{
  "model": "HuggingFaceTB/SmolLM2-360M-Instruct",
  "dataset": "chimbiwide/NPC-Dialogue_v2",
  "method": "lora",
  "dataset_size": 1689,
  "train_size": 1513,
  "validation_size": 176,
  "max_train_samples": 0,
  "max_eval_samples": 1000,
  "eval_steps": 47,
  "train_characters": 91,
  "validation_characters": 10,
  "character_overlap": 0,
  "max_seq_length": 2048,
  "lora_config": {
    "task_type": "CAUSAL_LM",
    "peft_type": "LORA",
    "auto_mapping": null,
    "peft_version": "0.18.1",
    "base_model_name_or_path": "HuggingFaceTB/SmolLM2-360M-Instruct",
    "revision": null,
    "inference_mode": false,
    "r": 16,
    "target_modules": [
      "down_proj",
      "gate_proj",
      "k_proj",
      "o_proj",
      "q_proj",
      "up_proj",
      "v_proj"
    ],
    "exclude_modules": null,
    "lora_alpha": 32,
    "lora_dropout": 0.05,
    "fan_in_fan_out": false,
    "bias": "none",
    "use_rslora": false,
    "modules_to_save": null,
    "init_lora_weights": true,
    "layers_to_transform": null,
    "layers_pattern": null,
    "rank_pattern": {},
    "alpha_pattern": {},
    "megatron_config": null,
    "megatron_core": "megatron.core",
    "trainable_token_indices": null,
    "loftq_config": {},
    "eva_config": null,
    "corda_config": null,
    "use_dora": false,
    "alora_invocation_tokens": null,
    "use_qalora": false,
    "qalora_group_size": 16,
    "layer_replication": null,
    "lora_bias": false,
    "target_parameters": null,
    "arrow_config": null,
    "ensure_weight_tying": false
  },
  "learning_rate": 0.0002,
  "batch_size": 8,
  "gradient_accumulation": 2,
  "effective_batch_size": 16,
  "epochs": 3.0,
  "warmup_ratio": 0.05,
  "warmup_steps": 14,
  "weight_decay": 0.01,
  "lr_scheduler": "cosine",
  "optimizer": "adamw_torch_fused",
  "precision": "bf16",
  "gradient_checkpointing": true,
  "assistant_only_loss": true,
  "total_parameters": 361821120,
  "trainable_parameters": 8683520,
  "trainable_percent": 2.3999,
  "training_loss": 2.2018708011560273,
  "validation_loss": 2.148780584335327,
  "perplexity": 8.5743962665088,
  "training_time_seconds": 1489.1,
  "training_time_minutes": 24.82,
  "peak_gpu_memory_gb": 9.93,
  "global_steps": 285,
  "loss_masking_check": {
    "supervised_token_ratio": 0.5492,
    "supervised_preview": "Ah, welcome, welcome! You find yourself in a corner of Calcutta where fortunes are made and lost quicker than the sweat dries on your brow. I am Bikram. What brings you to my humble… emporium, shall we say? Don't mind the smell; it's the scent of opportunity, my friend.<|im_end|>An artifact, you say? Calcutta is a magnet for such things, drawn in by the tides of trade and whispered secrets. But 's",
    "masked_preview": "<|im_start|>system\nEnter roleplay mode. You are Bikram. Background: Bikram's weathered face tells a story of hardship and resilience, etched with the lines of countless deals made in the shadows of Calcutta's bustling streets. His eyes, though hardened by experience, hold a flicker of warmth when he speaks of loyalty, a virtue he holds above all else. Bikram carries himself with a swagger that bel",
    "system_or_user_leaked": false
  },
  "gpu": {
    "device": "NVIDIA GeForce RTX 5060 Ti",
    "total_memory_gb": 17.07,
    "bf16_supported": true,
    "capability": "12.0"
  },
  "libraries": {
    "python": "3.12.3",
    "torch": "2.11.0+cu128",
    "transformers": "5.17.0",
    "datasets": "4.3.0",
    "trl": "0.24.0",
    "peft": "0.18.1",
    "accelerate": "1.12.0"
  },
  "seed": 42,
  "output_dir": "/mnt/d/work2/smollm2-npc-roleplay-npc/outputs/checkpoints/npc-lora/final",
  "log_history": [
    {
      "loss": 2.5523666381835937,
      "grad_norm": 0.22088582813739777,
      "learning_rate": 5.714285714285714e-05,
      "entropy": 1.933849000930786,
      "num_tokens": 93796.0,
      "mean_token_accuracy": 0.46158536076545714,
      "epoch": 0.05263157894736842,
      "step": 5
    },
    {
      "loss": 2.5331878662109375,
      "grad_norm": 0.21720781922340393,
      "learning_rate": 0.00012857142857142858,
      "entropy": 1.9523229598999023,
      "num_tokens": 187269.0,
      "mean_token_accuracy": 0.46900137364864347,
      "epoch": 0.10526315789473684,
      "step": 10
    },
    {
      "loss": 2.4539527893066406,
      "grad_norm": 0.13605234026908875,
      "learning_rate": 0.0002,
      "entropy": 2.1557540893554688,
      "num_tokens": 281613.0,
      "mean_token_accuracy": 0.4719751179218292,
      "epoch": 0.15789473684210525,
      "step": 15
    },
    {
      "loss": 2.451401138305664,
      "grad_norm": 0.23667477071285248,
      "learning_rate": 0.00019983206176618388,
      "entropy": 2.480435037612915,
      "num_tokens": 376141.0,
      "mean_token_accuracy": 0.4684509068727493,
      "epoch": 0.21052631578947367,
      "step": 20
    },
    {
      "loss": 2.4010854721069337,
      "grad_norm": 0.09741178154945374,
      "learning_rate": 0.000199328811129743,
      "entropy": 2.378065037727356,
      "num_tokens": 468513.0,
      "mean_token_accuracy": 0.478556826710701,
      "epoch": 0.2631578947368421,
      "step": 25
    },
    {
      "loss": 2.366695594787598,
      "grad_norm": 0.11083851754665375,
      "learning_rate": 0.00019849193839113833,
      "entropy": 2.217120313644409,
      "num_tokens": 561891.0,
      "mean_token_accuracy": 0.48194282352924345,
      "epoch": 0.3157894736842105,
      "step": 30
    },
    {
      "loss": 2.343669891357422,
      "grad_norm": 0.10740305483341217,
      "learning_rate": 0.00019732425440896297,
      "entropy": 2.188133120536804,
      "num_tokens": 656095.0,
      "mean_token_accuracy": 0.48512300848960876,
      "epoch": 0.3684210526315789,
      "step": 35
    },
    {
      "loss": 2.337441635131836,
      "grad_norm": 0.10451745986938477,
      "learning_rate": 0.0001958296811589293,
      "entropy": 2.2373024463653564,
      "num_tokens": 748364.0,
      "mean_token_accuracy": 0.4842404007911682,
      "epoch": 0.42105263157894735,
      "step": 40
    },
    {
      "loss": 2.3664779663085938,
      "grad_norm": 0.10740821063518524,
      "learning_rate": 0.0001940132385608757,
      "entropy": 2.279412937164307,
      "num_tokens": 842886.0,
      "mean_token_accuracy": 0.48362932801246644,
      "epoch": 0.47368421052631576,
      "step": 45
    },
    {
      "eval_loss": 2.316269636154175,
      "eval_runtime": 25.2544,
      "eval_samples_per_second": 6.969,
      "eval_steps_per_second": 0.871,
      "eval_entropy": 2.2317135334014893,
      "eval_num_tokens": 879988.0,
      "eval_mean_token_accuracy": 0.4894282506270842,
      "epoch": 0.49473684210526314,
      "step": 47
    },
    {
      "loss": 2.3454864501953123,
      "grad_norm": 0.11415872722864151,
      "learning_rate": 0.00019188102761803717,
      "entropy": 2.252223086357117,
      "num_tokens": 936226.0,
      "mean_token_accuracy": 0.48670867681503294,
      "epoch": 0.5263157894736842,
      "step": 50
    },
    {
      "loss": 2.3060874938964844,
      "grad_norm": 0.1160162165760994,
      "learning_rate": 0.0001894402099252109,
      "entropy": 2.2304810762405394,
      "num_tokens": 1028185.0,
      "mean_token_accuracy": 0.4880038559436798,
      "epoch": 0.5789473684210527,
      "step": 55
    },
    {
      "loss": 2.2843629837036135,
      "grad_norm": 0.12905658781528473,
      "learning_rate": 0.0001866989836146449,
      "entropy": 2.1765635013580322,
      "num_tokens": 1120518.0,
      "mean_token_accuracy": 0.49455042481422423,
      "epoch": 0.631578947368421,
      "step": 60
    },
    {
      "loss": 2.262358283996582,
      "grad_norm": 0.11617386341094971,
      "learning_rate": 0.00018366655582044094,
      "entropy": 2.161082220077515,
      "num_tokens": 1216629.0,
      "mean_token_accuracy": 0.49634212255477905,
      "epoch": 0.6842105263157895,
      "step": 65
    },
    {
      "loss": 2.274257850646973,
      "grad_norm": 0.14454935491085052,
      "learning_rate": 0.0001803531117539577,
      "entropy": 2.191727089881897,
      "num_tokens": 1308903.0,
      "mean_token_accuracy": 0.49855717420578005,
      "epoch": 0.7368421052631579,
      "step": 70
    },
    {
      "loss": 2.2217056274414064,
      "grad_norm": 0.14457330107688904,
      "learning_rate": 0.00017676978049408263,
      "entropy": 2.1600573301315307,
      "num_tokens": 1401788.0,
      "mean_token_accuracy": 0.4966869682073593,
      "epoch": 0.7894736842105263,
      "step": 75
    },
    {
      "loss": 2.2426210403442384,
      "grad_norm": 0.14771753549575806,
      "learning_rate": 0.00017292859760727493,
      "entropy": 2.1251904249191282,
      "num_tokens": 1493269.0,
      "mean_token_accuracy": 0.49993438124656675,
      "epoch": 0.8421052631578947,
      "step": 80
    },
    {
      "loss": 2.237934875488281,
      "grad_norm": 0.14660881459712982,
      "learning_rate": 0.00016884246472293016,
      "entropy": 2.160723400115967,
      "num_tokens": 1589104.0,
      "mean_token_accuracy": 0.5008507877588272,
      "epoch": 0.8947368421052632,
      "step": 85
    },
    {
      "loss": 2.215174674987793,
      "grad_norm": 0.14955751597881317,
      "learning_rate": 0.000164525106199843,
      "entropy": 2.150420093536377,
      "num_tokens": 1683525.0,
      "mean_token_accuracy": 0.5014137506484986,
      "epoch": 0.9473684210526315,
      "step": 90
    },
    {
      "eval_loss": 2.2206270694732666,
      "eval_runtime": 13.3703,
      "eval_samples_per_second": 13.164,
      "eval_steps_per_second": 1.645,
      "eval_entropy": 2.1415598500858652,
      "eval_num_tokens": 1759033.0,
      "eval_mean_token_accuracy": 0.5016853362321854,
      "epoch": 0.9894736842105263,
      "step": 94
    },
    {
      "loss": 2.210609245300293,
      "grad_norm": 0.2051151990890503,
      "learning_rate": 0.00015999102302931585,
      "entropy": 2.1453773021697997,
      "num_tokens": 1769255.0,
      "mean_token_accuracy": 0.5010978668928147,
      "epoch": 1.0,
      "step": 95
    },
    {
      "loss": 2.1714473724365235,
      "grad_norm": 0.15744632482528687,
      "learning_rate": 0.00015525544412974132,
      "entropy": 2.145352911949158,
      "num_tokens": 1864783.0,
      "mean_token_accuracy": 0.510258013010025,
      "epoch": 1.0526315789473684,
      "step": 100
    },
    {
      "loss": 2.212137222290039,
      "grad_norm": 0.16042566299438477,
      "learning_rate": 0.0001503342751962493,
      "entropy": 2.126456546783447,
      "num_tokens": 1957360.0,
      "mean_token_accuracy": 0.5051965832710266,
      "epoch": 1.1052631578947367,
      "step": 105
    },
    {
      "loss": 2.1988462448120116,
      "grad_norm": 0.16124625504016876,
      "learning_rate": 0.00014524404527721977,
      "entropy": 2.1093988180160523,
      "num_tokens": 2049648.0,
      "mean_token_accuracy": 0.5063745319843292,
      "epoch": 1.1578947368421053,
      "step": 110
    },
    {
      "loss": 2.192594528198242,
      "grad_norm": 0.18138575553894043,
      "learning_rate": 0.00014000185125709918,
      "entropy": 2.128497362136841,
      "num_tokens": 2143746.0,
      "mean_token_accuracy": 0.5051657497882843,
      "epoch": 1.2105263157894737,
      "step": 115
    },
    {
      "loss": 2.1997039794921873,
      "grad_norm": 0.1774953305721283,
      "learning_rate": 0.00013462530043198873,
      "entropy": 2.152763772010803,
      "num_tokens": 2238337.0,
      "mean_token_accuracy": 0.5037459582090378,
      "epoch": 1.263157894736842,
      "step": 120
    },
    {
      "loss": 2.1733221054077148,
      "grad_norm": 0.17004919052124023,
      "learning_rate": 0.00012913245137088024,
      "entropy": 2.1356810569763183,
      "num_tokens": 2330291.0,
      "mean_token_accuracy": 0.5107389390468597,
      "epoch": 1.3157894736842106,
      "step": 125
    },
    {
      "loss": 2.148809814453125,
      "grad_norm": 0.1917748898267746,
      "learning_rate": 0.00012354175326117253,
      "entropy": 2.093570041656494,
      "num_tokens": 2421723.0,
      "mean_token_accuracy": 0.5119283616542816,
      "epoch": 1.368421052631579,
      "step": 130
    },
    {
      "loss": 2.1357706069946287,
      "grad_norm": 0.18109489977359772,
      "learning_rate": 0.0001178719839421925,
      "entropy": 2.0645798206329347,
      "num_tokens": 2516541.0,
      "mean_token_accuracy": 0.515396112203598,
      "epoch": 1.4210526315789473,
      "step": 135
    },
    {
      "loss": 2.1544036865234375,
      "grad_norm": 0.19599980115890503,
      "learning_rate": 0.00011214218683485158,
      "entropy": 2.1346421003341676,
      "num_tokens": 2609031.0,
      "mean_token_accuracy": 0.5116421699523925,
      "epoch": 1.4736842105263157,
      "step": 140
    },
    {
      "eval_loss": 2.1792523860931396,
      "eval_runtime": 16.4067,
      "eval_samples_per_second": 10.727,
      "eval_steps_per_second": 1.341,
      "eval_entropy": 2.1185361363671045,
      "eval_num_tokens": 2627950.0,
      "eval_mean_token_accuracy": 0.5076680142771114,
      "epoch": 1.4842105263157894,
      "step": 141
    },
    {
      "loss": 2.169381332397461,
      "grad_norm": 0.18576543033123016,
      "learning_rate": 0.00010637160697927651,
      "entropy": 2.1318769693374633,
      "num_tokens": 2701848.0,
      "mean_token_accuracy": 0.5107553184032441,
      "epoch": 1.526315789473684,
      "step": 145
    },
    {
      "loss": 2.162215995788574,
      "grad_norm": 0.18139831721782684,
      "learning_rate": 0.00010057962639524798,
      "entropy": 2.121912145614624,
      "num_tokens": 2795827.0,
      "mean_token_accuracy": 0.5137030899524688,
      "epoch": 1.5789473684210527,
      "step": 150
    },
    {
      "loss": 2.1198862075805662,
      "grad_norm": 0.19324608147144318,
      "learning_rate": 9.478569898255765e-05,
      "entropy": 2.092076063156128,
      "num_tokens": 2889171.0,
      "mean_token_accuracy": 0.5189927399158478,
      "epoch": 1.631578947368421,
      "step": 155
    },
    {
      "loss": 2.135479545593262,
      "grad_norm": 0.18662935495376587,
      "learning_rate": 8.900928517993644e-05,
      "entropy": 2.107566738128662,
      "num_tokens": 2983944.0,
      "mean_token_accuracy": 0.5150025188922882,
      "epoch": 1.6842105263157894,
      "step": 160
    },
    {
      "loss": 2.168526840209961,
      "grad_norm": 0.1955968737602234,
      "learning_rate": 8.326978660202034e-05,
      "entropy": 2.1270210266113283,
      "num_tokens": 3078482.0,
      "mean_token_accuracy": 0.5109177112579346,
      "epoch": 1.736842105263158,
      "step": 165
    },
    {
      "loss": 2.1491790771484376,
      "grad_norm": 0.19812174141407013,
      "learning_rate": 7.758648087389277e-05,
      "entropy": 2.1165373802185057,
      "num_tokens": 3171229.0,
      "mean_token_accuracy": 0.5111929804086686,
      "epoch": 1.7894736842105263,
      "step": 170
    },
    {
      "loss": 2.160044860839844,
      "grad_norm": 0.2086932212114334,
      "learning_rate": 7.197845688207805e-05,
      "entropy": 2.110708808898926,
      "num_tokens": 3265986.0,
      "mean_token_accuracy": 0.5085264205932617,
      "epoch": 1.8421052631578947,
      "step": 175
    },
    {
      "loss": 2.156445121765137,
      "grad_norm": 0.19480496644973755,
      "learning_rate": 6.646455065946386e-05,
      "entropy": 2.117557668685913,
      "num_tokens": 3358807.0,
      "mean_token_accuracy": 0.513753566145897,
      "epoch": 1.8947368421052633,
      "step": 180
    },
    {
      "loss": 2.113090705871582,
      "grad_norm": 0.19168244302272797,
      "learning_rate": 6.106328211949928e-05,
      "entropy": 2.1011462211608887,
      "num_tokens": 3452203.0,
      "mean_token_accuracy": 0.5172903001308441,
      "epoch": 1.9473684210526314,
      "step": 185
    },
    {
      "eval_loss": 2.157062530517578,
      "eval_runtime": 15.9374,
      "eval_samples_per_second": 11.043,
      "eval_steps_per_second": 1.38,
      "eval_entropy": 2.0991858785802666,
      "eval_num_tokens": 3508507.0,
      "eval_mean_token_accuracy": 0.5112517042593523,
      "epoch": 1.9789473684210526,
      "step": 188
    },
    {
      "loss": 2.1452701568603514,
      "grad_norm": 0.24300329387187958,
      "learning_rate": 5.579279285216369e-05,
      "entropy": 2.122407627105713,
      "num_tokens": 3538510.0,
      "mean_token_accuracy": 0.5125555753707886,
      "epoch": 2.0,
      "step": 190
    },
    {
      "loss": 2.1096288681030275,
      "grad_norm": 0.20780698955059052,
      "learning_rate": 5.067078519063514e-05,
      "entropy": 2.0936718225479125,
      "num_tokens": 3633684.0,
      "mean_token_accuracy": 0.5186141610145569,
      "epoch": 2.0526315789473686,
      "step": 195
    },
    {
      "loss": 2.099007987976074,
      "grad_norm": 0.19569851458072662,
      "learning_rate": 4.571446275331903e-05,
      "entropy": 2.078820252418518,
      "num_tokens": 3727072.0,
      "mean_token_accuracy": 0.5218498349189759,
      "epoch": 2.1052631578947367,
      "step": 200
    },
    {
      "loss": 2.138174057006836,
      "grad_norm": 0.1941261887550354,
      "learning_rate": 4.094047266094225e-05,
      "entropy": 2.10717887878418,
      "num_tokens": 3821112.0,
      "mean_token_accuracy": 0.514563399553299,
      "epoch": 2.1578947368421053,
      "step": 205
    },
    {
      "loss": 2.1252628326416017,
      "grad_norm": 0.1947101503610611,
      "learning_rate": 3.6364849622792266e-05,
      "entropy": 2.108471989631653,
      "num_tokens": 3911202.0,
      "mean_token_accuracy": 0.5166740775108337,
      "epoch": 2.2105263157894735,
      "step": 210
    },
    {
      "loss": 2.099527359008789,
      "grad_norm": 0.2063671052455902,
      "learning_rate": 3.2002962079901744e-05,
      "entropy": 2.074895644187927,
      "num_tokens": 4004373.0,
      "mean_token_accuracy": 0.5181715756654739,
      "epoch": 2.263157894736842,
      "step": 215
    },
    {
      "loss": 2.1038749694824217,
      "grad_norm": 0.19067545235157013,
      "learning_rate": 2.7869460586071873e-05,
      "entropy": 2.0991530656814574,
      "num_tokens": 4097168.0,
      "mean_token_accuracy": 0.5198172926902771,
      "epoch": 2.3157894736842106,
      "step": 220
    },
    {
      "loss": 2.108317756652832,
      "grad_norm": 0.20180711150169373,
      "learning_rate": 2.3978228600109565e-05,
      "entropy": 2.0747674703598022,
      "num_tokens": 4192035.0,
      "mean_token_accuracy": 0.5210060477256775,
      "epoch": 2.3684210526315788,
      "step": 225
    },
    {
      "loss": 2.094546890258789,
      "grad_norm": 0.20153699815273285,
      "learning_rate": 2.0342335854556737e-05,
      "entropy": 2.0798715591430663,
      "num_tokens": 4284949.0,
      "mean_token_accuracy": 0.5181330442428589,
      "epoch": 2.4210526315789473,
      "step": 230
    },
    {
      "loss": 2.111064910888672,
      "grad_norm": 0.20009742677211761,
      "learning_rate": 1.6973994457534026e-05,
      "entropy": 2.087741422653198,
      "num_tokens": 4379919.0,
      "mean_token_accuracy": 0.5190323472023011,
      "epoch": 2.473684210526316,
      "step": 235
    },
    {
      "eval_loss": 2.1503143310546875,
      "eval_runtime": 15.7779,
      "eval_samples_per_second": 11.155,
      "eval_steps_per_second": 1.394,
      "eval_entropy": 2.0761942159045828,
      "eval_num_tokens": 4379919.0,
      "eval_mean_token_accuracy": 0.511995713819157,
      "epoch": 2.473684210526316,
      "step": 235
    },
    {
      "loss": 2.119691276550293,
      "grad_norm": 0.20606471598148346,
      "learning_rate": 1.3884517875143544e-05,
      "entropy": 2.0891559600830076,
      "num_tokens": 4473242.0,
      "mean_token_accuracy": 0.5179882824420929,
      "epoch": 2.526315789473684,
      "step": 240
    },
    {
      "loss": 2.121718406677246,
      "grad_norm": 0.19413025677204132,
      "learning_rate": 1.1084282932198541e-05,
      "entropy": 2.1111440420150758,
      "num_tokens": 4568065.0,
      "mean_token_accuracy": 0.5200768530368804,
      "epoch": 2.5789473684210527,
      "step": 245
    },
    {
      "loss": 2.1327035903930662,
      "grad_norm": 0.20437853038311005,
      "learning_rate": 8.58269495891081e-06,
      "entropy": 2.095879054069519,
      "num_tokens": 4661089.0,
      "mean_token_accuracy": 0.517047768831253,
      "epoch": 2.6315789473684212,
      "step": 250
    },
    {
      "loss": 2.077016830444336,
      "grad_norm": 0.20744766294956207,
      "learning_rate": 6.388156200599726e-06,
      "entropy": 2.064937162399292,
      "num_tokens": 4755205.0,
      "mean_token_accuracy": 0.5244661808013916,
      "epoch": 2.6842105263157894,
      "step": 255
    },
    {
      "loss": 2.109786033630371,
      "grad_norm": 0.2028643935918808,
      "learning_rate": 4.508037596527526e-06,
      "entropy": 2.082032287120819,
      "num_tokens": 4849257.0,
      "mean_token_accuracy": 0.5215404391288757,
      "epoch": 2.736842105263158,
      "step": 260
    },
    {
      "loss": 2.074248504638672,
      "grad_norm": 0.20752288401126862,
      "learning_rate": 2.9486540226488557e-06,
      "entropy": 2.0800060510635374,
      "num_tokens": 4941138.0,
      "mean_token_accuracy": 0.5221293807029724,
      "epoch": 2.7894736842105265,
      "step": 265
    },
    {
      "loss": 2.0968595504760743,
      "grad_norm": 0.1966981142759323,
      "learning_rate": 1.7152430814285303e-06,
      "entropy": 2.067763328552246,
      "num_tokens": 5035425.0,
      "mean_token_accuracy": 0.5213424026966095,
      "epoch": 2.8421052631578947,
      "step": 270
    },
    {
      "loss": 2.088235092163086,
      "grad_norm": 0.20720359683036804,
      "learning_rate": 8.119475099673036e-07,
      "entropy": 2.071122169494629,
      "num_tokens": 5127357.0,
      "mean_token_accuracy": 0.519515186548233,
      "epoch": 2.8947368421052633,
      "step": 275
    },
    {
      "loss": 2.1086212158203126,
      "grad_norm": 0.20018276572227478,
      "learning_rate": 2.418012655228452e-07,
      "entropy": 2.0884795427322387,
      "num_tokens": 5221009.0,
      "mean_token_accuracy": 0.5162034809589386,
      "epoch": 2.9473684210526314,
      "step": 280
    },
    {
      "eval_loss": 2.1488332748413086,
      "eval_runtime": 13.5679,
      "eval_samples_per_second": 12.972,
      "eval_steps_per_second": 1.621,
      "eval_entropy": 2.080313194881786,
      "eval_num_tokens": 5258147.0,
      "eval_mean_token_accuracy": 0.5125655924732034,
      "epoch": 2.968421052631579,
      "step": 282
    },
    {
      "loss": 2.1149166107177733,
      "grad_norm": 0.27149999141693115,
      "learning_rate": 6.719335161364804e-09,
      "entropy": 2.0989904403686523,
      "num_tokens": 5307765.0,
      "mean_token_accuracy": 0.5134236097335816,
      "epoch": 3.0,
      "step": 285
    },
    {
      "eval_loss": 2.148780584335327,
      "eval_runtime": 15.705,
      "eval_samples_per_second": 11.207,
      "eval_steps_per_second": 1.401,
      "eval_entropy": 2.0802648934451016,
      "eval_num_tokens": 5307765.0,
      "eval_mean_token_accuracy": 0.5120757411826741,
      "epoch": 3.0,
      "step": 285
    },
    {
      "train_runtime": 1594.7672,
      "train_samples_per_second": 2.846,
      "train_steps_per_second": 0.179,
      "total_flos": 1.20989712516768e+16,
      "train_loss": 2.2018708011560273,
      "epoch": 3.0,
      "step": 285
    },
    {
      "eval_loss": 2.148780584335327,
      "eval_runtime": 13.2149,
      "eval_samples_per_second": 13.318,
      "eval_steps_per_second": 1.665,
      "eval_entropy": 2.0802648934451016,
      "eval_num_tokens": 5307765.0,
      "eval_mean_token_accuracy": 0.5120757411826741,
      "epoch": 3.0,
      "step": 285
    }
  ]
}