checkpoint-9180/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 9180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.054466230936819175,
      "grad_norm": 5.168296813964844,
      "learning_rate": 5e-05,
      "loss": 1.747,
      "step": 500
    },
    {
      "epoch": 0.10893246187363835,
      "grad_norm": 0.6366938948631287,
      "learning_rate": 4.711981566820277e-05,
      "loss": 1.3516,
      "step": 1000
    },
    {
      "epoch": 0.16339869281045752,
      "grad_norm": 0.5679114460945129,
      "learning_rate": 4.423963133640553e-05,
      "loss": 1.3809,
      "step": 1500
    },
    {
      "epoch": 0.2178649237472767,
      "grad_norm": 1.4229077100753784,
      "learning_rate": 4.13594470046083e-05,
      "loss": 1.2784,
      "step": 2000
    },
    {
      "epoch": 0.27233115468409586,
      "grad_norm": 1.4274455308914185,
      "learning_rate": 3.847926267281106e-05,
      "loss": 1.2724,
      "step": 2500
    },
    {
      "epoch": 0.32679738562091504,
      "grad_norm": 1.3789653778076172,
      "learning_rate": 3.559907834101383e-05,
      "loss": 1.2497,
      "step": 3000
    },
    {
      "epoch": 0.3812636165577342,
      "grad_norm": 1.8324720859527588,
      "learning_rate": 3.271889400921659e-05,
      "loss": 1.2794,
      "step": 3500
    },
    {
      "epoch": 0.4357298474945534,
      "grad_norm": 2.032700777053833,
      "learning_rate": 2.9838709677419357e-05,
      "loss": 1.3075,
      "step": 4000
    },
    {
      "epoch": 0.49019607843137253,
      "grad_norm": 1.803504467010498,
      "learning_rate": 2.6958525345622122e-05,
      "loss": 1.2619,
      "step": 4500
    },
    {
      "epoch": 0.5446623093681917,
      "grad_norm": 2.303041934967041,
      "learning_rate": 2.4078341013824887e-05,
      "loss": 1.2637,
      "step": 5000
    },
    {
      "epoch": 0.599128540305011,
      "grad_norm": 1.4995568990707397,
      "learning_rate": 2.1198156682027652e-05,
      "loss": 1.2121,
      "step": 5500
    },
    {
      "epoch": 0.6535947712418301,
      "grad_norm": 2.217719078063965,
      "learning_rate": 1.8317972350230417e-05,
      "loss": 1.2217,
      "step": 6000
    },
    {
      "epoch": 0.7080610021786492,
      "grad_norm": 0.955868661403656,
      "learning_rate": 1.543778801843318e-05,
      "loss": 1.3003,
      "step": 6500
    },
    {
      "epoch": 0.7625272331154684,
      "grad_norm": 0.78927081823349,
      "learning_rate": 1.2557603686635947e-05,
      "loss": 1.2972,
      "step": 7000
    },
    {
      "epoch": 0.8169934640522876,
      "grad_norm": 2.1060714721679688,
      "learning_rate": 9.67741935483871e-06,
      "loss": 1.2399,
      "step": 7500
    },
    {
      "epoch": 0.8714596949891068,
      "grad_norm": 2.7912235260009766,
      "learning_rate": 6.7972350230414745e-06,
      "loss": 1.2342,
      "step": 8000
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 0.5627678632736206,
      "learning_rate": 3.9170506912442395e-06,
      "loss": 1.2395,
      "step": 8500
    },
    {
      "epoch": 0.9803921568627451,
      "grad_norm": 1.0158742666244507,
      "learning_rate": 1.0368663594470047e-06,
      "loss": 1.2676,
      "step": 9000
    }
  ],
  "logging_steps": 500,
  "max_steps": 9180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2398530207744000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}