last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004209197095654004,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004209197095654004,
      "grad_norm": 2.5869503021240234,
      "learning_rate": 2e-05,
      "loss": 2.4955,
      "step": 1
    },
    {
      "epoch": 0.0008418394191308007,
      "grad_norm": 2.541443109512329,
      "learning_rate": 4e-05,
      "loss": 2.5652,
      "step": 2
    },
    {
      "epoch": 0.0012627591286962013,
      "grad_norm": 2.7070512771606445,
      "learning_rate": 6e-05,
      "loss": 2.7273,
      "step": 3
    },
    {
      "epoch": 0.0012627591286962013,
      "eval_loss": 2.437267780303955,
      "eval_runtime": 47.3731,
      "eval_samples_per_second": 21.13,
      "eval_steps_per_second": 10.576,
      "step": 3
    },
    {
      "epoch": 0.0016836788382616015,
      "grad_norm": 2.4585676193237305,
      "learning_rate": 8e-05,
      "loss": 2.2576,
      "step": 4
    },
    {
      "epoch": 0.002104598547827002,
      "grad_norm": 2.4750375747680664,
      "learning_rate": 0.0001,
      "loss": 2.1981,
      "step": 5
    },
    {
      "epoch": 0.0025255182573924026,
      "grad_norm": 2.8116369247436523,
      "learning_rate": 0.00012,
      "loss": 2.3254,
      "step": 6
    },
    {
      "epoch": 0.0025255182573924026,
      "eval_loss": 2.21653413772583,
      "eval_runtime": 44.4526,
      "eval_samples_per_second": 22.518,
      "eval_steps_per_second": 11.27,
      "step": 6
    },
    {
      "epoch": 0.002946437966957803,
      "grad_norm": 2.617342710494995,
      "learning_rate": 0.00014,
      "loss": 2.1602,
      "step": 7
    },
    {
      "epoch": 0.003367357676523203,
      "grad_norm": 2.897243022918701,
      "learning_rate": 0.00016,
      "loss": 1.8888,
      "step": 8
    },
    {
      "epoch": 0.0037882773860886034,
      "grad_norm": 2.5292551517486572,
      "learning_rate": 0.00018,
      "loss": 1.9284,
      "step": 9
    },
    {
      "epoch": 0.0037882773860886034,
      "eval_loss": 1.7655130624771118,
      "eval_runtime": 44.8931,
      "eval_samples_per_second": 22.297,
      "eval_steps_per_second": 11.16,
      "step": 9
    },
    {
      "epoch": 0.004209197095654004,
      "grad_norm": 2.9057798385620117,
      "learning_rate": 0.0002,
      "loss": 1.9081,
      "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": 89038163804160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}