last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016300582745833164,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016300582745833165,
      "grad_norm": 1.4936350584030151,
      "learning_rate": 2e-05,
      "loss": 1.4625,
      "step": 1
    },
    {
      "epoch": 0.00016300582745833165,
      "eval_loss": 1.558783769607544,
      "eval_runtime": 394.7509,
      "eval_samples_per_second": 6.543,
      "eval_steps_per_second": 3.273,
      "step": 1
    },
    {
      "epoch": 0.0003260116549166633,
      "grad_norm": 1.1937557458877563,
      "learning_rate": 4e-05,
      "loss": 1.8338,
      "step": 2
    },
    {
      "epoch": 0.0004890174823749949,
      "grad_norm": 1.6563407182693481,
      "learning_rate": 6e-05,
      "loss": 1.5053,
      "step": 3
    },
    {
      "epoch": 0.0004890174823749949,
      "eval_loss": 1.5555469989776611,
      "eval_runtime": 394.1204,
      "eval_samples_per_second": 6.554,
      "eval_steps_per_second": 3.278,
      "step": 3
    },
    {
      "epoch": 0.0006520233098333266,
      "grad_norm": 2.6089930534362793,
      "learning_rate": 8e-05,
      "loss": 1.7923,
      "step": 4
    },
    {
      "epoch": 0.0008150291372916582,
      "grad_norm": 1.4390363693237305,
      "learning_rate": 0.0001,
      "loss": 1.2632,
      "step": 5
    },
    {
      "epoch": 0.0009780349647499898,
      "grad_norm": 1.1788365840911865,
      "learning_rate": 0.00012,
      "loss": 1.782,
      "step": 6
    },
    {
      "epoch": 0.0009780349647499898,
      "eval_loss": 1.522881031036377,
      "eval_runtime": 394.7109,
      "eval_samples_per_second": 6.544,
      "eval_steps_per_second": 3.273,
      "step": 6
    },
    {
      "epoch": 0.0011410407922083214,
      "grad_norm": 1.252583384513855,
      "learning_rate": 0.00014,
      "loss": 1.5854,
      "step": 7
    },
    {
      "epoch": 0.0013040466196666532,
      "grad_norm": 3.332509994506836,
      "learning_rate": 0.00016,
      "loss": 2.092,
      "step": 8
    },
    {
      "epoch": 0.0014670524471249848,
      "grad_norm": 0.9126483201980591,
      "learning_rate": 0.00018,
      "loss": 1.5811,
      "step": 9
    },
    {
      "epoch": 0.0014670524471249848,
      "eval_loss": 1.4459682703018188,
      "eval_runtime": 393.4548,
      "eval_samples_per_second": 6.565,
      "eval_steps_per_second": 3.284,
      "step": 9
    },
    {
      "epoch": 0.0016300582745833164,
      "grad_norm": 0.939946174621582,
      "learning_rate": 0.0002,
      "loss": 1.2683,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1935445139128320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}