checkpoint-10/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10256410256410256,
  "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,
      "eval_loss": 2.8341026306152344,
      "eval_runtime": 12.1694,
      "eval_samples_per_second": 3.451,
      "eval_steps_per_second": 1.726,
      "step": 0
    },
    {
      "epoch": 0.010256410256410256,
      "grad_norm": 1.5949193239212036,
      "learning_rate": 0.0,
      "loss": 1.9494,
      "step": 1
    },
    {
      "epoch": 0.020512820512820513,
      "grad_norm": 1.186781644821167,
      "learning_rate": 2e-05,
      "loss": 1.3728,
      "step": 2
    },
    {
      "epoch": 0.03076923076923077,
      "grad_norm": 1.1918362379074097,
      "learning_rate": 4e-05,
      "loss": 2.3531,
      "step": 3
    },
    {
      "epoch": 0.03076923076923077,
      "eval_loss": 2.829076051712036,
      "eval_runtime": 9.3467,
      "eval_samples_per_second": 4.494,
      "eval_steps_per_second": 2.247,
      "step": 3
    },
    {
      "epoch": 0.041025641025641026,
      "grad_norm": 3.728801965713501,
      "learning_rate": 6e-05,
      "loss": 3.7678,
      "step": 4
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 1.5064353942871094,
      "learning_rate": 8e-05,
      "loss": 3.749,
      "step": 5
    },
    {
      "epoch": 0.06153846153846154,
      "grad_norm": 2.4485437870025635,
      "learning_rate": 0.0001,
      "loss": 2.0761,
      "step": 6
    },
    {
      "epoch": 0.06153846153846154,
      "eval_loss": 2.7467548847198486,
      "eval_runtime": 8.5188,
      "eval_samples_per_second": 4.93,
      "eval_steps_per_second": 2.465,
      "step": 6
    },
    {
      "epoch": 0.07179487179487179,
      "grad_norm": 1.7899224758148193,
      "learning_rate": 0.00012,
      "loss": 3.1194,
      "step": 7
    },
    {
      "epoch": 0.08205128205128205,
      "grad_norm": 1.307887077331543,
      "learning_rate": 0.00014,
      "loss": 2.1832,
      "step": 8
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 1.4753953218460083,
      "learning_rate": 0.00016,
      "loss": 1.48,
      "step": 9
    },
    {
      "epoch": 0.09230769230769231,
      "eval_loss": 2.6240603923797607,
      "eval_runtime": 13.4331,
      "eval_samples_per_second": 3.127,
      "eval_steps_per_second": 1.563,
      "step": 9
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 2.0359137058258057,
      "learning_rate": 0.00018,
      "loss": 2.0234,
      "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": 109489453793280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}