last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.996738682227693e-05,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.996376313586324e-06,
      "grad_norm": 0.5858293175697327,
      "learning_rate": 2e-05,
      "loss": 0.9971,
      "step": 1
    },
    {
      "epoch": 9.996376313586324e-06,
      "eval_loss": 1.090817928314209,
      "eval_runtime": 1731.2248,
      "eval_samples_per_second": 24.33,
      "eval_steps_per_second": 12.165,
      "step": 1
    },
    {
      "epoch": 1.999275262717265e-05,
      "grad_norm": 0.5270435810089111,
      "learning_rate": 4e-05,
      "loss": 1.016,
      "step": 2
    },
    {
      "epoch": 2.9989128940758976e-05,
      "grad_norm": 0.8396885991096497,
      "learning_rate": 6e-05,
      "loss": 1.2244,
      "step": 3
    },
    {
      "epoch": 2.9989128940758976e-05,
      "eval_loss": 1.089734435081482,
      "eval_runtime": 1730.6344,
      "eval_samples_per_second": 24.338,
      "eval_steps_per_second": 12.17,
      "step": 3
    },
    {
      "epoch": 3.99855052543453e-05,
      "grad_norm": 0.302880197763443,
      "learning_rate": 8e-05,
      "loss": 0.9304,
      "step": 4
    },
    {
      "epoch": 4.9981881567931625e-05,
      "grad_norm": 0.5103569626808167,
      "learning_rate": 0.0001,
      "loss": 0.9792,
      "step": 5
    },
    {
      "epoch": 5.997825788151795e-05,
      "grad_norm": 0.46589794754981995,
      "learning_rate": 0.00012,
      "loss": 0.7116,
      "step": 6
    },
    {
      "epoch": 5.997825788151795e-05,
      "eval_loss": 1.0812393426895142,
      "eval_runtime": 1730.2785,
      "eval_samples_per_second": 24.343,
      "eval_steps_per_second": 12.172,
      "step": 6
    },
    {
      "epoch": 6.997463419510427e-05,
      "grad_norm": 0.5339783430099487,
      "learning_rate": 0.00014,
      "loss": 1.0301,
      "step": 7
    },
    {
      "epoch": 7.99710105086906e-05,
      "grad_norm": 0.4392818510532379,
      "learning_rate": 0.00016,
      "loss": 1.241,
      "step": 8
    },
    {
      "epoch": 8.996738682227693e-05,
      "grad_norm": 0.38018661737442017,
      "learning_rate": 0.00018,
      "loss": 1.3821,
      "step": 9
    },
    {
      "epoch": 8.996738682227693e-05,
      "eval_loss": 1.042019248008728,
      "eval_runtime": 1729.4949,
      "eval_samples_per_second": 24.355,
      "eval_steps_per_second": 12.178,
      "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": 2405646792130560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}