last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003625231612019657,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.028035124466285e-05,
      "grad_norm": 2.175239324569702,
      "learning_rate": 2e-05,
      "loss": 1.292,
      "step": 1
    },
    {
      "epoch": 4.028035124466285e-05,
      "eval_loss": 1.337856650352478,
      "eval_runtime": 367.7074,
      "eval_samples_per_second": 28.43,
      "eval_steps_per_second": 14.215,
      "step": 1
    },
    {
      "epoch": 8.05607024893257e-05,
      "grad_norm": 1.7362862825393677,
      "learning_rate": 4e-05,
      "loss": 1.1974,
      "step": 2
    },
    {
      "epoch": 0.00012084105373398856,
      "grad_norm": 1.8394321203231812,
      "learning_rate": 6e-05,
      "loss": 1.0682,
      "step": 3
    },
    {
      "epoch": 0.00012084105373398856,
      "eval_loss": 1.314394235610962,
      "eval_runtime": 367.6612,
      "eval_samples_per_second": 28.434,
      "eval_steps_per_second": 14.217,
      "step": 3
    },
    {
      "epoch": 0.0001611214049786514,
      "grad_norm": 2.364299774169922,
      "learning_rate": 8e-05,
      "loss": 1.3598,
      "step": 4
    },
    {
      "epoch": 0.00020140175622331428,
      "grad_norm": 2.242465019226074,
      "learning_rate": 0.0001,
      "loss": 1.1288,
      "step": 5
    },
    {
      "epoch": 0.00024168210746797713,
      "grad_norm": 2.6861603260040283,
      "learning_rate": 0.00012,
      "loss": 1.2543,
      "step": 6
    },
    {
      "epoch": 0.00024168210746797713,
      "eval_loss": 1.0420364141464233,
      "eval_runtime": 368.0677,
      "eval_samples_per_second": 28.402,
      "eval_steps_per_second": 14.201,
      "step": 6
    },
    {
      "epoch": 0.00028196245871264,
      "grad_norm": 2.8985276222229004,
      "learning_rate": 0.00014,
      "loss": 1.0801,
      "step": 7
    },
    {
      "epoch": 0.0003222428099573028,
      "grad_norm": 2.775141477584839,
      "learning_rate": 0.00016,
      "loss": 0.9911,
      "step": 8
    },
    {
      "epoch": 0.0003625231612019657,
      "grad_norm": 2.5354292392730713,
      "learning_rate": 0.00018,
      "loss": 0.7613,
      "step": 9
    },
    {
      "epoch": 0.0003625231612019657,
      "eval_loss": 0.5746785402297974,
      "eval_runtime": 368.3895,
      "eval_samples_per_second": 28.378,
      "eval_steps_per_second": 14.189,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1719982274641920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}