last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008592910848549946,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "grad_norm": 0.5830567479133606,
      "learning_rate": 2e-05,
      "loss": 0.966,
      "step": 1
    },
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 1.4169929027557373,
      "eval_runtime": 56.6371,
      "eval_samples_per_second": 8.652,
      "eval_steps_per_second": 4.326,
      "step": 1
    },
    {
      "epoch": 0.0017185821697099893,
      "grad_norm": 0.5659509301185608,
      "learning_rate": 4e-05,
      "loss": 0.9081,
      "step": 2
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 1.0802857875823975,
      "learning_rate": 6e-05,
      "loss": 1.3303,
      "step": 3
    },
    {
      "epoch": 0.0025778732545649837,
      "eval_loss": 1.4119172096252441,
      "eval_runtime": 57.3235,
      "eval_samples_per_second": 8.548,
      "eval_steps_per_second": 4.274,
      "step": 3
    },
    {
      "epoch": 0.0034371643394199786,
      "grad_norm": 0.8123120069503784,
      "learning_rate": 8e-05,
      "loss": 1.1989,
      "step": 4
    },
    {
      "epoch": 0.004296455424274973,
      "grad_norm": 0.7593491077423096,
      "learning_rate": 0.0001,
      "loss": 1.1392,
      "step": 5
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 0.6966873407363892,
      "learning_rate": 0.00012,
      "loss": 1.1108,
      "step": 6
    },
    {
      "epoch": 0.0051557465091299675,
      "eval_loss": 1.335013747215271,
      "eval_runtime": 57.6983,
      "eval_samples_per_second": 8.492,
      "eval_steps_per_second": 4.246,
      "step": 6
    },
    {
      "epoch": 0.006015037593984963,
      "grad_norm": 0.9385346174240112,
      "learning_rate": 0.00014,
      "loss": 1.3349,
      "step": 7
    },
    {
      "epoch": 0.006874328678839957,
      "grad_norm": 1.0830007791519165,
      "learning_rate": 0.00016,
      "loss": 1.1764,
      "step": 8
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 1.4780082702636719,
      "learning_rate": 0.00018,
      "loss": 1.2777,
      "step": 9
    },
    {
      "epoch": 0.007733619763694952,
      "eval_loss": 1.119867205619812,
      "eval_runtime": 57.7497,
      "eval_samples_per_second": 8.485,
      "eval_steps_per_second": 4.242,
      "step": 9
    },
    {
      "epoch": 0.008592910848549946,
      "grad_norm": 0.9420672059059143,
      "learning_rate": 0.0002,
      "loss": 1.0253,
      "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": 1628734142545920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}