last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0016300582745833164,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016300582745833165,
      "grad_norm": 1.1543225049972534,
      "learning_rate": 2e-05,
      "loss": 1.4298,
      "step": 1
    },
    {
      "epoch": 0.00016300582745833165,
      "eval_loss": 1.5093533992767334,
      "eval_runtime": 786.8257,
      "eval_samples_per_second": 3.283,
      "eval_steps_per_second": 1.642,
      "step": 1
    },
    {
      "epoch": 0.0003260116549166633,
      "grad_norm": 1.0734559297561646,
      "learning_rate": 4e-05,
      "loss": 1.7919,
      "step": 2
    },
    {
      "epoch": 0.0004890174823749949,
      "grad_norm": 1.3371057510375977,
      "learning_rate": 6e-05,
      "loss": 1.5337,
      "step": 3
    },
    {
      "epoch": 0.0004890174823749949,
      "eval_loss": 1.505882978439331,
      "eval_runtime": 788.72,
      "eval_samples_per_second": 3.275,
      "eval_steps_per_second": 1.638,
      "step": 3
    },
    {
      "epoch": 0.0006520233098333266,
      "grad_norm": 1.652315378189087,
      "learning_rate": 8e-05,
      "loss": 1.8656,
      "step": 4
    },
    {
      "epoch": 0.0008150291372916582,
      "grad_norm": 1.0174154043197632,
      "learning_rate": 0.0001,
      "loss": 1.2689,
      "step": 5
    },
    {
      "epoch": 0.0009780349647499898,
      "grad_norm": 0.7671542763710022,
      "learning_rate": 0.00012,
      "loss": 1.6685,
      "step": 6
    },
    {
      "epoch": 0.0009780349647499898,
      "eval_loss": 1.4657011032104492,
      "eval_runtime": 788.5529,
      "eval_samples_per_second": 3.276,
      "eval_steps_per_second": 1.638,
      "step": 6
    },
    {
      "epoch": 0.0011410407922083214,
      "grad_norm": 0.8560234308242798,
      "learning_rate": 0.00014,
      "loss": 1.5098,
      "step": 7
    },
    {
      "epoch": 0.0013040466196666532,
      "grad_norm": 3.3206217288970947,
      "learning_rate": 0.00016,
      "loss": 2.1037,
      "step": 8
    },
    {
      "epoch": 0.0014670524471249848,
      "grad_norm": 0.6197188496589661,
      "learning_rate": 0.00018,
      "loss": 1.4734,
      "step": 9
    },
    {
      "epoch": 0.0014670524471249848,
      "eval_loss": 1.3432879447937012,
      "eval_runtime": 788.8077,
      "eval_samples_per_second": 3.275,
      "eval_steps_per_second": 1.638,
      "step": 9
    },
    {
      "epoch": 0.0016300582745833164,
      "grad_norm": 0.623649537563324,
      "learning_rate": 0.0002,
      "loss": 1.1344,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5589685858467840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}