Training in progress, step 466

config.json

@@ -0,0 +1,94 @@
+{
+  "_name_or_path": "Wonder-Griffin/JudgeLLM",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "batch_size": 32,
+  "bias": true,
+  "block_size": 512,
+  "bos_token_id": 50256,
+  "dim_feedforward": 3072,
+  "dropout": 0.1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "ff_expansion_factor": 4,
+  "hidden_act": "gelu",
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "inference_mode": true,
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "label_smoothing": 0.1,
+  "layer_norm_epsilon": 1e-05,
+  "learning_rate": 0.0003,
+  "log_interval": 100,
+  "max_grad_norm": 1.0,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 512,
+  "output_dir": "C:/Users/wonde/output",
+  "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_heads": {
+    "classifier_head": {
+      "params": {
+        "num_labels": 5
+      },
+      "type": "JudgeClassifier"
+    },
+    "lm_head": {
+      "params": {
+        "vocab_size": 50257
+      },
+      "type": "JudgeCasualLMHead"
+    },
+    "qa_head": {
+      "params": {
+        "num_labels": 2
+      },
+      "type": "JudgeWithQA"
+    }
+  },
+  "task_specific_params": {
+    "question-answering": {
+      "max_answer_length": 30
+    },
+    "sequence-classification": {
+      "eval_steps": 500
+    },
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 100
+    }
+  },
+  "torch_dtype": "float32",
+  "total_steps": 10000,
+  "transformers_version": "4.43.3",
+  "use_cache": true,
+  "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 sha256:605b4d35bf5178a1ff4b06e5146993d2f0c7bf5d748e15a0ab49a94f254657f9
+size 496201344

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b0e6d5fd63e63df0df51e84f7c7129c7ca2370cff4550f323b1df6053dae29
+size 5112