Training in progress, step 300

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": null,
+  "embd_pdrop": 0.1,
+  "eos_token_id": null,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 512,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 512,
+  "pad_token_id": 3,
+  "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": 119
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd906e655f8e9ba58049311d7989a4675d4f61966268eb87e4d41fa2c2b5c22
+size 76961160

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "pad_token": "[PAD]"
+}

tokenizer.json

@@ -0,0 +1,183 @@
+{
+  "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": "[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
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "WhitespaceSplit"
+  },
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "[UNK]": 0,
+      "[CLS]": 1,
+      "[SEP]": 2,
+      "[PAD]": 3,
+      "[MASK]": 4,
+      "TIME_DELTA=4": 5,
+      "TIME_DELTA=2": 6,
+      "BAR_END": 7,
+      "BAR_START": 8,
+      "TRACK_START": 9,
+      "TRACK_END": 10,
+      "NOTE_OFF=67": 11,
+      "NOTE_ON=67": 12,
+      "NOTE_ON=65": 13,
+      "NOTE_OFF=65": 14,
+      "NOTE_ON=62": 15,
+      "NOTE_OFF=62": 16,
+      "NOTE_ON=60": 17,
+      "NOTE_OFF=60": 18,
+      "TIME_DELTA=8": 19,
+      "NOTE_OFF=64": 20,
+      "NOTE_ON=64": 21,
+      "NOTE_ON=63": 22,
+      "NOTE_OFF=63": 23,
+      "NOTE_OFF=66": 24,
+      "NOTE_ON=66": 25,
+      "NOTE_OFF=69": 26,
+      "NOTE_ON=69": 27,
+      "NOTE_OFF=68": 28,
+      "NOTE_ON=68": 29,
+      "NOTE_ON=61": 30,
+      "NOTE_OFF=61": 31,
+      "NOTE_OFF=58": 32,
+      "NOTE_ON=58": 33,
+      "NOTE_ON=55": 34,
+      "NOTE_OFF=55": 35,
+      "NOTE_OFF=70": 36,
+      "NOTE_ON=70": 37,
+      "NOTE_OFF=59": 38,
+      "NOTE_ON=59": 39,
+      "NOTE_OFF=57": 40,
+      "NOTE_ON=57": 41,
+      "NOTE_ON=56": 42,
+      "NOTE_OFF=56": 43,
+      "NOTE_OFF=53": 44,
+      "NOTE_ON=53": 45,
+      "NOTE_OFF=71": 46,
+      "NOTE_ON=71": 47,
+      "NOTE_ON=72": 48,
+      "NOTE_OFF=72": 49,
+      "NOTE_ON=54": 50,
+      "NOTE_OFF=54": 51,
+      "NOTE_ON=52": 52,
+      "NOTE_OFF=52": 53,
+      "NOTE_OFF=50": 54,
+      "NOTE_ON=50": 55,
+      "NOTE_ON=51": 56,
+      "NOTE_OFF=51": 57,
+      "NOTE_ON=48": 58,
+      "NOTE_OFF=48": 59,
+      "NOTE_OFF=73": 60,
+      "NOTE_ON=73": 61,
+      "NOTE_OFF=74": 62,
+      "NOTE_ON=74": 63,
+      "NOTE_OFF=49": 64,
+      "NOTE_ON=49": 65,
+      "NOTE_ON=47": 66,
+      "NOTE_OFF=47": 67,
+      "NOTE_ON=75": 68,
+      "NOTE_OFF=75": 69,
+      "NOTE_OFF=46": 70,
+      "NOTE_ON=46": 71,
+      "INST=24": 72,
+      "PIECE_END": 73,
+      "INST=48": 74,
+      "GENRE=JSFAKES": 75,
+      "INST=0": 76,
+      "PIECE_START": 77,
+      "STYLE=JSFAKES": 78,
+      "INST=32": 79,
+      "TIME_DELTA=1": 80,
+      "NOTE_OFF=45": 81,
+      "NOTE_ON=45": 82,
+      "NOTE_ON=76": 83,
+      "NOTE_OFF=76": 84,
+      "TIME_DELTA=6": 85,
+      "NOTE_OFF=44": 86,
+      "NOTE_ON=44": 87,
+      "TIME_DELTA=12": 88,
+      "NOTE_ON=43": 89,
+      "NOTE_OFF=43": 90,
+      "NOTE_OFF=77": 91,
+      "NOTE_ON=77": 92,
+      "NOTE_OFF=78": 93,
+      "NOTE_ON=78": 94,
+      "NOTE_OFF=41": 95,
+      "NOTE_ON=41": 96,
+      "NOTE_ON=42": 97,
+      "NOTE_OFF=42": 98,
+      "NOTE_ON=79": 99,
+      "NOTE_OFF=79": 100,
+      "NOTE_OFF=40": 101,
+      "NOTE_ON=40": 102,
+      "TIME_DELTA=16": 103,
+      "NOTE_ON=39": 104,
+      "NOTE_OFF=39": 105,
+      "NOTE_OFF=80": 106,
+      "NOTE_ON=80": 107,
+      "TIME_DELTA=3": 108,
+      "NOTE_OFF=38": 109,
+      "NOTE_ON=38": 110,
+      "NOTE_OFF=37": 111,
+      "NOTE_ON=37": 112,
+      "NOTE_ON=36": 113,
+      "NOTE_OFF=36": 114,
+      "NOTE_OFF=81": 115,
+      "NOTE_ON=81": 116,
+      "TIME_DELTA=7": 117,
+      "TIME_DELTA=10": 118
+    },
+    "unk_token": "[UNK]"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9db46e4f9bd9f64282a4b33572e38235b7f7336fa3b3385f1adee18cf782d84d
+size 4536