last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009538950715421303,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010598834128245894,
      "grad_norm": 0.5681617259979248,
      "learning_rate": 2e-05,
      "loss": 5.9436,
      "step": 1
    },
    {
      "epoch": 0.0010598834128245894,
      "eval_loss": 1.5727260112762451,
      "eval_runtime": 27.5953,
      "eval_samples_per_second": 14.423,
      "eval_steps_per_second": 7.211,
      "step": 1
    },
    {
      "epoch": 0.0021197668256491787,
      "grad_norm": 0.540979266166687,
      "learning_rate": 4e-05,
      "loss": 7.3717,
      "step": 2
    },
    {
      "epoch": 0.003179650238473768,
      "grad_norm": 0.5864607691764832,
      "learning_rate": 6e-05,
      "loss": 6.0089,
      "step": 3
    },
    {
      "epoch": 0.003179650238473768,
      "eval_loss": 1.57161545753479,
      "eval_runtime": 27.5907,
      "eval_samples_per_second": 14.425,
      "eval_steps_per_second": 7.213,
      "step": 3
    },
    {
      "epoch": 0.0042395336512983575,
      "grad_norm": 0.6696896553039551,
      "learning_rate": 8e-05,
      "loss": 6.4535,
      "step": 4
    },
    {
      "epoch": 0.005299417064122946,
      "grad_norm": 0.7241686582565308,
      "learning_rate": 0.0001,
      "loss": 6.1643,
      "step": 5
    },
    {
      "epoch": 0.006359300476947536,
      "grad_norm": 0.7567851543426514,
      "learning_rate": 0.00012,
      "loss": 6.1087,
      "step": 6
    },
    {
      "epoch": 0.006359300476947536,
      "eval_loss": 1.5505568981170654,
      "eval_runtime": 27.6384,
      "eval_samples_per_second": 14.4,
      "eval_steps_per_second": 7.2,
      "step": 6
    },
    {
      "epoch": 0.007419183889772125,
      "grad_norm": 0.9638036489486694,
      "learning_rate": 0.00014,
      "loss": 6.2643,
      "step": 7
    },
    {
      "epoch": 0.008479067302596715,
      "grad_norm": 1.229278326034546,
      "learning_rate": 0.00016,
      "loss": 6.0166,
      "step": 8
    },
    {
      "epoch": 0.009538950715421303,
      "grad_norm": 1.4966942071914673,
      "learning_rate": 0.00018,
      "loss": 5.9872,
      "step": 9
    },
    {
      "epoch": 0.009538950715421303,
      "eval_loss": 1.4243505001068115,
      "eval_runtime": 27.6135,
      "eval_samples_per_second": 14.413,
      "eval_steps_per_second": 7.207,
      "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": 2931748635672576.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}