{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 100,
  "global_step": 330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09111617312072894,
      "grad_norm": 0.6609868407249451,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 0.9616,
      "step": 10
    },
    {
      "epoch": 0.18223234624145787,
      "grad_norm": 0.47854021191596985,
      "learning_rate": 5.757575757575758e-05,
      "loss": 0.6243,
      "step": 20
    },
    {
      "epoch": 0.2733485193621868,
      "grad_norm": 0.3362863063812256,
      "learning_rate": 8.787878787878789e-05,
      "loss": 0.4652,
      "step": 30
    },
    {
      "epoch": 0.36446469248291574,
      "grad_norm": 0.2833992838859558,
      "learning_rate": 9.989933382359422e-05,
      "loss": 0.417,
      "step": 40
    },
    {
      "epoch": 0.45558086560364464,
      "grad_norm": 0.25973188877105713,
      "learning_rate": 9.928561894527353e-05,
      "loss": 0.3717,
      "step": 50
    },
    {
      "epoch": 0.5466970387243736,
      "grad_norm": 0.2526822090148926,
      "learning_rate": 9.812096688325354e-05,
      "loss": 0.3537,
      "step": 60
    },
    {
      "epoch": 0.6378132118451025,
      "grad_norm": 0.27696409821510315,
      "learning_rate": 9.641839665080363e-05,
      "loss": 0.3549,
      "step": 70
    },
    {
      "epoch": 0.7289293849658315,
      "grad_norm": 0.2620004117488861,
      "learning_rate": 9.419694035645751e-05,
      "loss": 0.3487,
      "step": 80
    },
    {
      "epoch": 0.8200455580865603,
      "grad_norm": 0.2623962461948395,
      "learning_rate": 9.14814304544018e-05,
      "loss": 0.3373,
      "step": 90
    },
    {
      "epoch": 0.9111617312072893,
      "grad_norm": 0.25898459553718567,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.3258,
      "step": 100
    },
    {
      "epoch": 0.9111617312072893,
      "eval_loss": 0.3247193992137909,
      "eval_runtime": 220.1924,
      "eval_samples_per_second": 1.771,
      "eval_steps_per_second": 0.445,
      "step": 100
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2992849051952362,
      "learning_rate": 8.469485410510545e-05,
      "loss": 0.3189,
      "step": 110
    },
    {
      "epoch": 1.0911161731207288,
      "grad_norm": 0.2806636691093445,
      "learning_rate": 8.06996511113601e-05,
      "loss": 0.2635,
      "step": 120
    },
    {
      "epoch": 1.182232346241458,
      "grad_norm": 0.3009299039840698,
      "learning_rate": 7.636127338052512e-05,
      "loss": 0.2591,
      "step": 130
    },
    {
      "epoch": 1.2733485193621867,
      "grad_norm": 0.2634446322917938,
      "learning_rate": 7.172821728253562e-05,
      "loss": 0.2522,
      "step": 140
    },
    {
      "epoch": 1.3644646924829158,
      "grad_norm": 0.25836703181266785,
      "learning_rate": 6.685227323685209e-05,
      "loss": 0.255,
      "step": 150
    },
    {
      "epoch": 1.4555808656036446,
      "grad_norm": 0.2524298131465912,
      "learning_rate": 6.178794677547137e-05,
      "loss": 0.2609,
      "step": 160
    },
    {
      "epoch": 1.5466970387243735,
      "grad_norm": 0.2687428593635559,
      "learning_rate": 5.6591849255168015e-05,
      "loss": 0.2486,
      "step": 170
    },
    {
      "epoch": 1.6378132118451025,
      "grad_norm": 0.2657402455806732,
      "learning_rate": 5.132206502986368e-05,
      "loss": 0.2414,
      "step": 180
    },
    {
      "epoch": 1.7289293849658316,
      "grad_norm": 0.270682156085968,
      "learning_rate": 4.603750215716057e-05,
      "loss": 0.2416,
      "step": 190
    },
    {
      "epoch": 1.8200455580865604,
      "grad_norm": 0.2766685485839844,
      "learning_rate": 4.0797233897138985e-05,
      "loss": 0.2463,
      "step": 200
    },
    {
      "epoch": 1.8200455580865604,
      "eval_loss": 0.30126097798347473,
      "eval_runtime": 97.3172,
      "eval_samples_per_second": 4.008,
      "eval_steps_per_second": 1.007,
      "step": 200
    },
    {
      "epoch": 1.9111617312072893,
      "grad_norm": 0.25800785422325134,
      "learning_rate": 3.5659838364445505e-05,
      "loss": 0.2402,
      "step": 210
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.278238445520401,
      "learning_rate": 3.0682743715343564e-05,
      "loss": 0.2455,
      "step": 220
    },
    {
      "epoch": 2.091116173120729,
      "grad_norm": 0.25559282302856445,
      "learning_rate": 2.5921586189524694e-05,
      "loss": 0.1869,
      "step": 230
    },
    {
      "epoch": 2.1822323462414577,
      "grad_norm": 0.271758109331131,
      "learning_rate": 2.1429588182782144e-05,
      "loss": 0.182,
      "step": 240
    },
    {
      "epoch": 2.273348519362187,
      "grad_norm": 0.26463642716407776,
      "learning_rate": 1.725696330273575e-05,
      "loss": 0.1812,
      "step": 250
    },
    {
      "epoch": 2.364464692482916,
      "grad_norm": 0.26230356097221375,
      "learning_rate": 1.345035505816642e-05,
      "loss": 0.186,
      "step": 260
    },
    {
      "epoch": 2.4555808656036446,
      "grad_norm": 0.26036038994789124,
      "learning_rate": 1.0052315456547934e-05,
      "loss": 0.1816,
      "step": 270
    },
    {
      "epoch": 2.5466970387243735,
      "grad_norm": 0.24081580340862274,
      "learning_rate": 7.100829338251147e-06,
      "loss": 0.165,
      "step": 280
    },
    {
      "epoch": 2.6378132118451028,
      "grad_norm": 0.2601291239261627,
      "learning_rate": 4.6288897646302785e-06,
      "loss": 0.1747,
      "step": 290
    },
    {
      "epoch": 2.7289293849658316,
      "grad_norm": 0.26094359159469604,
      "learning_rate": 2.664129206497479e-06,
      "loss": 0.1706,
      "step": 300
    },
    {
      "epoch": 2.7289293849658316,
      "eval_loss": 0.3079453408718109,
      "eval_runtime": 96.434,
      "eval_samples_per_second": 4.044,
      "eval_steps_per_second": 1.016,
      "step": 300
    },
    {
      "epoch": 2.8200455580865604,
      "grad_norm": 0.25573495030403137,
      "learning_rate": 1.2285106557296477e-06,
      "loss": 0.1731,
      "step": 310
    },
    {
      "epoch": 2.9111617312072893,
      "grad_norm": 0.23953253030776978,
      "learning_rate": 3.380821129028489e-07,
      "loss": 0.1722,
      "step": 320
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.28564217686653137,
      "learning_rate": 2.797195404247166e-09,
      "loss": 0.1705,
      "step": 330
    },
    {
      "epoch": 3.0,
      "step": 330,
      "total_flos": 5.7502645012240794e+17,
      "train_loss": 0.2902192401163506,
      "train_runtime": 4452.9364,
      "train_samples_per_second": 2.365,
      "train_steps_per_second": 0.074
    }
  ],
  "logging_steps": 10,
  "max_steps": 330,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.7502645012240794e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}