Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: TR_200_41
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# TR_200_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2885
+- Accuracy: 0.6093
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0006
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 41
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 10.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.485         | 1.0   | 2856  | 1.6960          | 0.4942   |
+| 0.3846        | 2.0   | 5712  | 1.5430          | 0.5348   |
+| 0.3593        | 3.0   | 8568  | 1.4665          | 0.5547   |
+| 0.3438        | 4.0   | 11424 | 1.4175          | 0.5707   |
+| 0.3341        | 5.0   | 14280 | 1.3928          | 0.5774   |
+| 0.3252        | 6.0   | 17136 | 1.3625          | 0.5861   |
+| 0.3192        | 7.0   | 19992 | 1.3340          | 0.5943   |
+| 0.3112        | 8.0   | 22848 | 1.3175          | 0.5998   |
+| 0.3038        | 9.0   | 25704 | 1.3009          | 0.6055   |
+| 0.298         | 10.0  | 28560 | 1.2885          | 0.6093   |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.5.1+cu121
+- Datasets 3.6.0
+- Tokenizers 0.21.1

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.6093458532175187,
+    "eval_loss": 1.288467288017273,
+    "eval_runtime": 10.2823,
+    "eval_samples": 684,
+    "eval_samples_per_second": 66.522,
+    "eval_steps_per_second": 2.14,
+    "perplexity": 3.6272228051709097,
+    "total_flos": 2.387294650368e+17,
+    "train_loss": 0.35219172576562363,
+    "train_runtime": 24797.7753,
+    "train_samples": 91365,
+    "train_samples_per_second": 36.844,
+    "train_steps_per_second": 1.152
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 512,
+  "pad_token_id": 0,
+  "prefix": "<|endoftext|>",
+  "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": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 200
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.6093458532175187,
+    "eval_loss": 1.288467288017273,
+    "eval_runtime": 10.2823,
+    "eval_samples": 684,
+    "eval_samples_per_second": 66.522,
+    "eval_steps_per_second": 2.14,
+    "perplexity": 3.6272228051709097
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}

merges.txt

@@ -0,0 +1,22 @@
+#version: 0.2
+Ä ±
+Ġ b
+a r
+Ã ¼
+e r
+Å Ł
+a n
+i n
+e n
+Ġ k
+Ã §
+Ġ s
+Ġ d
+i r
+Ä Ł
+Ġ y
+ı n
+Ġ g
+Ġ o
+i l
+m a

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1b159f53bbcd63bc83d44032c1b44700b765228f6ce68a50bfe3fe614c9b7b
+size 342426240

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<pad>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,398 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "Lowercase"
+  },
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "<|endoftext|>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "<|endoftext|>": {
+        "id": "<|endoftext|>",
+        "ids": [
+          1
+        ],
+        "tokens": [
+          "<|endoftext|>"
+        ]
+      }
+    }
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "<unk>",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<pad>": 0,
+      "<|endoftext|>": 1,
+      "<s>": 2,
+      "<unk>": 3,
+      "!": 4,
+      "\"": 5,
+      "#": 6,
+      "$": 7,
+      "%": 8,
+      "&": 9,
+      "'": 10,
+      "(": 11,
+      ")": 12,
+      "*": 13,
+      "+": 14,
+      ",": 15,
+      "-": 16,
+      ".": 17,
+      "/": 18,
+      "0": 19,
+      "1": 20,
+      "2": 21,
+      "3": 22,
+      "4": 23,
+      "5": 24,
+      "6": 25,
+      "7": 26,
+      "8": 27,
+      "9": 28,
+      ":": 29,
+      ";": 30,
+      "<": 31,
+      "=": 32,
+      ">": 33,
+      "?": 34,
+      "@": 35,
+      "[": 36,
+      "\\": 37,
+      "]": 38,
+      "^": 39,
+      "_": 40,
+      "`": 41,
+      "a": 42,
+      "b": 43,
+      "c": 44,
+      "d": 45,
+      "e": 46,
+      "f": 47,
+      "g": 48,
+      "h": 49,
+      "i": 50,
+      "j": 51,
+      "k": 52,
+      "l": 53,
+      "m": 54,
+      "n": 55,
+      "o": 56,
+      "p": 57,
+      "q": 58,
+      "r": 59,
+      "s": 60,
+      "t": 61,
+      "u": 62,
+      "v": 63,
+      "w": 64,
+      "x": 65,
+      "y": 66,
+      "z": 67,
+      "{": 68,
+      "|": 69,
+      "}": 70,
+      "~": 71,
+      "¡": 72,
+      "¢": 73,
+      "£": 74,
+      "¤": 75,
+      "¥": 76,
+      "¦": 77,
+      "§": 78,
+      "¨": 79,
+      "©": 80,
+      "ª": 81,
+      "«": 82,
+      "¬": 83,
+      "®": 84,
+      "¯": 85,
+      "°": 86,
+      "±": 87,
+      "²": 88,
+      "³": 89,
+      "´": 90,
+      "µ": 91,
+      "¶": 92,
+      "·": 93,
+      "¸": 94,
+      "¹": 95,
+      "º": 96,
+      "»": 97,
+      "¼": 98,
+      "½": 99,
+      "¾": 100,
+      "¿": 101,
+      "Â": 102,
+      "Ã": 103,
+      "Ä": 104,
+      "Å": 105,
+      "Æ": 106,
+      "Ç": 107,
+      "È": 108,
+      "É": 109,
+      "Ê": 110,
+      "Ë": 111,
+      "Ì": 112,
+      "Î": 113,
+      "Ï": 114,
+      "Ð": 115,
+      "Ñ": 116,
+      "Ò": 117,
+      "Ó": 118,
+      "Õ": 119,
+      "Ö": 120,
+      "×": 121,
+      "Ø": 122,
+      "Ù": 123,
+      "Û": 124,
+      "Þ": 125,
+      "à": 126,
+      "á": 127,
+      "â": 128,
+      "ã": 129,
+      "ä": 130,
+      "å": 131,
+      "æ": 132,
+      "ç": 133,
+      "è": 134,
+      "é": 135,
+      "ê": 136,
+      "ë": 137,
+      "ì": 138,
+      "í": 139,
+      "î": 140,
+      "ï": 141,
+      "ð": 142,
+      "Ċ": 143,
+      "Ġ": 144,
+      "Ģ": 145,
+      "ģ": 146,
+      "Ĥ": 147,
+      "ĥ": 148,
+      "Ħ": 149,
+      "ħ": 150,
+      "Ĩ": 151,
+      "ĩ": 152,
+      "Ī": 153,
+      "ī": 154,
+      "Ĭ": 155,
+      "ĭ": 156,
+      "Į": 157,
+      "į": 158,
+      "İ": 159,
+      "ı": 160,
+      "IJ": 161,
+      "ij": 162,
+      "Ĵ": 163,
+      "ĵ": 164,
+      "Ķ": 165,
+      "ķ": 166,
+      "ĸ": 167,
+      "Ĺ": 168,
+      "ĺ": 169,
+      "Ļ": 170,
+      "ļ": 171,
+      "Ľ": 172,
+      "ľ": 173,
+      "Ŀ": 174,
+      "ŀ": 175,
+      "Ł": 176,
+      "ł": 177,
+      "Ń": 178,
+      "ı": 179,
+      "Ġb": 180,
+      "ar": 181,
+      "ü": 182,
+      "er": 183,
+      "ÅŁ": 184,
+      "an": 185,
+      "in": 186,
+      "en": 187,
+      "Ġk": 188,
+      "ç": 189,
+      "Ġs": 190,
+      "Ġd": 191,
+      "ir": 192,
+      "ÄŁ": 193,
+      "Ġy": 194,
+      "ın": 195,
+      "Ġg": 196,
+      "Ġo": 197,
+      "il": 198,
+      "ma": 199
+    },
+    "merges": [
+      [
+        "Ä",
+        "±"
+      ],
+      [
+        "Ġ",
+        "b"
+      ],
+      [
+        "a",
+        "r"
+      ],
+      [
+        "Ã",
+        "¼"
+      ],
+      [
+        "e",
+        "r"
+      ],
+      [
+        "Å",
+        "Ł"
+      ],
+      [
+        "a",
+        "n"
+      ],
+      [
+        "i",
+        "n"
+      ],
+      [
+        "e",
+        "n"
+      ],
+      [
+        "Ġ",
+        "k"
+      ],
+      [
+        "Ã",
+        "§"
+      ],
+      [
+        "Ġ",
+        "s"
+      ],
+      [
+        "Ġ",
+        "d"
+      ],
+      [
+        "i",
+        "r"
+      ],
+      [
+        "Ä",
+        "Ł"
+      ],
+      [
+        "Ġ",
+        "y"
+      ],
+      [
+        "ı",
+        "n"
+      ],
+      [
+        "Ġ",
+        "g"
+      ],
+      [
+        "Ġ",
+        "o"
+      ],
+      [
+        "i",
+        "l"
+      ],
+      [
+        "m",
+        "a"
+      ]
+    ]
+  }
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 2.387294650368e+17,
+    "train_loss": 0.35219172576562363,
+    "train_runtime": 24797.7753,
+    "train_samples": 91365,
+    "train_samples_per_second": 36.844,
+    "train_steps_per_second": 1.152
+}

trainer_state.json

@@ -0,0 +1,329 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 28560,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.35014005602240894,
+      "grad_norm": 13124.1923828125,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 0.6555,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7002801120448179,
+      "grad_norm": 9263.9365234375,
+      "learning_rate": 0.0005782510885341073,
+      "loss": 0.485,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4941692129868049,
+      "eval_loss": 1.695952296257019,
+      "eval_runtime": 15.3882,
+      "eval_samples_per_second": 44.45,
+      "eval_steps_per_second": 1.43,
+      "step": 2856
+    },
+    {
+      "epoch": 1.050420168067227,
+      "grad_norm": 8019.04931640625,
+      "learning_rate": 0.0005564804063860668,
+      "loss": 0.4275,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4005602240896358,
+      "grad_norm": 7421.74853515625,
+      "learning_rate": 0.0005347097242380261,
+      "loss": 0.4009,
+      "step": 4000
+    },
+    {
+      "epoch": 1.7507002801120448,
+      "grad_norm": 6680.69140625,
+      "learning_rate": 0.0005129390420899855,
+      "loss": 0.3846,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5348302262505579,
+      "eval_loss": 1.5430383682250977,
+      "eval_runtime": 10.493,
+      "eval_samples_per_second": 65.186,
+      "eval_steps_per_second": 2.097,
+      "step": 5712
+    },
+    {
+      "epoch": 2.100840336134454,
+      "grad_norm": 6414.6875,
+      "learning_rate": 0.0004911683599419448,
+      "loss": 0.3745,
+      "step": 6000
+    },
+    {
+      "epoch": 2.450980392156863,
+      "grad_norm": 6100.486328125,
+      "learning_rate": 0.00046939767779390415,
+      "loss": 0.3654,
+      "step": 7000
+    },
+    {
+      "epoch": 2.8011204481792715,
+      "grad_norm": 6541.07275390625,
+      "learning_rate": 0.00044762699564586357,
+      "loss": 0.3593,
+      "step": 8000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5546629129902382,
+      "eval_loss": 1.4664632081985474,
+      "eval_runtime": 10.4709,
+      "eval_samples_per_second": 65.324,
+      "eval_steps_per_second": 2.101,
+      "step": 8568
+    },
+    {
+      "epoch": 3.1512605042016806,
+      "grad_norm": 6968.591796875,
+      "learning_rate": 0.00042585631349782287,
+      "loss": 0.3535,
+      "step": 9000
+    },
+    {
+      "epoch": 3.5014005602240896,
+      "grad_norm": 6259.02685546875,
+      "learning_rate": 0.00040408563134978223,
+      "loss": 0.3476,
+      "step": 10000
+    },
+    {
+      "epoch": 3.8515406162464987,
+      "grad_norm": 5834.7548828125,
+      "learning_rate": 0.0003823149492017416,
+      "loss": 0.3438,
+      "step": 11000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5707419233014042,
+      "eval_loss": 1.4174976348876953,
+      "eval_runtime": 15.0661,
+      "eval_samples_per_second": 45.4,
+      "eval_steps_per_second": 1.46,
+      "step": 11424
+    },
+    {
+      "epoch": 4.201680672268908,
+      "grad_norm": 5648.84814453125,
+      "learning_rate": 0.000360544267053701,
+      "loss": 0.3403,
+      "step": 12000
+    },
+    {
+      "epoch": 4.551820728291316,
+      "grad_norm": 6200.31298828125,
+      "learning_rate": 0.00033877358490566037,
+      "loss": 0.3361,
+      "step": 13000
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 5265.44775390625,
+      "learning_rate": 0.00031700290275761973,
+      "loss": 0.3341,
+      "step": 14000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5773938270333367,
+      "eval_loss": 1.3927898406982422,
+      "eval_runtime": 15.378,
+      "eval_samples_per_second": 44.479,
+      "eval_steps_per_second": 1.431,
+      "step": 14280
+    },
+    {
+      "epoch": 5.2521008403361344,
+      "grad_norm": 5555.48486328125,
+      "learning_rate": 0.0002952322206095791,
+      "loss": 0.3302,
+      "step": 15000
+    },
+    {
+      "epoch": 5.602240896358543,
+      "grad_norm": 5694.87890625,
+      "learning_rate": 0.00027346153846153845,
+      "loss": 0.3271,
+      "step": 16000
+    },
+    {
+      "epoch": 5.9523809523809526,
+      "grad_norm": 5353.783203125,
+      "learning_rate": 0.0002516908563134978,
+      "loss": 0.3252,
+      "step": 17000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5860970920451815,
+      "eval_loss": 1.3625472784042358,
+      "eval_runtime": 15.2445,
+      "eval_samples_per_second": 44.869,
+      "eval_steps_per_second": 1.443,
+      "step": 17136
+    },
+    {
+      "epoch": 6.302521008403361,
+      "grad_norm": 5537.6591796875,
+      "learning_rate": 0.00022992017416545717,
+      "loss": 0.3209,
+      "step": 18000
+    },
+    {
+      "epoch": 6.652661064425771,
+      "grad_norm": 5149.9501953125,
+      "learning_rate": 0.00020814949201741653,
+      "loss": 0.3192,
+      "step": 19000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5942910930293771,
+      "eval_loss": 1.334036111831665,
+      "eval_runtime": 15.3529,
+      "eval_samples_per_second": 44.552,
+      "eval_steps_per_second": 1.433,
+      "step": 19992
+    },
+    {
+      "epoch": 7.002801120448179,
+      "grad_norm": 6287.0166015625,
+      "learning_rate": 0.0001863788098693759,
+      "loss": 0.3174,
+      "step": 20000
+    },
+    {
+      "epoch": 7.352941176470588,
+      "grad_norm": 5925.09228515625,
+      "learning_rate": 0.00016460812772133528,
+      "loss": 0.3133,
+      "step": 21000
+    },
+    {
+      "epoch": 7.703081232492997,
+      "grad_norm": 5756.06787109375,
+      "learning_rate": 0.0001428374455732946,
+      "loss": 0.3112,
+      "step": 22000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5998243325207997,
+      "eval_loss": 1.3174924850463867,
+      "eval_runtime": 15.3544,
+      "eval_samples_per_second": 44.547,
+      "eval_steps_per_second": 1.433,
+      "step": 22848
+    },
+    {
+      "epoch": 8.053221288515406,
+      "grad_norm": 5942.7607421875,
+      "learning_rate": 0.00012106676342525399,
+      "loss": 0.3097,
+      "step": 23000
+    },
+    {
+      "epoch": 8.403361344537815,
+      "grad_norm": 6329.1103515625,
+      "learning_rate": 9.929608127721335e-05,
+      "loss": 0.306,
+      "step": 24000
+    },
+    {
+      "epoch": 8.753501400560225,
+      "grad_norm": 6101.3408203125,
+      "learning_rate": 7.75253991291727e-05,
+      "loss": 0.3038,
+      "step": 25000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6055206509424246,
+      "eval_loss": 1.3009241819381714,
+      "eval_runtime": 10.6137,
+      "eval_samples_per_second": 64.445,
+      "eval_steps_per_second": 2.073,
+      "step": 25704
+    },
+    {
+      "epoch": 9.103641456582633,
+      "grad_norm": 6770.501953125,
+      "learning_rate": 5.5754716981132066e-05,
+      "loss": 0.3025,
+      "step": 26000
+    },
+    {
+      "epoch": 9.453781512605042,
+      "grad_norm": 6355.373046875,
+      "learning_rate": 3.3984034833091434e-05,
+      "loss": 0.2991,
+      "step": 27000
+    },
+    {
+      "epoch": 9.803921568627452,
+      "grad_norm": 5946.85693359375,
+      "learning_rate": 1.2213352685050797e-05,
+      "loss": 0.298,
+      "step": 28000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.6093458532175187,
+      "eval_loss": 1.288467288017273,
+      "eval_runtime": 10.3972,
+      "eval_samples_per_second": 65.787,
+      "eval_steps_per_second": 2.116,
+      "step": 28560
+    },
+    {
+      "epoch": 10.0,
+      "step": 28560,
+      "total_flos": 2.387294650368e+17,
+      "train_loss": 0.35219172576562363,
+      "train_runtime": 24797.7753,
+      "train_samples_per_second": 36.844,
+      "train_steps_per_second": 1.152
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 28560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.387294650368e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c884b19a142582f64869e1e21ef209ee824bb24763cb5789f80ee547c02645
+size 5304

vocab.json

@@ -0,0 +1 @@
+{"<pad>":0,"<|endoftext|>":1,"<s>":2,"<unk>":3,"!":4,"\"":5,"#":6,"$":7,"%":8,"&":9,"'":10,"(":11,")":12,"*":13,"+":14,",":15,"-":16,".":17,"/":18,"0":19,"1":20,"2":21,"3":22,"4":23,"5":24,"6":25,"7":26,"8":27,"9":28,":":29,";":30,"<":31,"=":32,">":33,"?":34,"@":35,"[":36,"\\":37,"]":38,"^":39,"_":40,"`":41,"a":42,"b":43,"c":44,"d":45,"e":46,"f":47,"g":48,"h":49,"i":50,"j":51,"k":52,"l":53,"m":54,"n":55,"o":56,"p":57,"q":58,"r":59,"s":60,"t":61,"u":62,"v":63,"w":64,"x":65,"y":66,"z":67,"{":68,"|":69,"}":70,"~":71,"¡":72,"¢":73,"£":74,"¤":75,"¥":76,"¦":77,"§":78,"¨":79,"©":80,"ª":81,"«":82,"¬":83,"®":84,"¯":85,"°":86,"±":87,"²":88,"³":89,"´":90,"µ":91,"¶":92,"·":93,"¸":94,"¹":95,"º":96,"»":97,"¼":98,"½":99,"¾":100,"¿":101,"Â":102,"Ã":103,"Ä":104,"Å":105,"Æ":106,"Ç":107,"È":108,"É":109,"Ê":110,"Ë":111,"Ì":112,"Î":113,"Ï":114,"Ð":115,"Ñ":116,"Ò":117,"Ó":118,"Õ":119,"Ö":120,"×":121,"Ø":122,"Ù":123,"Û":124,"Þ":125,"à":126,"á":127,"â":128,"ã":129,"ä":130,"å":131,"æ":132,"ç":133,"è":134,"é":135,"ê":136,"ë":137,"ì":138,"í":139,"î":140,"ï":141,"ð":142,"Ċ":143,"Ġ":144,"Ģ":145,"ģ":146,"Ĥ":147,"ĥ":148,"Ħ":149,"ħ":150,"Ĩ":151,"ĩ":152,"Ī":153,"ī":154,"Ĭ":155,"ĭ":156,"Į":157,"į":158,"İ":159,"ı":160,"IJ":161,"ij":162,"Ĵ":163,"ĵ":164,"Ķ":165,"ķ":166,"ĸ":167,"Ĺ":168,"ĺ":169,"Ļ":170,"ļ":171,"Ľ":172,"ľ":173,"Ŀ":174,"ŀ":175,"Ł":176,"ł":177,"Ń":178,"ı":179,"Ġb":180,"ar":181,"ü":182,"er":183,"ÅŁ":184,"an":185,"in":186,"en":187,"Ġk":188,"ç":189,"Ġs":190,"Ġd":191,"ir":192,"ÄŁ":193,"Ġy":194,"ın":195,"Ġg":196,"Ġo":197,"il":198,"ma":199}