last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002841806125670982,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00031575623618566466,
      "grad_norm": 9.31529426574707,
      "learning_rate": 2e-05,
      "loss": 4.6027,
      "step": 1
    },
    {
      "epoch": 0.0006315124723713293,
      "grad_norm": 9.449015617370605,
      "learning_rate": 4e-05,
      "loss": 5.0384,
      "step": 2
    },
    {
      "epoch": 0.000947268708556994,
      "grad_norm": 7.18820858001709,
      "learning_rate": 6e-05,
      "loss": 3.8766,
      "step": 3
    },
    {
      "epoch": 0.000947268708556994,
      "eval_loss": 1.1006500720977783,
      "eval_runtime": 67.1068,
      "eval_samples_per_second": 19.879,
      "eval_steps_per_second": 9.939,
      "step": 3
    },
    {
      "epoch": 0.0012630249447426586,
      "grad_norm": 9.729961395263672,
      "learning_rate": 8e-05,
      "loss": 3.6835,
      "step": 4
    },
    {
      "epoch": 0.0015787811809283233,
      "grad_norm": 6.866478443145752,
      "learning_rate": 0.0001,
      "loss": 3.6681,
      "step": 5
    },
    {
      "epoch": 0.001894537417113988,
      "grad_norm": 11.468867301940918,
      "learning_rate": 0.00012,
      "loss": 4.1188,
      "step": 6
    },
    {
      "epoch": 0.001894537417113988,
      "eval_loss": 1.0359723567962646,
      "eval_runtime": 66.6466,
      "eval_samples_per_second": 20.016,
      "eval_steps_per_second": 10.008,
      "step": 6
    },
    {
      "epoch": 0.0022102936532996525,
      "grad_norm": 9.589306831359863,
      "learning_rate": 0.00014,
      "loss": 4.2976,
      "step": 7
    },
    {
      "epoch": 0.0025260498894853173,
      "grad_norm": 8.981024742126465,
      "learning_rate": 0.00016,
      "loss": 5.1871,
      "step": 8
    },
    {
      "epoch": 0.002841806125670982,
      "grad_norm": 7.4614644050598145,
      "learning_rate": 0.00018,
      "loss": 4.3596,
      "step": 9
    },
    {
      "epoch": 0.002841806125670982,
      "eval_loss": 1.0006051063537598,
      "eval_runtime": 67.0363,
      "eval_samples_per_second": 19.9,
      "eval_steps_per_second": 9.95,
      "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": 1752671799214080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}