last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0001693870939738424,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.693870939738424e-05,
      "grad_norm": 22.163108825683594,
      "learning_rate": 2e-05,
      "loss": 21.3169,
      "step": 1
    },
    {
      "epoch": 1.693870939738424e-05,
      "eval_loss": 2.290062189102173,
      "eval_runtime": 5153.9246,
      "eval_samples_per_second": 9.646,
      "eval_steps_per_second": 4.823,
      "step": 1
    },
    {
      "epoch": 3.387741879476848e-05,
      "grad_norm": 31.874303817749023,
      "learning_rate": 4e-05,
      "loss": 19.141,
      "step": 2
    },
    {
      "epoch": 5.081612819215272e-05,
      "grad_norm": 16.09918212890625,
      "learning_rate": 6e-05,
      "loss": 16.7916,
      "step": 3
    },
    {
      "epoch": 6.775483758953696e-05,
      "grad_norm": 25.90465545654297,
      "learning_rate": 8e-05,
      "loss": 19.5082,
      "step": 4
    },
    {
      "epoch": 8.46935469869212e-05,
      "grad_norm": 19.378210067749023,
      "learning_rate": 0.0001,
      "loss": 17.8913,
      "step": 5
    },
    {
      "epoch": 8.46935469869212e-05,
      "eval_loss": 2.2351300716400146,
      "eval_runtime": 5147.8027,
      "eval_samples_per_second": 9.658,
      "eval_steps_per_second": 4.829,
      "step": 5
    },
    {
      "epoch": 0.00010163225638430543,
      "grad_norm": 19.173131942749023,
      "learning_rate": 0.00012,
      "loss": 17.3923,
      "step": 6
    },
    {
      "epoch": 0.00011857096578168967,
      "grad_norm": 32.09618377685547,
      "learning_rate": 0.00014,
      "loss": 20.1479,
      "step": 7
    },
    {
      "epoch": 0.0001355096751790739,
      "grad_norm": 21.93677520751953,
      "learning_rate": 0.00016,
      "loss": 17.782,
      "step": 8
    },
    {
      "epoch": 0.00015244838457645815,
      "grad_norm": 21.510074615478516,
      "learning_rate": 0.00018,
      "loss": 17.7573,
      "step": 9
    },
    {
      "epoch": 0.0001693870939738424,
      "grad_norm": 40.90770721435547,
      "learning_rate": 0.0002,
      "loss": 20.1925,
      "step": 10
    },
    {
      "epoch": 0.0001693870939738424,
      "eval_loss": 2.188427686691284,
      "eval_runtime": 5141.4887,
      "eval_samples_per_second": 9.669,
      "eval_steps_per_second": 4.835,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.402135828758528e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}