HarshalH/OnlySFT

README.md

@@ -3,11 +3,9 @@ library_name: transformers
 license: mit
 base_model: gpt2
 tags:
-- trl
-- sft
 - generated_from_trainer
 datasets:
-- generator
+- scitldr
 model-index:
 - name: output_dir
   results: []
@@ -18,10 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output_dir
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the scitldr dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4202
-- Model Preparation Time: 0.0039
+- Loss: 3.3648
 
 ## Model description
 
@@ -40,21 +37,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 4
-- eval_batch_size: 8
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3.0
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 125  | 3.4195          |
+| No log        | 2.0   | 250  | 3.3752          |
+| No log        | 3.0   | 375  | 3.3648          |
 
 
 ### Framework versions
 
-- Transformers 4.44.2
+- Transformers 4.45.1
 - Pytorch 2.4.0
-- Datasets 3.0.0
-- Tokenizers 0.19.1
+- Datasets 3.0.1
+- Tokenizers 0.20.0

config.json

@@ -33,7 +33,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.45.1",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.45.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71ed609a2380b88caf4c1cd6b5a8b23ffe45d318b69c7234f2a9b3ca68930ba7
+oid sha256:0d9ab37ac1418f598d273a6d8d27aaeffc53d4702e6ac0def9615308793d5386
 size 497774208

runs/Oct06_04-23-21_40898b2f87bd/events.out.tfevents.1728188604.40898b2f87bd.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d6458371251173f54403a3d9797da8042c06f4fa0a232dd04476858dc3cf8c
+size 6361

runs/Oct06_04-23-21_40898b2f87bd/events.out.tfevents.1728189041.40898b2f87bd.30.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8869f39408e58cc12ce0675cead841db4b64a0e654a32c49110b30efb13f08fd
+size 359

tokenizer_config.json

@@ -11,7 +11,7 @@
     }
   },
   "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
   "pad_token": "<|endoftext|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:001ed3f93051497be8912b177276192701edca05cdcd60f16d6c9519a42961f4
-size 5496
+oid sha256:ed9f52ffddeb48fb2940c27b404e8f16eed53e637af8752e5a7ac9eb6df99acc
+size 5240