last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004590080326405712,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005100089251561902,
      "grad_norm": 0.6477348208427429,
      "learning_rate": 2e-05,
      "loss": 0.9055,
      "step": 1
    },
    {
      "epoch": 0.0005100089251561902,
      "eval_loss": 0.9768646955490112,
      "eval_runtime": 31.7825,
      "eval_samples_per_second": 25.989,
      "eval_steps_per_second": 12.995,
      "step": 1
    },
    {
      "epoch": 0.0010200178503123804,
      "grad_norm": 0.6465352773666382,
      "learning_rate": 4e-05,
      "loss": 1.0606,
      "step": 2
    },
    {
      "epoch": 0.0015300267754685707,
      "grad_norm": 0.7141121029853821,
      "learning_rate": 6e-05,
      "loss": 0.8647,
      "step": 3
    },
    {
      "epoch": 0.0015300267754685707,
      "eval_loss": 0.975134551525116,
      "eval_runtime": 31.8344,
      "eval_samples_per_second": 25.947,
      "eval_steps_per_second": 12.973,
      "step": 3
    },
    {
      "epoch": 0.002040035700624761,
      "grad_norm": 0.6297356486320496,
      "learning_rate": 8e-05,
      "loss": 0.9368,
      "step": 4
    },
    {
      "epoch": 0.0025500446257809514,
      "grad_norm": 0.5470901131629944,
      "learning_rate": 0.0001,
      "loss": 0.8759,
      "step": 5
    },
    {
      "epoch": 0.0030600535509371415,
      "grad_norm": 0.7647647857666016,
      "learning_rate": 0.00012,
      "loss": 0.9711,
      "step": 6
    },
    {
      "epoch": 0.0030600535509371415,
      "eval_loss": 0.9506816864013672,
      "eval_runtime": 31.8613,
      "eval_samples_per_second": 25.925,
      "eval_steps_per_second": 12.962,
      "step": 6
    },
    {
      "epoch": 0.0035700624760933316,
      "grad_norm": 0.7155371308326721,
      "learning_rate": 0.00014,
      "loss": 0.8848,
      "step": 7
    },
    {
      "epoch": 0.004080071401249522,
      "grad_norm": 0.8622905611991882,
      "learning_rate": 0.00016,
      "loss": 1.0579,
      "step": 8
    },
    {
      "epoch": 0.004590080326405712,
      "grad_norm": 1.134154200553894,
      "learning_rate": 0.00018,
      "loss": 0.9633,
      "step": 9
    },
    {
      "epoch": 0.004590080326405712,
      "eval_loss": 0.921898365020752,
      "eval_runtime": 31.9041,
      "eval_samples_per_second": 25.89,
      "eval_steps_per_second": 12.945,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 900175195275264.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}