End of training

.gitignore

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

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 5,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 20,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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": 223
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 5,
+  "transformers_version": "4.30.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc56c3323da40ca2d4d750770e991e68ee2db716e0d14b2a195fa73d2c575b7e
+size 344102749

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "\n",
+  "mask_token": "[MASK]",
+  "pad_token": "\n",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json

@@ -0,0 +1,519 @@
+{
+  "version": "1.0",
+  "truncation": {
+    "direction": "Right",
+    "max_length": 20,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "[UNK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "[CLS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "[SEP]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 4,
+      "content": "[MASK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 5,
+      "content": "\n",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": null,
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "[UNK]",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "vocab": {
+      "[UNK]": 0,
+      "[CLS]": 1,
+      "[SEP]": 2,
+      "[PAD]": 3,
+      "[MASK]": 4,
+      "\n": 5,
+      "A": 6,
+      "B": 7,
+      "C": 8,
+      "D": 9,
+      "BB": 10,
+      "AA": 11,
+      "DD": 12,
+      "CC": 13,
+      "BBBB": 14,
+      "AAAA": 15,
+      "DDDD": 16,
+      "CCCC": 17,
+      "BBBBBBBB": 18,
+      "AAAAAAAA": 19,
+      "DDDDDDDD": 20,
+      "CCCCCCCC": 21,
+      "BBB": 22,
+      "AAA": 23,
+      "CCC": 24,
+      "DDD": 25,
+      "BBBBB": 26,
+      "AAAAA": 27,
+      "DDDDD": 28,
+      "CCCCC": 29,
+      "BBBBBB": 30,
+      "AAAAAA": 31,
+      "DDDDDD": 32,
+      "CCCCCC": 33,
+      "BBBBBBB": 34,
+      "BBBBBBBBBBBBBBBB": 35,
+      "AAAAAAA": 36,
+      "AAAAAAAAAAAAAAAA": 37,
+      "DDDDDDD": 38,
+      "CCCCCCC": 39,
+      "DDDDDDDDDDDDDDDD": 40,
+      "CCCCCCCCCCCCCCCC": 41,
+      "BBBBBBBBB": 42,
+      "AAAAAAAAA": 43,
+      "DDDDDDDDD": 44,
+      "BBBBBBBBBB": 45,
+      "AAAAAAAAAA": 46,
+      "CCCCCCCCC": 47,
+      "BBBBBBBBBBB": 48,
+      "AAAAAAAAAAA": 49,
+      "DDDDDDDDDD": 50,
+      "CCCCCCCCCC": 51,
+      "BBBBBBBBBBBB": 52,
+      "DDDDDDDDDDD": 53,
+      "AAAAAAAAAAAA": 54,
+      "CCCCCCCCCCC": 55,
+      "BBBAAA": 56,
+      "BBBBBBBBBBBBB": 57,
+      "AAAAAAAAAAAAA": 58,
+      "BBBCCC": 59,
+      "DDDDDDDDDDDD": 60,
+      "BBBDDD": 61,
+      "CCCCCCCCCCCC": 62,
+      "AAACCC": 63,
+      "AAADDD": 64,
+      "AAAAAAAAAAAAAA": 65,
+      "AAAABBBB": 66,
+      "BBBBBBBBBBBBBB": 67,
+      "DDDDDDDDDDDDD": 68,
+      "CCCCCCCCCCCCC": 69,
+      "BBBBBBBBBBBBBBB": 70,
+      "AAABBB": 71,
+      "DDDCCC": 72,
+      "BBBBAAAA": 73,
+      "AAAAAAAAAAAAAAA": 74,
+      "BBBBCCCC": 75,
+      "DDDDDDDDDDDDDD": 76,
+      "BBBBDDDD": 77,
+      "BBBBCCC": 78,
+      "AAAACCCC": 79,
+      "AAAADDDD": 80,
+      "AAAACCC": 81,
+      "BBBCCCC": 82,
+      "CCCCCCCCCCCCCC": 83,
+      "BBBDDDD": 84,
+      "AAADDDD": 85,
+      "AAAADDD": 86,
+      "BBBBDDD": 87,
+      "AAACCCC": 88,
+      "DDDDDDDDDDDDDDD": 89,
+      "CCCCCCCCCCCCCCC": 90,
+      "BBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBB": 91,
+      "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA": 92,
+      "BBBBAAAAA": 93,
+      "BBBAA": 94,
+      "AAAABBBBB": 95,
+      "CCCDDD": 96,
+      "BBBBAAA": 97,
+      "BBBCC": 98,
+      "BBBBBBBBBBBBBBBBB": 99,
+      "BBBBBAAAAA": 100,
+      "AAAAAAAAAAAAAAAAA": 101,
+      "BBBDD": 102,
+      "AAABB": 103,
+      "BBBBBCCCC": 104,
+      "DDDDCCCC": 105,
+      "BBBBDDDDD": 106,
+      "BBBAAAAA": 107,
+      "BBBBCCCCC": 108,
+      "BBBAAAA": 109,
+      "AAACC": 110,
+      "DDDDCCC": 111,
+      "AAADD": 112,
+      "BBBBBBBBBBBBBBBBBB": 113,
+      "AAAAACCCC": 114,
+      "AAAACCCCC": 115,
+      "AAAAAAAAAAAAAAAAAA": 116,
+      "BBCCC": 117,
+      "AAAADDDDD": 118,
+      "BBBBBDDDD": 119,
+      "BBBCCCCC": 120,
+      "BBBBBCCC": 121,
+      "DDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDD": 122,
+      "BBBBBDDDDD": 123,
+      "DDDCCCC": 124,
+      "AAAABBBBBB": 125,
+      "BBBBAAAAAA": 126,
+      "CCCCCCCCCCCCCCCCC": 127,
+      "BBBDDDDD": 128,
+      "BBBBBCCCCC": 129,
+      "BBDDD": 130,
+      "DDDDDDDDDDDDDDDDD": 131,
+      "AADDD": 132,
+      "BBBBBDDD": 133,
+      "AAAAADDDD": 134,
+      "AAABBBBBB": 135,
+      "AACCC": 136,
+      "BBBAAAAAA": 137,
+      "AAAAACCCCC": 138,
+      "DDDDDCCCC": 139,
+      "BBBBBAAAAAA": 140,
+      "AAAAACCC": 141,
+      "AAACCCCC": 142,
+      "CCCCCCCCCCCCCCCCCC": 143,
+      "DDDDDDDDDDDDDDDDDD": 144,
+      "AAADDDDD": 145,
+      "AAAAADDDDD": 146,
+      "AAAADDDDDD": 147,
+      "BBBBDDDDDD": 148,
+      "BBBBBBCCCC": 149,
+      "DDCCC": 150,
+      "CCCCCCCCCCCCCCCCCCCCCCCCCCCCCCCC": 151,
+      "BBBBCCCCCC": 152,
+      "AAAAAACCCC": 153,
+      "BBBBBBDDDD": 154,
+      "AAAABBBBBBB": 155,
+      "BBBCCCCCC": 156,
+      "BBBBBBDDDDD": 157,
+      "BBBBBCCCCCC": 158,
+      "BBBDDDDDD": 159,
+      "AAAACCCCCC": 160,
+      "BBCC": 161,
+      "CCCCDDD": 162,
+      "AAAAADDD": 163,
+      "BBBBBDDDDDD": 164,
+      "BBBBBBCCC": 165,
+      "DDDDCCCCC": 166,
+      "BBBBBBCCCCC": 167,
+      "BBBBAAAAAAA": 168,
+      "AAACCCCCC": 169,
+      "AAABBBBBBB": 170,
+      "CCDDD": 171,
+      "BBBBBAAAA": 172,
+      "BBBBBBDDD": 173,
+      "AAAAAADDDDD": 174,
+      "CCCCDDDD": 175,
+      "AAAAAACCCCC": 176,
+      "AAAAADDDDDD": 177,
+      "DDDDDDDDDDDDDDDDDDD": 178,
+      "BBAA": 179,
+      "AAABBBB": 180,
+      "AAABBBBB": 181,
+      "BBBAAAAAAA": 182,
+      "AAAAAADDDD": 183,
+      "CCCCCCCCCCCCCCCCCCC": 184,
+      "AAAAACCCCCC": 185,
+      "AAAAABBBBBB": 186,
+      "AAADDDDDD": 187,
+      "BBBBBBBCCCC": 188,
+      "BBDD": 189,
+      "BBBBBBBCCC": 190,
+      "CCCCCDDDD": 191,
+      "AAAAAACCC": 192,
+      "BBBBBAAAAAAA": 193,
+      "BBBDDDDDDD": 194,
+      "DDDDDCCC": 195,
+      "DDDDDCCCCC": 196,
+      "AAAAAADDDDDD": 197,
+      "AACC": 198,
+      "BBBBBBBDDDD": 199,
+      "AAAAAADDD": 200,
+      "BBBBCCCCCCC": 201,
+      "AAAABBBBBBBB": 202,
+      "BBBCCCCCCC": 203,
+      "BBBBBDDDDDDD": 204,
+      "BBBBDDDDDDD": 205,
+      "BBBBBBCCCCCC": 206,
+      "AAAACCCCCCC": 207,
+      "AAABBBBBBBB": 208,
+      "BBCCCC": 209,
+      "AAAADDDDDDD": 210,
+      "BBBAAAAAAAA": 211,
+      "BBBBBBDDDDDD": 212,
+      "BBBBAAAAAAAA": 213,
+      "AAAAAACCCCCC": 214,
+      "BBBBBBAAAAA": 215,
+      "BBBBCC": 216,
+      "AAAAAAACCCC": 217,
+      "DDDDDDDDDDDDDDDDDDDD": 218,
+      "AAACCCCCCC": 219,
+      "BBBBBBBDDD": 220,
+      "BBBBBBBCCCCC": 221,
+      "AADD": 222
+    },
+    "merges": [
+      "B B",
+      "A A",
+      "D D",
+      "C C",
+      "BB BB",
+      "AA AA",
+      "DD DD",
+      "CC CC",
+      "BBBB BBBB",
+      "AAAA AAAA",
+      "DDDD DDDD",
+      "CCCC CCCC",
+      "BB B",
+      "AA A",
+      "CC C",
+      "DD D",
+      "BBBB B",
+      "AAAA A",
+      "DDDD D",
+      "CCCC C",
+      "BBBB BB",
+      "AAAA AA",
+      "DDDD DD",
+      "CCCC CC",
+      "BBBB BBB",
+      "BBBBBBBB BBBBBBBB",
+      "AAAA AAA",
+      "AAAAAAAA AAAAAAAA",
+      "DDDD DDD",
+      "CCCC CCC",
+      "DDDDDDDD DDDDDDDD",
+      "CCCCCCCC CCCCCCCC",
+      "BBBBBBBB B",
+      "AAAAAAAA A",
+      "DDDDDDDD D",
+      "BBBBBBBB BB",
+      "AAAAAAAA AA",
+      "CCCCCCCC C",
+      "BBBBBBBB BBB",
+      "AAAAAAAA AAA",
+      "DDDDDDDD DD",
+      "CCCCCCCC CC",
+      "BBBBBBBB BBBB",
+      "DDDDDDDD DDD",
+      "AAAAAAAA AAAA",
+      "CCCCCCCC CCC",
+      "BBB AAA",
+      "BBBBBBBB BBBBB",
+      "AAAAAAAA AAAAA",
+      "BBB CCC",
+      "DDDDDDDD DDDD",
+      "BBB DDD",
+      "CCCCCCCC CCCC",
+      "AAA CCC",
+      "AAA DDD",
+      "AAAAAAAA AAAAAA",
+      "AAAA BBBB",
+      "BBBBBBBB BBBBBB",
+      "DDDDDDDD DDDDD",
+      "CCCCCCCC CCCCC",
+      "BBBBBBBB BBBBBBB",
+      "AAA BBB",
+      "DDD CCC",
+      "BBBB AAAA",
+      "AAAAAAAA AAAAAAA",
+      "BBBB CCCC",
+      "DDDDDDDD DDDDDD",
+      "BBBB DDDD",
+      "BBBB CCC",
+      "AAAA CCCC",
+      "AAAA DDDD",
+      "AAAA CCC",
+      "BBB CCCC",
+      "CCCCCCCC CCCCCC",
+      "BBB DDDD",
+      "AAA DDDD",
+      "AAAA DDD",
+      "BBBB DDD",
+      "AAA CCCC",
+      "DDDDDDDD DDDDDDD",
+      "CCCCCCCC CCCCCCC",
+      "BBBBBBBBBBBBBBBB BBBBBBBBBBBBBBBB",
+      "AAAAAAAAAAAAAAAA AAAAAAAAAAAAAAAA",
+      "BBBB AAAAA",
+      "BBB AA",
+      "AAAA BBBBB",
+      "CCC DDD",
+      "BBBB AAA",
+      "BBB CC",
+      "BBBBBBBBBBBBBBBB B",
+      "BBBBB AAAAA",
+      "AAAAAAAAAAAAAAAA A",
+      "BBB DD",
+      "AAA BB",
+      "BBBBB CCCC",
+      "DDDD CCCC",
+      "BBBB DDDDD",
+      "BBB AAAAA",
+      "BBBB CCCCC",
+      "BBB AAAA",
+      "AAA CC",
+      "DDDD CCC",
+      "AAA DD",
+      "BBBBBBBBBBBBBBBB BB",
+      "AAAAA CCCC",
+      "AAAA CCCCC",
+      "AAAAAAAAAAAAAAAA AA",
+      "BB CCC",
+      "AAAA DDDDD",
+      "BBBBB DDDD",
+      "BBB CCCCC",
+      "BBBBB CCC",
+      "DDDDDDDDDDDDDDDD DDDDDDDDDDDDDDDD",
+      "BBBBB DDDDD",
+      "DDD CCCC",
+      "AAAA BBBBBB",
+      "BBBB AAAAAA",
+      "CCCCCCCCCCCCCCCC C",
+      "BBB DDDDD",
+      "BBBBB CCCCC",
+      "BB DDD",
+      "DDDDDDDDDDDDDDDD D",
+      "AA DDD",
+      "BBBBB DDD",
+      "AAAAA DDDD",
+      "AAA BBBBBB",
+      "AA CCC",
+      "BBB AAAAAA",
+      "AAAAA CCCCC",
+      "DDDDD CCCC",
+      "BBBBB AAAAAA",
+      "AAAAA CCC",
+      "AAA CCCCC",
+      "CCCCCCCCCCCCCCCC CC",
+      "DDDDDDDDDDDDDDDD DD",
+      "AAA DDDDD",
+      "AAAAA DDDDD",
+      "AAAA DDDDDD",
+      "BBBB DDDDDD",
+      "BBBBBB CCCC",
+      "DD CCC",
+      "CCCCCCCCCCCCCCCC CCCCCCCCCCCCCCCC",
+      "BBBB CCCCCC",
+      "AAAAAA CCCC",
+      "BBBBBB DDDD",
+      "AAAA BBBBBBB",
+      "BBB CCCCCC",
+      "BBBBBB DDDDD",
+      "BBBBB CCCCCC",
+      "BBB DDDDDD",
+      "AAAA CCCCCC",
+      "BB CC",
+      "CCCC DDD",
+      "AAAAA DDD",
+      "BBBBB DDDDDD",
+      "BBBBBB CCC",
+      "DDDD CCCCC",
+      "BBBBBB CCCCC",
+      "BBBB AAAAAAA",
+      "AAA CCCCCC",
+      "AAA BBBBBBB",
+      "CC DDD",
+      "BBBBB AAAA",
+      "BBBBBB DDD",
+      "AAAAAA DDDDD",
+      "CCCC DDDD",
+      "AAAAAA CCCCC",
+      "AAAAA DDDDDD",
+      "DDDDDDDDDDDDDDDD DDD",
+      "BB AA",
+      "AAA BBBB",
+      "AAA BBBBB",
+      "BBB AAAAAAA",
+      "AAAAAA DDDD",
+      "CCCCCCCCCCCCCCCC CCC",
+      "AAAAA CCCCCC",
+      "AAAAA BBBBBB",
+      "AAA DDDDDD",
+      "BBBBBBB CCCC",
+      "BB DD",
+      "BBBBBBB CCC",
+      "CCCCC DDDD",
+      "AAAAAA CCC",
+      "BBBBB AAAAAAA",
+      "BBB DDDDDDD",
+      "DDDDD CCC",
+      "DDDDD CCCCC",
+      "AAAAAA DDDDDD",
+      "AA CC",
+      "BBBBBBB DDDD",
+      "AAAAAA DDD",
+      "BBBB CCCCCCC",
+      "AAAA BBBBBBBB",
+      "BBB CCCCCCC",
+      "BBBBB DDDDDDD",
+      "BBBB DDDDDDD",
+      "BBBBBB CCCCCC",
+      "AAAA CCCCCCC",
+      "AAA BBBBBBBB",
+      "BB CCCC",
+      "AAAA DDDDDDD",
+      "BBB AAAAAAAA",
+      "BBBBBB DDDDDD",
+      "BBBB AAAAAAAA",
+      "AAAAAA CCCCCC",
+      "BBBBBB AAAAA",
+      "BBBB CC",
+      "AAAAAAA CCCC",
+      "DDDDDDDDDDDDDDDD DDDD",
+      "AAA CCCCCCC",
+      "BBBBBBB DDD",
+      "BBBBBBB CCCCC",
+      "AA DD"
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,5 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553005660a19b817a9fbed1ae41fc7c480fcc4cb32bf9251221698de1e539581
+size 3899