last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00025442864866583975,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.5442864866583977e-05,
      "grad_norm": 11.654986381530762,
      "learning_rate": 2e-05,
      "loss": 3.9018,
      "step": 1
    },
    {
      "epoch": 2.5442864866583977e-05,
      "eval_loss": 0.8175949454307556,
      "eval_runtime": 915.505,
      "eval_samples_per_second": 18.076,
      "eval_steps_per_second": 9.039,
      "step": 1
    },
    {
      "epoch": 5.0885729733167954e-05,
      "grad_norm": 12.344443321228027,
      "learning_rate": 4e-05,
      "loss": 4.0644,
      "step": 2
    },
    {
      "epoch": 7.632859459975193e-05,
      "grad_norm": 8.388327598571777,
      "learning_rate": 6e-05,
      "loss": 2.7135,
      "step": 3
    },
    {
      "epoch": 7.632859459975193e-05,
      "eval_loss": 0.7987396717071533,
      "eval_runtime": 914.3305,
      "eval_samples_per_second": 18.1,
      "eval_steps_per_second": 9.05,
      "step": 3
    },
    {
      "epoch": 0.00010177145946633591,
      "grad_norm": 12.010126113891602,
      "learning_rate": 8e-05,
      "loss": 3.2288,
      "step": 4
    },
    {
      "epoch": 0.00012721432433291987,
      "grad_norm": 7.178957939147949,
      "learning_rate": 0.0001,
      "loss": 2.4284,
      "step": 5
    },
    {
      "epoch": 0.00015265718919950385,
      "grad_norm": 9.45927906036377,
      "learning_rate": 0.00012,
      "loss": 3.1922,
      "step": 6
    },
    {
      "epoch": 0.00015265718919950385,
      "eval_loss": 0.7086840867996216,
      "eval_runtime": 913.8224,
      "eval_samples_per_second": 18.11,
      "eval_steps_per_second": 9.055,
      "step": 6
    },
    {
      "epoch": 0.00017810005406608783,
      "grad_norm": 8.467989921569824,
      "learning_rate": 0.00014,
      "loss": 3.2375,
      "step": 7
    },
    {
      "epoch": 0.00020354291893267182,
      "grad_norm": 11.662957191467285,
      "learning_rate": 0.00016,
      "loss": 2.5557,
      "step": 8
    },
    {
      "epoch": 0.0002289857837992558,
      "grad_norm": 10.597448348999023,
      "learning_rate": 0.00018,
      "loss": 2.2207,
      "step": 9
    },
    {
      "epoch": 0.0002289857837992558,
      "eval_loss": 0.6690574288368225,
      "eval_runtime": 914.7446,
      "eval_samples_per_second": 18.091,
      "eval_steps_per_second": 9.046,
      "step": 9
    },
    {
      "epoch": 0.00025442864866583975,
      "grad_norm": 9.91763687133789,
      "learning_rate": 0.0002,
      "loss": 3.1985,
      "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": 3461526803447808.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}