last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006670619626445301,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.411799584939223e-05,
      "grad_norm": 0.6643247008323669,
      "learning_rate": 2e-05,
      "loss": 1.953,
      "step": 1
    },
    {
      "epoch": 7.411799584939223e-05,
      "eval_loss": 2.0409247875213623,
      "eval_runtime": 260.8967,
      "eval_samples_per_second": 21.775,
      "eval_steps_per_second": 10.889,
      "step": 1
    },
    {
      "epoch": 0.00014823599169878446,
      "grad_norm": 0.5005900263786316,
      "learning_rate": 4e-05,
      "loss": 2.2695,
      "step": 2
    },
    {
      "epoch": 0.0002223539875481767,
      "grad_norm": 0.4671008586883545,
      "learning_rate": 6e-05,
      "loss": 2.3442,
      "step": 3
    },
    {
      "epoch": 0.0002223539875481767,
      "eval_loss": 2.0367813110351562,
      "eval_runtime": 259.1545,
      "eval_samples_per_second": 21.921,
      "eval_steps_per_second": 10.963,
      "step": 3
    },
    {
      "epoch": 0.0002964719833975689,
      "grad_norm": 0.6753953099250793,
      "learning_rate": 8e-05,
      "loss": 2.3004,
      "step": 4
    },
    {
      "epoch": 0.0003705899792469612,
      "grad_norm": 0.6175580024719238,
      "learning_rate": 0.0001,
      "loss": 2.1341,
      "step": 5
    },
    {
      "epoch": 0.0004447079750963534,
      "grad_norm": 1.1478474140167236,
      "learning_rate": 0.00012,
      "loss": 1.6489,
      "step": 6
    },
    {
      "epoch": 0.0004447079750963534,
      "eval_loss": 1.9228562116622925,
      "eval_runtime": 259.5731,
      "eval_samples_per_second": 21.886,
      "eval_steps_per_second": 10.945,
      "step": 6
    },
    {
      "epoch": 0.0005188259709457457,
      "grad_norm": 0.5905793309211731,
      "learning_rate": 0.00014,
      "loss": 2.2964,
      "step": 7
    },
    {
      "epoch": 0.0005929439667951378,
      "grad_norm": 1.2702723741531372,
      "learning_rate": 0.00016,
      "loss": 1.4202,
      "step": 8
    },
    {
      "epoch": 0.0006670619626445301,
      "grad_norm": 0.6873392462730408,
      "learning_rate": 0.00018,
      "loss": 1.9848,
      "step": 9
    },
    {
      "epoch": 0.0006670619626445301,
      "eval_loss": 1.632455825805664,
      "eval_runtime": 259.5253,
      "eval_samples_per_second": 21.89,
      "eval_steps_per_second": 10.947,
      "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": 2849583755427840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}