last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004253056884635832,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004253056884635832,
      "grad_norm": 23.240222930908203,
      "learning_rate": 2e-05,
      "loss": 6.2103,
      "step": 1
    },
    {
      "epoch": 0.0008506113769271664,
      "grad_norm": 17.026002883911133,
      "learning_rate": 4e-05,
      "loss": 6.6524,
      "step": 2
    },
    {
      "epoch": 0.0012759170653907496,
      "grad_norm": 19.665388107299805,
      "learning_rate": 6e-05,
      "loss": 6.3369,
      "step": 3
    },
    {
      "epoch": 0.0012759170653907496,
      "eval_loss": 1.5670489072799683,
      "eval_runtime": 34.2006,
      "eval_samples_per_second": 28.947,
      "eval_steps_per_second": 14.473,
      "step": 3
    },
    {
      "epoch": 0.0017012227538543328,
      "grad_norm": 19.655567169189453,
      "learning_rate": 8e-05,
      "loss": 6.759,
      "step": 4
    },
    {
      "epoch": 0.002126528442317916,
      "grad_norm": 19.10618019104004,
      "learning_rate": 0.0001,
      "loss": 6.0482,
      "step": 5
    },
    {
      "epoch": 0.002551834130781499,
      "grad_norm": 22.587932586669922,
      "learning_rate": 0.00012,
      "loss": 6.3116,
      "step": 6
    },
    {
      "epoch": 0.002551834130781499,
      "eval_loss": 1.5588480234146118,
      "eval_runtime": 35.3112,
      "eval_samples_per_second": 28.036,
      "eval_steps_per_second": 14.018,
      "step": 6
    },
    {
      "epoch": 0.0029771398192450825,
      "grad_norm": 19.050405502319336,
      "learning_rate": 0.00014,
      "loss": 6.4988,
      "step": 7
    },
    {
      "epoch": 0.0034024455077086655,
      "grad_norm": 21.619447708129883,
      "learning_rate": 0.00016,
      "loss": 6.3776,
      "step": 8
    },
    {
      "epoch": 0.003827751196172249,
      "grad_norm": 17.375764846801758,
      "learning_rate": 0.00018,
      "loss": 6.7369,
      "step": 9
    },
    {
      "epoch": 0.003827751196172249,
      "eval_loss": 1.5340806245803833,
      "eval_runtime": 34.2694,
      "eval_samples_per_second": 28.889,
      "eval_steps_per_second": 14.444,
      "step": 9
    },
    {
      "epoch": 0.004253056884635832,
      "grad_norm": 21.274797439575195,
      "learning_rate": 0.0002,
      "loss": 6.2291,
      "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": 162297846693888.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}