last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006146281499692686,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006146281499692685,
      "grad_norm": 0.42315444350242615,
      "learning_rate": 2e-05,
      "loss": 0.9809,
      "step": 1
    },
    {
      "epoch": 0.0006146281499692685,
      "eval_loss": 1.4701610803604126,
      "eval_runtime": 32.8088,
      "eval_samples_per_second": 20.879,
      "eval_steps_per_second": 10.455,
      "step": 1
    },
    {
      "epoch": 0.001229256299938537,
      "grad_norm": 0.47359389066696167,
      "learning_rate": 4e-05,
      "loss": 0.9859,
      "step": 2
    },
    {
      "epoch": 0.0018438844499078057,
      "grad_norm": 0.3760848343372345,
      "learning_rate": 6e-05,
      "loss": 1.1985,
      "step": 3
    },
    {
      "epoch": 0.0018438844499078057,
      "eval_loss": 1.4673006534576416,
      "eval_runtime": 30.7848,
      "eval_samples_per_second": 22.251,
      "eval_steps_per_second": 11.142,
      "step": 3
    },
    {
      "epoch": 0.002458512599877074,
      "grad_norm": 0.30434760451316833,
      "learning_rate": 8e-05,
      "loss": 0.799,
      "step": 4
    },
    {
      "epoch": 0.003073140749846343,
      "grad_norm": 0.41436293721199036,
      "learning_rate": 0.0001,
      "loss": 1.2349,
      "step": 5
    },
    {
      "epoch": 0.0036877688998156115,
      "grad_norm": 0.4243198037147522,
      "learning_rate": 0.00012,
      "loss": 0.9476,
      "step": 6
    },
    {
      "epoch": 0.0036877688998156115,
      "eval_loss": 1.4463762044906616,
      "eval_runtime": 30.8197,
      "eval_samples_per_second": 22.226,
      "eval_steps_per_second": 11.129,
      "step": 6
    },
    {
      "epoch": 0.0043023970497848806,
      "grad_norm": 0.620731770992279,
      "learning_rate": 0.00014,
      "loss": 1.7876,
      "step": 7
    },
    {
      "epoch": 0.004917025199754148,
      "grad_norm": 0.5794855952262878,
      "learning_rate": 0.00016,
      "loss": 1.1375,
      "step": 8
    },
    {
      "epoch": 0.005531653349723417,
      "grad_norm": 0.6219256520271301,
      "learning_rate": 0.00018,
      "loss": 0.6744,
      "step": 9
    },
    {
      "epoch": 0.005531653349723417,
      "eval_loss": 1.357763409614563,
      "eval_runtime": 30.8167,
      "eval_samples_per_second": 22.228,
      "eval_steps_per_second": 11.13,
      "step": 9
    },
    {
      "epoch": 0.006146281499692686,
      "grad_norm": 0.5443244576454163,
      "learning_rate": 0.0002,
      "loss": 1.0572,
      "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": 2866824584626176.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}