last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03303964757709251,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011013215859030838,
      "eval_loss": 1.0214498043060303,
      "eval_runtime": 131.8379,
      "eval_samples_per_second": 2.905,
      "eval_steps_per_second": 1.456,
      "step": 1
    },
    {
      "epoch": 0.003303964757709251,
      "grad_norm": 0.8215807676315308,
      "learning_rate": 4e-05,
      "loss": 0.9981,
      "step": 3
    },
    {
      "epoch": 0.005506607929515419,
      "eval_loss": 0.9466868042945862,
      "eval_runtime": 131.3132,
      "eval_samples_per_second": 2.917,
      "eval_steps_per_second": 1.462,
      "step": 5
    },
    {
      "epoch": 0.006607929515418502,
      "grad_norm": 0.6482104063034058,
      "learning_rate": 8e-05,
      "loss": 0.9949,
      "step": 6
    },
    {
      "epoch": 0.009911894273127754,
      "grad_norm": 0.5679072141647339,
      "learning_rate": 0.00012,
      "loss": 0.7606,
      "step": 9
    },
    {
      "epoch": 0.011013215859030838,
      "eval_loss": 0.798348605632782,
      "eval_runtime": 131.3534,
      "eval_samples_per_second": 2.916,
      "eval_steps_per_second": 1.462,
      "step": 10
    },
    {
      "epoch": 0.013215859030837005,
      "grad_norm": 0.4688282907009125,
      "learning_rate": 0.00016,
      "loss": 0.8901,
      "step": 12
    },
    {
      "epoch": 0.016519823788546256,
      "grad_norm": 0.3975431025028229,
      "learning_rate": 0.0002,
      "loss": 0.6951,
      "step": 15
    },
    {
      "epoch": 0.016519823788546256,
      "eval_loss": 0.7155141234397888,
      "eval_runtime": 131.1724,
      "eval_samples_per_second": 2.92,
      "eval_steps_per_second": 1.464,
      "step": 15
    },
    {
      "epoch": 0.019823788546255508,
      "grad_norm": 0.5499920845031738,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.8033,
      "step": 18
    },
    {
      "epoch": 0.022026431718061675,
      "eval_loss": 0.6734703779220581,
      "eval_runtime": 131.2,
      "eval_samples_per_second": 2.919,
      "eval_steps_per_second": 1.463,
      "step": 20
    },
    {
      "epoch": 0.023127753303964757,
      "grad_norm": 0.36365655064582825,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6383,
      "step": 21
    },
    {
      "epoch": 0.02643171806167401,
      "grad_norm": 0.3813054859638214,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.6955,
      "step": 24
    },
    {
      "epoch": 0.02753303964757709,
      "eval_loss": 0.6509636640548706,
      "eval_runtime": 131.2701,
      "eval_samples_per_second": 2.918,
      "eval_steps_per_second": 1.463,
      "step": 25
    },
    {
      "epoch": 0.02973568281938326,
      "grad_norm": 0.4139375388622284,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.5708,
      "step": 27
    },
    {
      "epoch": 0.03303964757709251,
      "grad_norm": 0.3623638153076172,
      "learning_rate": 0.0,
      "loss": 0.6539,
      "step": 30
    },
    {
      "epoch": 0.03303964757709251,
      "eval_loss": 0.6442951560020447,
      "eval_runtime": 131.0953,
      "eval_samples_per_second": 2.922,
      "eval_steps_per_second": 1.465,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.1515104885407744e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}