checkpoint-133/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 133,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15037593984962405,
      "grad_norm": 0.5201665759086609,
      "learning_rate": 0.0002,
      "loss": 1.0025,
      "step": 10
    },
    {
      "epoch": 0.3007518796992481,
      "grad_norm": 0.1790522187948227,
      "learning_rate": 0.0002,
      "loss": 0.6023,
      "step": 20
    },
    {
      "epoch": 0.45112781954887216,
      "grad_norm": 0.19227077066898346,
      "learning_rate": 0.0002,
      "loss": 0.5238,
      "step": 30
    },
    {
      "epoch": 0.6015037593984962,
      "grad_norm": 0.167165145277977,
      "learning_rate": 0.0002,
      "loss": 0.5075,
      "step": 40
    },
    {
      "epoch": 0.7518796992481203,
      "grad_norm": 0.15390199422836304,
      "learning_rate": 0.0002,
      "loss": 0.4849,
      "step": 50
    },
    {
      "epoch": 0.9022556390977443,
      "grad_norm": 0.15909235179424286,
      "learning_rate": 0.0002,
      "loss": 0.473,
      "step": 60
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 0.12911486625671387,
      "learning_rate": 0.0002,
      "loss": 0.441,
      "step": 70
    },
    {
      "epoch": 1.2030075187969924,
      "grad_norm": 0.15087230503559113,
      "learning_rate": 0.0002,
      "loss": 0.3775,
      "step": 80
    },
    {
      "epoch": 1.3533834586466165,
      "grad_norm": 0.14530335366725922,
      "learning_rate": 0.0002,
      "loss": 0.3831,
      "step": 90
    },
    {
      "epoch": 1.5037593984962405,
      "grad_norm": 0.13804097473621368,
      "learning_rate": 0.0002,
      "loss": 0.3766,
      "step": 100
    },
    {
      "epoch": 1.6541353383458648,
      "grad_norm": 0.1351165771484375,
      "learning_rate": 0.0002,
      "loss": 0.3823,
      "step": 110
    },
    {
      "epoch": 1.8045112781954886,
      "grad_norm": 0.14214953780174255,
      "learning_rate": 0.0002,
      "loss": 0.3862,
      "step": 120
    },
    {
      "epoch": 1.954887218045113,
      "grad_norm": 0.14559713006019592,
      "learning_rate": 0.0002,
      "loss": 0.385,
      "step": 130
    }
  ],
  "logging_steps": 10,
  "max_steps": 198,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.14459808270123e+17,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}