Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilgpt2
+base_model: Mohit1Kulkarni/My-Science-LLM
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,10 +13,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # Mohit1Kulkarni/My-Science-LLM
 
-This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
+This model is a fine-tuned version of [Mohit1Kulkarni/My-Science-LLM](https://huggingface.co/Mohit1Kulkarni/My-Science-LLM) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.9337
-- Epoch: 1
+- Train Loss: 1.8569
+- Epoch: 0
 
 ## Model description
 
@@ -42,8 +42,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Epoch |
 |:----------:|:-----:|
-| 2.0504     | 0     |
-| 1.9337     | 1     |
+| 1.8569     | 0     |
 
 
 ### Framework versions

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilgpt2",
+  "_name_or_path": "Mohit1Kulkarni/My-Science-LLM",
   "_num_labels": 1,
   "activation_function": "gelu_new",
   "architectures": [

special_tokens_map.json

@@ -1,5 +1,12 @@
 {
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": "<|endoftext|>"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f15f1767c2d685f317bb14aee812b6ada4ec06d487ea51da5189c9a28b4f6c
+oid sha256:9c6f6fd0d1df51bbe430b367ce1ffb8cb0eacfa4be859c888d7611733927f28b
 size 327745472

tokenizer.json

@@ -11,6 +11,15 @@
       "rstrip": false,
       "normalized": true,
       "special": true
+    },
+    {
+      "id": 50257,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -8,12 +8,21 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "50257": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
+  "pad_token": "[PAD]",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }