{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9937888198757764,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024844720496894408,
      "grad_norm": 0.22360646249577132,
      "learning_rate": 0.0001,
      "loss": 0.3155,
      "step": 1
    },
    {
      "epoch": 0.049689440993788817,
      "grad_norm": 1.6354713380395525,
      "learning_rate": 0.0001,
      "loss": 0.4894,
      "step": 2
    },
    {
      "epoch": 0.07453416149068323,
      "grad_norm": 21.686343056691,
      "learning_rate": 0.0001,
      "loss": 5.1274,
      "step": 3
    },
    {
      "epoch": 0.09937888198757763,
      "grad_norm": 14.478086289344557,
      "learning_rate": 0.0001,
      "loss": 0.6788,
      "step": 4
    },
    {
      "epoch": 0.12422360248447205,
      "grad_norm": 10.40331474659814,
      "learning_rate": 0.0001,
      "loss": 0.7381,
      "step": 5
    },
    {
      "epoch": 0.14906832298136646,
      "grad_norm": 14.828952914633255,
      "learning_rate": 0.0001,
      "loss": 1.0551,
      "step": 6
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 1.0287292990470505,
      "learning_rate": 0.0001,
      "loss": 0.4616,
      "step": 7
    },
    {
      "epoch": 0.19875776397515527,
      "grad_norm": 4.424881730530812,
      "learning_rate": 0.0001,
      "loss": 0.7389,
      "step": 8
    },
    {
      "epoch": 0.2236024844720497,
      "grad_norm": 1.5788138903378481,
      "learning_rate": 0.0001,
      "loss": 0.5233,
      "step": 9
    },
    {
      "epoch": 0.2484472049689441,
      "grad_norm": 1.6155451789191035,
      "learning_rate": 0.0001,
      "loss": 0.4922,
      "step": 10
    },
    {
      "epoch": 0.2732919254658385,
      "grad_norm": 53.16385537396071,
      "learning_rate": 0.0001,
      "loss": 1.0959,
      "step": 11
    },
    {
      "epoch": 0.2981366459627329,
      "grad_norm": 2.0002784882087092,
      "learning_rate": 0.0001,
      "loss": 0.6879,
      "step": 12
    },
    {
      "epoch": 0.32298136645962733,
      "grad_norm": 1.1683199154602835,
      "learning_rate": 0.0001,
      "loss": 0.4369,
      "step": 13
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 1.033205019062668,
      "learning_rate": 0.0001,
      "loss": 0.3917,
      "step": 14
    },
    {
      "epoch": 0.37267080745341613,
      "grad_norm": 0.4412023447127328,
      "learning_rate": 0.0001,
      "loss": 0.3448,
      "step": 15
    },
    {
      "epoch": 0.39751552795031053,
      "grad_norm": 0.9578202521179224,
      "learning_rate": 0.0001,
      "loss": 0.3459,
      "step": 16
    },
    {
      "epoch": 0.422360248447205,
      "grad_norm": 2.289275193987449,
      "learning_rate": 0.0001,
      "loss": 0.534,
      "step": 17
    },
    {
      "epoch": 0.4472049689440994,
      "grad_norm": 0.6666094964330221,
      "learning_rate": 0.0001,
      "loss": 0.3535,
      "step": 18
    },
    {
      "epoch": 0.4720496894409938,
      "grad_norm": 0.7930206978533701,
      "learning_rate": 0.0001,
      "loss": 0.3496,
      "step": 19
    },
    {
      "epoch": 0.4968944099378882,
      "grad_norm": 0.3055608278925833,
      "learning_rate": 0.0001,
      "loss": 0.3339,
      "step": 20
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.29784796389686363,
      "learning_rate": 0.0001,
      "loss": 0.31,
      "step": 21
    },
    {
      "epoch": 0.546583850931677,
      "grad_norm": 0.21503207187750886,
      "learning_rate": 0.0001,
      "loss": 0.2922,
      "step": 22
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.15247931417135197,
      "learning_rate": 0.0001,
      "loss": 0.292,
      "step": 23
    },
    {
      "epoch": 0.5962732919254659,
      "grad_norm": 0.19200002221931217,
      "learning_rate": 0.0001,
      "loss": 0.2937,
      "step": 24
    },
    {
      "epoch": 0.6211180124223602,
      "grad_norm": 0.12937354448998015,
      "learning_rate": 0.0001,
      "loss": 0.2701,
      "step": 25
    },
    {
      "epoch": 0.6459627329192547,
      "grad_norm": 0.7041267128561529,
      "learning_rate": 0.0001,
      "loss": 0.2806,
      "step": 26
    },
    {
      "epoch": 0.6708074534161491,
      "grad_norm": 0.1703017837650162,
      "learning_rate": 0.0001,
      "loss": 0.2733,
      "step": 27
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.1670950080367148,
      "learning_rate": 0.0001,
      "loss": 0.2691,
      "step": 28
    },
    {
      "epoch": 0.7204968944099379,
      "grad_norm": 0.15191029267235273,
      "learning_rate": 0.0001,
      "loss": 0.2611,
      "step": 29
    },
    {
      "epoch": 0.7453416149068323,
      "grad_norm": 0.10352109095733353,
      "learning_rate": 0.0001,
      "loss": 0.2764,
      "step": 30
    },
    {
      "epoch": 0.7701863354037267,
      "grad_norm": 0.11621572352545091,
      "learning_rate": 0.0001,
      "loss": 0.259,
      "step": 31
    },
    {
      "epoch": 0.7950310559006211,
      "grad_norm": 0.1047835528239364,
      "learning_rate": 0.0001,
      "loss": 0.2507,
      "step": 32
    },
    {
      "epoch": 0.8198757763975155,
      "grad_norm": 0.10515270423855971,
      "learning_rate": 0.0001,
      "loss": 0.2743,
      "step": 33
    },
    {
      "epoch": 0.84472049689441,
      "grad_norm": 0.05663550910043551,
      "learning_rate": 0.0001,
      "loss": 0.2565,
      "step": 34
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.09940447058540708,
      "learning_rate": 0.0001,
      "loss": 0.2558,
      "step": 35
    },
    {
      "epoch": 0.8944099378881988,
      "grad_norm": 0.09817461399434704,
      "learning_rate": 0.0001,
      "loss": 0.2483,
      "step": 36
    },
    {
      "epoch": 0.9192546583850931,
      "grad_norm": 0.06027821970777435,
      "learning_rate": 0.0001,
      "loss": 0.2516,
      "step": 37
    },
    {
      "epoch": 0.9440993788819876,
      "grad_norm": 0.08188481055174467,
      "learning_rate": 0.0001,
      "loss": 0.2305,
      "step": 38
    },
    {
      "epoch": 0.968944099378882,
      "grad_norm": 0.09993015738582685,
      "learning_rate": 0.0001,
      "loss": 0.2559,
      "step": 39
    },
    {
      "epoch": 0.9937888198757764,
      "grad_norm": 0.09361624235588561,
      "learning_rate": 0.0001,
      "loss": 0.2556,
      "step": 40
    },
    {
      "epoch": 0.9937888198757764,
      "step": 40,
      "total_flos": 55331389440000.0,
      "train_loss": 0.5212820250540972,
      "train_runtime": 2252.6119,
      "train_samples_per_second": 3.42,
      "train_steps_per_second": 0.018
    }
  ],
  "logging_steps": 1,
  "max_steps": 40,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 55331389440000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}