Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: DE_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. -->
+
+# DE_200_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3525
+- Accuracy: 0.5875
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.5107        | 1.0   | 2898  | 1.8788          | 0.4432   |
+| 0.4165        | 2.0   | 5796  | 1.6591          | 0.5004   |
+| 0.3794        | 3.0   | 8694  | 1.5665          | 0.5259   |
+| 0.3596        | 4.0   | 11592 | 1.5097          | 0.5398   |
+| 0.3466        | 5.0   | 14490 | 1.4665          | 0.5539   |
+| 0.3361        | 6.0   | 17388 | 1.4283          | 0.5635   |
+| 0.3272        | 7.0   | 20286 | 1.4044          | 0.5709   |
+| 0.3196        | 8.0   | 23184 | 1.3859          | 0.5763   |
+| 0.3108        | 9.0   | 26082 | 1.3630          | 0.5840   |
+| 0.3064        | 10.0  | 28980 | 1.3525          | 0.5875   |
+
+
+### 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": 0.5875368753103367,
+    "eval_loss": 1.3525028228759766,
+    "eval_runtime": 10.2205,
+    "eval_samples": 670,
+    "eval_samples_per_second": 65.555,
+    "eval_steps_per_second": 2.055,
+    "perplexity": 3.8670920753360716,
+    "total_flos": 2.422569074688e+17,
+    "train_loss": 0.3669595490660315,
+    "train_runtime": 25080.1118,
+    "train_samples": 92715,
+    "train_samples_per_second": 36.968,
+    "train_steps_per_second": 1.155
+}

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": 0.5875368753103367,
+    "eval_loss": 1.3525028228759766,
+    "eval_runtime": 10.2205,
+    "eval_samples": 670,
+    "eval_samples_per_second": 65.555,
+    "eval_steps_per_second": 2.055,
+    "perplexity": 3.8670920753360716
+}

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
+e n
+e r
+c h
+Ġ d
+Ġ s
+i n
+i e
+Ġ w
+i ch
+u n
+Ġ a
+s t
+Ġ m
+e in
+Ġ h
+Ġ g
+e s
+a s
+Ġ b
+Ġ n
+Ġ i

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8c85467bb0dad27eaff07cfb58c40f4b4bc6507fe43c867951d6187ee2045d4
+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,
+      "ª": 80,
+      "«": 81,
+      "¬": 82,
+      "®": 83,
+      "¯": 84,
+      "°": 85,
+      "±": 86,
+      "²": 87,
+      "³": 88,
+      "´": 89,
+      "µ": 90,
+      "¶": 91,
+      "·": 92,
+      "¸": 93,
+      "¹": 94,
+      "º": 95,
+      "»": 96,
+      "¼": 97,
+      "½": 98,
+      "¾": 99,
+      "¿": 100,
+      "Â": 101,
+      "Ã": 102,
+      "Ä": 103,
+      "Å": 104,
+      "Æ": 105,
+      "Ç": 106,
+      "È": 107,
+      "É": 108,
+      "Ê": 109,
+      "Ë": 110,
+      "Ì": 111,
+      "Î": 112,
+      "Ï": 113,
+      "Ð": 114,
+      "Ñ": 115,
+      "Ò": 116,
+      "Ó": 117,
+      "Õ": 118,
+      "Ö": 119,
+      "×": 120,
+      "Ø": 121,
+      "Ù": 122,
+      "Ú": 123,
+      "Û": 124,
+      "à": 125,
+      "á": 126,
+      "â": 127,
+      "ã": 128,
+      "ä": 129,
+      "å": 130,
+      "æ": 131,
+      "ç": 132,
+      "è": 133,
+      "é": 134,
+      "ê": 135,
+      "ë": 136,
+      "ì": 137,
+      "í": 138,
+      "î": 139,
+      "ï": 140,
+      "ð": 141,
+      "Ċ": 142,
+      "Ġ": 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,
+      "en": 179,
+      "er": 180,
+      "ch": 181,
+      "Ġd": 182,
+      "Ġs": 183,
+      "in": 184,
+      "ie": 185,
+      "Ġw": 186,
+      "ich": 187,
+      "un": 188,
+      "Ġa": 189,
+      "st": 190,
+      "Ġm": 191,
+      "ein": 192,
+      "Ġh": 193,
+      "Ġg": 194,
+      "es": 195,
+      "as": 196,
+      "Ġb": 197,
+      "Ġn": 198,
+      "Ġi": 199
+    },
+    "merges": [
+      [
+        "e",
+        "n"
+      ],
+      [
+        "e",
+        "r"
+      ],
+      [
+        "c",
+        "h"
+      ],
+      [
+        "Ġ",
+        "d"
+      ],
+      [
+        "Ġ",
+        "s"
+      ],
+      [
+        "i",
+        "n"
+      ],
+      [
+        "i",
+        "e"
+      ],
+      [
+        "Ġ",
+        "w"
+      ],
+      [
+        "i",
+        "ch"
+      ],
+      [
+        "u",
+        "n"
+      ],
+      [
+        "Ġ",
+        "a"
+      ],
+      [
+        "s",
+        "t"
+      ],
+      [
+        "Ġ",
+        "m"
+      ],
+      [
+        "e",
+        "in"
+      ],
+      [
+        "Ġ",
+        "h"
+      ],
+      [
+        "Ġ",
+        "g"
+      ],
+      [
+        "e",
+        "s"
+      ],
+      [
+        "a",
+        "s"
+      ],
+      [
+        "Ġ",
+        "b"
+      ],
+      [
+        "Ġ",
+        "n"
+      ],
+      [
+        "Ġ",
+        "i"
+      ]
+    ]
+  }
+}

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": 2.422569074688e+17,
+    "train_loss": 0.3669595490660315,
+    "train_runtime": 25080.1118,
+    "train_samples": 92715,
+    "train_samples_per_second": 36.968,
+    "train_steps_per_second": 1.155
+}

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": 28980,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3450655624568668,
+      "grad_norm": 12397.57421875,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 0.6679,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6901311249137336,
+      "grad_norm": 10429.0537109375,
+      "learning_rate": 0.000578577555396712,
+      "loss": 0.5107,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.44315798697315767,
+      "eval_loss": 1.8788169622421265,
+      "eval_runtime": 10.9096,
+      "eval_samples_per_second": 61.414,
+      "eval_steps_per_second": 1.925,
+      "step": 2898
+    },
+    {
+      "epoch": 1.0351966873706004,
+      "grad_norm": 9541.001953125,
+      "learning_rate": 0.000557133666904932,
+      "loss": 0.465,
+      "step": 3000
+    },
+    {
+      "epoch": 1.3802622498274673,
+      "grad_norm": 8465.48828125,
+      "learning_rate": 0.0005356897784131522,
+      "loss": 0.4374,
+      "step": 4000
+    },
+    {
+      "epoch": 1.725327812284334,
+      "grad_norm": 8387.8720703125,
+      "learning_rate": 0.0005142458899213724,
+      "loss": 0.4165,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5003855477991647,
+      "eval_loss": 1.65910804271698,
+      "eval_runtime": 10.4073,
+      "eval_samples_per_second": 64.378,
+      "eval_steps_per_second": 2.018,
+      "step": 5796
+    },
+    {
+      "epoch": 2.070393374741201,
+      "grad_norm": 7152.541015625,
+      "learning_rate": 0.0004928020014295925,
+      "loss": 0.4007,
+      "step": 6000
+    },
+    {
+      "epoch": 2.4154589371980677,
+      "grad_norm": 6726.79345703125,
+      "learning_rate": 0.0004713581129378127,
+      "loss": 0.3885,
+      "step": 7000
+    },
+    {
+      "epoch": 2.7605244996549345,
+      "grad_norm": 6598.8408203125,
+      "learning_rate": 0.0004499142244460328,
+      "loss": 0.3794,
+      "step": 8000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5258784356105968,
+      "eval_loss": 1.5665066242218018,
+      "eval_runtime": 10.3868,
+      "eval_samples_per_second": 64.505,
+      "eval_steps_per_second": 2.022,
+      "step": 8694
+    },
+    {
+      "epoch": 3.1055900621118013,
+      "grad_norm": 6030.8671875,
+      "learning_rate": 0.000428470335954253,
+      "loss": 0.3713,
+      "step": 9000
+    },
+    {
+      "epoch": 3.450655624568668,
+      "grad_norm": 6469.8154296875,
+      "learning_rate": 0.00040702644746247316,
+      "loss": 0.3646,
+      "step": 10000
+    },
+    {
+      "epoch": 3.795721187025535,
+      "grad_norm": 5848.75634765625,
+      "learning_rate": 0.00038558255897069334,
+      "loss": 0.3596,
+      "step": 11000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5398457808803342,
+      "eval_loss": 1.5097391605377197,
+      "eval_runtime": 10.3887,
+      "eval_samples_per_second": 64.493,
+      "eval_steps_per_second": 2.021,
+      "step": 11592
+    },
+    {
+      "epoch": 4.140786749482402,
+      "grad_norm": 5841.65283203125,
+      "learning_rate": 0.00036413867047891345,
+      "loss": 0.3547,
+      "step": 12000
+    },
+    {
+      "epoch": 4.485852311939269,
+      "grad_norm": 5639.96435546875,
+      "learning_rate": 0.0003426947819871336,
+      "loss": 0.3496,
+      "step": 13000
+    },
+    {
+      "epoch": 4.830917874396135,
+      "grad_norm": 6607.05859375,
+      "learning_rate": 0.0003212508934953538,
+      "loss": 0.3466,
+      "step": 14000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5539036714665421,
+      "eval_loss": 1.4664909839630127,
+      "eval_runtime": 10.4004,
+      "eval_samples_per_second": 64.421,
+      "eval_steps_per_second": 2.019,
+      "step": 14490
+    },
+    {
+      "epoch": 5.175983436853002,
+      "grad_norm": 6289.2412109375,
+      "learning_rate": 0.00029980700500357397,
+      "loss": 0.3423,
+      "step": 15000
+    },
+    {
+      "epoch": 5.521048999309869,
+      "grad_norm": 6008.00146484375,
+      "learning_rate": 0.00027836311651179414,
+      "loss": 0.3385,
+      "step": 16000
+    },
+    {
+      "epoch": 5.866114561766736,
+      "grad_norm": 6221.515625,
+      "learning_rate": 0.0002569192280200143,
+      "loss": 0.3361,
+      "step": 17000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5635160790957152,
+      "eval_loss": 1.428313970565796,
+      "eval_runtime": 10.5943,
+      "eval_samples_per_second": 63.242,
+      "eval_steps_per_second": 1.982,
+      "step": 17388
+    },
+    {
+      "epoch": 6.211180124223603,
+      "grad_norm": 6032.64794921875,
+      "learning_rate": 0.00023547533952823443,
+      "loss": 0.3323,
+      "step": 18000
+    },
+    {
+      "epoch": 6.5562456866804695,
+      "grad_norm": 5749.06982421875,
+      "learning_rate": 0.00021403145103645457,
+      "loss": 0.3292,
+      "step": 19000
+    },
+    {
+      "epoch": 6.901311249137336,
+      "grad_norm": 6140.248046875,
+      "learning_rate": 0.00019258756254467475,
+      "loss": 0.3272,
+      "step": 20000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5708852995297485,
+      "eval_loss": 1.4043962955474854,
+      "eval_runtime": 10.5807,
+      "eval_samples_per_second": 63.323,
+      "eval_steps_per_second": 1.985,
+      "step": 20286
+    },
+    {
+      "epoch": 7.246376811594203,
+      "grad_norm": 6093.1396484375,
+      "learning_rate": 0.00017114367405289492,
+      "loss": 0.3235,
+      "step": 21000
+    },
+    {
+      "epoch": 7.59144237405107,
+      "grad_norm": 6653.38916015625,
+      "learning_rate": 0.00014969978556111506,
+      "loss": 0.3203,
+      "step": 22000
+    },
+    {
+      "epoch": 7.936507936507937,
+      "grad_norm": 6364.10693359375,
+      "learning_rate": 0.00012825589706933524,
+      "loss": 0.3196,
+      "step": 23000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5763384642346,
+      "eval_loss": 1.38591468334198,
+      "eval_runtime": 10.3897,
+      "eval_samples_per_second": 64.487,
+      "eval_steps_per_second": 2.021,
+      "step": 23184
+    },
+    {
+      "epoch": 8.281573498964804,
+      "grad_norm": 6245.546875,
+      "learning_rate": 0.00010681200857755538,
+      "loss": 0.3153,
+      "step": 24000
+    },
+    {
+      "epoch": 8.62663906142167,
+      "grad_norm": 6126.087890625,
+      "learning_rate": 8.536812008577554e-05,
+      "loss": 0.3135,
+      "step": 25000
+    },
+    {
+      "epoch": 8.971704623878537,
+      "grad_norm": 6089.27685546875,
+      "learning_rate": 6.392423159399571e-05,
+      "loss": 0.3108,
+      "step": 26000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5839851622513654,
+      "eval_loss": 1.3629769086837769,
+      "eval_runtime": 10.4049,
+      "eval_samples_per_second": 64.393,
+      "eval_steps_per_second": 2.018,
+      "step": 26082
+    },
+    {
+      "epoch": 9.316770186335404,
+      "grad_norm": 6497.2294921875,
+      "learning_rate": 4.248034310221586e-05,
+      "loss": 0.3076,
+      "step": 27000
+    },
+    {
+      "epoch": 9.66183574879227,
+      "grad_norm": 6822.0712890625,
+      "learning_rate": 2.1036454610436023e-05,
+      "loss": 0.3064,
+      "step": 28000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.5875368753103367,
+      "eval_loss": 1.3525028228759766,
+      "eval_runtime": 10.3916,
+      "eval_samples_per_second": 64.475,
+      "eval_steps_per_second": 2.021,
+      "step": 28980
+    },
+    {
+      "epoch": 10.0,
+      "step": 28980,
+      "total_flos": 2.422569074688e+17,
+      "train_loss": 0.3669595490660315,
+      "train_runtime": 25080.1118,
+      "train_samples_per_second": 36.968,
+      "train_steps_per_second": 1.155
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 28980,
+  "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": 2.422569074688e+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 sha256:0caaf783f2cf756e0abf9da484156e9b702cdbb943bd769929a580b3e13ceef5
+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,"ª":80,"«":81,"¬":82,"®":83,"¯":84,"°":85,"±":86,"²":87,"³":88,"´":89,"µ":90,"¶":91,"·":92,"¸":93,"¹":94,"º":95,"»":96,"¼":97,"½":98,"¾":99,"¿":100,"Â":101,"Ã":102,"Ä":103,"Å":104,"Æ":105,"Ç":106,"È":107,"É":108,"Ê":109,"Ë":110,"Ì":111,"Î":112,"Ï":113,"Ð":114,"Ñ":115,"Ò":116,"Ó":117,"Õ":118,"Ö":119,"×":120,"Ø":121,"Ù":122,"Ú":123,"Û":124,"à":125,"á":126,"â":127,"ã":128,"ä":129,"å":130,"æ":131,"ç":132,"è":133,"é":134,"ê":135,"ë":136,"ì":137,"í":138,"î":139,"ï":140,"ð":141,"Ċ":142,"Ġ":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,"en":179,"er":180,"ch":181,"Ġd":182,"Ġs":183,"in":184,"ie":185,"Ġw":186,"ich":187,"un":188,"Ġa":189,"st":190,"Ġm":191,"ein":192,"Ġh":193,"Ġg":194,"es":195,"as":196,"Ġb":197,"Ġn":198,"Ġi":199}