Upload best model (Val Loss: 4.485)

config.json

@@ -0,0 +1,27 @@
+{
+  "vocab_size": 50257,
+  "context_length": 256,
+  "emb_dim": 768,
+  "n_heads": 12,
+  "n_layers": 12,
+  "drop_rate": 0.1,
+  "qkv_bias": false,
+  "max_length": 256,
+  "output_dimension": 768,
+  "batch_size": 8,
+  "architectures": [
+    "GPTModel"
+  ],
+  "model_type": "gpt2",
+  "n_positions": 256,
+  "n_embd": 768,
+  "n_layer": 12,
+  "n_head": 12,
+  "activation_function": "gelu_new",
+  "resid_pdrop": 0.1,
+  "attn_pdrop": 0.1,
+  "layer_norm_epsilon": 1e-05,
+  "initializer_range": 0.02,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 50256,
+  "do_sample": true,
+  "eos_token_id": 50256,
+  "max_length": 256,
+  "pad_token_id": 50256,
+  "temperature": 0.8,
+  "transformers_version": "4.57.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad82f01d60aea30cf187a5bde28f272788deb1a508fd27dd2c9813ae01dc45a7
+size 652889751

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}