trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9988649262202043,
  "eval_steps": 6,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05448354143019296,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.073,
      "step": 6
    },
    {
      "epoch": 0.10896708286038592,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.039,
      "step": 12
    },
    {
      "epoch": 0.16345062429057888,
      "grad_norm": 0.44932249188423157,
      "learning_rate": 0.0016329931618554523,
      "loss": 1.0353,
      "step": 18
    },
    {
      "epoch": 0.21793416572077184,
      "grad_norm": 0.7056324481964111,
      "learning_rate": 0.001,
      "loss": 0.9232,
      "step": 24
    },
    {
      "epoch": 0.2724177071509648,
      "grad_norm": 0.21584172546863556,
      "learning_rate": 0.0007559289460184544,
      "loss": 0.7909,
      "step": 30
    },
    {
      "epoch": 0.32690124858115777,
      "grad_norm": 0.19453680515289307,
      "learning_rate": 0.0006324555320336759,
      "loss": 0.7352,
      "step": 36
    },
    {
      "epoch": 0.3813847900113507,
      "grad_norm": 0.19031628966331482,
      "learning_rate": 0.0005547001962252292,
      "loss": 0.7123,
      "step": 42
    },
    {
      "epoch": 0.4358683314415437,
      "grad_norm": 0.1654825061559677,
      "learning_rate": 0.0005,
      "loss": 0.6918,
      "step": 48
    },
    {
      "epoch": 0.49035187287173665,
      "grad_norm": 0.1845771223306656,
      "learning_rate": 0.0004588314677411235,
      "loss": 0.7118,
      "step": 54
    },
    {
      "epoch": 0.5448354143019296,
      "grad_norm": 0.19587676227092743,
      "learning_rate": 0.00042640143271122083,
      "loss": 0.6994,
      "step": 60
    },
    {
      "epoch": 0.5993189557321226,
      "grad_norm": 0.20122814178466797,
      "learning_rate": 0.0004,
      "loss": 0.672,
      "step": 66
    },
    {
      "epoch": 0.6538024971623155,
      "grad_norm": 0.21745193004608154,
      "learning_rate": 0.0003779644730092272,
      "loss": 0.6553,
      "step": 72
    },
    {
      "epoch": 0.7082860385925085,
      "grad_norm": 0.17879709601402283,
      "learning_rate": 0.00035921060405354985,
      "loss": 0.6807,
      "step": 78
    },
    {
      "epoch": 0.7627695800227015,
      "grad_norm": 0.18536536395549774,
      "learning_rate": 0.00034299717028501764,
      "loss": 0.6738,
      "step": 84
    },
    {
      "epoch": 0.8172531214528944,
      "grad_norm": 0.20840761065483093,
      "learning_rate": 0.0003287979746107146,
      "loss": 0.669,
      "step": 90
    },
    {
      "epoch": 0.8717366628830874,
      "grad_norm": 0.16762040555477142,
      "learning_rate": 0.00031622776601683794,
      "loss": 0.6734,
      "step": 96
    },
    {
      "epoch": 0.9262202043132803,
      "grad_norm": 0.16556385159492493,
      "learning_rate": 0.00030499714066520935,
      "loss": 0.6661,
      "step": 102
    },
    {
      "epoch": 0.9807037457434733,
      "grad_norm": 0.1867838054895401,
      "learning_rate": 0.0002948839123097943,
      "loss": 0.6784,
      "step": 108
    },
    {
      "epoch": 0.9988649262202043,
      "step": 110,
      "total_flos": 1.1172110162041242e+18,
      "train_loss": 0.7636631564660505,
      "train_runtime": 975.3131,
      "train_samples_per_second": 14.451,
      "train_steps_per_second": 0.113
    }
  ],
  "logging_steps": 6,
  "max_steps": 110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 6,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1172110162041242e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}