last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008531149359097404,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.531149359097404e-05,
      "grad_norm": 0.9246206879615784,
      "learning_rate": 2e-05,
      "loss": 2.7629,
      "step": 1
    },
    {
      "epoch": 8.531149359097404e-05,
      "eval_loss": 3.126101493835449,
      "eval_runtime": 186.4915,
      "eval_samples_per_second": 26.468,
      "eval_steps_per_second": 13.234,
      "step": 1
    },
    {
      "epoch": 0.00017062298718194808,
      "grad_norm": 0.9634801745414734,
      "learning_rate": 4e-05,
      "loss": 3.0406,
      "step": 2
    },
    {
      "epoch": 0.00025593448077292216,
      "grad_norm": 0.8098450899124146,
      "learning_rate": 6e-05,
      "loss": 3.1467,
      "step": 3
    },
    {
      "epoch": 0.00025593448077292216,
      "eval_loss": 3.123194694519043,
      "eval_runtime": 185.5012,
      "eval_samples_per_second": 26.609,
      "eval_steps_per_second": 13.304,
      "step": 3
    },
    {
      "epoch": 0.00034124597436389616,
      "grad_norm": 0.825379490852356,
      "learning_rate": 8e-05,
      "loss": 2.9947,
      "step": 4
    },
    {
      "epoch": 0.0004265574679548702,
      "grad_norm": 0.9180529713630676,
      "learning_rate": 0.0001,
      "loss": 3.139,
      "step": 5
    },
    {
      "epoch": 0.0005118689615458443,
      "grad_norm": 0.9415570497512817,
      "learning_rate": 0.00012,
      "loss": 2.9949,
      "step": 6
    },
    {
      "epoch": 0.0005118689615458443,
      "eval_loss": 3.084035873413086,
      "eval_runtime": 185.6399,
      "eval_samples_per_second": 26.589,
      "eval_steps_per_second": 13.295,
      "step": 6
    },
    {
      "epoch": 0.0005971804551368183,
      "grad_norm": 1.120742917060852,
      "learning_rate": 0.00014,
      "loss": 2.7756,
      "step": 7
    },
    {
      "epoch": 0.0006824919487277923,
      "grad_norm": 1.188589334487915,
      "learning_rate": 0.00016,
      "loss": 2.5867,
      "step": 8
    },
    {
      "epoch": 0.0007678034423187664,
      "grad_norm": 1.3696794509887695,
      "learning_rate": 0.00018,
      "loss": 3.2372,
      "step": 9
    },
    {
      "epoch": 0.0007678034423187664,
      "eval_loss": 2.8644986152648926,
      "eval_runtime": 185.6674,
      "eval_samples_per_second": 26.585,
      "eval_steps_per_second": 13.293,
      "step": 9
    },
    {
      "epoch": 0.0008531149359097404,
      "grad_norm": 1.5594573020935059,
      "learning_rate": 0.0002,
      "loss": 2.7987,
      "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": 2059778654208000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}