Training in progress, step 100

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "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": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13fbc4a8b5b8a8c8c0f5bb62651b39220452e9279f819675fbd2fbfda387ae5f
+size 343691904

runs/Mar07_21-15-11_DESKTOP-C4VDTPF/events.out.tfevents.1709835327.DESKTOP-C4VDTPF.30740.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00a0b9abd34b9c28676b5f477a01524ad2bdc8c62a28195d48c8a918aff3053f
+size 8764

runs/Mar08_01-23-08_DESKTOP-C4VDTPF/events.out.tfevents.1709850193.DESKTOP-C4VDTPF.30740.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d82a9e29f3af749e84c46cf9f43e7ebcebdc0a861181672fc755ff05fd74290b
+size 4774

runs/Mar08_01-24-03_DESKTOP-C4VDTPF/events.out.tfevents.1709850245.DESKTOP-C4VDTPF.30740.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3ebf911268ad104e3ef81f12eb510f1fc73e56c86508d982a695ef75c43194
+size 4428

runs/Mar08_01-42-21_DESKTOP-C4VDTPF/events.out.tfevents.1709851344.DESKTOP-C4VDTPF.30740.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210bef5ccfe81ac491f6efa9cb83630bf143a21256064e9dffaddb25f1986861
+size 5832

runs/Mar08_01-43-01_DESKTOP-C4VDTPF/events.out.tfevents.1709851384.DESKTOP-C4VDTPF.30740.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897c24d43f42913d6b7898daa656bc5f9e62ee22e00e45ef6d38d8311ce6ecb0
+size 5260

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,241 @@
+{
+  "version": "1.0",
+  "truncation": {
+    "direction": "Right",
+    "max_length": 20,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<|endoftext|>"
+  },
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Digits",
+    "individual_digits": true
+  },
+  "post_processor": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": false,
+    "use_regex": true
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "vocab": {
+      "<|endoftext|>": 0,
+      "\n": 1,
+      "\r": 2,
+      "$": 3,
+      "+": 4,
+      "0": 5,
+      "1": 6,
+      "2": 7,
+      "3": 8,
+      "4": 9,
+      "5": 10,
+      "6": 11,
+      "7": 12,
+      "8": 13,
+      "9": 14,
+      ";": 15,
+      "=": 16,
+      "$$": 17,
+      ";=": 18,
+      "$=": 19,
+      "$+": 20,
+      "+;": 21,
+      "=+": 22,
+      "$;": 23,
+      ";;": 24,
+      "==": 25,
+      "++": 26,
+      ";$": 27,
+      ";+": 28,
+      "=;": 29,
+      "=$": 30,
+      "+$": 31,
+      "+=": 32,
+      ";$=": 33,
+      "$+=": 34,
+      "=;=": 35,
+      "$+$": 36,
+      "+$=": 37,
+      "=$;": 38,
+      ";=$": 39,
+      ";=;": 40,
+      "$+;": 41,
+      "=+$": 42,
+      "==;": 43,
+      "+$$": 44,
+      "+;=": 45,
+      "=$$": 46,
+      "$$=": 47,
+      ";=+": 48,
+      "$==": 49,
+      "=++": 50,
+      "++=": 51,
+      "$;=": 52,
+      "+$+": 53,
+      ";$;": 54,
+      ";++": 55,
+      "=$=": 56,
+      "=+;": 57,
+      "==+": 58,
+      "$$$": 59,
+      "$$;": 60,
+      "$$;;": 61,
+      "$=$;": 62,
+      "+;+": 63,
+      "+;+;": 64,
+      "$;+": 65,
+      ";;$": 66,
+      "===": 67,
+      "++$": 68,
+      ";+$": 69,
+      "\r\n": 70,
+      "+=+": 71,
+      "+$;": 72,
+      "+==": 73,
+      "+=$": 74,
+      ";$$": 75,
+      ";;=": 76,
+      ";$+": 77,
+      ";+;": 78,
+      ";;=;": 79,
+      "=$+": 80,
+      "=;;": 81,
+      "=;$": 82,
+      "=$+$": 83,
+      "==+$": 84,
+      "$$+": 85,
+      "$$$$": 86,
+      "$$$;": 87,
+      "$$=;": 88,
+      "$$;=+": 89,
+      ";==": 90,
+      ";==+": 91,
+      ";=++": 92,
+      ";=;$": 93,
+      ";==;": 94,
+      "$=+": 95,
+      "$=++": 96,
+      "$=;+": 97,
+      "$==++": 98,
+      "$++": 99
+    },
+    "merges": [
+      "$ $",
+      "; =",
+      "$ =",
+      "$ +",
+      "+ ;",
+      "= +",
+      "$ ;",
+      "; ;",
+      "= =",
+      "+ +",
+      "; $",
+      "; +",
+      "= ;",
+      "= $",
+      "+ $",
+      "+ =",
+      "; $=",
+      "$+ =",
+      "= ;=",
+      "$+ $",
+      "+ $=",
+      "= $;",
+      ";= $",
+      ";= ;",
+      "$+ ;",
+      "=+ $",
+      "== ;",
+      "+ $$",
+      "+ ;=",
+      "= $$",
+      "$$ =",
+      ";= +",
+      "$= =",
+      "=+ +",
+      "++ =",
+      "$ ;=",
+      "+ $+",
+      "; $;",
+      "; ++",
+      "= $=",
+      "= +;",
+      "= =+",
+      "$$ $",
+      "$$ ;",
+      "$$ ;;",
+      "$= $;",
+      "+; +",
+      "+; +;",
+      "$; +",
+      ";; $",
+      "== =",
+      "++ $",
+      ";+ $",
+      "\r \n",
+      "+ =+",
+      "+ $;",
+      "+ ==",
+      "+ =$",
+      "; $$",
+      "; ;=",
+      "; $+",
+      "; +;",
+      "; ;=;",
+      "= $+",
+      "= ;;",
+      "= ;$",
+      "= $+$",
+      "= =+$",
+      "$$ +",
+      "$$ $$",
+      "$$ $;",
+      "$$ =;",
+      "$$ ;=+",
+      ";= =",
+      ";= =+",
+      ";= ++",
+      ";= ;$",
+      ";= =;",
+      "$= +",
+      "$= ++",
+      "$= ;+",
+      "$= =++",
+      "$+ +"
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cdced9a69f638b11b5680c60e66fc295d25f07b40be8a1e7ff1f04a81a64341
+size 4536