last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.017052721330112264,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005684240443370755,
      "eval_loss": 2.5152714252471924,
      "eval_runtime": 44.5753,
      "eval_samples_per_second": 16.624,
      "eval_steps_per_second": 8.323,
      "step": 1
    },
    {
      "epoch": 0.0017052721330112265,
      "grad_norm": 1.4441981315612793,
      "learning_rate": 3e-05,
      "loss": 2.2584,
      "step": 3
    },
    {
      "epoch": 0.002842120221685377,
      "eval_loss": 2.496779203414917,
      "eval_runtime": 43.489,
      "eval_samples_per_second": 17.039,
      "eval_steps_per_second": 8.531,
      "step": 5
    },
    {
      "epoch": 0.003410544266022453,
      "grad_norm": 1.1282055377960205,
      "learning_rate": 6e-05,
      "loss": 2.4447,
      "step": 6
    },
    {
      "epoch": 0.005115816399033679,
      "grad_norm": 1.5021233558654785,
      "learning_rate": 9e-05,
      "loss": 2.2768,
      "step": 9
    },
    {
      "epoch": 0.005684240443370754,
      "eval_loss": 2.324876546859741,
      "eval_runtime": 43.5022,
      "eval_samples_per_second": 17.034,
      "eval_steps_per_second": 8.528,
      "step": 10
    },
    {
      "epoch": 0.006821088532044906,
      "grad_norm": 1.4783978462219238,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.3298,
      "step": 12
    },
    {
      "epoch": 0.008526360665056132,
      "grad_norm": 1.7873011827468872,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.3034,
      "step": 15
    },
    {
      "epoch": 0.008526360665056132,
      "eval_loss": 2.2579123973846436,
      "eval_runtime": 43.5312,
      "eval_samples_per_second": 17.022,
      "eval_steps_per_second": 8.523,
      "step": 15
    },
    {
      "epoch": 0.010231632798067358,
      "grad_norm": 1.354712963104248,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.0323,
      "step": 18
    },
    {
      "epoch": 0.011368480886741509,
      "eval_loss": 2.1692159175872803,
      "eval_runtime": 43.4964,
      "eval_samples_per_second": 17.036,
      "eval_steps_per_second": 8.529,
      "step": 20
    },
    {
      "epoch": 0.011936904931078584,
      "grad_norm": 1.7508783340454102,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 2.0437,
      "step": 21
    },
    {
      "epoch": 0.013642177064089812,
      "grad_norm": 1.6392158269882202,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.0193,
      "step": 24
    },
    {
      "epoch": 0.014210601108426887,
      "eval_loss": 2.1386632919311523,
      "eval_runtime": 43.4885,
      "eval_samples_per_second": 17.039,
      "eval_steps_per_second": 8.531,
      "step": 25
    },
    {
      "epoch": 0.015347449197101038,
      "grad_norm": 1.4378986358642578,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.913,
      "step": 27
    },
    {
      "epoch": 0.017052721330112264,
      "grad_norm": 1.2889617681503296,
      "learning_rate": 0.0,
      "loss": 2.0382,
      "step": 30
    },
    {
      "epoch": 0.017052721330112264,
      "eval_loss": 2.1310107707977295,
      "eval_runtime": 43.4946,
      "eval_samples_per_second": 17.037,
      "eval_steps_per_second": 8.53,
      "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": 1.1221045163851776e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}