trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9936628643852978,
  "eval_steps": 50,
  "global_step": 147,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06759611322348964,
      "grad_norm": 6.16084466512128,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.0855,
      "step": 10
    },
    {
      "epoch": 0.13519222644697929,
      "grad_norm": 3.497086396174302,
      "learning_rate": 9.964639423366442e-06,
      "loss": 0.7122,
      "step": 20
    },
    {
      "epoch": 0.20278833967046894,
      "grad_norm": 2.6933889117498127,
      "learning_rate": 9.68474862499881e-06,
      "loss": 0.5732,
      "step": 30
    },
    {
      "epoch": 0.27038445289395857,
      "grad_norm": 2.6966538346452094,
      "learning_rate": 9.140746393556853e-06,
      "loss": 0.5274,
      "step": 40
    },
    {
      "epoch": 0.33798056611744826,
      "grad_norm": 2.709346620508466,
      "learning_rate": 8.363301868506264e-06,
      "loss": 0.4945,
      "step": 50
    },
    {
      "epoch": 0.33798056611744826,
      "eval_loss": 0.4356246590614319,
      "eval_runtime": 6.3988,
      "eval_samples_per_second": 60.48,
      "eval_steps_per_second": 7.658,
      "step": 50
    },
    {
      "epoch": 0.4055766793409379,
      "grad_norm": 3.1656760844291267,
      "learning_rate": 7.396244933600285e-06,
      "loss": 0.476,
      "step": 60
    },
    {
      "epoch": 0.47317279256442757,
      "grad_norm": 2.5563614993729598,
      "learning_rate": 6.294095225512604e-06,
      "loss": 0.4591,
      "step": 70
    },
    {
      "epoch": 0.5407689057879171,
      "grad_norm": 2.392298112754115,
      "learning_rate": 5.118988487730537e-06,
      "loss": 0.44,
      "step": 80
    },
    {
      "epoch": 0.6083650190114068,
      "grad_norm": 2.598895314476247,
      "learning_rate": 3.937173552235117e-06,
      "loss": 0.4577,
      "step": 90
    },
    {
      "epoch": 0.6759611322348965,
      "grad_norm": 2.3301001202203975,
      "learning_rate": 2.8152774381532033e-06,
      "loss": 0.4438,
      "step": 100
    },
    {
      "epoch": 0.6759611322348965,
      "eval_loss": 0.3885859251022339,
      "eval_runtime": 6.3869,
      "eval_samples_per_second": 60.593,
      "eval_steps_per_second": 7.672,
      "step": 100
    },
    {
      "epoch": 0.7435572454583862,
      "grad_norm": 2.41225835615904,
      "learning_rate": 1.8165491294045596e-06,
      "loss": 0.44,
      "step": 110
    },
    {
      "epoch": 0.8111533586818758,
      "grad_norm": 2.3212619903795653,
      "learning_rate": 9.972937953781985e-07,
      "loss": 0.4203,
      "step": 120
    },
    {
      "epoch": 0.8787494719053655,
      "grad_norm": 2.3281357946059558,
      "learning_rate": 4.036984820916723e-07,
      "loss": 0.4026,
      "step": 130
    },
    {
      "epoch": 0.9463455851288551,
      "grad_norm": 2.4364627230218816,
      "learning_rate": 6.922823140906754e-08,
      "loss": 0.4334,
      "step": 140
    },
    {
      "epoch": 0.9936628643852978,
      "step": 147,
      "total_flos": 55493244223488.0,
      "train_loss": 0.5211580756570207,
      "train_runtime": 1269.1418,
      "train_samples_per_second": 14.918,
      "train_steps_per_second": 0.116
    }
  ],
  "logging_steps": 10,
  "max_steps": 147,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 55493244223488.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}