497774208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d71d4c8f547cfcff924aefb90cef55f99bb7395cb644387d09bf01c6ffd5521
+oid sha256:7754ba7e04107c776be7ebac6a4a8aa8ebcd0d6639f23390d70e376da197c1f4
 size 5048