Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: EN_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. -->
+
+# EN_200_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3528
+- Accuracy: 0.5924
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.4984        | 1.0   | 2708  | 1.8213          | 0.4633   |
+| 0.408         | 2.0   | 5416  | 1.6398          | 0.5107   |
+| 0.3764        | 3.0   | 8124  | 1.5575          | 0.5334   |
+| 0.3628        | 4.0   | 10832 | 1.5048          | 0.5470   |
+| 0.3505        | 5.0   | 13540 | 1.4624          | 0.5583   |
+| 0.3399        | 6.0   | 16248 | 1.4278          | 0.5712   |
+| 0.3334        | 7.0   | 18956 | 1.4061          | 0.5766   |
+| 0.3248        | 8.0   | 21664 | 1.3806          | 0.5834   |
+| 0.3178        | 9.0   | 24372 | 1.3640          | 0.5893   |
+| 0.311         | 10.0  | 27080 | 1.3528          | 0.5924   |
+
+
+### 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": 0.5924084271233505,
+    "eval_loss": 1.3527692556381226,
+    "eval_runtime": 9.3845,
+    "eval_samples": 623,
+    "eval_samples_per_second": 66.386,
+    "eval_steps_per_second": 2.131,
+    "perplexity": 3.8681225326268716,
+    "total_flos": 2.2639125528576e+17,
+    "train_loss": 0.36916396628454484,
+    "train_runtime": 23461.5127,
+    "train_samples": 86643,
+    "train_samples_per_second": 36.93,
+    "train_steps_per_second": 1.154
+}

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": 0.5924084271233505,
+    "eval_loss": 1.3527692556381226,
+    "eval_runtime": 9.3845,
+    "eval_samples": 623,
+    "eval_samples_per_second": 66.386,
+    "eval_steps_per_second": 2.131,
+    "perplexity": 3.8681225326268716
+}

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 +1,23 @@
+#version: 0.2
+Ġ t
+Ġ a
+Ġt h
+Ġ i
+Ġ w
+o u
+Ġ s
+e r
+Ġth e
+i n
+Ġ h
+Ġ o
+r e
+a t
+Ġ y
+Ġ m
+Ġ c
+Ġ b
+n d
+Ġy ou
+Ġ d
+Ġ f

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6565f163a8dfdc63cd58ffef5c37f0fbed1ddb6e53e947db85f28ec45735a5a5
+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 +1,402 @@
+{
+  "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,
+      "Ì": 111,
+      "Î": 112,
+      "Ï": 113,
+      "Ð": 114,
+      "Ñ": 115,
+      "Ò": 116,
+      "Ó": 117,
+      "Ö": 118,
+      "×": 119,
+      "Ø": 120,
+      "Ù": 121,
+      "Ú": 122,
+      "Û": 123,
+      "Þ": 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,
+      "Ģ": 144,
+      "ģ": 145,
+      "Ĥ": 146,
+      "ĥ": 147,
+      "Ħ": 148,
+      "ħ": 149,
+      "Ĩ": 150,
+      "ĩ": 151,
+      "Ī": 152,
+      "ī": 153,
+      "Ĭ": 154,
+      "ĭ": 155,
+      "Į": 156,
+      "į": 157,
+      "İ": 158,
+      "ı": 159,
+      "IJ": 160,
+      "ij": 161,
+      "Ĵ": 162,
+      "ĵ": 163,
+      "Ķ": 164,
+      "ķ": 165,
+      "ĸ": 166,
+      "Ĺ": 167,
+      "ĺ": 168,
+      "Ļ": 169,
+      "ļ": 170,
+      "Ľ": 171,
+      "ľ": 172,
+      "Ŀ": 173,
+      "ŀ": 174,
+      "Ł": 175,
+      "ł": 176,
+      "Ń": 177,
+      "Ġt": 178,
+      "Ġa": 179,
+      "Ġth": 180,
+      "Ġi": 181,
+      "Ġw": 182,
+      "ou": 183,
+      "Ġs": 184,
+      "er": 185,
+      "Ġthe": 186,
+      "in": 187,
+      "Ġh": 188,
+      "Ġo": 189,
+      "re": 190,
+      "at": 191,
+      "Ġy": 192,
+      "Ġm": 193,
+      "Ġc": 194,
+      "Ġb": 195,
+      "nd": 196,
+      "Ġyou": 197,
+      "Ġd": 198,
+      "Ġf": 199
+    },
+    "merges": [
+      [
+        "Ġ",
+        "t"
+      ],
+      [
+        "Ġ",
+        "a"
+      ],
+      [
+        "Ġt",
+        "h"
+      ],
+      [
+        "Ġ",
+        "i"
+      ],
+      [
+        "Ġ",
+        "w"
+      ],
+      [
+        "o",
+        "u"
+      ],
+      [
+        "Ġ",
+        "s"
+      ],
+      [
+        "e",
+        "r"
+      ],
+      [
+        "Ġth",
+        "e"
+      ],
+      [
+        "i",
+        "n"
+      ],
+      [
+        "Ġ",
+        "h"
+      ],
+      [
+        "Ġ",
+        "o"
+      ],
+      [
+        "r",
+        "e"
+      ],
+      [
+        "a",
+        "t"
+      ],
+      [
+        "Ġ",
+        "y"
+      ],
+      [
+        "Ġ",
+        "m"
+      ],
+      [
+        "Ġ",
+        "c"
+      ],
+      [
+        "Ġ",
+        "b"
+      ],
+      [
+        "n",
+        "d"
+      ],
+      [
+        "Ġy",
+        "ou"
+      ],
+      [
+        "Ġ",
+        "d"
+      ],
+      [
+        "Ġ",
+        "f"
+      ]
+    ]
+  }
+}

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": 2.2639125528576e+17,
+    "train_loss": 0.36916396628454484,
+    "train_runtime": 23461.5127,
+    "train_samples": 86643,
+    "train_samples_per_second": 36.93,
+    "train_steps_per_second": 1.154
+}

trainer_state.json

@@ -0,0 +1,322 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 27080,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.36927621861152143,
+      "grad_norm": 13247.388671875,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 0.6625,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7385524372230429,
+      "grad_norm": 9940.6201171875,
+      "learning_rate": 0.0005770168711656441,
+      "loss": 0.4984,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.46332530241587166,
+      "eval_loss": 1.8212859630584717,
+      "eval_runtime": 10.2423,
+      "eval_samples_per_second": 60.826,
+      "eval_steps_per_second": 1.953,
+      "step": 2708
+    },
+    {
+      "epoch": 1.1078286558345642,
+      "grad_norm": 8275.166015625,
+      "learning_rate": 0.000554010736196319,
+      "loss": 0.4532,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4771048744460857,
+      "grad_norm": 7695.97265625,
+      "learning_rate": 0.0005310046012269938,
+      "loss": 0.4253,
+      "step": 4000
+    },
+    {
+      "epoch": 1.846381093057607,
+      "grad_norm": 6635.02685546875,
+      "learning_rate": 0.0005079984662576687,
+      "loss": 0.408,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5106941037150584,
+      "eval_loss": 1.6397608518600464,
+      "eval_runtime": 9.7196,
+      "eval_samples_per_second": 64.097,
+      "eval_steps_per_second": 2.058,
+      "step": 5416
+    },
+    {
+      "epoch": 2.2156573116691285,
+      "grad_norm": 7749.61181640625,
+      "learning_rate": 0.00048499233128834355,
+      "loss": 0.3934,
+      "step": 6000
+    },
+    {
+      "epoch": 2.58493353028065,
+      "grad_norm": 6143.23388671875,
+      "learning_rate": 0.0004619861963190184,
+      "loss": 0.3836,
+      "step": 7000
+    },
+    {
+      "epoch": 2.9542097488921715,
+      "grad_norm": 6868.88916015625,
+      "learning_rate": 0.00043898006134969323,
+      "loss": 0.3764,
+      "step": 8000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5333796131966716,
+      "eval_loss": 1.5575107336044312,
+      "eval_runtime": 9.7301,
+      "eval_samples_per_second": 64.028,
+      "eval_steps_per_second": 2.055,
+      "step": 8124
+    },
+    {
+      "epoch": 3.323485967503693,
+      "grad_norm": 6560.751953125,
+      "learning_rate": 0.00041597392638036807,
+      "loss": 0.3684,
+      "step": 9000
+    },
+    {
+      "epoch": 3.692762186115214,
+      "grad_norm": 6382.58203125,
+      "learning_rate": 0.0003929677914110429,
+      "loss": 0.3628,
+      "step": 10000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.547043690494514,
+      "eval_loss": 1.5047563314437866,
+      "eval_runtime": 9.717,
+      "eval_samples_per_second": 64.115,
+      "eval_steps_per_second": 2.058,
+      "step": 10832
+    },
+    {
+      "epoch": 4.062038404726736,
+      "grad_norm": 5827.2607421875,
+      "learning_rate": 0.0003699616564417178,
+      "loss": 0.3585,
+      "step": 11000
+    },
+    {
+      "epoch": 4.431314623338257,
+      "grad_norm": 6025.1650390625,
+      "learning_rate": 0.00034695552147239264,
+      "loss": 0.3539,
+      "step": 12000
+    },
+    {
+      "epoch": 4.800590841949779,
+      "grad_norm": 5609.11474609375,
+      "learning_rate": 0.0003239493865030675,
+      "loss": 0.3505,
+      "step": 13000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5583267630586173,
+      "eval_loss": 1.4623572826385498,
+      "eval_runtime": 9.7131,
+      "eval_samples_per_second": 64.14,
+      "eval_steps_per_second": 2.059,
+      "step": 13540
+    },
+    {
+      "epoch": 5.1698670605613,
+      "grad_norm": 5670.53466796875,
+      "learning_rate": 0.0003009432515337423,
+      "loss": 0.3465,
+      "step": 14000
+    },
+    {
+      "epoch": 5.539143279172821,
+      "grad_norm": 6664.6083984375,
+      "learning_rate": 0.00027793711656441715,
+      "loss": 0.3426,
+      "step": 15000
+    },
+    {
+      "epoch": 5.908419497784343,
+      "grad_norm": 5798.9404296875,
+      "learning_rate": 0.000254930981595092,
+      "loss": 0.3399,
+      "step": 16000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5711521487154196,
+      "eval_loss": 1.427840232849121,
+      "eval_runtime": 9.718,
+      "eval_samples_per_second": 64.108,
+      "eval_steps_per_second": 2.058,
+      "step": 16248
+    },
+    {
+      "epoch": 6.277695716395864,
+      "grad_norm": 5907.61376953125,
+      "learning_rate": 0.00023192484662576683,
+      "loss": 0.3356,
+      "step": 17000
+    },
+    {
+      "epoch": 6.646971935007386,
+      "grad_norm": 5923.216796875,
+      "learning_rate": 0.0002089187116564417,
+      "loss": 0.3334,
+      "step": 18000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5765989326313872,
+      "eval_loss": 1.406113624572754,
+      "eval_runtime": 9.7146,
+      "eval_samples_per_second": 64.13,
+      "eval_steps_per_second": 2.059,
+      "step": 18956
+    },
+    {
+      "epoch": 7.016248153618907,
+      "grad_norm": 6729.748046875,
+      "learning_rate": 0.00018591257668711654,
+      "loss": 0.3315,
+      "step": 19000
+    },
+    {
+      "epoch": 7.385524372230428,
+      "grad_norm": 6439.97607421875,
+      "learning_rate": 0.00016290644171779137,
+      "loss": 0.3267,
+      "step": 20000
+    },
+    {
+      "epoch": 7.75480059084195,
+      "grad_norm": 6263.06689453125,
+      "learning_rate": 0.00013990030674846624,
+      "loss": 0.3248,
+      "step": 21000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5833838537723848,
+      "eval_loss": 1.3805782794952393,
+      "eval_runtime": 9.8981,
+      "eval_samples_per_second": 62.941,
+      "eval_steps_per_second": 2.021,
+      "step": 21664
+    },
+    {
+      "epoch": 8.124076809453472,
+      "grad_norm": 6769.88916015625,
+      "learning_rate": 0.00011689417177914109,
+      "loss": 0.3226,
+      "step": 22000
+    },
+    {
+      "epoch": 8.493353028064993,
+      "grad_norm": 5885.490234375,
+      "learning_rate": 9.388803680981594e-05,
+      "loss": 0.3188,
+      "step": 23000
+    },
+    {
+      "epoch": 8.862629246676514,
+      "grad_norm": 6447.85498046875,
+      "learning_rate": 7.08819018404908e-05,
+      "loss": 0.3178,
+      "step": 24000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5892798245972238,
+      "eval_loss": 1.3639582395553589,
+      "eval_runtime": 9.9358,
+      "eval_samples_per_second": 62.703,
+      "eval_steps_per_second": 2.013,
+      "step": 24372
+    },
+    {
+      "epoch": 9.231905465288035,
+      "grad_norm": 6391.68896484375,
+      "learning_rate": 4.787576687116564e-05,
+      "loss": 0.3141,
+      "step": 25000
+    },
+    {
+      "epoch": 9.601181683899556,
+      "grad_norm": 6642.7880859375,
+      "learning_rate": 2.4869631901840487e-05,
+      "loss": 0.3118,
+      "step": 26000
+    },
+    {
+      "epoch": 9.970457902511079,
+      "grad_norm": 6367.48193359375,
+      "learning_rate": 1.863496932515337e-06,
+      "loss": 0.311,
+      "step": 27000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.5924084271233505,
+      "eval_loss": 1.3527692556381226,
+      "eval_runtime": 9.7249,
+      "eval_samples_per_second": 64.063,
+      "eval_steps_per_second": 2.057,
+      "step": 27080
+    },
+    {
+      "epoch": 10.0,
+      "step": 27080,
+      "total_flos": 2.2639125528576e+17,
+      "train_loss": 0.36916396628454484,
+      "train_runtime": 23461.5127,
+      "train_samples_per_second": 36.93,
+      "train_steps_per_second": 1.154
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 27080,
+  "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": 2.2639125528576e+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 sha256:4bd1e96e670eef1df35c0a586ddd686d0a45bebd21e2c5fb5c42a31a3398e261
+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,"Ì":111,"Î":112,"Ï":113,"Ð":114,"Ñ":115,"Ò":116,"Ó":117,"Ö":118,"×":119,"Ø":120,"Ù":121,"Ú":122,"Û":123,"Þ":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,"Ģ":144,"ģ":145,"Ĥ":146,"ĥ":147,"Ħ":148,"ħ":149,"Ĩ":150,"ĩ":151,"Ī":152,"ī":153,"Ĭ":154,"ĭ":155,"Į":156,"į":157,"İ":158,"ı":159,"IJ":160,"ij":161,"Ĵ":162,"ĵ":163,"Ķ":164,"ķ":165,"ĸ":166,"Ĺ":167,"ĺ":168,"Ļ":169,"ļ":170,"Ľ":171,"ľ":172,"Ŀ":173,"ŀ":174,"Ł":175,"ł":176,"Ń":177,"Ġt":178,"Ġa":179,"Ġth":180,"Ġi":181,"Ġw":182,"ou":183,"Ġs":184,"er":185,"Ġthe":186,"in":187,"Ġh":188,"Ġo":189,"re":190,"at":191,"Ġy":192,"Ġm":193,"Ġc":194,"Ġb":195,"nd":196,"Ġyou":197,"Ġd":198,"Ġf":199}