Training in progress, step 1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 16,
+  "n_head": 2,
+  "n_inner": null,
+  "n_layer": 2,
+  "n_positions": 30,
+  "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_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 70
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f557fea27b9647d605e046df3300af1f6f5c072fdc9444abf6490a8129e11d
+size 41730

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<pad>",
+    "<mask>",
+    "<bos>"
+  ],
+  "bos_token": "<bos>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,166 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<mask>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "WhitespaceSplit"
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "<bos>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "<bos>": {
+        "id": "<bos>",
+        "ids": [
+          3
+        ],
+        "tokens": [
+          "<bos>"
+        ]
+      }
+    }
+  },
+  "decoder": null,
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "<unk>": 0,
+      "<pad>": 1,
+      "<mask>": 2,
+      "<bos>": 3,
+      ".": 4,
+      "the": 5,
+      "and": 6,
+      ",": 7,
+      "it": 8,
+      "had": 9,
+      "in": 10,
+      "was": 11,
+      "he": 12,
+      "here": 13,
+      "Bible": 14,
+      "n<apostrophe>t": 15,
+      "to": 16,
+      "He": 17,
+      "a": 18,
+      "boy": 19,
+      "But": 20,
+      "Oh": 21,
+      "knew": 22,
+      "<apostrophe>s": 23,
+      "moved": 24,
+      "none": 25,
+      "that": 26,
+      "Today": 27,
+      "finger": 28,
+      "help": 29,
+      "quite": 30,
+      "should": 31,
+      "justice": 32,
+      "really": 33,
+      "then": 34,
+      "told": 35,
+      "virtue": 36,
+      "by": 37,
+      "did": 38,
+      "ditch": 39,
+      "meant": 40,
+      "now": 41,
+      "of": 42,
+      "care": 43,
+      "finally": 44,
+      "find": 45,
+      "mattered": 46,
+      "them": 47,
+      "world": 48,
+      ":": 49,
+      "Tuesday": 50,
+      "happened": 51,
+      "intended": 52,
+      "not": 53,
+      "they": 54,
+      "what": 55,
+      "And": 56,
+      "They": 57,
+      "class": 58,
+      "leave": 59,
+      "rising": 60,
+      "saw": 61,
+      "Because": 62,
+      "like": 63,
+      "lip": 64,
+      "narrowed": 65,
+      "sure": 66,
+      "there": 67,
+      "cows": 68,
+      "quivered": 69
+    },
+    "unk_token": "<unk>"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<pad>",
+    "<mask>",
+    "<bos>"
+  ],
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": true,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c3edcf4027dd0552bcd8a57cbd2eb4e8d4aaa09f3f0e4b8ec6cf52bf14d4fe
+size 4408