last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008350730688935281,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008350730688935282,
      "grad_norm": 34.41777038574219,
      "learning_rate": 2e-05,
      "loss": 12.0944,
      "step": 1
    },
    {
      "epoch": 0.0016701461377870565,
      "grad_norm": 37.28947830200195,
      "learning_rate": 4e-05,
      "loss": 12.7113,
      "step": 2
    },
    {
      "epoch": 0.0025052192066805845,
      "grad_norm": 34.697181701660156,
      "learning_rate": 6e-05,
      "loss": 13.6961,
      "step": 3
    },
    {
      "epoch": 0.0025052192066805845,
      "eval_loss": 3.374755382537842,
      "eval_runtime": 23.7322,
      "eval_samples_per_second": 21.279,
      "eval_steps_per_second": 10.661,
      "step": 3
    },
    {
      "epoch": 0.003340292275574113,
      "grad_norm": 29.592744827270508,
      "learning_rate": 8e-05,
      "loss": 11.8721,
      "step": 4
    },
    {
      "epoch": 0.0041753653444676405,
      "grad_norm": 31.35338020324707,
      "learning_rate": 0.0001,
      "loss": 13.9192,
      "step": 5
    },
    {
      "epoch": 0.005010438413361169,
      "grad_norm": 43.517852783203125,
      "learning_rate": 0.00012,
      "loss": 13.0854,
      "step": 6
    },
    {
      "epoch": 0.005010438413361169,
      "eval_loss": 2.9446611404418945,
      "eval_runtime": 31.8134,
      "eval_samples_per_second": 15.874,
      "eval_steps_per_second": 7.953,
      "step": 6
    },
    {
      "epoch": 0.005845511482254697,
      "grad_norm": 24.93547821044922,
      "learning_rate": 0.00014,
      "loss": 12.2567,
      "step": 7
    },
    {
      "epoch": 0.006680584551148226,
      "grad_norm": 22.281667709350586,
      "learning_rate": 0.00016,
      "loss": 11.7375,
      "step": 8
    },
    {
      "epoch": 0.007515657620041753,
      "grad_norm": 15.962149620056152,
      "learning_rate": 0.00018,
      "loss": 10.4534,
      "step": 9
    },
    {
      "epoch": 0.007515657620041753,
      "eval_loss": 2.6566338539123535,
      "eval_runtime": 32.5283,
      "eval_samples_per_second": 15.525,
      "eval_steps_per_second": 7.778,
      "step": 9
    },
    {
      "epoch": 0.008350730688935281,
      "grad_norm": 19.56305503845215,
      "learning_rate": 0.0002,
      "loss": 10.9146,
      "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": 1753442880061440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}