{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.013688917767997247,
      "learning_rate": 2e-05,
      "loss": 0.2377,
      "step": 1
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.013044702711837308,
      "learning_rate": 4e-05,
      "loss": 0.2193,
      "step": 2
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.01195549314705343,
      "learning_rate": 6.000000000000001e-05,
      "loss": 0.2472,
      "step": 3
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.013993680621594439,
      "learning_rate": 8e-05,
      "loss": 0.2282,
      "step": 4
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.01615174667606147,
      "learning_rate": 7.983897175980957e-05,
      "loss": 0.215,
      "step": 5
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.021585137184598355,
      "learning_rate": 7.93571835439452e-05,
      "loss": 0.1857,
      "step": 6
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.01908734543124658,
      "learning_rate": 7.855851442783414e-05,
      "loss": 0.2083,
      "step": 7
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.012842430589925161,
      "learning_rate": 7.74493948255895e-05,
      "loss": 0.2184,
      "step": 8
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.01165067546553439,
      "learning_rate": 7.603875471609677e-05,
      "loss": 0.1985,
      "step": 9
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.015346040117118166,
      "learning_rate": 7.433795174407465e-05,
      "loss": 0.1947,
      "step": 10
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.02124485539227202,
      "learning_rate": 7.236067977499791e-05,
      "loss": 0.2397,
      "step": 11
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.023862835250197997,
      "learning_rate": 7.012285864014445e-05,
      "loss": 0.2005,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.020622133901439132,
      "learning_rate": 6.76425059594746e-05,
      "loss": 0.1935,
      "step": 13
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.0127068327256986,
      "learning_rate": 6.493959207434934e-05,
      "loss": 0.2005,
      "step": 14
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 0.009353212751999008,
      "learning_rate": 6.20358792580841e-05,
      "loss": 0.1944,
      "step": 15
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.008113229006924183,
      "learning_rate": 5.895474649891995e-05,
      "loss": 0.1837,
      "step": 16
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.007965014572487397,
      "learning_rate": 5.572100126615695e-05,
      "loss": 0.1998,
      "step": 17
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.00932427738920718,
      "learning_rate": 5.23606797749979e-05,
      "loss": 0.1883,
      "step": 18
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.009162009614029023,
      "learning_rate": 4.890083735825258e-05,
      "loss": 0.1732,
      "step": 19
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.009443684882688904,
      "learning_rate": 4.5369330632706223e-05,
      "loss": 0.1933,
      "step": 20
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.010312591479874733,
      "learning_rate": 4.17945932140206e-05,
      "loss": 0.1618,
      "step": 21
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.010692703682913874,
      "learning_rate": 3.820540678597942e-05,
      "loss": 0.1624,
      "step": 22
    },
    {
      "epoch": 1.7692307692307692,
      "grad_norm": 0.010215195041087853,
      "learning_rate": 3.4630669367293797e-05,
      "loss": 0.1799,
      "step": 23
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.009919177893052678,
      "learning_rate": 3.109916264174743e-05,
      "loss": 0.163,
      "step": 24
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.009732551047429282,
      "learning_rate": 2.7639320225002108e-05,
      "loss": 0.1564,
      "step": 25
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.010114890113896807,
      "learning_rate": 2.427899873384306e-05,
      "loss": 0.1671,
      "step": 26
    },
    {
      "epoch": 2.076923076923077,
      "grad_norm": 0.008348766016583242,
      "learning_rate": 2.1045253501080058e-05,
      "loss": 0.168,
      "step": 27
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.007364694056744346,
      "learning_rate": 1.7964120741915905e-05,
      "loss": 0.1651,
      "step": 28
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.007478361889654999,
      "learning_rate": 1.5060407925650662e-05,
      "loss": 0.1856,
      "step": 29
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.007384767210156832,
      "learning_rate": 1.2357494040525416e-05,
      "loss": 0.1822,
      "step": 30
    },
    {
      "epoch": 2.3846153846153846,
      "grad_norm": 0.007684065844376266,
      "learning_rate": 9.877141359855567e-06,
      "loss": 0.1525,
      "step": 31
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.007647488017693971,
      "learning_rate": 7.639320225002106e-06,
      "loss": 0.142,
      "step": 32
    },
    {
      "epoch": 2.5384615384615383,
      "grad_norm": 0.007548385731849388,
      "learning_rate": 5.662048255925357e-06,
      "loss": 0.1545,
      "step": 33
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.00738070644714142,
      "learning_rate": 3.961245283903239e-06,
      "loss": 0.1879,
      "step": 34
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.006831313367281853,
      "learning_rate": 2.550605174410512e-06,
      "loss": 0.1555,
      "step": 35
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.007289613113738482,
      "learning_rate": 1.4414855721658705e-06,
      "loss": 0.1448,
      "step": 36
    },
    {
      "epoch": 2.8461538461538463,
      "grad_norm": 0.007230609075304686,
      "learning_rate": 6.428164560548134e-07,
      "loss": 0.1496,
      "step": 37
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.007399385285996099,
      "learning_rate": 1.6102824019043728e-07,
      "loss": 0.1413,
      "step": 38
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.007095584428279655,
      "learning_rate": 0.0,
      "loss": 0.1657,
      "step": 39
    },
    {
      "epoch": 3.0,
      "step": 39,
      "total_flos": 87871145639936.0,
      "train_loss": 0.18475643105995962,
      "train_runtime": 1149.6371,
      "train_samples_per_second": 0.522,
      "train_steps_per_second": 0.034
    }
  ],
  "logging_steps": 1,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 87871145639936.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}