last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0004525057505939138,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.0278416732657086e-05,
      "grad_norm": 0.2741275131702423,
      "learning_rate": 2e-05,
      "loss": 1.4864,
      "step": 1
    },
    {
      "epoch": 5.0278416732657086e-05,
      "eval_loss": 1.7782368659973145,
      "eval_runtime": 1156.3654,
      "eval_samples_per_second": 7.243,
      "eval_steps_per_second": 3.622,
      "step": 1
    },
    {
      "epoch": 0.00010055683346531417,
      "grad_norm": 0.4866497218608856,
      "learning_rate": 4e-05,
      "loss": 1.7741,
      "step": 2
    },
    {
      "epoch": 0.00015083525019797127,
      "grad_norm": 0.2840794026851654,
      "learning_rate": 6e-05,
      "loss": 1.9167,
      "step": 3
    },
    {
      "epoch": 0.00015083525019797127,
      "eval_loss": 1.7769949436187744,
      "eval_runtime": 1171.8749,
      "eval_samples_per_second": 7.147,
      "eval_steps_per_second": 3.574,
      "step": 3
    },
    {
      "epoch": 0.00020111366693062834,
      "grad_norm": 0.4316411018371582,
      "learning_rate": 8e-05,
      "loss": 1.7962,
      "step": 4
    },
    {
      "epoch": 0.00025139208366328547,
      "grad_norm": 0.34983840584754944,
      "learning_rate": 0.0001,
      "loss": 2.1419,
      "step": 5
    },
    {
      "epoch": 0.00030167050039594254,
      "grad_norm": 0.28104010224342346,
      "learning_rate": 0.00012,
      "loss": 1.8218,
      "step": 6
    },
    {
      "epoch": 0.00030167050039594254,
      "eval_loss": 1.7353360652923584,
      "eval_runtime": 1159.2615,
      "eval_samples_per_second": 7.224,
      "eval_steps_per_second": 3.613,
      "step": 6
    },
    {
      "epoch": 0.0003519489171285996,
      "grad_norm": 0.31961575150489807,
      "learning_rate": 0.00014,
      "loss": 1.777,
      "step": 7
    },
    {
      "epoch": 0.0004022273338612567,
      "grad_norm": 0.4506252110004425,
      "learning_rate": 0.00016,
      "loss": 1.7637,
      "step": 8
    },
    {
      "epoch": 0.0004525057505939138,
      "grad_norm": 0.5181860327720642,
      "learning_rate": 0.00018,
      "loss": 1.6113,
      "step": 9
    },
    {
      "epoch": 0.0004525057505939138,
      "eval_loss": 1.6632812023162842,
      "eval_runtime": 1157.8037,
      "eval_samples_per_second": 7.234,
      "eval_steps_per_second": 3.617,
      "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": 1960465551851520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}