last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003216106260150835,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.2161062601508354e-05,
      "grad_norm": 0.04531170427799225,
      "learning_rate": 2e-05,
      "loss": 10.3721,
      "step": 1
    },
    {
      "epoch": 3.2161062601508354e-05,
      "eval_loss": 10.37723159790039,
      "eval_runtime": 40.482,
      "eval_samples_per_second": 323.403,
      "eval_steps_per_second": 161.701,
      "step": 1
    },
    {
      "epoch": 6.432212520301671e-05,
      "grad_norm": 0.04875646531581879,
      "learning_rate": 4e-05,
      "loss": 10.3779,
      "step": 2
    },
    {
      "epoch": 9.648318780452506e-05,
      "grad_norm": 0.05363098531961441,
      "learning_rate": 6e-05,
      "loss": 10.3819,
      "step": 3
    },
    {
      "epoch": 9.648318780452506e-05,
      "eval_loss": 10.377202987670898,
      "eval_runtime": 40.0347,
      "eval_samples_per_second": 327.016,
      "eval_steps_per_second": 163.508,
      "step": 3
    },
    {
      "epoch": 0.00012864425040603342,
      "grad_norm": 0.04144046828150749,
      "learning_rate": 8e-05,
      "loss": 10.3668,
      "step": 4
    },
    {
      "epoch": 0.00016080531300754176,
      "grad_norm": 0.05666772276163101,
      "learning_rate": 0.0001,
      "loss": 10.3752,
      "step": 5
    },
    {
      "epoch": 0.0001929663756090501,
      "grad_norm": 0.050154298543930054,
      "learning_rate": 0.00012,
      "loss": 10.3765,
      "step": 6
    },
    {
      "epoch": 0.0001929663756090501,
      "eval_loss": 10.377058029174805,
      "eval_runtime": 40.4833,
      "eval_samples_per_second": 323.393,
      "eval_steps_per_second": 161.696,
      "step": 6
    },
    {
      "epoch": 0.00022512743821055849,
      "grad_norm": 0.030777351930737495,
      "learning_rate": 0.00014,
      "loss": 10.3733,
      "step": 7
    },
    {
      "epoch": 0.00025728850081206683,
      "grad_norm": 0.05287371948361397,
      "learning_rate": 0.00016,
      "loss": 10.3731,
      "step": 8
    },
    {
      "epoch": 0.0002894495634135752,
      "grad_norm": 0.03980984911322594,
      "learning_rate": 0.00018,
      "loss": 10.3822,
      "step": 9
    },
    {
      "epoch": 0.0002894495634135752,
      "eval_loss": 10.376822471618652,
      "eval_runtime": 40.6101,
      "eval_samples_per_second": 322.383,
      "eval_steps_per_second": 161.192,
      "step": 9
    },
    {
      "epoch": 0.0003216106260150835,
      "grad_norm": 0.05820821225643158,
      "learning_rate": 0.0002,
      "loss": 10.3769,
      "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": 142239989760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}