last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0047175374454534735,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00047175374454534735,
      "grad_norm": 0.02135482057929039,
      "learning_rate": 2e-05,
      "loss": 10.3884,
      "step": 1
    },
    {
      "epoch": 0.00047175374454534735,
      "eval_loss": 10.383219718933105,
      "eval_runtime": 3.2242,
      "eval_samples_per_second": 276.968,
      "eval_steps_per_second": 138.639,
      "step": 1
    },
    {
      "epoch": 0.0009435074890906947,
      "grad_norm": 0.05195602774620056,
      "learning_rate": 4e-05,
      "loss": 10.3795,
      "step": 2
    },
    {
      "epoch": 0.001415261233636042,
      "grad_norm": 0.026217341423034668,
      "learning_rate": 6e-05,
      "loss": 10.39,
      "step": 3
    },
    {
      "epoch": 0.001415261233636042,
      "eval_loss": 10.383208274841309,
      "eval_runtime": 3.2353,
      "eval_samples_per_second": 276.014,
      "eval_steps_per_second": 138.162,
      "step": 3
    },
    {
      "epoch": 0.0018870149781813894,
      "grad_norm": 0.023581691086292267,
      "learning_rate": 8e-05,
      "loss": 10.3762,
      "step": 4
    },
    {
      "epoch": 0.0023587687227267368,
      "grad_norm": 0.029611019417643547,
      "learning_rate": 0.0001,
      "loss": 10.3863,
      "step": 5
    },
    {
      "epoch": 0.002830522467272084,
      "grad_norm": 0.024547450244426727,
      "learning_rate": 0.00012,
      "loss": 10.377,
      "step": 6
    },
    {
      "epoch": 0.002830522467272084,
      "eval_loss": 10.383139610290527,
      "eval_runtime": 3.3048,
      "eval_samples_per_second": 270.213,
      "eval_steps_per_second": 135.258,
      "step": 6
    },
    {
      "epoch": 0.0033022762118174315,
      "grad_norm": 0.018600204959511757,
      "learning_rate": 0.00014,
      "loss": 10.3892,
      "step": 7
    },
    {
      "epoch": 0.003774029956362779,
      "grad_norm": 0.023554163053631783,
      "learning_rate": 0.00016,
      "loss": 10.3856,
      "step": 8
    },
    {
      "epoch": 0.004245783700908126,
      "grad_norm": 0.01966540701687336,
      "learning_rate": 0.00018,
      "loss": 10.3806,
      "step": 9
    },
    {
      "epoch": 0.004245783700908126,
      "eval_loss": 10.38302230834961,
      "eval_runtime": 3.2947,
      "eval_samples_per_second": 271.045,
      "eval_steps_per_second": 135.674,
      "step": 9
    },
    {
      "epoch": 0.0047175374454534735,
      "grad_norm": 0.02262878604233265,
      "learning_rate": 0.0002,
      "loss": 10.379,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 258618163200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}