last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00017722876245585895,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.7722876245585897e-05,
      "grad_norm": 1.3439900875091553,
      "learning_rate": 2e-05,
      "loss": 1.8227,
      "step": 1
    },
    {
      "epoch": 3.5445752491171794e-05,
      "grad_norm": 0.9422560930252075,
      "learning_rate": 4e-05,
      "loss": 1.2666,
      "step": 2
    },
    {
      "epoch": 5.316862873675769e-05,
      "grad_norm": 1.6748251914978027,
      "learning_rate": 6e-05,
      "loss": 2.3018,
      "step": 3
    },
    {
      "epoch": 5.316862873675769e-05,
      "eval_loss": 2.190770387649536,
      "eval_runtime": 1243.6417,
      "eval_samples_per_second": 19.104,
      "eval_steps_per_second": 9.552,
      "step": 3
    },
    {
      "epoch": 7.089150498234359e-05,
      "grad_norm": 1.9085613489151,
      "learning_rate": 8e-05,
      "loss": 2.3133,
      "step": 4
    },
    {
      "epoch": 8.861438122792948e-05,
      "grad_norm": 1.7611125707626343,
      "learning_rate": 0.0001,
      "loss": 2.2499,
      "step": 5
    },
    {
      "epoch": 0.00010633725747351538,
      "grad_norm": 2.2537074089050293,
      "learning_rate": 0.00012,
      "loss": 2.0662,
      "step": 6
    },
    {
      "epoch": 0.00010633725747351538,
      "eval_loss": 1.8127288818359375,
      "eval_runtime": 1249.5736,
      "eval_samples_per_second": 19.013,
      "eval_steps_per_second": 9.506,
      "step": 6
    },
    {
      "epoch": 0.00012406013371910128,
      "grad_norm": 1.4571468830108643,
      "learning_rate": 0.00014,
      "loss": 1.1742,
      "step": 7
    },
    {
      "epoch": 0.00014178300996468718,
      "grad_norm": 1.365078091621399,
      "learning_rate": 0.00016,
      "loss": 1.3437,
      "step": 8
    },
    {
      "epoch": 0.00015950588621027308,
      "grad_norm": 1.2348759174346924,
      "learning_rate": 0.00018,
      "loss": 1.1785,
      "step": 9
    },
    {
      "epoch": 0.00015950588621027308,
      "eval_loss": 1.2093638181686401,
      "eval_runtime": 1246.7289,
      "eval_samples_per_second": 19.056,
      "eval_steps_per_second": 9.528,
      "step": 9
    },
    {
      "epoch": 0.00017722876245585895,
      "grad_norm": 1.0697853565216064,
      "learning_rate": 0.0002,
      "loss": 1.1478,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1771409642618880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}