last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0051013901288101005,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005101390128810101,
      "grad_norm": 0.25031808018684387,
      "learning_rate": 2e-05,
      "loss": 2.5092,
      "step": 1
    },
    {
      "epoch": 0.0010202780257620202,
      "grad_norm": 0.27107110619544983,
      "learning_rate": 4e-05,
      "loss": 2.6743,
      "step": 2
    },
    {
      "epoch": 0.0015304170386430302,
      "grad_norm": 0.24843961000442505,
      "learning_rate": 6e-05,
      "loss": 2.4752,
      "step": 3
    },
    {
      "epoch": 0.0015304170386430302,
      "eval_loss": 2.6821274757385254,
      "eval_runtime": 75.2159,
      "eval_samples_per_second": 10.982,
      "eval_steps_per_second": 5.491,
      "step": 3
    },
    {
      "epoch": 0.0020405560515240405,
      "grad_norm": 0.25299274921417236,
      "learning_rate": 8e-05,
      "loss": 2.7086,
      "step": 4
    },
    {
      "epoch": 0.0025506950644050503,
      "grad_norm": 0.2649744749069214,
      "learning_rate": 0.0001,
      "loss": 2.422,
      "step": 5
    },
    {
      "epoch": 0.0030608340772860605,
      "grad_norm": 0.2959408760070801,
      "learning_rate": 0.00012,
      "loss": 2.6637,
      "step": 6
    },
    {
      "epoch": 0.0030608340772860605,
      "eval_loss": 2.6740875244140625,
      "eval_runtime": 75.7278,
      "eval_samples_per_second": 10.907,
      "eval_steps_per_second": 5.454,
      "step": 6
    },
    {
      "epoch": 0.0035709730901670707,
      "grad_norm": 0.28532931208610535,
      "learning_rate": 0.00014,
      "loss": 2.3546,
      "step": 7
    },
    {
      "epoch": 0.004081112103048081,
      "grad_norm": 0.39420419931411743,
      "learning_rate": 0.00016,
      "loss": 2.9987,
      "step": 8
    },
    {
      "epoch": 0.00459125111592909,
      "grad_norm": 0.3755263388156891,
      "learning_rate": 0.00018,
      "loss": 2.5646,
      "step": 9
    },
    {
      "epoch": 0.00459125111592909,
      "eval_loss": 2.6205434799194336,
      "eval_runtime": 75.4786,
      "eval_samples_per_second": 10.943,
      "eval_steps_per_second": 5.472,
      "step": 9
    },
    {
      "epoch": 0.0051013901288101005,
      "grad_norm": 0.4062849283218384,
      "learning_rate": 0.0002,
      "loss": 2.4832,
      "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": 3136744882962432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}