last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.022197558268590455,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022197558268590455,
      "grad_norm": 0.025404546409845352,
      "learning_rate": 2e-05,
      "loss": 10.3769,
      "step": 1
    },
    {
      "epoch": 0.0022197558268590455,
      "eval_loss": 10.37777328491211,
      "eval_runtime": 1.2457,
      "eval_samples_per_second": 152.531,
      "eval_steps_per_second": 76.265,
      "step": 1
    },
    {
      "epoch": 0.004439511653718091,
      "grad_norm": 0.02415435202419758,
      "learning_rate": 4e-05,
      "loss": 10.3758,
      "step": 2
    },
    {
      "epoch": 0.006659267480577136,
      "grad_norm": 0.027586132287979126,
      "learning_rate": 6e-05,
      "loss": 10.3763,
      "step": 3
    },
    {
      "epoch": 0.006659267480577136,
      "eval_loss": 10.377732276916504,
      "eval_runtime": 1.2364,
      "eval_samples_per_second": 153.67,
      "eval_steps_per_second": 76.835,
      "step": 3
    },
    {
      "epoch": 0.008879023307436182,
      "grad_norm": 0.025835813954472542,
      "learning_rate": 8e-05,
      "loss": 10.3749,
      "step": 4
    },
    {
      "epoch": 0.011098779134295227,
      "grad_norm": 0.0256224162876606,
      "learning_rate": 0.0001,
      "loss": 10.3748,
      "step": 5
    },
    {
      "epoch": 0.013318534961154272,
      "grad_norm": 0.018543493002653122,
      "learning_rate": 0.00012,
      "loss": 10.3791,
      "step": 6
    },
    {
      "epoch": 0.013318534961154272,
      "eval_loss": 10.377586364746094,
      "eval_runtime": 1.268,
      "eval_samples_per_second": 149.84,
      "eval_steps_per_second": 74.92,
      "step": 6
    },
    {
      "epoch": 0.01553829078801332,
      "grad_norm": 0.025994783267378807,
      "learning_rate": 0.00014,
      "loss": 10.379,
      "step": 7
    },
    {
      "epoch": 0.017758046614872364,
      "grad_norm": 0.025559840723872185,
      "learning_rate": 0.00016,
      "loss": 10.3769,
      "step": 8
    },
    {
      "epoch": 0.01997780244173141,
      "grad_norm": 0.020570356398820877,
      "learning_rate": 0.00018,
      "loss": 10.3795,
      "step": 9
    },
    {
      "epoch": 0.01997780244173141,
      "eval_loss": 10.37732982635498,
      "eval_runtime": 1.2633,
      "eval_samples_per_second": 150.402,
      "eval_steps_per_second": 75.201,
      "step": 9
    },
    {
      "epoch": 0.022197558268590455,
      "grad_norm": 0.02001837082207203,
      "learning_rate": 0.0002,
      "loss": 10.3791,
      "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": 1046048931840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}