{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 439,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04555808656036447,
      "grad_norm": 0.5296587944030762,
      "learning_rate": 9.948875483893885e-05,
      "loss": 0.3433,
      "step": 20
    },
    {
      "epoch": 0.09111617312072894,
      "grad_norm": 0.042843956500291824,
      "learning_rate": 9.796547422034374e-05,
      "loss": 0.0076,
      "step": 40
    },
    {
      "epoch": 0.11389521640091116,
      "eval_loss": 0.005896100774407387,
      "eval_runtime": 122.4009,
      "eval_samples_per_second": 7.957,
      "eval_steps_per_second": 0.4,
      "step": 50
    },
    {
      "epoch": 0.1366742596810934,
      "grad_norm": 0.04506906867027283,
      "learning_rate": 9.546130893802246e-05,
      "loss": 0.006,
      "step": 60
    },
    {
      "epoch": 0.18223234624145787,
      "grad_norm": 0.04249206930398941,
      "learning_rate": 9.20274686872984e-05,
      "loss": 0.006,
      "step": 80
    },
    {
      "epoch": 0.22779043280182232,
      "grad_norm": 0.034582458436489105,
      "learning_rate": 8.773417483665309e-05,
      "loss": 0.0054,
      "step": 100
    },
    {
      "epoch": 0.22779043280182232,
      "eval_loss": 0.004958716221153736,
      "eval_runtime": 122.3931,
      "eval_samples_per_second": 7.958,
      "eval_steps_per_second": 0.4,
      "step": 100
    },
    {
      "epoch": 0.2733485193621868,
      "grad_norm": 0.09121271967887878,
      "learning_rate": 8.266922441433284e-05,
      "loss": 0.0043,
      "step": 120
    },
    {
      "epoch": 0.31890660592255127,
      "grad_norm": 0.025009050965309143,
      "learning_rate": 7.693619467611464e-05,
      "loss": 0.0041,
      "step": 140
    },
    {
      "epoch": 0.3416856492027335,
      "eval_loss": 0.0036018535029143095,
      "eval_runtime": 122.4383,
      "eval_samples_per_second": 7.955,
      "eval_steps_per_second": 0.4,
      "step": 150
    },
    {
      "epoch": 0.36446469248291574,
      "grad_norm": 0.06171397864818573,
      "learning_rate": 7.065232497047384e-05,
      "loss": 0.0036,
      "step": 160
    },
    {
      "epoch": 0.41002277904328016,
      "grad_norm": 0.0585937425494194,
      "learning_rate": 6.394611921660036e-05,
      "loss": 0.003,
      "step": 180
    },
    {
      "epoch": 0.45558086560364464,
      "grad_norm": 0.03573513403534889,
      "learning_rate": 5.695471802412413e-05,
      "loss": 0.0026,
      "step": 200
    },
    {
      "epoch": 0.45558086560364464,
      "eval_loss": 0.0025479402393102646,
      "eval_runtime": 122.4406,
      "eval_samples_per_second": 7.955,
      "eval_steps_per_second": 0.4,
      "step": 200
    },
    {
      "epoch": 0.5011389521640092,
      "grad_norm": 0.08403529226779938,
      "learning_rate": 4.982109419419277e-05,
      "loss": 0.0023,
      "step": 220
    },
    {
      "epoch": 0.5466970387243736,
      "grad_norm": 0.08128103613853455,
      "learning_rate": 4.269112895336161e-05,
      "loss": 0.0025,
      "step": 240
    },
    {
      "epoch": 0.5694760820045558,
      "eval_loss": 0.002369565423578024,
      "eval_runtime": 122.4121,
      "eval_samples_per_second": 7.957,
      "eval_steps_per_second": 0.4,
      "step": 250
    },
    {
      "epoch": 0.592255125284738,
      "grad_norm": 0.04797542467713356,
      "learning_rate": 3.5710628710747e-05,
      "loss": 0.0025,
      "step": 260
    },
    {
      "epoch": 0.6378132118451025,
      "grad_norm": 0.041951198130846024,
      "learning_rate": 2.9022343345181846e-05,
      "loss": 0.0022,
      "step": 280
    },
    {
      "epoch": 0.683371298405467,
      "grad_norm": 0.03911906108260155,
      "learning_rate": 2.276304699782381e-05,
      "loss": 0.0022,
      "step": 300
    },
    {
      "epoch": 0.683371298405467,
      "eval_loss": 0.0020905383862555027,
      "eval_runtime": 122.4348,
      "eval_samples_per_second": 7.955,
      "eval_steps_per_second": 0.4,
      "step": 300
    },
    {
      "epoch": 0.7289293849658315,
      "grad_norm": 0.07351183891296387,
      "learning_rate": 1.7060741067442288e-05,
      "loss": 0.0021,
      "step": 320
    },
    {
      "epoch": 0.7744874715261959,
      "grad_norm": 0.06717297434806824,
      "learning_rate": 1.2032036606589175e-05,
      "loss": 0.0022,
      "step": 340
    },
    {
      "epoch": 0.7972665148063781,
      "eval_loss": 0.0018556159920990467,
      "eval_runtime": 122.4481,
      "eval_samples_per_second": 7.954,
      "eval_steps_per_second": 0.4,
      "step": 350
    },
    {
      "epoch": 0.8200455580865603,
      "grad_norm": 0.03857114166021347,
      "learning_rate": 7.779769648145201e-06,
      "loss": 0.0015,
      "step": 360
    },
    {
      "epoch": 0.8656036446469249,
      "grad_norm": 0.036848343908786774,
      "learning_rate": 4.390898228352131e-06,
      "loss": 0.0018,
      "step": 380
    },
    {
      "epoch": 0.9111617312072893,
      "grad_norm": 0.09445371478796005,
      "learning_rate": 1.9347241118030823e-06,
      "loss": 0.0021,
      "step": 400
    },
    {
      "epoch": 0.9111617312072893,
      "eval_loss": 0.0018473172094672918,
      "eval_runtime": 122.4479,
      "eval_samples_per_second": 7.954,
      "eval_steps_per_second": 0.4,
      "step": 400
    },
    {
      "epoch": 0.9567198177676538,
      "grad_norm": 0.04989920184016228,
      "learning_rate": 4.614755837704321e-07,
      "loss": 0.0018,
      "step": 420
    },
    {
      "epoch": 1.0,
      "step": 439,
      "total_flos": 9.38862713986089e+17,
      "train_loss": 0.018706909701194197,
      "train_runtime": 4591.0233,
      "train_samples_per_second": 1.909,
      "train_steps_per_second": 0.096
    }
  ],
  "logging_steps": 20,
  "max_steps": 439,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.38862713986089e+17,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}