last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00026731177909354576,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.6731177909354575e-05,
      "grad_norm": 0.5658635497093201,
      "learning_rate": 2e-05,
      "loss": 0.936,
      "step": 1
    },
    {
      "epoch": 2.6731177909354575e-05,
      "eval_loss": 0.754760205745697,
      "eval_runtime": 1446.2606,
      "eval_samples_per_second": 5.446,
      "eval_steps_per_second": 2.723,
      "step": 1
    },
    {
      "epoch": 5.346235581870915e-05,
      "grad_norm": 0.48800089955329895,
      "learning_rate": 4e-05,
      "loss": 0.7319,
      "step": 2
    },
    {
      "epoch": 8.019353372806372e-05,
      "grad_norm": 0.4071688652038574,
      "learning_rate": 6e-05,
      "loss": 0.5428,
      "step": 3
    },
    {
      "epoch": 8.019353372806372e-05,
      "eval_loss": 0.750458300113678,
      "eval_runtime": 1446.0968,
      "eval_samples_per_second": 5.446,
      "eval_steps_per_second": 2.723,
      "step": 3
    },
    {
      "epoch": 0.0001069247116374183,
      "grad_norm": 0.5141913294792175,
      "learning_rate": 8e-05,
      "loss": 0.8591,
      "step": 4
    },
    {
      "epoch": 0.00013365588954677288,
      "grad_norm": 0.3930897116661072,
      "learning_rate": 0.0001,
      "loss": 0.5014,
      "step": 5
    },
    {
      "epoch": 0.00016038706745612744,
      "grad_norm": 0.4725160002708435,
      "learning_rate": 0.00012,
      "loss": 0.6867,
      "step": 6
    },
    {
      "epoch": 0.00016038706745612744,
      "eval_loss": 0.7054961323738098,
      "eval_runtime": 1446.2097,
      "eval_samples_per_second": 5.446,
      "eval_steps_per_second": 2.723,
      "step": 6
    },
    {
      "epoch": 0.00018711824536548203,
      "grad_norm": 0.5095219016075134,
      "learning_rate": 0.00014,
      "loss": 0.4361,
      "step": 7
    },
    {
      "epoch": 0.0002138494232748366,
      "grad_norm": 0.5460357666015625,
      "learning_rate": 0.00016,
      "loss": 0.6091,
      "step": 8
    },
    {
      "epoch": 0.0002405806011841912,
      "grad_norm": 0.5249965190887451,
      "learning_rate": 0.00018,
      "loss": 0.3963,
      "step": 9
    },
    {
      "epoch": 0.0002405806011841912,
      "eval_loss": 0.6169511675834656,
      "eval_runtime": 1446.3469,
      "eval_samples_per_second": 5.445,
      "eval_steps_per_second": 2.723,
      "step": 9
    },
    {
      "epoch": 0.00026731177909354576,
      "grad_norm": 0.8788390159606934,
      "learning_rate": 0.0002,
      "loss": 0.6028,
      "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": 6534582019031040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}