trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 130,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 1.2109375,
      "learning_rate": 2e-05,
      "loss": 0.1718768835067749,
      "step": 5
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 1.4296875,
      "learning_rate": 2e-05,
      "loss": 0.1568902015686035,
      "step": 10
    },
    {
      "epoch": 1.156862745098039,
      "grad_norm": 1.84375,
      "learning_rate": 2e-05,
      "loss": 0.03657715022563934,
      "step": 15
    },
    {
      "epoch": 1.5490196078431373,
      "grad_norm": 3.265625,
      "learning_rate": 2e-05,
      "loss": -0.06722038388252258,
      "step": 20
    },
    {
      "epoch": 1.9411764705882353,
      "grad_norm": 6.59375,
      "learning_rate": 2e-05,
      "loss": -0.2638897180557251,
      "step": 25
    },
    {
      "epoch": 2.313725490196078,
      "grad_norm": 11.3125,
      "learning_rate": 2e-05,
      "loss": -0.579369306564331,
      "step": 30
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 79.0,
      "learning_rate": 2e-05,
      "loss": -1.2475934028625488,
      "step": 35
    },
    {
      "epoch": 3.0784313725490198,
      "grad_norm": 912.0,
      "learning_rate": 2e-05,
      "loss": -6.139412689208984,
      "step": 40
    },
    {
      "epoch": 3.4705882352941178,
      "grad_norm": 864.0,
      "learning_rate": 2e-05,
      "loss": -15.210101318359374,
      "step": 45
    },
    {
      "epoch": 3.8627450980392157,
      "grad_norm": 1232.0,
      "learning_rate": 2e-05,
      "loss": -24.12535858154297,
      "step": 50
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 2320.0,
      "learning_rate": 2e-05,
      "loss": -34.546392822265624,
      "step": 55
    },
    {
      "epoch": 4.627450980392156,
      "grad_norm": 1952.0,
      "learning_rate": 2e-05,
      "loss": -43.57229309082031,
      "step": 60
    },
    {
      "epoch": 5.0,
      "grad_norm": 1968.0,
      "learning_rate": 2e-05,
      "loss": -53.41856689453125,
      "step": 65
    },
    {
      "epoch": 5.392156862745098,
      "grad_norm": 1272.0,
      "learning_rate": 2e-05,
      "loss": -65.10404052734376,
      "step": 70
    },
    {
      "epoch": 5.784313725490196,
      "grad_norm": 4640.0,
      "learning_rate": 2e-05,
      "loss": -69.12217407226562,
      "step": 75
    },
    {
      "epoch": 6.1568627450980395,
      "grad_norm": 2096.0,
      "learning_rate": 2e-05,
      "loss": -77.57564697265624,
      "step": 80
    },
    {
      "epoch": 6.549019607843137,
      "grad_norm": 1528.0,
      "learning_rate": 2e-05,
      "loss": -82.6677734375,
      "step": 85
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 784.0,
      "learning_rate": 2e-05,
      "loss": -85.05569458007812,
      "step": 90
    },
    {
      "epoch": 7.313725490196078,
      "grad_norm": 408.0,
      "learning_rate": 2e-05,
      "loss": -89.292626953125,
      "step": 95
    },
    {
      "epoch": 7.705882352941177,
      "grad_norm": 840.0,
      "learning_rate": 2e-05,
      "loss": -93.61953735351562,
      "step": 100
    },
    {
      "epoch": 8.07843137254902,
      "grad_norm": 1448.0,
      "learning_rate": 2e-05,
      "loss": -95.10314331054687,
      "step": 105
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 292.0,
      "learning_rate": 2e-05,
      "loss": -97.13496704101563,
      "step": 110
    },
    {
      "epoch": 8.862745098039216,
      "grad_norm": 243.0,
      "learning_rate": 2e-05,
      "loss": -98.05059814453125,
      "step": 115
    },
    {
      "epoch": 9.235294117647058,
      "grad_norm": 1456.0,
      "learning_rate": 2e-05,
      "loss": -99.17882080078125,
      "step": 120
    },
    {
      "epoch": 9.627450980392156,
      "grad_norm": 2016.0,
      "learning_rate": 2e-05,
      "loss": -101.27008056640625,
      "step": 125
    },
    {
      "epoch": 10.0,
      "grad_norm": 348.0,
      "learning_rate": 2e-05,
      "loss": -101.03255004882813,
      "step": 130
    },
    {
      "epoch": 10.0,
      "step": 130,
      "total_flos": 0.0,
      "train_loss": -51.26971183774563,
      "train_runtime": 1185.8143,
      "train_samples_per_second": 3.432,
      "train_steps_per_second": 0.11
    }
  ],
  "logging_steps": 5,
  "max_steps": 130,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}