last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0221606648199446,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00221606648199446,
      "grad_norm": 0.18554984033107758,
      "learning_rate": 2e-05,
      "loss": 0.3396,
      "step": 1
    },
    {
      "epoch": 0.00443213296398892,
      "grad_norm": 0.21258427202701569,
      "learning_rate": 4e-05,
      "loss": 0.3511,
      "step": 2
    },
    {
      "epoch": 0.006648199445983379,
      "grad_norm": 0.19484710693359375,
      "learning_rate": 6e-05,
      "loss": 0.2573,
      "step": 3
    },
    {
      "epoch": 0.006648199445983379,
      "eval_loss": 0.33617910742759705,
      "eval_runtime": 16.4143,
      "eval_samples_per_second": 11.575,
      "eval_steps_per_second": 5.788,
      "step": 3
    },
    {
      "epoch": 0.00886426592797784,
      "grad_norm": 0.21325641870498657,
      "learning_rate": 8e-05,
      "loss": 0.3279,
      "step": 4
    },
    {
      "epoch": 0.0110803324099723,
      "grad_norm": 0.19823859632015228,
      "learning_rate": 0.0001,
      "loss": 0.3385,
      "step": 5
    },
    {
      "epoch": 0.013296398891966758,
      "grad_norm": 0.22237731516361237,
      "learning_rate": 0.00012,
      "loss": 0.3052,
      "step": 6
    },
    {
      "epoch": 0.013296398891966758,
      "eval_loss": 0.3171418011188507,
      "eval_runtime": 16.4816,
      "eval_samples_per_second": 11.528,
      "eval_steps_per_second": 5.764,
      "step": 6
    },
    {
      "epoch": 0.01551246537396122,
      "grad_norm": 0.2168574333190918,
      "learning_rate": 0.00014,
      "loss": 0.3258,
      "step": 7
    },
    {
      "epoch": 0.01772853185595568,
      "grad_norm": 0.22396127879619598,
      "learning_rate": 0.00016,
      "loss": 0.2401,
      "step": 8
    },
    {
      "epoch": 0.019944598337950138,
      "grad_norm": 0.3879891037940979,
      "learning_rate": 0.00018,
      "loss": 0.2834,
      "step": 9
    },
    {
      "epoch": 0.019944598337950138,
      "eval_loss": 0.2934502065181732,
      "eval_runtime": 16.4438,
      "eval_samples_per_second": 11.554,
      "eval_steps_per_second": 5.777,
      "step": 9
    },
    {
      "epoch": 0.0221606648199446,
      "grad_norm": 0.1541282683610916,
      "learning_rate": 0.0002,
      "loss": 0.3023,
      "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": 2221860958765056.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}