tiny/checkpoints/checkpoint-200/trainer_state.json

{
  "best_global_step": 200,
  "best_metric": 0.0,
  "best_model_checkpoint": "cache/tiny/checkpoints/checkpoint-200",
  "epoch": 1.0309278350515463,
  "eval_steps": 200,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25773195876288657,
      "grad_norm": 0.0,
      "learning_rate": 9.800000000000001e-06,
      "loss": 3.6191610717773437,
      "step": 50
    },
    {
      "epoch": 0.5154639175257731,
      "grad_norm": 0.0,
      "learning_rate": 1.9800000000000004e-05,
      "loss": 3.6191610717773437,
      "step": 100
    },
    {
      "epoch": 0.7731958762886598,
      "grad_norm": 0.0,
      "learning_rate": 2.98e-05,
      "loss": 3.6191610717773437,
      "step": 150
    },
    {
      "epoch": 1.0309278350515463,
      "grad_norm": 0.0,
      "learning_rate": 3.9800000000000005e-05,
      "loss": 3.607529602050781,
      "step": 200
    },
    {
      "epoch": 1.0309278350515463,
      "eval_loss": 3.965736150741577,
      "eval_runtime": 1.0875,
      "eval_samples_per_second": 941.638,
      "eval_steps_per_second": 0.92,
      "eval_teacher_cosine_loss": 1.0,
      "eval_teacher_cosine_mean": 0.0,
      "eval_teacher_cosine_p10": 0.0,
      "eval_teacher_cosine_p50": 0.0,
      "step": 200
    }
  ],
  "logging_steps": 50,
  "max_steps": 2328,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 512,
  "trial_name": null,
  "trial_params": null
}