checkpoint-10/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1238390092879257,
  "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,
      "eval_loss": 0.9052417278289795,
      "eval_runtime": 8.4448,
      "eval_samples_per_second": 4.026,
      "eval_steps_per_second": 2.013,
      "step": 0
    },
    {
      "epoch": 0.01238390092879257,
      "grad_norm": 0.8082026243209839,
      "learning_rate": 0.0,
      "loss": 1.1985,
      "step": 1
    },
    {
      "epoch": 0.02476780185758514,
      "grad_norm": 0.50789475440979,
      "learning_rate": 2e-05,
      "loss": 0.6888,
      "step": 2
    },
    {
      "epoch": 0.03715170278637771,
      "grad_norm": 0.8321412205696106,
      "learning_rate": 4e-05,
      "loss": 1.0164,
      "step": 3
    },
    {
      "epoch": 0.03715170278637771,
      "eval_loss": 0.9056991338729858,
      "eval_runtime": 7.8859,
      "eval_samples_per_second": 4.312,
      "eval_steps_per_second": 2.156,
      "step": 3
    },
    {
      "epoch": 0.04953560371517028,
      "grad_norm": 0.4088127613067627,
      "learning_rate": 6e-05,
      "loss": 0.7558,
      "step": 4
    },
    {
      "epoch": 0.06191950464396285,
      "grad_norm": 0.7107352614402771,
      "learning_rate": 8e-05,
      "loss": 1.2576,
      "step": 5
    },
    {
      "epoch": 0.07430340557275542,
      "grad_norm": 0.5187698006629944,
      "learning_rate": 0.0001,
      "loss": 1.0848,
      "step": 6
    },
    {
      "epoch": 0.07430340557275542,
      "eval_loss": 0.9046434164047241,
      "eval_runtime": 7.844,
      "eval_samples_per_second": 4.335,
      "eval_steps_per_second": 2.167,
      "step": 6
    },
    {
      "epoch": 0.08668730650154799,
      "grad_norm": 0.5227215886116028,
      "learning_rate": 0.00012,
      "loss": 0.7471,
      "step": 7
    },
    {
      "epoch": 0.09907120743034056,
      "grad_norm": 0.49186187982559204,
      "learning_rate": 0.00014,
      "loss": 0.9016,
      "step": 8
    },
    {
      "epoch": 0.11145510835913312,
      "grad_norm": 0.49750179052352905,
      "learning_rate": 0.00016,
      "loss": 1.0387,
      "step": 9
    },
    {
      "epoch": 0.11145510835913312,
      "eval_loss": 0.9022544622421265,
      "eval_runtime": 7.9872,
      "eval_samples_per_second": 4.257,
      "eval_steps_per_second": 2.128,
      "step": 9
    },
    {
      "epoch": 0.1238390092879257,
      "grad_norm": 0.5828521847724915,
      "learning_rate": 0.00018,
      "loss": 0.7156,
      "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": 240545515438080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}