Upload model

README.md

@@ -1,12 +1,12 @@
 ---
-license: unlicense
 datasets:
 - HuggingFaceFW/fineweb
 language:
 - en
+library_name: transformers
+license: unlicense
 metrics:
 - accuracy
-library_name: transformers
 pipeline_tag: text-generation
 ---
 # Judge-GPT2

config.json

@@ -1,75 +1,44 @@
-{
-    "return_dict": true,
-    "output_hidden_states": false,
-    "output_attentions": false,
-    "torchscript": false,
-    "torch_dtype": null,
-    "use_bfloat16": false,
-    "tf_legacy_loss": false,
-    "pruned_heads": {},
-    "tie_word_embeddings": true,
-    "chunk_size_feed_forward": 0,
-    "is_encoder_decoder": false,
-    "is_decoder": false,
-    "cross_attention_hidden_size": null,
-    "add_cross_attention": false,
-    "tie_encoder_decoder": false,
-    "max_length": 20,
-    "min_length": 0,
-    "do_sample": false,
-    "early_stopping": false,
-    "num_beams": 1,
-    "num_beam_groups": 1,
-    "diversity_penalty": 0.0,
-    "temperature": 1.0,
-    "top_k": 50,
-    "top_p": 1.0,
-    "typical_p": 1.0,
-    "repetition_penalty": 1.0,
-    "length_penalty": 1.0,
-    "no_repeat_ngram_size": 0,
-    "encoder_no_repeat_ngram_size": 0,
-    "bad_words_ids": null,
-    "num_return_sequences": 1,
-    "output_scores": false,
-    "return_dict_in_generate": false,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "remove_invalid_values": false,
-    "exponential_decay_length_penalty": null,
-    "suppress_tokens": null,
-    "begin_suppress_tokens": null,
-    "architectures": [],
-    "finetuning_task": null,
-    "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-    },
-    "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1
-    },
-    "tokenizer_class": null,
-    "prefix": null,
-    "bos_token_id": null,
-    "pad_token_id": null,
-    "eos_token_id": null,
-    "sep_token_id": null,
-    "decoder_start_token_id": null,
-    "task_specific_params": null,
-    "problem_type": null,
-    "_name_or_path": "",
-    "transformers_version": "4.43.3",
-    "vocab_size": 50257,
-    "n_layer": 12,
-    "n_head": 12,
-    "n_embd": 768,
-    "output_dir": "./results",
-    "block_size": 512,
-    "hidden_size": 768,
-    "dropout": 0.1,
-    "bias": true,
-    "ff_expansion_factor": 4,
-    "label_smoothing": 0.1,
-    "model_type": "judge-gpt"
-}
+{
+  "_name_or_path": "C:/Users/wonde/output/Judge-GPT2",
+  "architectures": [
+    "JudgeModel"
+  ],
+  "batch_size": 32,
+  "bias": true,
+  "block_size": 512,
+  "dim_feedforward": 3072,
+  "dropout": 0.1,
+  "ff_expansion_factor": 4,
+  "hidden_act": "gelu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "label_smoothing": 0.1,
+  "learning_rate": 0.0003,
+  "log_interval": 100,
+  "max_grad_norm": 1.0,
+  "max_position_embeddings": 512,
+  "model_type": "judge-gpt",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_layer": 12,
+  "output_dir": "C:/Users/wonde/output",
+  "torch_dtype": "float32",
+  "total_steps": 10000,
+  "transformers_version": "4.43.3",
+  "vocab_size": 50257,
+  "warmup_steps": 1000,
+  "weight_decay": 0.01
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5604eef91cb6d746ac20147f3def910276f7cba6ddc9b1aa5e712f793f6bd1
+size 963697256