last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04748713889988128,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015829046299960427,
      "eval_loss": 3.308307647705078,
      "eval_runtime": 29.2827,
      "eval_samples_per_second": 9.118,
      "eval_steps_per_second": 4.576,
      "step": 1
    },
    {
      "epoch": 0.004748713889988128,
      "grad_norm": 1.196844220161438,
      "learning_rate": 4e-05,
      "loss": 12.8218,
      "step": 3
    },
    {
      "epoch": 0.007914523149980214,
      "eval_loss": 3.297595500946045,
      "eval_runtime": 29.4236,
      "eval_samples_per_second": 9.074,
      "eval_steps_per_second": 4.554,
      "step": 5
    },
    {
      "epoch": 0.009497427779976256,
      "grad_norm": 1.2031594514846802,
      "learning_rate": 8e-05,
      "loss": 13.3919,
      "step": 6
    },
    {
      "epoch": 0.014246141669964385,
      "grad_norm": 1.380180835723877,
      "learning_rate": 0.00012,
      "loss": 12.9002,
      "step": 9
    },
    {
      "epoch": 0.015829046299960427,
      "eval_loss": 3.203984022140503,
      "eval_runtime": 29.468,
      "eval_samples_per_second": 9.061,
      "eval_steps_per_second": 4.547,
      "step": 10
    },
    {
      "epoch": 0.018994855559952513,
      "grad_norm": 1.636251449584961,
      "learning_rate": 0.00016,
      "loss": 12.8921,
      "step": 12
    },
    {
      "epoch": 0.02374356944994064,
      "grad_norm": 2.213144063949585,
      "learning_rate": 0.0002,
      "loss": 12.4253,
      "step": 15
    },
    {
      "epoch": 0.02374356944994064,
      "eval_loss": 2.9763691425323486,
      "eval_runtime": 28.8362,
      "eval_samples_per_second": 9.259,
      "eval_steps_per_second": 4.647,
      "step": 15
    },
    {
      "epoch": 0.02849228333992877,
      "grad_norm": 2.92785382270813,
      "learning_rate": 0.00018090169943749476,
      "loss": 12.2475,
      "step": 18
    },
    {
      "epoch": 0.031658092599920855,
      "eval_loss": 2.8532521724700928,
      "eval_runtime": 29.2118,
      "eval_samples_per_second": 9.14,
      "eval_steps_per_second": 4.587,
      "step": 20
    },
    {
      "epoch": 0.0332409972299169,
      "grad_norm": 3.543342113494873,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.1149,
      "step": 21
    },
    {
      "epoch": 0.037989711119905026,
      "grad_norm": 3.853139877319336,
      "learning_rate": 6.909830056250527e-05,
      "loss": 11.0996,
      "step": 24
    },
    {
      "epoch": 0.03957261574990107,
      "eval_loss": 2.788191080093384,
      "eval_runtime": 29.2926,
      "eval_samples_per_second": 9.115,
      "eval_steps_per_second": 4.575,
      "step": 25
    },
    {
      "epoch": 0.04273842500989315,
      "grad_norm": 3.464561939239502,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 11.4012,
      "step": 27
    },
    {
      "epoch": 0.04748713889988128,
      "grad_norm": 3.4989161491394043,
      "learning_rate": 0.0,
      "loss": 11.0014,
      "step": 30
    },
    {
      "epoch": 0.04748713889988128,
      "eval_loss": 2.768246650695801,
      "eval_runtime": 26.7805,
      "eval_samples_per_second": 9.97,
      "eval_steps_per_second": 5.004,
      "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": 1792376423055360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}