last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003880669415474169,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.880669415474169e-05,
      "grad_norm": 0.5085901021957397,
      "learning_rate": 2e-05,
      "loss": 1.3977,
      "step": 1
    },
    {
      "epoch": 3.880669415474169e-05,
      "eval_loss": 1.444132685661316,
      "eval_runtime": 490.6111,
      "eval_samples_per_second": 11.06,
      "eval_steps_per_second": 11.06,
      "step": 1
    },
    {
      "epoch": 7.761338830948338e-05,
      "grad_norm": 0.9531174302101135,
      "learning_rate": 4e-05,
      "loss": 1.2155,
      "step": 2
    },
    {
      "epoch": 0.00011642008246422508,
      "grad_norm": 0.7220588326454163,
      "learning_rate": 6e-05,
      "loss": 1.1571,
      "step": 3
    },
    {
      "epoch": 0.00011642008246422508,
      "eval_loss": 1.4257819652557373,
      "eval_runtime": 489.878,
      "eval_samples_per_second": 11.076,
      "eval_steps_per_second": 11.076,
      "step": 3
    },
    {
      "epoch": 0.00015522677661896676,
      "grad_norm": 1.264121413230896,
      "learning_rate": 8e-05,
      "loss": 1.1042,
      "step": 4
    },
    {
      "epoch": 0.00019403347077370846,
      "grad_norm": 0.9557339549064636,
      "learning_rate": 0.0001,
      "loss": 1.25,
      "step": 5
    },
    {
      "epoch": 0.00023284016492845016,
      "grad_norm": 0.6429188847541809,
      "learning_rate": 0.00012,
      "loss": 1.2236,
      "step": 6
    },
    {
      "epoch": 0.00023284016492845016,
      "eval_loss": 1.3257832527160645,
      "eval_runtime": 489.9181,
      "eval_samples_per_second": 11.075,
      "eval_steps_per_second": 11.075,
      "step": 6
    },
    {
      "epoch": 0.00027164685908319185,
      "grad_norm": 0.8257654905319214,
      "learning_rate": 0.00014,
      "loss": 1.1723,
      "step": 7
    },
    {
      "epoch": 0.0003104535532379335,
      "grad_norm": 0.8499470353126526,
      "learning_rate": 0.00016,
      "loss": 1.1895,
      "step": 8
    },
    {
      "epoch": 0.00034926024739267525,
      "grad_norm": 1.2237374782562256,
      "learning_rate": 0.00018,
      "loss": 1.2761,
      "step": 9
    },
    {
      "epoch": 0.00034926024739267525,
      "eval_loss": 1.176152229309082,
      "eval_runtime": 490.047,
      "eval_samples_per_second": 11.072,
      "eval_steps_per_second": 11.072,
      "step": 9
    },
    {
      "epoch": 0.0003880669415474169,
      "grad_norm": 0.6154380440711975,
      "learning_rate": 0.0002,
      "loss": 0.7538,
      "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": 1306268836823040.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}