checkpoint-140/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1,
  "eval_steps": 500,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014285714285714285,
      "grad_norm": 3.377620220184326,
      "learning_rate": 0.0002380952380952381,
      "loss": 5.6223,
      "step": 20
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 2.886795997619629,
      "learning_rate": 0.0004761904761904762,
      "loss": 4.431,
      "step": 40
    },
    {
      "epoch": 0.04285714285714286,
      "grad_norm": 2.803114175796509,
      "learning_rate": 0.0004933726067746687,
      "loss": 4.0911,
      "step": 60
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 2.301974058151245,
      "learning_rate": 0.00048600883652430047,
      "loss": 3.8864,
      "step": 80
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 1.8850748538970947,
      "learning_rate": 0.0004786450662739323,
      "loss": 3.723,
      "step": 100
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 2.110988140106201,
      "learning_rate": 0.00047128129602356405,
      "loss": 3.852,
      "step": 120
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.5434200763702393,
      "learning_rate": 0.0004639175257731959,
      "loss": 3.7659,
      "step": 140
    }
  ],
  "logging_steps": 20,
  "max_steps": 1400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 848786620416000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}