last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011243060923336379,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.621530461668189e-05,
      "eval_loss": 0.6464069485664368,
      "eval_runtime": 609.7389,
      "eval_samples_per_second": 12.284,
      "eval_steps_per_second": 6.142,
      "step": 1
    },
    {
      "epoch": 0.0005621530461668189,
      "grad_norm": 0.34330883622169495,
      "learning_rate": 0.0002,
      "loss": 0.5058,
      "step": 10
    },
    {
      "epoch": 0.0011243060923336377,
      "grad_norm": 0.3404369056224823,
      "learning_rate": 0.0002,
      "loss": 0.4254,
      "step": 20
    },
    {
      "epoch": 0.0016864591385004567,
      "grad_norm": 0.3144387900829315,
      "learning_rate": 0.0002,
      "loss": 0.4065,
      "step": 30
    },
    {
      "epoch": 0.0022486121846672755,
      "grad_norm": 0.3841158151626587,
      "learning_rate": 0.0002,
      "loss": 0.3781,
      "step": 40
    },
    {
      "epoch": 0.0028107652308340947,
      "grad_norm": 0.3709113299846649,
      "learning_rate": 0.0002,
      "loss": 0.3482,
      "step": 50
    },
    {
      "epoch": 0.0028107652308340947,
      "eval_loss": 0.34076154232025146,
      "eval_runtime": 608.9426,
      "eval_samples_per_second": 12.3,
      "eval_steps_per_second": 6.15,
      "step": 50
    },
    {
      "epoch": 0.0033729182770009134,
      "grad_norm": 0.4097980260848999,
      "learning_rate": 0.0002,
      "loss": 0.3564,
      "step": 60
    },
    {
      "epoch": 0.003935071323167732,
      "grad_norm": 0.3512555956840515,
      "learning_rate": 0.0002,
      "loss": 0.3117,
      "step": 70
    },
    {
      "epoch": 0.004497224369334551,
      "grad_norm": 0.43151453137397766,
      "learning_rate": 0.0002,
      "loss": 0.3573,
      "step": 80
    },
    {
      "epoch": 0.005059377415501371,
      "grad_norm": 0.6613090634346008,
      "learning_rate": 0.0002,
      "loss": 0.3253,
      "step": 90
    },
    {
      "epoch": 0.005621530461668189,
      "grad_norm": 0.3564847409725189,
      "learning_rate": 0.0002,
      "loss": 0.3236,
      "step": 100
    },
    {
      "epoch": 0.005621530461668189,
      "eval_loss": 0.32292038202285767,
      "eval_runtime": 609.3281,
      "eval_samples_per_second": 12.292,
      "eval_steps_per_second": 6.146,
      "step": 100
    },
    {
      "epoch": 0.006183683507835008,
      "grad_norm": 0.3181847929954529,
      "learning_rate": 0.0002,
      "loss": 0.3241,
      "step": 110
    },
    {
      "epoch": 0.006745836554001827,
      "grad_norm": 0.42424142360687256,
      "learning_rate": 0.0002,
      "loss": 0.2953,
      "step": 120
    },
    {
      "epoch": 0.007307989600168646,
      "grad_norm": 0.4498586058616638,
      "learning_rate": 0.0002,
      "loss": 0.3619,
      "step": 130
    },
    {
      "epoch": 0.007870142646335464,
      "grad_norm": 0.35849127173423767,
      "learning_rate": 0.0002,
      "loss": 0.3218,
      "step": 140
    },
    {
      "epoch": 0.008432295692502284,
      "grad_norm": 0.38611167669296265,
      "learning_rate": 0.0002,
      "loss": 0.3287,
      "step": 150
    },
    {
      "epoch": 0.008432295692502284,
      "eval_loss": 0.31369704008102417,
      "eval_runtime": 609.316,
      "eval_samples_per_second": 12.292,
      "eval_steps_per_second": 6.146,
      "step": 150
    },
    {
      "epoch": 0.008994448738669102,
      "grad_norm": 0.3397560119628906,
      "learning_rate": 0.0002,
      "loss": 0.3234,
      "step": 160
    },
    {
      "epoch": 0.009556601784835922,
      "grad_norm": 0.4362323582172394,
      "learning_rate": 0.0002,
      "loss": 0.3112,
      "step": 170
    },
    {
      "epoch": 0.010118754831002741,
      "grad_norm": 0.3360973596572876,
      "learning_rate": 0.0002,
      "loss": 0.3057,
      "step": 180
    },
    {
      "epoch": 0.010680907877169559,
      "grad_norm": 0.40133044123649597,
      "learning_rate": 0.0002,
      "loss": 0.3276,
      "step": 190
    },
    {
      "epoch": 0.011243060923336379,
      "grad_norm": 0.4047779142856598,
      "learning_rate": 0.0002,
      "loss": 0.2977,
      "step": 200
    },
    {
      "epoch": 0.011243060923336379,
      "eval_loss": 0.30774378776550293,
      "eval_runtime": 609.1932,
      "eval_samples_per_second": 12.295,
      "eval_steps_per_second": 6.147,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.880649602085683e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}