last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002919068817047362,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00029190688170473617,
      "grad_norm": 1.1034588813781738,
      "learning_rate": 2e-05,
      "loss": 2.8594,
      "step": 1
    },
    {
      "epoch": 0.00029190688170473617,
      "eval_loss": 3.0735156536102295,
      "eval_runtime": 157.4323,
      "eval_samples_per_second": 4.586,
      "eval_steps_per_second": 4.586,
      "step": 1
    },
    {
      "epoch": 0.0005838137634094723,
      "grad_norm": 1.5020511150360107,
      "learning_rate": 4e-05,
      "loss": 2.6109,
      "step": 2
    },
    {
      "epoch": 0.0008757206451142086,
      "grad_norm": 0.7591434717178345,
      "learning_rate": 6e-05,
      "loss": 2.0645,
      "step": 3
    },
    {
      "epoch": 0.0008757206451142086,
      "eval_loss": 2.9684507846832275,
      "eval_runtime": 156.9028,
      "eval_samples_per_second": 4.602,
      "eval_steps_per_second": 4.602,
      "step": 3
    },
    {
      "epoch": 0.0011676275268189447,
      "grad_norm": 1.551091194152832,
      "learning_rate": 8e-05,
      "loss": 2.6092,
      "step": 4
    },
    {
      "epoch": 0.001459534408523681,
      "grad_norm": 0.9703443646430969,
      "learning_rate": 0.0001,
      "loss": 2.2054,
      "step": 5
    },
    {
      "epoch": 0.001751441290228417,
      "grad_norm": 0.7744807600975037,
      "learning_rate": 0.00012,
      "loss": 2.2196,
      "step": 6
    },
    {
      "epoch": 0.001751441290228417,
      "eval_loss": 2.5537147521972656,
      "eval_runtime": 156.9202,
      "eval_samples_per_second": 4.601,
      "eval_steps_per_second": 4.601,
      "step": 6
    },
    {
      "epoch": 0.0020433481719331534,
      "grad_norm": 0.948012113571167,
      "learning_rate": 0.00014,
      "loss": 2.2248,
      "step": 7
    },
    {
      "epoch": 0.0023352550536378893,
      "grad_norm": 1.4153283834457397,
      "learning_rate": 0.00016,
      "loss": 2.2715,
      "step": 8
    },
    {
      "epoch": 0.0026271619353426257,
      "grad_norm": 1.536092758178711,
      "learning_rate": 0.00018,
      "loss": 2.5885,
      "step": 9
    },
    {
      "epoch": 0.0026271619353426257,
      "eval_loss": 2.1300644874572754,
      "eval_runtime": 156.9377,
      "eval_samples_per_second": 4.601,
      "eval_steps_per_second": 4.601,
      "step": 9
    },
    {
      "epoch": 0.002919068817047362,
      "grad_norm": 1.0753655433654785,
      "learning_rate": 0.0002,
      "loss": 2.3009,
      "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": 6990386933268480.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}