last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4547392354696604,
  "eval_steps": 40,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002273696177348302,
      "eval_loss": 1.7713795900344849,
      "eval_runtime": 138.3342,
      "eval_samples_per_second": 5.357,
      "eval_steps_per_second": 2.682,
      "step": 1
    },
    {
      "epoch": 0.09094784709393207,
      "grad_norm": 15.345763206481934,
      "learning_rate": 1e-05,
      "loss": 28.3617,
      "step": 40
    },
    {
      "epoch": 0.09094784709393207,
      "eval_loss": 1.6924622058868408,
      "eval_runtime": 137.5081,
      "eval_samples_per_second": 5.389,
      "eval_steps_per_second": 2.698,
      "step": 40
    },
    {
      "epoch": 0.18189569418786414,
      "grad_norm": 11.842877388000488,
      "learning_rate": 2e-05,
      "loss": 25.7981,
      "step": 80
    },
    {
      "epoch": 0.18189569418786414,
      "eval_loss": 1.4607499837875366,
      "eval_runtime": 139.0999,
      "eval_samples_per_second": 5.327,
      "eval_steps_per_second": 2.667,
      "step": 80
    },
    {
      "epoch": 0.2728435412817962,
      "grad_norm": 16.96082305908203,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 23.7631,
      "step": 120
    },
    {
      "epoch": 0.2728435412817962,
      "eval_loss": 1.3726365566253662,
      "eval_runtime": 138.4449,
      "eval_samples_per_second": 5.352,
      "eval_steps_per_second": 2.68,
      "step": 120
    },
    {
      "epoch": 0.3637913883757283,
      "grad_norm": 9.453910827636719,
      "learning_rate": 5.000000000000003e-06,
      "loss": 22.3112,
      "step": 160
    },
    {
      "epoch": 0.3637913883757283,
      "eval_loss": 1.3575067520141602,
      "eval_runtime": 138.7048,
      "eval_samples_per_second": 5.342,
      "eval_steps_per_second": 2.675,
      "step": 160
    },
    {
      "epoch": 0.4547392354696604,
      "grad_norm": 14.091168403625488,
      "learning_rate": 0.0,
      "loss": 22.6738,
      "step": 200
    },
    {
      "epoch": 0.4547392354696604,
      "eval_loss": 1.3547651767730713,
      "eval_runtime": 138.2478,
      "eval_samples_per_second": 5.36,
      "eval_steps_per_second": 2.684,
      "step": 200
    }
  ],
  "logging_steps": 40,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 40,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.5654589342613504e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}