last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010370754472387866,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010370754472387865,
      "grad_norm": 3.4765625,
      "learning_rate": 2e-05,
      "loss": 5.1195,
      "step": 1
    },
    {
      "epoch": 0.0010370754472387865,
      "eval_loss": 1.3504574298858643,
      "eval_runtime": 12.5004,
      "eval_samples_per_second": 32.479,
      "eval_steps_per_second": 16.24,
      "step": 1
    },
    {
      "epoch": 0.002074150894477573,
      "grad_norm": 3.6647281646728516,
      "learning_rate": 4e-05,
      "loss": 5.3506,
      "step": 2
    },
    {
      "epoch": 0.00311122634171636,
      "grad_norm": 3.4481334686279297,
      "learning_rate": 6e-05,
      "loss": 5.1075,
      "step": 3
    },
    {
      "epoch": 0.00311122634171636,
      "eval_loss": 1.346051573753357,
      "eval_runtime": 12.445,
      "eval_samples_per_second": 32.624,
      "eval_steps_per_second": 16.312,
      "step": 3
    },
    {
      "epoch": 0.004148301788955146,
      "grad_norm": 3.799755811691284,
      "learning_rate": 8e-05,
      "loss": 6.4002,
      "step": 4
    },
    {
      "epoch": 0.005185377236193933,
      "grad_norm": 3.4368438720703125,
      "learning_rate": 0.0001,
      "loss": 4.3152,
      "step": 5
    },
    {
      "epoch": 0.00622245268343272,
      "grad_norm": 4.421343803405762,
      "learning_rate": 0.00012,
      "loss": 5.3543,
      "step": 6
    },
    {
      "epoch": 0.00622245268343272,
      "eval_loss": 1.2915544509887695,
      "eval_runtime": 12.5774,
      "eval_samples_per_second": 32.28,
      "eval_steps_per_second": 16.14,
      "step": 6
    },
    {
      "epoch": 0.007259528130671506,
      "grad_norm": 3.8659937381744385,
      "learning_rate": 0.00014,
      "loss": 5.1438,
      "step": 7
    },
    {
      "epoch": 0.008296603577910292,
      "grad_norm": 4.2471795082092285,
      "learning_rate": 0.00016,
      "loss": 5.241,
      "step": 8
    },
    {
      "epoch": 0.00933367902514908,
      "grad_norm": 3.9067635536193848,
      "learning_rate": 0.00018,
      "loss": 4.5605,
      "step": 9
    },
    {
      "epoch": 0.00933367902514908,
      "eval_loss": 1.1102535724639893,
      "eval_runtime": 12.611,
      "eval_samples_per_second": 32.194,
      "eval_steps_per_second": 16.097,
      "step": 9
    },
    {
      "epoch": 0.010370754472387866,
      "grad_norm": 3.511530876159668,
      "learning_rate": 0.0002,
      "loss": 4.1345,
      "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": 940902212173824.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}