{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09861932938856016,
  "eval_steps": 3,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0039447731755424065,
      "grad_norm": 12.976507186889648,
      "learning_rate": 2e-05,
      "loss": 4.4657,
      "step": 1
    },
    {
      "epoch": 0.0039447731755424065,
      "eval_loss": 4.758858680725098,
      "eval_runtime": 55.6388,
      "eval_samples_per_second": 3.846,
      "eval_steps_per_second": 1.923,
      "step": 1
    },
    {
      "epoch": 0.007889546351084813,
      "grad_norm": 13.14622688293457,
      "learning_rate": 4e-05,
      "loss": 4.9917,
      "step": 2
    },
    {
      "epoch": 0.011834319526627219,
      "grad_norm": 12.798720359802246,
      "learning_rate": 6e-05,
      "loss": 4.6799,
      "step": 3
    },
    {
      "epoch": 0.011834319526627219,
      "eval_loss": 4.390668869018555,
      "eval_runtime": 55.6508,
      "eval_samples_per_second": 3.845,
      "eval_steps_per_second": 1.923,
      "step": 3
    },
    {
      "epoch": 0.015779092702169626,
      "grad_norm": 14.236764907836914,
      "learning_rate": 8e-05,
      "loss": 4.4007,
      "step": 4
    },
    {
      "epoch": 0.01972386587771203,
      "grad_norm": 13.787552833557129,
      "learning_rate": 0.0001,
      "loss": 3.3517,
      "step": 5
    },
    {
      "epoch": 0.023668639053254437,
      "grad_norm": 8.283570289611816,
      "learning_rate": 0.00012,
      "loss": 2.134,
      "step": 6
    },
    {
      "epoch": 0.023668639053254437,
      "eval_loss": 1.3221015930175781,
      "eval_runtime": 22.4177,
      "eval_samples_per_second": 9.546,
      "eval_steps_per_second": 4.773,
      "step": 6
    },
    {
      "epoch": 0.027613412228796843,
      "grad_norm": 8.216385841369629,
      "learning_rate": 0.00014,
      "loss": 1.2896,
      "step": 7
    },
    {
      "epoch": 0.03155818540433925,
      "grad_norm": 6.406145095825195,
      "learning_rate": 0.00016,
      "loss": 0.8047,
      "step": 8
    },
    {
      "epoch": 0.03550295857988166,
      "grad_norm": 3.431140661239624,
      "learning_rate": 0.00018,
      "loss": 0.3771,
      "step": 9
    },
    {
      "epoch": 0.03550295857988166,
      "eval_loss": 0.2606837749481201,
      "eval_runtime": 22.2961,
      "eval_samples_per_second": 9.598,
      "eval_steps_per_second": 4.799,
      "step": 9
    },
    {
      "epoch": 0.03944773175542406,
      "grad_norm": 2.6710612773895264,
      "learning_rate": 0.0002,
      "loss": 0.3443,
      "step": 10
    },
    {
      "epoch": 0.04339250493096647,
      "grad_norm": 3.338960886001587,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.3629,
      "step": 11
    },
    {
      "epoch": 0.047337278106508875,
      "grad_norm": 3.4746296405792236,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.3309,
      "step": 12
    },
    {
      "epoch": 0.047337278106508875,
      "eval_loss": 0.21770305931568146,
      "eval_runtime": 22.2279,
      "eval_samples_per_second": 9.628,
      "eval_steps_per_second": 4.814,
      "step": 12
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 1.2108609676361084,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.1741,
      "step": 13
    },
    {
      "epoch": 0.055226824457593686,
      "grad_norm": 1.4882214069366455,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.18,
      "step": 14
    },
    {
      "epoch": 0.05917159763313609,
      "grad_norm": 1.1287225484848022,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.2078,
      "step": 15
    },
    {
      "epoch": 0.05917159763313609,
      "eval_loss": 0.19682614505290985,
      "eval_runtime": 22.1862,
      "eval_samples_per_second": 9.646,
      "eval_steps_per_second": 4.823,
      "step": 15
    },
    {
      "epoch": 0.0631163708086785,
      "grad_norm": 1.3745402097702026,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.3157,
      "step": 16
    },
    {
      "epoch": 0.0670611439842209,
      "grad_norm": 1.2767657041549683,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.2803,
      "step": 17
    },
    {
      "epoch": 0.07100591715976332,
      "grad_norm": 0.49950045347213745,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0943,
      "step": 18
    },
    {
      "epoch": 0.07100591715976332,
      "eval_loss": 0.21179427206516266,
      "eval_runtime": 22.2542,
      "eval_samples_per_second": 9.616,
      "eval_steps_per_second": 4.808,
      "step": 18
    },
    {
      "epoch": 0.07495069033530571,
      "grad_norm": 1.7894467115402222,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.2785,
      "step": 19
    },
    {
      "epoch": 0.07889546351084813,
      "grad_norm": 0.9164059162139893,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.209,
      "step": 20
    },
    {
      "epoch": 0.08284023668639054,
      "grad_norm": 1.0299311876296997,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.2146,
      "step": 21
    },
    {
      "epoch": 0.08284023668639054,
      "eval_loss": 0.18857908248901367,
      "eval_runtime": 22.4293,
      "eval_samples_per_second": 9.541,
      "eval_steps_per_second": 4.771,
      "step": 21
    },
    {
      "epoch": 0.08678500986193294,
      "grad_norm": 0.6787167191505432,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.1958,
      "step": 22
    },
    {
      "epoch": 0.09072978303747535,
      "grad_norm": 0.8082757592201233,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.2158,
      "step": 23
    },
    {
      "epoch": 0.09467455621301775,
      "grad_norm": 1.5938321352005005,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.2725,
      "step": 24
    },
    {
      "epoch": 0.09467455621301775,
      "eval_loss": 0.19068406522274017,
      "eval_runtime": 22.3143,
      "eval_samples_per_second": 9.59,
      "eval_steps_per_second": 4.795,
      "step": 24
    },
    {
      "epoch": 0.09861932938856016,
      "grad_norm": 0.9700214266777039,
      "learning_rate": 0.0,
      "loss": 0.1544,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.26729302278144e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}