{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 147,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 4.106373310089111,
      "learning_rate": 2e-05,
      "loss": 1.2854,
      "step": 5
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 1.1787455081939697,
      "learning_rate": 1.9938879040295508e-05,
      "loss": 0.5714,
      "step": 10
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 1.0353399515151978,
      "learning_rate": 1.975626331552507e-05,
      "loss": 0.424,
      "step": 15
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 0.9334375262260437,
      "learning_rate": 1.9454385155359704e-05,
      "loss": 0.3665,
      "step": 20
    },
    {
      "epoch": 0.5102040816326531,
      "grad_norm": 0.8077430725097656,
      "learning_rate": 1.903693477637204e-05,
      "loss": 0.3533,
      "step": 25
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 0.786541759967804,
      "learning_rate": 1.850901517212062e-05,
      "loss": 0.3211,
      "step": 30
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.6843534708023071,
      "learning_rate": 1.7877079733177185e-05,
      "loss": 0.3147,
      "step": 35
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 0.6673664450645447,
      "learning_rate": 1.7148853359641627e-05,
      "loss": 0.2972,
      "step": 40
    },
    {
      "epoch": 0.9183673469387755,
      "grad_norm": 0.6665471792221069,
      "learning_rate": 1.6333238030480473e-05,
      "loss": 0.2947,
      "step": 45
    },
    {
      "epoch": 1.0204081632653061,
      "grad_norm": 0.6398372650146484,
      "learning_rate": 1.5440203984027323e-05,
      "loss": 0.2689,
      "step": 50
    },
    {
      "epoch": 1.1224489795918366,
      "grad_norm": 0.5915564894676208,
      "learning_rate": 1.4480667839875786e-05,
      "loss": 0.2341,
      "step": 55
    },
    {
      "epoch": 1.2244897959183674,
      "grad_norm": 0.5560858845710754,
      "learning_rate": 1.3466359152026197e-05,
      "loss": 0.23,
      "step": 60
    },
    {
      "epoch": 1.3265306122448979,
      "grad_norm": 0.6363187432289124,
      "learning_rate": 1.2409677024566145e-05,
      "loss": 0.2209,
      "step": 65
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.5852870941162109,
      "learning_rate": 1.1323538542642227e-05,
      "loss": 0.2096,
      "step": 70
    },
    {
      "epoch": 1.5306122448979593,
      "grad_norm": 0.5593776702880859,
      "learning_rate": 1.022122087153187e-05,
      "loss": 0.2155,
      "step": 75
    },
    {
      "epoch": 1.6326530612244898,
      "grad_norm": 0.5509619116783142,
      "learning_rate": 9.116198954026577e-06,
      "loss": 0.2104,
      "step": 80
    },
    {
      "epoch": 1.7346938775510203,
      "grad_norm": 0.5514574646949768,
      "learning_rate": 8.021980790144828e-06,
      "loss": 0.2097,
      "step": 85
    },
    {
      "epoch": 1.836734693877551,
      "grad_norm": 0.6069679856300354,
      "learning_rate": 6.951942312747135e-06,
      "loss": 0.2062,
      "step": 90
    },
    {
      "epoch": 1.9387755102040818,
      "grad_norm": 0.6014193296432495,
      "learning_rate": 5.919163877565351e-06,
      "loss": 0.2075,
      "step": 95
    },
    {
      "epoch": 2.0408163265306123,
      "grad_norm": 0.5056990385055542,
      "learning_rate": 4.936270366423563e-06,
      "loss": 0.1778,
      "step": 100
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.6073999404907227,
      "learning_rate": 4.015276858259427e-06,
      "loss": 0.1457,
      "step": 105
    },
    {
      "epoch": 2.2448979591836733,
      "grad_norm": 0.5745469331741333,
      "learning_rate": 3.167441754493066e-06,
      "loss": 0.1441,
      "step": 110
    },
    {
      "epoch": 2.3469387755102042,
      "grad_norm": 0.5980499386787415,
      "learning_rate": 2.403129154167153e-06,
      "loss": 0.1426,
      "step": 115
    },
    {
      "epoch": 2.4489795918367347,
      "grad_norm": 0.5385629534721375,
      "learning_rate": 1.7316821612109136e-06,
      "loss": 0.1341,
      "step": 120
    },
    {
      "epoch": 2.5510204081632653,
      "grad_norm": 0.5529075860977173,
      "learning_rate": 1.161308672544389e-06,
      "loss": 0.1367,
      "step": 125
    },
    {
      "epoch": 2.6530612244897958,
      "grad_norm": 0.5598864555358887,
      "learning_rate": 6.989810431710375e-07,
      "loss": 0.1356,
      "step": 130
    },
    {
      "epoch": 2.7551020408163263,
      "grad_norm": 0.5336365699768066,
      "learning_rate": 3.5035085477190143e-07,
      "loss": 0.1352,
      "step": 135
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.516101598739624,
      "learning_rate": 1.1967982968635994e-07,
      "loss": 0.1373,
      "step": 140
    },
    {
      "epoch": 2.9591836734693877,
      "grad_norm": 0.5510626435279846,
      "learning_rate": 9.78773480026396e-09,
      "loss": 0.1373,
      "step": 145
    },
    {
      "epoch": 3.0,
      "step": 147,
      "total_flos": 1.9096132999184384e+17,
      "train_loss": 0.26934566870838605,
      "train_runtime": 589.2508,
      "train_samples_per_second": 15.879,
      "train_steps_per_second": 0.249
    }
  ],
  "logging_steps": 5,
  "max_steps": 147,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9096132999184384e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}