Add checkpoint

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: AR_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. -->
+
+# AR_200_41
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5234
+- Accuracy: 0.5250
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.5298        | 1.0   | 2845  | 1.9969          | 0.3939   |
+| 0.4512        | 2.0   | 5690  | 1.8217          | 0.4384   |
+| 0.4173        | 3.0   | 8535  | 1.7295          | 0.4640   |
+| 0.3977        | 4.0   | 11380 | 1.6786          | 0.4796   |
+| 0.3841        | 5.0   | 14225 | 1.6362          | 0.4906   |
+| 0.3747        | 6.0   | 17070 | 1.6065          | 0.4991   |
+| 0.3677        | 7.0   | 19915 | 1.5772          | 0.5071   |
+| 0.3586        | 8.0   | 22760 | 1.5534          | 0.5143   |
+| 0.3504        | 9.0   | 25605 | 1.5324          | 0.5215   |
+| 0.3437        | 10.0  | 28450 | 1.5234          | 0.5250   |
+
+
+### 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": 0.5249648690662798,
+    "eval_loss": 1.523409128189087,
+    "eval_runtime": 9.5399,
+    "eval_samples": 603,
+    "eval_samples_per_second": 63.208,
+    "eval_steps_per_second": 1.992,
+    "perplexity": 4.587839096715507,
+    "total_flos": 2.3783323336704e+17,
+    "train_loss": 0.40263440499196784,
+    "train_runtime": 24635.8124,
+    "train_samples": 91022,
+    "train_samples_per_second": 36.947,
+    "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": 0.5249648690662798,
+    "eval_loss": 1.523409128189087,
+    "eval_runtime": 9.5399,
+    "eval_samples": 603,
+    "eval_samples_per_second": 63.208,
+    "eval_steps_per_second": 1.992,
+    "perplexity": 4.587839096715507
+}

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 +1,25 @@
+#version: 0.2
+Ø §
+Ù Ħ
+Ġ Ø
+Ġ Ù
+Ù Ĭ
+Ù Ĩ
+ا ÙĦ
+Ù ħ
+Ġ اÙĦ
+Ø ±
+Ø ª
+Ù Ī
+Ø ¯
+Ù ĥ
+Ø ¹
+Ø ©
+Ø ¨
+Ù ĩ
+ĠÙ ħ
+ĠØ £
+Ø ³
+Ù Ĥ
+Ġ ÙĦ
+Ù ģ

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50dbdfde4c92c0d3b59116bab895f69634558b8a79796204134262a83db2f865
+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 +1,410 @@
+{
+  "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,
+      "×": 117,
+      "Ø": 118,
+      "Ù": 119,
+      "Ú": 120,
+      "Û": 121,
+      "Ü": 122,
+      "à": 123,
+      "á": 124,
+      "â": 125,
+      "ã": 126,
+      "ä": 127,
+      "å": 128,
+      "æ": 129,
+      "ç": 130,
+      "è": 131,
+      "é": 132,
+      "ê": 133,
+      "ë": 134,
+      "ì": 135,
+      "í": 136,
+      "î": 137,
+      "ï": 138,
+      "ð": 139,
+      "Ċ": 140,
+      "Ġ": 141,
+      "Ģ": 142,
+      "ģ": 143,
+      "Ĥ": 144,
+      "ĥ": 145,
+      "Ħ": 146,
+      "ħ": 147,
+      "Ĩ": 148,
+      "ĩ": 149,
+      "Ī": 150,
+      "ī": 151,
+      "Ĭ": 152,
+      "ĭ": 153,
+      "Į": 154,
+      "į": 155,
+      "İ": 156,
+      "ı": 157,
+      "IJ": 158,
+      "ij": 159,
+      "Ĵ": 160,
+      "ĵ": 161,
+      "Ķ": 162,
+      "ķ": 163,
+      "ĸ": 164,
+      "Ĺ": 165,
+      "ĺ": 166,
+      "Ļ": 167,
+      "ļ": 168,
+      "Ľ": 169,
+      "ľ": 170,
+      "Ŀ": 171,
+      "ŀ": 172,
+      "Ł": 173,
+      "ł": 174,
+      "Ń": 175,
+      "ا": 176,
+      "ÙĦ": 177,
+      "ĠØ": 178,
+      "ĠÙ": 179,
+      "ÙĬ": 180,
+      "ÙĨ": 181,
+      "اÙĦ": 182,
+      "Ùħ": 183,
+      "ĠاÙĦ": 184,
+      "ر": 185,
+      "ت": 186,
+      "ÙĪ": 187,
+      "د": 188,
+      "Ùĥ": 189,
+      "ع": 190,
+      "Ø©": 191,
+      "ب": 192,
+      "Ùĩ": 193,
+      "ĠÙħ": 194,
+      "ĠØ£": 195,
+      "س": 196,
+      "ÙĤ": 197,
+      "ĠÙĦ": 198,
+      "Ùģ": 199
+    },
+    "merges": [
+      [
+        "Ø",
+        "§"
+      ],
+      [
+        "Ù",
+        "Ħ"
+      ],
+      [
+        "Ġ",
+        "Ø"
+      ],
+      [
+        "Ġ",
+        "Ù"
+      ],
+      [
+        "Ù",
+        "Ĭ"
+      ],
+      [
+        "Ù",
+        "Ĩ"
+      ],
+      [
+        "ا",
+        "ÙĦ"
+      ],
+      [
+        "Ù",
+        "ħ"
+      ],
+      [
+        "Ġ",
+        "اÙĦ"
+      ],
+      [
+        "Ø",
+        "±"
+      ],
+      [
+        "Ø",
+        "ª"
+      ],
+      [
+        "Ù",
+        "Ī"
+      ],
+      [
+        "Ø",
+        "¯"
+      ],
+      [
+        "Ù",
+        "ĥ"
+      ],
+      [
+        "Ø",
+        "¹"
+      ],
+      [
+        "Ø",
+        "©"
+      ],
+      [
+        "Ø",
+        "¨"
+      ],
+      [
+        "Ù",
+        "ĩ"
+      ],
+      [
+        "ĠÙ",
+        "ħ"
+      ],
+      [
+        "ĠØ",
+        "£"
+      ],
+      [
+        "Ø",
+        "³"
+      ],
+      [
+        "Ù",
+        "Ĥ"
+      ],
+      [
+        "Ġ",
+        "ÙĦ"
+      ],
+      [
+        "Ù",
+        "ģ"
+      ]
+    ]
+  }
+}

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": 2.3783323336704e+17,
+    "train_loss": 0.40263440499196784,
+    "train_runtime": 24635.8124,
+    "train_samples": 91022,
+    "train_samples_per_second": 36.947,
+    "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": 28450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.351493848857645,
+      "grad_norm": 12501.5126953125,
+      "learning_rate": 0.0005993999999999999,
+      "loss": 0.6616,
+      "step": 1000
+    },
+    {
+      "epoch": 0.70298769771529,
+      "grad_norm": 11799.552734375,
+      "learning_rate": 0.0005781639344262295,
+      "loss": 0.5298,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.39387861735030005,
+      "eval_loss": 1.9969476461410522,
+      "eval_runtime": 10.2477,
+      "eval_samples_per_second": 58.843,
+      "eval_steps_per_second": 1.854,
+      "step": 2845
+    },
+    {
+      "epoch": 1.054481546572935,
+      "grad_norm": 10105.4248046875,
+      "learning_rate": 0.0005563060109289616,
+      "loss": 0.4896,
+      "step": 3000
+    },
+    {
+      "epoch": 1.40597539543058,
+      "grad_norm": 9273.8095703125,
+      "learning_rate": 0.0005344480874316939,
+      "loss": 0.4687,
+      "step": 4000
+    },
+    {
+      "epoch": 1.757469244288225,
+      "grad_norm": 8524.5703125,
+      "learning_rate": 0.0005125901639344262,
+      "loss": 0.4512,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.43839510860569947,
+      "eval_loss": 1.821701169013977,
+      "eval_runtime": 9.7306,
+      "eval_samples_per_second": 61.97,
+      "eval_steps_per_second": 1.953,
+      "step": 5690
+    },
+    {
+      "epoch": 2.10896309314587,
+      "grad_norm": 8911.6494140625,
+      "learning_rate": 0.0004907322404371584,
+      "loss": 0.437,
+      "step": 6000
+    },
+    {
+      "epoch": 2.460456942003515,
+      "grad_norm": 6983.92236328125,
+      "learning_rate": 0.00046887431693989066,
+      "loss": 0.4253,
+      "step": 7000
+    },
+    {
+      "epoch": 2.81195079086116,
+      "grad_norm": 7203.26025390625,
+      "learning_rate": 0.00044701639344262294,
+      "loss": 0.4173,
+      "step": 8000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4640041800131761,
+      "eval_loss": 1.729548692703247,
+      "eval_runtime": 9.8999,
+      "eval_samples_per_second": 60.909,
+      "eval_steps_per_second": 1.919,
+      "step": 8535
+    },
+    {
+      "epoch": 3.1634446397188047,
+      "grad_norm": 7449.33203125,
+      "learning_rate": 0.00042515846994535517,
+      "loss": 0.4092,
+      "step": 9000
+    },
+    {
+      "epoch": 3.51493848857645,
+      "grad_norm": 7554.9697265625,
+      "learning_rate": 0.0004033005464480874,
+      "loss": 0.4028,
+      "step": 10000
+    },
+    {
+      "epoch": 3.866432337434095,
+      "grad_norm": 7199.42626953125,
+      "learning_rate": 0.0003814426229508197,
+      "loss": 0.3977,
+      "step": 11000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.4796013409793823,
+      "eval_loss": 1.6785619258880615,
+      "eval_runtime": 10.0375,
+      "eval_samples_per_second": 60.075,
+      "eval_steps_per_second": 1.893,
+      "step": 11380
+    },
+    {
+      "epoch": 4.21792618629174,
+      "grad_norm": 7292.9921875,
+      "learning_rate": 0.0003595846994535519,
+      "loss": 0.392,
+      "step": 12000
+    },
+    {
+      "epoch": 4.569420035149385,
+      "grad_norm": 6805.3798828125,
+      "learning_rate": 0.00033772677595628414,
+      "loss": 0.3879,
+      "step": 13000
+    },
+    {
+      "epoch": 4.92091388400703,
+      "grad_norm": 7368.5224609375,
+      "learning_rate": 0.00031586885245901637,
+      "loss": 0.3841,
+      "step": 14000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.49063553725177117,
+      "eval_loss": 1.6362360715866089,
+      "eval_runtime": 9.729,
+      "eval_samples_per_second": 61.98,
+      "eval_steps_per_second": 1.953,
+      "step": 14225
+    },
+    {
+      "epoch": 5.272407732864675,
+      "grad_norm": 7300.4189453125,
+      "learning_rate": 0.0002940109289617486,
+      "loss": 0.3799,
+      "step": 15000
+    },
+    {
+      "epoch": 5.62390158172232,
+      "grad_norm": 6178.0908203125,
+      "learning_rate": 0.0002721530054644809,
+      "loss": 0.3764,
+      "step": 16000
+    },
+    {
+      "epoch": 5.975395430579965,
+      "grad_norm": 6489.77490234375,
+      "learning_rate": 0.0002502950819672131,
+      "loss": 0.3747,
+      "step": 17000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.4991123962704417,
+      "eval_loss": 1.6064575910568237,
+      "eval_runtime": 9.7095,
+      "eval_samples_per_second": 62.104,
+      "eval_steps_per_second": 1.957,
+      "step": 17070
+    },
+    {
+      "epoch": 6.3268892794376095,
+      "grad_norm": 7217.43701171875,
+      "learning_rate": 0.00022843715846994535,
+      "loss": 0.3693,
+      "step": 18000
+    },
+    {
+      "epoch": 6.678383128295255,
+      "grad_norm": 6669.8017578125,
+      "learning_rate": 0.00020657923497267757,
+      "loss": 0.3677,
+      "step": 19000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5070570175865616,
+      "eval_loss": 1.5771993398666382,
+      "eval_runtime": 9.7124,
+      "eval_samples_per_second": 62.086,
+      "eval_steps_per_second": 1.956,
+      "step": 19915
+    },
+    {
+      "epoch": 7.0298769771529,
+      "grad_norm": 7067.46533203125,
+      "learning_rate": 0.00018472131147540983,
+      "loss": 0.3655,
+      "step": 20000
+    },
+    {
+      "epoch": 7.381370826010545,
+      "grad_norm": 6705.837890625,
+      "learning_rate": 0.00016286338797814206,
+      "loss": 0.3605,
+      "step": 21000
+    },
+    {
+      "epoch": 7.73286467486819,
+      "grad_norm": 6395.66162109375,
+      "learning_rate": 0.00014100546448087432,
+      "loss": 0.3586,
+      "step": 22000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5143298510708039,
+      "eval_loss": 1.5533959865570068,
+      "eval_runtime": 9.7631,
+      "eval_samples_per_second": 61.763,
+      "eval_steps_per_second": 1.946,
+      "step": 22760
+    },
+    {
+      "epoch": 8.084358523725834,
+      "grad_norm": 7270.5849609375,
+      "learning_rate": 0.00011914754098360655,
+      "loss": 0.3549,
+      "step": 23000
+    },
+    {
+      "epoch": 8.43585237258348,
+      "grad_norm": 7109.36328125,
+      "learning_rate": 9.728961748633879e-05,
+      "loss": 0.3524,
+      "step": 24000
+    },
+    {
+      "epoch": 8.787346221441124,
+      "grad_norm": 6891.5283203125,
+      "learning_rate": 7.543169398907103e-05,
+      "loss": 0.3504,
+      "step": 25000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5215475135736841,
+      "eval_loss": 1.5324053764343262,
+      "eval_runtime": 9.718,
+      "eval_samples_per_second": 62.05,
+      "eval_steps_per_second": 1.955,
+      "step": 25605
+    },
+    {
+      "epoch": 9.13884007029877,
+      "grad_norm": 7154.31298828125,
+      "learning_rate": 5.357377049180328e-05,
+      "loss": 0.3472,
+      "step": 26000
+    },
+    {
+      "epoch": 9.490333919156415,
+      "grad_norm": 7199.95068359375,
+      "learning_rate": 3.171584699453552e-05,
+      "loss": 0.3449,
+      "step": 27000
+    },
+    {
+      "epoch": 9.84182776801406,
+      "grad_norm": 6995.279296875,
+      "learning_rate": 9.857923497267758e-06,
+      "loss": 0.3437,
+      "step": 28000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.5249648690662798,
+      "eval_loss": 1.523409128189087,
+      "eval_runtime": 9.7518,
+      "eval_samples_per_second": 61.835,
+      "eval_steps_per_second": 1.948,
+      "step": 28450
+    },
+    {
+      "epoch": 10.0,
+      "step": 28450,
+      "total_flos": 2.3783323336704e+17,
+      "train_loss": 0.40263440499196784,
+      "train_runtime": 24635.8124,
+      "train_samples_per_second": 36.947,
+      "train_steps_per_second": 1.155
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 28450,
+  "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": 2.3783323336704e+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:f5d9168668a97f6310f79ab6c49f350fcd589434b5def82bd11a6e70d5e0378f
+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,"×":117,"Ø":118,"Ù":119,"Ú":120,"Û":121,"Ü":122,"à":123,"á":124,"â":125,"ã":126,"ä":127,"å":128,"æ":129,"ç":130,"è":131,"é":132,"ê":133,"ë":134,"ì":135,"í":136,"î":137,"ï":138,"ð":139,"Ċ":140,"Ġ":141,"Ģ":142,"ģ":143,"Ĥ":144,"ĥ":145,"Ħ":146,"ħ":147,"Ĩ":148,"ĩ":149,"Ī":150,"ī":151,"Ĭ":152,"ĭ":153,"Į":154,"į":155,"İ":156,"ı":157,"IJ":158,"ij":159,"Ĵ":160,"ĵ":161,"Ķ":162,"ķ":163,"ĸ":164,"Ĺ":165,"ĺ":166,"Ļ":167,"ļ":168,"Ľ":169,"ľ":170,"Ŀ":171,"ŀ":172,"Ł":173,"ł":174,"Ń":175,"ا":176,"ÙĦ":177,"ĠØ":178,"ĠÙ":179,"ÙĬ":180,"ÙĨ":181,"اÙĦ":182,"Ùħ":183,"ĠاÙĦ":184,"ر":185,"ت":186,"ÙĪ":187,"د":188,"Ùĥ":189,"ع":190,"Ø©":191,"ب":192,"Ùĩ":193,"ĠÙħ":194,"ĠØ£":195,"س":196,"ÙĤ":197,"ĠÙĦ":198,"Ùģ":199}