{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 0.04074497464410111,
      "learning_rate": 1.25e-05,
      "loss": 0.0786,
      "step": 1
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.03544656177940455,
      "learning_rate": 2.5e-05,
      "loss": 0.0215,
      "step": 2
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.018154290180036683,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.0191,
      "step": 3
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.03822847268094023,
      "learning_rate": 5e-05,
      "loss": 0.0627,
      "step": 4
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.04828355560141872,
      "learning_rate": 4.990486745229364e-05,
      "loss": 0.1141,
      "step": 5
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.01442910143611697,
      "learning_rate": 4.962019382530521e-05,
      "loss": 0.0124,
      "step": 6
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.013509316351523514,
      "learning_rate": 4.914814565722671e-05,
      "loss": 0.0095,
      "step": 7
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.0152325820014462,
      "learning_rate": 4.849231551964771e-05,
      "loss": 0.0042,
      "step": 8
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.05761117819516412,
      "learning_rate": 4.765769467591625e-05,
      "loss": 0.0546,
      "step": 9
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.029227415412209183,
      "learning_rate": 4.665063509461097e-05,
      "loss": 0.0312,
      "step": 10
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.07332487393622646,
      "learning_rate": 4.54788011072248e-05,
      "loss": 0.154,
      "step": 11
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.042736802026228475,
      "learning_rate": 4.415111107797445e-05,
      "loss": 0.0673,
      "step": 12
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.038741379672252337,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.0479,
      "step": 13
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.04842992397907143,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 0.045,
      "step": 14
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.05626270106755772,
      "learning_rate": 3.933941090877615e-05,
      "loss": 0.0692,
      "step": 15
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.05786807350124687,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.0374,
      "step": 16
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.042298303771381225,
      "learning_rate": 3.556545654351749e-05,
      "loss": 0.0296,
      "step": 17
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.07999466592387253,
      "learning_rate": 3.355050358314172e-05,
      "loss": 0.0571,
      "step": 18
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.02867198837847147,
      "learning_rate": 3.147047612756302e-05,
      "loss": 0.0126,
      "step": 19
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.04013117527409576,
      "learning_rate": 2.9341204441673266e-05,
      "loss": 0.0257,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.02044483833014965,
      "eval_runtime": 0.4168,
      "eval_samples_per_second": 2.399,
      "eval_steps_per_second": 2.399,
      "step": 20
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.057259960904440216,
      "learning_rate": 2.717889356869146e-05,
      "loss": 0.0287,
      "step": 21
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.04308952396294515,
      "learning_rate": 2.5e-05,
      "loss": 0.0173,
      "step": 22
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.023557986103955056,
      "learning_rate": 2.2821106431308544e-05,
      "loss": 0.0216,
      "step": 23
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.06386951127637508,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 0.0657,
      "step": 24
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.054763104678913314,
      "learning_rate": 1.852952387243698e-05,
      "loss": 0.0887,
      "step": 25
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.046022276699395966,
      "learning_rate": 1.6449496416858284e-05,
      "loss": 0.0354,
      "step": 26
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.015738196398920462,
      "learning_rate": 1.443454345648252e-05,
      "loss": 0.0181,
      "step": 27
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.07291025365320726,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.0886,
      "step": 28
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.04208219657111186,
      "learning_rate": 1.0660589091223855e-05,
      "loss": 0.0452,
      "step": 29
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.06313579923379013,
      "learning_rate": 8.930309757836517e-06,
      "loss": 0.0295,
      "step": 30
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.015372026542706347,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.0079,
      "step": 31
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.028152351446944102,
      "learning_rate": 5.848888922025553e-06,
      "loss": 0.0119,
      "step": 32
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.03777807518313565,
      "learning_rate": 4.521198892775203e-06,
      "loss": 0.0069,
      "step": 33
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.03642754435104511,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.0192,
      "step": 34
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.04684071272816586,
      "learning_rate": 2.3423053240837515e-06,
      "loss": 0.0287,
      "step": 35
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.026021617666382578,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 0.0225,
      "step": 36
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.03654671101676226,
      "learning_rate": 8.51854342773295e-07,
      "loss": 0.0191,
      "step": 37
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.030285276846994395,
      "learning_rate": 3.7980617469479953e-07,
      "loss": 0.0186,
      "step": 38
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.031899337025318504,
      "learning_rate": 9.513254770636137e-08,
      "loss": 0.0319,
      "step": 39
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.0035402779112469695,
      "learning_rate": 0.0,
      "loss": 0.0008,
      "step": 40
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.021046113222837448,
      "eval_runtime": 1.4327,
      "eval_samples_per_second": 0.698,
      "eval_steps_per_second": 0.698,
      "step": 40
    },
    {
      "epoch": 2.0,
      "step": 40,
      "total_flos": 421468569600.0,
      "train_loss": 0.039000130115891804,
      "train_runtime": 156.7594,
      "train_samples_per_second": 0.51,
      "train_steps_per_second": 0.255
    }
  ],
  "logging_steps": 1,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 421468569600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}