last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005405811247090622,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.006456941211803e-05,
      "grad_norm": 0.18168316781520844,
      "learning_rate": 2e-05,
      "loss": 1.668,
      "step": 1
    },
    {
      "epoch": 6.006456941211803e-05,
      "eval_loss": 1.6562931537628174,
      "eval_runtime": 601.6426,
      "eval_samples_per_second": 11.653,
      "eval_steps_per_second": 5.827,
      "step": 1
    },
    {
      "epoch": 0.00012012913882423606,
      "grad_norm": 0.15870024263858795,
      "learning_rate": 4e-05,
      "loss": 1.5504,
      "step": 2
    },
    {
      "epoch": 0.00018019370823635407,
      "grad_norm": 0.19789431989192963,
      "learning_rate": 6e-05,
      "loss": 1.4139,
      "step": 3
    },
    {
      "epoch": 0.00018019370823635407,
      "eval_loss": 1.6558383703231812,
      "eval_runtime": 600.9327,
      "eval_samples_per_second": 11.667,
      "eval_steps_per_second": 5.834,
      "step": 3
    },
    {
      "epoch": 0.00024025827764847211,
      "grad_norm": 0.19479113817214966,
      "learning_rate": 8e-05,
      "loss": 1.7555,
      "step": 4
    },
    {
      "epoch": 0.00030032284706059013,
      "grad_norm": 0.136930450797081,
      "learning_rate": 0.0001,
      "loss": 1.5729,
      "step": 5
    },
    {
      "epoch": 0.00036038741647270814,
      "grad_norm": 0.16922074556350708,
      "learning_rate": 0.00012,
      "loss": 1.5918,
      "step": 6
    },
    {
      "epoch": 0.00036038741647270814,
      "eval_loss": 1.6521847248077393,
      "eval_runtime": 600.6386,
      "eval_samples_per_second": 11.673,
      "eval_steps_per_second": 5.837,
      "step": 6
    },
    {
      "epoch": 0.0004204519858848262,
      "grad_norm": 0.18312940001487732,
      "learning_rate": 0.00014,
      "loss": 1.8521,
      "step": 7
    },
    {
      "epoch": 0.00048051655529694423,
      "grad_norm": 0.19604727625846863,
      "learning_rate": 0.00016,
      "loss": 1.7933,
      "step": 8
    },
    {
      "epoch": 0.0005405811247090622,
      "grad_norm": 0.1954066902399063,
      "learning_rate": 0.00018,
      "loss": 1.7782,
      "step": 9
    },
    {
      "epoch": 0.0005405811247090622,
      "eval_loss": 1.6387897729873657,
      "eval_runtime": 600.7873,
      "eval_samples_per_second": 11.67,
      "eval_steps_per_second": 5.836,
      "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": 1168569347604480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}