last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04195804195804196,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004662004662004662,
      "grad_norm": 1.8823851346969604,
      "learning_rate": 2e-05,
      "loss": 2.5338,
      "step": 1
    },
    {
      "epoch": 0.004662004662004662,
      "eval_loss": 2.43222975730896,
      "eval_runtime": 23.5145,
      "eval_samples_per_second": 3.87,
      "eval_steps_per_second": 1.956,
      "step": 1
    },
    {
      "epoch": 0.009324009324009324,
      "grad_norm": 1.8490875959396362,
      "learning_rate": 4e-05,
      "loss": 2.5053,
      "step": 2
    },
    {
      "epoch": 0.013986013986013986,
      "grad_norm": 1.7731785774230957,
      "learning_rate": 6e-05,
      "loss": 2.4701,
      "step": 3
    },
    {
      "epoch": 0.013986013986013986,
      "eval_loss": 2.3677921295166016,
      "eval_runtime": 22.8875,
      "eval_samples_per_second": 3.976,
      "eval_steps_per_second": 2.01,
      "step": 3
    },
    {
      "epoch": 0.018648018648018648,
      "grad_norm": 1.8156577348709106,
      "learning_rate": 8e-05,
      "loss": 2.4177,
      "step": 4
    },
    {
      "epoch": 0.023310023310023312,
      "grad_norm": 1.799171805381775,
      "learning_rate": 0.0001,
      "loss": 2.258,
      "step": 5
    },
    {
      "epoch": 0.027972027972027972,
      "grad_norm": 1.4947116374969482,
      "learning_rate": 0.00012,
      "loss": 1.9516,
      "step": 6
    },
    {
      "epoch": 0.027972027972027972,
      "eval_loss": 1.6914260387420654,
      "eval_runtime": 22.9057,
      "eval_samples_per_second": 3.973,
      "eval_steps_per_second": 2.008,
      "step": 6
    },
    {
      "epoch": 0.03263403263403263,
      "grad_norm": 1.7764925956726074,
      "learning_rate": 0.00014,
      "loss": 1.7216,
      "step": 7
    },
    {
      "epoch": 0.037296037296037296,
      "grad_norm": 2.334268808364868,
      "learning_rate": 0.00016,
      "loss": 1.5436,
      "step": 8
    },
    {
      "epoch": 0.04195804195804196,
      "grad_norm": 2.2170941829681396,
      "learning_rate": 0.00018,
      "loss": 1.2657,
      "step": 9
    },
    {
      "epoch": 0.04195804195804196,
      "eval_loss": 0.9850502610206604,
      "eval_runtime": 22.9684,
      "eval_samples_per_second": 3.962,
      "eval_steps_per_second": 2.003,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6676985552044032.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}