trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4756242568370987,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03170828378913991,
      "grad_norm": 11.620649337768555,
      "learning_rate": 0.00011399999999999999,
      "loss": 7.7223,
      "step": 20
    },
    {
      "epoch": 0.06341656757827982,
      "grad_norm": 1.8820377588272095,
      "learning_rate": 0.000234,
      "loss": 1.8545,
      "step": 40
    },
    {
      "epoch": 0.09512485136741974,
      "grad_norm": 1.3315837383270264,
      "learning_rate": 0.00029868292682926826,
      "loss": 1.2718,
      "step": 60
    },
    {
      "epoch": 0.12683313515655964,
      "grad_norm": 1.0603790283203125,
      "learning_rate": 0.00029575609756097557,
      "loss": 1.1449,
      "step": 80
    },
    {
      "epoch": 0.15854141894569956,
      "grad_norm": 1.1477017402648926,
      "learning_rate": 0.00029282926829268287,
      "loss": 1.1018,
      "step": 100
    },
    {
      "epoch": 0.1902497027348395,
      "grad_norm": 1.0604023933410645,
      "learning_rate": 0.0002899024390243902,
      "loss": 1.0883,
      "step": 120
    },
    {
      "epoch": 0.22195798652397938,
      "grad_norm": 0.8798519372940063,
      "learning_rate": 0.0002869756097560975,
      "loss": 1.0645,
      "step": 140
    },
    {
      "epoch": 0.2536662703131193,
      "grad_norm": 1.0906599760055542,
      "learning_rate": 0.0002840487804878048,
      "loss": 1.0418,
      "step": 160
    },
    {
      "epoch": 0.2853745541022592,
      "grad_norm": 0.9430219531059265,
      "learning_rate": 0.0002811219512195122,
      "loss": 1.0316,
      "step": 180
    },
    {
      "epoch": 0.3170828378913991,
      "grad_norm": 1.0706809759140015,
      "learning_rate": 0.0002781951219512195,
      "loss": 1.0286,
      "step": 200
    },
    {
      "epoch": 0.34879112168053905,
      "grad_norm": 0.8156995177268982,
      "learning_rate": 0.00027526829268292684,
      "loss": 1.0293,
      "step": 220
    },
    {
      "epoch": 0.380499405469679,
      "grad_norm": 0.8572260737419128,
      "learning_rate": 0.00027234146341463414,
      "loss": 1.0051,
      "step": 240
    },
    {
      "epoch": 0.41220768925881884,
      "grad_norm": 0.9287059307098389,
      "learning_rate": 0.00026941463414634144,
      "loss": 1.0152,
      "step": 260
    },
    {
      "epoch": 0.44391597304795877,
      "grad_norm": 0.8125821352005005,
      "learning_rate": 0.00026648780487804874,
      "loss": 1.0098,
      "step": 280
    },
    {
      "epoch": 0.4756242568370987,
      "grad_norm": 0.8053847551345825,
      "learning_rate": 0.0002635609756097561,
      "loss": 1.0029,
      "step": 300
    }
  ],
  "logging_steps": 20,
  "max_steps": 2100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.570903380983808e+17,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}