last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.243478260869565,
  "eval_steps": 25,
  "global_step": 11,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2782608695652174,
      "grad_norm": 9.516831398010254,
      "learning_rate": 9.81771838126524e-05,
      "loss": 4.754,
      "step": 1
    },
    {
      "epoch": 0.2782608695652174,
      "eval_loss": 4.028190612792969,
      "eval_runtime": 4.778,
      "eval_samples_per_second": 10.465,
      "eval_steps_per_second": 2.721,
      "step": 1
    },
    {
      "epoch": 0.5565217391304348,
      "grad_norm": 6.878223896026611,
      "learning_rate": 9.285640897740315e-05,
      "loss": 3.6801,
      "step": 2
    },
    {
      "epoch": 0.8347826086956521,
      "grad_norm": 3.9273295402526855,
      "learning_rate": 8.446873302753784e-05,
      "loss": 2.9229,
      "step": 3
    },
    {
      "epoch": 1.1739130434782608,
      "grad_norm": 12.356541633605957,
      "learning_rate": 7.369367558508489e-05,
      "loss": 4.8926,
      "step": 4
    },
    {
      "epoch": 1.4521739130434783,
      "grad_norm": 7.297130584716797,
      "learning_rate": 6.140416772229784e-05,
      "loss": 2.3841,
      "step": 5
    },
    {
      "epoch": 1.7304347826086957,
      "grad_norm": 4.193726062774658,
      "learning_rate": 4.859583227770218e-05,
      "loss": 2.4246,
      "step": 6
    },
    {
      "epoch": 2.0695652173913044,
      "grad_norm": 4.52116584777832,
      "learning_rate": 3.630632441491512e-05,
      "loss": 3.4063,
      "step": 7
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 2.53560733795166,
      "learning_rate": 2.5531266972462177e-05,
      "loss": 2.1103,
      "step": 8
    },
    {
      "epoch": 2.626086956521739,
      "grad_norm": 3.1475982666015625,
      "learning_rate": 1.7143591022596845e-05,
      "loss": 1.8013,
      "step": 9
    },
    {
      "epoch": 2.9043478260869566,
      "grad_norm": 4.16361141204834,
      "learning_rate": 1.1822816187347623e-05,
      "loss": 2.8903,
      "step": 10
    },
    {
      "epoch": 3.243478260869565,
      "grad_norm": 3.3099284172058105,
      "learning_rate": 1e-05,
      "loss": 2.1938,
      "step": 11
    }
  ],
  "logging_steps": 1,
  "max_steps": 11,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.358385455782953e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}