{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.88659793814433,
  "eval_steps": 7,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.041237113402061855,
      "eval_loss": 2.0562095642089844,
      "eval_runtime": 2.9139,
      "eval_samples_per_second": 14.071,
      "eval_steps_per_second": 2.059,
      "step": 1
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 1.2591140270233154,
      "learning_rate": 3e-05,
      "loss": 1.9881,
      "step": 3
    },
    {
      "epoch": 0.24742268041237114,
      "grad_norm": 1.3045929670333862,
      "learning_rate": 6e-05,
      "loss": 1.9707,
      "step": 6
    },
    {
      "epoch": 0.28865979381443296,
      "eval_loss": 1.8532114028930664,
      "eval_runtime": 2.9739,
      "eval_samples_per_second": 13.787,
      "eval_steps_per_second": 2.018,
      "step": 7
    },
    {
      "epoch": 0.3711340206185567,
      "grad_norm": 1.4863039255142212,
      "learning_rate": 9e-05,
      "loss": 1.7318,
      "step": 9
    },
    {
      "epoch": 0.4948453608247423,
      "grad_norm": 1.4484189748764038,
      "learning_rate": 9.975153876827008e-05,
      "loss": 1.5902,
      "step": 12
    },
    {
      "epoch": 0.5773195876288659,
      "eval_loss": 1.459747314453125,
      "eval_runtime": 2.9899,
      "eval_samples_per_second": 13.713,
      "eval_steps_per_second": 2.007,
      "step": 14
    },
    {
      "epoch": 0.6185567010309279,
      "grad_norm": 1.3237439393997192,
      "learning_rate": 9.84538643114539e-05,
      "loss": 1.4891,
      "step": 15
    },
    {
      "epoch": 0.7422680412371134,
      "grad_norm": 1.3351250886917114,
      "learning_rate": 9.607381059352038e-05,
      "loss": 1.4098,
      "step": 18
    },
    {
      "epoch": 0.865979381443299,
      "grad_norm": 1.3576433658599854,
      "learning_rate": 9.266454408160779e-05,
      "loss": 1.228,
      "step": 21
    },
    {
      "epoch": 0.865979381443299,
      "eval_loss": 1.3227709531784058,
      "eval_runtime": 3.0131,
      "eval_samples_per_second": 13.607,
      "eval_steps_per_second": 1.991,
      "step": 21
    },
    {
      "epoch": 0.9896907216494846,
      "grad_norm": 1.2061851024627686,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.3031,
      "step": 24
    },
    {
      "epoch": 1.1134020618556701,
      "grad_norm": 1.1129889488220215,
      "learning_rate": 8.308429187984297e-05,
      "loss": 1.4281,
      "step": 27
    },
    {
      "epoch": 1.1546391752577319,
      "eval_loss": 1.2710272073745728,
      "eval_runtime": 3.0113,
      "eval_samples_per_second": 13.615,
      "eval_steps_per_second": 1.993,
      "step": 28
    },
    {
      "epoch": 1.2371134020618557,
      "grad_norm": 1.0241196155548096,
      "learning_rate": 7.712731319328798e-05,
      "loss": 1.0659,
      "step": 30
    },
    {
      "epoch": 1.3608247422680413,
      "grad_norm": 1.213539719581604,
      "learning_rate": 7.056435515653059e-05,
      "loss": 1.0993,
      "step": 33
    },
    {
      "epoch": 1.443298969072165,
      "eval_loss": 1.2519707679748535,
      "eval_runtime": 3.0101,
      "eval_samples_per_second": 13.621,
      "eval_steps_per_second": 1.993,
      "step": 35
    },
    {
      "epoch": 1.4845360824742269,
      "grad_norm": 1.1910161972045898,
      "learning_rate": 6.354202340715026e-05,
      "loss": 1.0659,
      "step": 36
    },
    {
      "epoch": 1.6082474226804124,
      "grad_norm": 1.2115846872329712,
      "learning_rate": 5.621718523237427e-05,
      "loss": 1.0223,
      "step": 39
    },
    {
      "epoch": 1.731958762886598,
      "grad_norm": 1.3184078931808472,
      "learning_rate": 4.875346541309637e-05,
      "loss": 1.0009,
      "step": 42
    },
    {
      "epoch": 1.731958762886598,
      "eval_loss": 1.2434487342834473,
      "eval_runtime": 3.0216,
      "eval_samples_per_second": 13.569,
      "eval_steps_per_second": 1.986,
      "step": 42
    },
    {
      "epoch": 1.8556701030927836,
      "grad_norm": 1.2150309085845947,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.9667,
      "step": 45
    },
    {
      "epoch": 1.9793814432989691,
      "grad_norm": 1.312495231628418,
      "learning_rate": 3.4075667487415785e-05,
      "loss": 1.0141,
      "step": 48
    },
    {
      "epoch": 2.020618556701031,
      "eval_loss": 1.2144564390182495,
      "eval_runtime": 3.0168,
      "eval_samples_per_second": 13.59,
      "eval_steps_per_second": 1.989,
      "step": 49
    },
    {
      "epoch": 2.1030927835051547,
      "grad_norm": 1.2755225896835327,
      "learning_rate": 2.718946713234185e-05,
      "loss": 1.2721,
      "step": 51
    },
    {
      "epoch": 2.2268041237113403,
      "grad_norm": 1.2755869626998901,
      "learning_rate": 2.0812816388260518e-05,
      "loss": 0.8322,
      "step": 54
    },
    {
      "epoch": 2.3092783505154637,
      "eval_loss": 1.2048313617706299,
      "eval_runtime": 3.016,
      "eval_samples_per_second": 13.594,
      "eval_steps_per_second": 1.989,
      "step": 56
    },
    {
      "epoch": 2.350515463917526,
      "grad_norm": 1.1833029985427856,
      "learning_rate": 1.5088159095696363e-05,
      "loss": 0.8151,
      "step": 57
    },
    {
      "epoch": 2.4742268041237114,
      "grad_norm": 1.187381386756897,
      "learning_rate": 1.0143374638853891e-05,
      "loss": 0.8196,
      "step": 60
    },
    {
      "epoch": 2.597938144329897,
      "grad_norm": 1.330628514289856,
      "learning_rate": 6.088921331488568e-06,
      "loss": 0.8458,
      "step": 63
    },
    {
      "epoch": 2.597938144329897,
      "eval_loss": 1.2047181129455566,
      "eval_runtime": 3.0172,
      "eval_samples_per_second": 13.589,
      "eval_steps_per_second": 1.989,
      "step": 63
    },
    {
      "epoch": 2.7216494845360826,
      "grad_norm": 1.3034956455230713,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.8017,
      "step": 66
    },
    {
      "epoch": 2.845360824742268,
      "grad_norm": 1.2311569452285767,
      "learning_rate": 9.913756075728087e-07,
      "loss": 0.8266,
      "step": 69
    },
    {
      "epoch": 2.88659793814433,
      "eval_loss": 1.205170750617981,
      "eval_runtime": 3.0134,
      "eval_samples_per_second": 13.606,
      "eval_steps_per_second": 1.991,
      "step": 70
    }
  ],
  "logging_steps": 3,
  "max_steps": 73,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 7,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0340054014623744e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}