last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00028650216667263544,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.8650216667263546e-05,
      "grad_norm": 2.263956069946289,
      "learning_rate": 2e-05,
      "loss": 1.8881,
      "step": 1
    },
    {
      "epoch": 2.8650216667263546e-05,
      "eval_loss": 0.4815528988838196,
      "eval_runtime": 501.2114,
      "eval_samples_per_second": 29.323,
      "eval_steps_per_second": 14.662,
      "step": 1
    },
    {
      "epoch": 5.730043333452709e-05,
      "grad_norm": 2.303901195526123,
      "learning_rate": 4e-05,
      "loss": 1.361,
      "step": 2
    },
    {
      "epoch": 8.595065000179063e-05,
      "grad_norm": 3.3438093662261963,
      "learning_rate": 6e-05,
      "loss": 2.5778,
      "step": 3
    },
    {
      "epoch": 8.595065000179063e-05,
      "eval_loss": 0.47494086623191833,
      "eval_runtime": 498.937,
      "eval_samples_per_second": 29.457,
      "eval_steps_per_second": 14.729,
      "step": 3
    },
    {
      "epoch": 0.00011460086666905418,
      "grad_norm": 2.527754545211792,
      "learning_rate": 8e-05,
      "loss": 1.5649,
      "step": 4
    },
    {
      "epoch": 0.00014325108333631772,
      "grad_norm": 2.9490365982055664,
      "learning_rate": 0.0001,
      "loss": 1.9874,
      "step": 5
    },
    {
      "epoch": 0.00017190130000358127,
      "grad_norm": 2.3964216709136963,
      "learning_rate": 0.00012,
      "loss": 1.5091,
      "step": 6
    },
    {
      "epoch": 0.00017190130000358127,
      "eval_loss": 0.4131721556186676,
      "eval_runtime": 500.2763,
      "eval_samples_per_second": 29.378,
      "eval_steps_per_second": 14.69,
      "step": 6
    },
    {
      "epoch": 0.00020055151667084482,
      "grad_norm": 2.542708396911621,
      "learning_rate": 0.00014,
      "loss": 1.2259,
      "step": 7
    },
    {
      "epoch": 0.00022920173333810837,
      "grad_norm": 2.9221901893615723,
      "learning_rate": 0.00016,
      "loss": 1.528,
      "step": 8
    },
    {
      "epoch": 0.0002578519500053719,
      "grad_norm": 3.213486671447754,
      "learning_rate": 0.00018,
      "loss": 1.2064,
      "step": 9
    },
    {
      "epoch": 0.0002578519500053719,
      "eval_loss": 0.2691572606563568,
      "eval_runtime": 500.1422,
      "eval_samples_per_second": 29.386,
      "eval_steps_per_second": 14.694,
      "step": 9
    },
    {
      "epoch": 0.00028650216667263544,
      "grad_norm": 4.0016584396362305,
      "learning_rate": 0.0002,
      "loss": 1.2215,
      "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": 1628733135912960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}