last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10025062656641603,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010025062656641603,
      "grad_norm": 21.28019142150879,
      "learning_rate": 2e-05,
      "loss": 6.1371,
      "step": 1
    },
    {
      "epoch": 0.010025062656641603,
      "eval_loss": 6.394162178039551,
      "eval_runtime": 9.5693,
      "eval_samples_per_second": 4.494,
      "eval_steps_per_second": 2.299,
      "step": 1
    },
    {
      "epoch": 0.020050125313283207,
      "grad_norm": 24.765010833740234,
      "learning_rate": 4e-05,
      "loss": 6.6622,
      "step": 2
    },
    {
      "epoch": 0.03007518796992481,
      "grad_norm": 19.849573135375977,
      "learning_rate": 6e-05,
      "loss": 6.6966,
      "step": 3
    },
    {
      "epoch": 0.03007518796992481,
      "eval_loss": 6.185020446777344,
      "eval_runtime": 8.2531,
      "eval_samples_per_second": 5.21,
      "eval_steps_per_second": 2.666,
      "step": 3
    },
    {
      "epoch": 0.040100250626566414,
      "grad_norm": 18.815658569335938,
      "learning_rate": 8e-05,
      "loss": 5.9323,
      "step": 4
    },
    {
      "epoch": 0.05012531328320802,
      "grad_norm": 19.071056365966797,
      "learning_rate": 0.0001,
      "loss": 5.4602,
      "step": 5
    },
    {
      "epoch": 0.06015037593984962,
      "grad_norm": 26.607534408569336,
      "learning_rate": 0.00012,
      "loss": 5.8849,
      "step": 6
    },
    {
      "epoch": 0.06015037593984962,
      "eval_loss": 5.290524482727051,
      "eval_runtime": 8.3367,
      "eval_samples_per_second": 5.158,
      "eval_steps_per_second": 2.639,
      "step": 6
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 19.01709747314453,
      "learning_rate": 0.00014,
      "loss": 4.9242,
      "step": 7
    },
    {
      "epoch": 0.08020050125313283,
      "grad_norm": 24.233760833740234,
      "learning_rate": 0.00016,
      "loss": 4.2854,
      "step": 8
    },
    {
      "epoch": 0.09022556390977443,
      "grad_norm": 24.025436401367188,
      "learning_rate": 0.00018,
      "loss": 4.359,
      "step": 9
    },
    {
      "epoch": 0.09022556390977443,
      "eval_loss": 2.969768524169922,
      "eval_runtime": 8.296,
      "eval_samples_per_second": 5.183,
      "eval_steps_per_second": 2.652,
      "step": 9
    },
    {
      "epoch": 0.10025062656641603,
      "grad_norm": 27.722116470336914,
      "learning_rate": 0.0002,
      "loss": 2.908,
      "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": 621231451668480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}