{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 59,
  "global_step": 236,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00423728813559322,
      "eval_loss": 1.7249085903167725,
      "eval_runtime": 8.4443,
      "eval_samples_per_second": 11.842,
      "eval_steps_per_second": 5.921,
      "step": 1
    },
    {
      "epoch": 0.0211864406779661,
      "grad_norm": 0.34860244393348694,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.3692,
      "step": 5
    },
    {
      "epoch": 0.0423728813559322,
      "grad_norm": 0.24737317860126495,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.7379,
      "step": 10
    },
    {
      "epoch": 0.0635593220338983,
      "grad_norm": 0.3292003571987152,
      "learning_rate": 5e-05,
      "loss": 1.8021,
      "step": 15
    },
    {
      "epoch": 0.0847457627118644,
      "grad_norm": 0.5094640851020813,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.7655,
      "step": 20
    },
    {
      "epoch": 0.1059322033898305,
      "grad_norm": 0.5904861688613892,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.7297,
      "step": 25
    },
    {
      "epoch": 0.1271186440677966,
      "grad_norm": 0.7554088830947876,
      "learning_rate": 0.0001,
      "loss": 1.6078,
      "step": 30
    },
    {
      "epoch": 0.1483050847457627,
      "grad_norm": 0.5578835606575012,
      "learning_rate": 9.985471028179154e-05,
      "loss": 1.6425,
      "step": 35
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 0.6163862943649292,
      "learning_rate": 9.941968549125481e-05,
      "loss": 1.5532,
      "step": 40
    },
    {
      "epoch": 0.1906779661016949,
      "grad_norm": 0.7516969442367554,
      "learning_rate": 9.869745381355906e-05,
      "loss": 1.7323,
      "step": 45
    },
    {
      "epoch": 0.211864406779661,
      "grad_norm": 2.109365940093994,
      "learning_rate": 9.769221256218164e-05,
      "loss": 1.5351,
      "step": 50
    },
    {
      "epoch": 0.2330508474576271,
      "grad_norm": 0.44315698742866516,
      "learning_rate": 9.64098037858483e-05,
      "loss": 1.2733,
      "step": 55
    },
    {
      "epoch": 0.25,
      "eval_loss": 1.4840701818466187,
      "eval_runtime": 8.6604,
      "eval_samples_per_second": 11.547,
      "eval_steps_per_second": 5.773,
      "step": 59
    },
    {
      "epoch": 0.2542372881355932,
      "grad_norm": 0.3630428910255432,
      "learning_rate": 9.485768031694872e-05,
      "loss": 1.5799,
      "step": 60
    },
    {
      "epoch": 0.2754237288135593,
      "grad_norm": 0.3667657673358917,
      "learning_rate": 9.304486245873972e-05,
      "loss": 1.6658,
      "step": 65
    },
    {
      "epoch": 0.2966101694915254,
      "grad_norm": 0.5239521265029907,
      "learning_rate": 9.098188556305263e-05,
      "loss": 1.793,
      "step": 70
    },
    {
      "epoch": 0.3177966101694915,
      "grad_norm": 0.4729391932487488,
      "learning_rate": 8.868073880316124e-05,
      "loss": 1.5419,
      "step": 75
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 0.46771642565727234,
      "learning_rate": 8.615479549763756e-05,
      "loss": 1.7167,
      "step": 80
    },
    {
      "epoch": 0.3601694915254237,
      "grad_norm": 0.6532709002494812,
      "learning_rate": 8.341873539012444e-05,
      "loss": 1.5274,
      "step": 85
    },
    {
      "epoch": 0.3813559322033898,
      "grad_norm": 0.7305452227592468,
      "learning_rate": 8.048845933670273e-05,
      "loss": 1.5357,
      "step": 90
    },
    {
      "epoch": 0.4025423728813559,
      "grad_norm": 0.9167357683181763,
      "learning_rate": 7.73809968966554e-05,
      "loss": 1.3621,
      "step": 95
    },
    {
      "epoch": 0.423728813559322,
      "grad_norm": 1.8313207626342773,
      "learning_rate": 7.411440736367281e-05,
      "loss": 1.4205,
      "step": 100
    },
    {
      "epoch": 0.4449152542372881,
      "grad_norm": 0.38461220264434814,
      "learning_rate": 7.070767481266492e-05,
      "loss": 1.1588,
      "step": 105
    },
    {
      "epoch": 0.4661016949152542,
      "grad_norm": 0.3785201907157898,
      "learning_rate": 6.718059777212567e-05,
      "loss": 1.5231,
      "step": 110
    },
    {
      "epoch": 0.4872881355932203,
      "grad_norm": 0.4216236472129822,
      "learning_rate": 6.355367416322779e-05,
      "loss": 1.662,
      "step": 115
    },
    {
      "epoch": 0.5,
      "eval_loss": 1.4526076316833496,
      "eval_runtime": 8.5518,
      "eval_samples_per_second": 11.693,
      "eval_steps_per_second": 5.847,
      "step": 118
    },
    {
      "epoch": 0.5084745762711864,
      "grad_norm": 0.45605048537254333,
      "learning_rate": 5.9847982174335316e-05,
      "loss": 1.7207,
      "step": 120
    },
    {
      "epoch": 0.5296610169491526,
      "grad_norm": 0.4846043288707733,
      "learning_rate": 5.608505776324158e-05,
      "loss": 1.4496,
      "step": 125
    },
    {
      "epoch": 0.5508474576271186,
      "grad_norm": 0.6062460541725159,
      "learning_rate": 5.228676949903973e-05,
      "loss": 1.5234,
      "step": 130
    },
    {
      "epoch": 0.5720338983050848,
      "grad_norm": 0.5876784324645996,
      "learning_rate": 4.847519147099294e-05,
      "loss": 1.4498,
      "step": 135
    },
    {
      "epoch": 0.5932203389830508,
      "grad_norm": 0.6600533723831177,
      "learning_rate": 4.46724750030062e-05,
      "loss": 1.6008,
      "step": 140
    },
    {
      "epoch": 0.614406779661017,
      "grad_norm": 0.8463802933692932,
      "learning_rate": 4.0900719919241935e-05,
      "loss": 1.4843,
      "step": 145
    },
    {
      "epoch": 0.635593220338983,
      "grad_norm": 1.585313081741333,
      "learning_rate": 3.7181846109031005e-05,
      "loss": 1.6269,
      "step": 150
    },
    {
      "epoch": 0.6567796610169492,
      "grad_norm": 0.3185465931892395,
      "learning_rate": 3.353746613749094e-05,
      "loss": 1.1721,
      "step": 155
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 0.3304313123226166,
      "learning_rate": 2.9988759642186097e-05,
      "loss": 1.3918,
      "step": 160
    },
    {
      "epoch": 0.6991525423728814,
      "grad_norm": 0.35727110505104065,
      "learning_rate": 2.6556350245784833e-05,
      "loss": 1.6054,
      "step": 165
    },
    {
      "epoch": 0.7203389830508474,
      "grad_norm": 0.41722163558006287,
      "learning_rate": 2.3260185700046294e-05,
      "loss": 1.612,
      "step": 170
    },
    {
      "epoch": 0.7415254237288136,
      "grad_norm": 0.44186127185821533,
      "learning_rate": 2.011942195769122e-05,
      "loss": 1.3327,
      "step": 175
    },
    {
      "epoch": 0.75,
      "eval_loss": 1.4384088516235352,
      "eval_runtime": 8.6854,
      "eval_samples_per_second": 11.514,
      "eval_steps_per_second": 5.757,
      "step": 177
    },
    {
      "epoch": 0.7627118644067796,
      "grad_norm": 0.5537221431732178,
      "learning_rate": 1.7152311845883095e-05,
      "loss": 1.4988,
      "step": 180
    },
    {
      "epoch": 0.7838983050847458,
      "grad_norm": 0.676834762096405,
      "learning_rate": 1.4376098988303405e-05,
      "loss": 1.3876,
      "step": 185
    },
    {
      "epoch": 0.8050847457627118,
      "grad_norm": 0.6886051297187805,
      "learning_rate": 1.1806917592302762e-05,
      "loss": 1.6185,
      "step": 190
    },
    {
      "epoch": 0.826271186440678,
      "grad_norm": 0.9627895951271057,
      "learning_rate": 9.459698683523204e-06,
      "loss": 1.4325,
      "step": 195
    },
    {
      "epoch": 0.847457627118644,
      "grad_norm": 1.889673113822937,
      "learning_rate": 7.348083332917926e-06,
      "loss": 1.5114,
      "step": 200
    },
    {
      "epoch": 0.8686440677966102,
      "grad_norm": 0.32479622960090637,
      "learning_rate": 5.484343380457125e-06,
      "loss": 1.3119,
      "step": 205
    },
    {
      "epoch": 0.8898305084745762,
      "grad_norm": 0.4083038568496704,
      "learning_rate": 3.879310116241042e-06,
      "loss": 1.5227,
      "step": 210
    },
    {
      "epoch": 0.9110169491525424,
      "grad_norm": 0.42401042580604553,
      "learning_rate": 2.542311333496622e-06,
      "loss": 1.4954,
      "step": 215
    },
    {
      "epoch": 0.9322033898305084,
      "grad_norm": 0.542686402797699,
      "learning_rate": 1.4811171192794627e-06,
      "loss": 1.5561,
      "step": 220
    },
    {
      "epoch": 0.9533898305084746,
      "grad_norm": 0.6815149784088135,
      "learning_rate": 7.018946979234997e-07,
      "loss": 1.4592,
      "step": 225
    },
    {
      "epoch": 0.9745762711864406,
      "grad_norm": 0.6367012858390808,
      "learning_rate": 2.0917258966953733e-07,
      "loss": 1.5196,
      "step": 230
    },
    {
      "epoch": 0.9957627118644068,
      "grad_norm": 1.104602575302124,
      "learning_rate": 5.814292768108187e-09,
      "loss": 1.5794,
      "step": 235
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.404936671257019,
      "eval_runtime": 8.6769,
      "eval_samples_per_second": 11.525,
      "eval_steps_per_second": 5.762,
      "step": 236
    }
  ],
  "logging_steps": 5,
  "max_steps": 236,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 8.267951517990912e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}