last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0031235358425737935,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00031235358425737937,
      "grad_norm": 1.7035882472991943,
      "learning_rate": 2e-05,
      "loss": 2.3158,
      "step": 1
    },
    {
      "epoch": 0.00031235358425737937,
      "eval_loss": 3.249058961868286,
      "eval_runtime": 40.8768,
      "eval_samples_per_second": 16.513,
      "eval_steps_per_second": 16.513,
      "step": 1
    },
    {
      "epoch": 0.0006247071685147587,
      "grad_norm": 1.4208407402038574,
      "learning_rate": 4e-05,
      "loss": 2.7722,
      "step": 2
    },
    {
      "epoch": 0.0009370607527721381,
      "grad_norm": 1.8023598194122314,
      "learning_rate": 6e-05,
      "loss": 1.8802,
      "step": 3
    },
    {
      "epoch": 0.0009370607527721381,
      "eval_loss": 3.2127676010131836,
      "eval_runtime": 40.8761,
      "eval_samples_per_second": 16.513,
      "eval_steps_per_second": 16.513,
      "step": 3
    },
    {
      "epoch": 0.0012494143370295175,
      "grad_norm": 1.861438512802124,
      "learning_rate": 8e-05,
      "loss": 2.709,
      "step": 4
    },
    {
      "epoch": 0.0015617679212868967,
      "grad_norm": 1.0186002254486084,
      "learning_rate": 0.0001,
      "loss": 2.4372,
      "step": 5
    },
    {
      "epoch": 0.0018741215055442762,
      "grad_norm": 2.189230442047119,
      "learning_rate": 0.00012,
      "loss": 2.0855,
      "step": 6
    },
    {
      "epoch": 0.0018741215055442762,
      "eval_loss": 3.0582637786865234,
      "eval_runtime": 40.8911,
      "eval_samples_per_second": 16.507,
      "eval_steps_per_second": 16.507,
      "step": 6
    },
    {
      "epoch": 0.0021864750898016555,
      "grad_norm": 2.9822628498077393,
      "learning_rate": 0.00014,
      "loss": 3.1322,
      "step": 7
    },
    {
      "epoch": 0.002498828674059035,
      "grad_norm": 2.649256944656372,
      "learning_rate": 0.00016,
      "loss": 2.8415,
      "step": 8
    },
    {
      "epoch": 0.002811182258316414,
      "grad_norm": 2.0153281688690186,
      "learning_rate": 0.00018,
      "loss": 2.7623,
      "step": 9
    },
    {
      "epoch": 0.002811182258316414,
      "eval_loss": 2.7458770275115967,
      "eval_runtime": 40.8846,
      "eval_samples_per_second": 16.51,
      "eval_steps_per_second": 16.51,
      "step": 9
    },
    {
      "epoch": 0.0031235358425737935,
      "grad_norm": 2.347788095474243,
      "learning_rate": 0.0002,
      "loss": 2.3914,
      "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": 967722569564160.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}