last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006159215726530822,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00020530719088436073,
      "eval_loss": 0.9339624047279358,
      "eval_runtime": 66.9622,
      "eval_samples_per_second": 30.629,
      "eval_steps_per_second": 15.322,
      "step": 1
    },
    {
      "epoch": 0.0006159215726530821,
      "grad_norm": 3.8116061687469482,
      "learning_rate": 3e-05,
      "loss": 8.9118,
      "step": 3
    },
    {
      "epoch": 0.0010265359544218036,
      "eval_loss": 0.931273877620697,
      "eval_runtime": 65.1942,
      "eval_samples_per_second": 31.46,
      "eval_steps_per_second": 15.738,
      "step": 5
    },
    {
      "epoch": 0.0012318431453061643,
      "grad_norm": 12.710003852844238,
      "learning_rate": 6e-05,
      "loss": 10.8839,
      "step": 6
    },
    {
      "epoch": 0.0018477647179592465,
      "grad_norm": 14.395166397094727,
      "learning_rate": 9e-05,
      "loss": 11.4354,
      "step": 9
    },
    {
      "epoch": 0.002053071908843607,
      "eval_loss": 0.8914007544517517,
      "eval_runtime": 65.1581,
      "eval_samples_per_second": 31.477,
      "eval_steps_per_second": 15.746,
      "step": 10
    },
    {
      "epoch": 0.0024636862906123286,
      "grad_norm": 10.116308212280273,
      "learning_rate": 9.755282581475769e-05,
      "loss": 8.9857,
      "step": 12
    },
    {
      "epoch": 0.003079607863265411,
      "grad_norm": 10.924723625183105,
      "learning_rate": 8.535533905932738e-05,
      "loss": 7.3211,
      "step": 15
    },
    {
      "epoch": 0.003079607863265411,
      "eval_loss": 0.8407554030418396,
      "eval_runtime": 65.2409,
      "eval_samples_per_second": 31.437,
      "eval_steps_per_second": 15.726,
      "step": 15
    },
    {
      "epoch": 0.003695529435918493,
      "grad_norm": 13.506694793701172,
      "learning_rate": 6.545084971874738e-05,
      "loss": 8.1083,
      "step": 18
    },
    {
      "epoch": 0.004106143817687214,
      "eval_loss": 0.8125434517860413,
      "eval_runtime": 65.1722,
      "eval_samples_per_second": 31.47,
      "eval_steps_per_second": 15.743,
      "step": 20
    },
    {
      "epoch": 0.004311451008571575,
      "grad_norm": 13.035810470581055,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 7.1339,
      "step": 21
    },
    {
      "epoch": 0.004927372581224657,
      "grad_norm": 9.902789115905762,
      "learning_rate": 2.061073738537635e-05,
      "loss": 5.4977,
      "step": 24
    },
    {
      "epoch": 0.0051326797721090184,
      "eval_loss": 0.7941518425941467,
      "eval_runtime": 65.2408,
      "eval_samples_per_second": 31.437,
      "eval_steps_per_second": 15.726,
      "step": 25
    },
    {
      "epoch": 0.005543294153877739,
      "grad_norm": 8.039051055908203,
      "learning_rate": 5.449673790581611e-06,
      "loss": 6.109,
      "step": 27
    },
    {
      "epoch": 0.006159215726530822,
      "grad_norm": 13.466979026794434,
      "learning_rate": 0.0,
      "loss": 6.987,
      "step": 30
    },
    {
      "epoch": 0.006159215726530822,
      "eval_loss": 0.7893955707550049,
      "eval_runtime": 65.2128,
      "eval_samples_per_second": 31.451,
      "eval_steps_per_second": 15.733,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4387988985348096.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}