checkpoint-355/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5047991468183434,
  "eval_steps": 71,
  "global_step": 355,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07109847138286526,
      "grad_norm": 1.4222540855407715,
      "learning_rate": 0.0009303977272727273,
      "loss": 7.489,
      "step": 50
    },
    {
      "epoch": 0.10095982936366868,
      "eval_loss": 1.4995908737182617,
      "eval_runtime": 4.381,
      "eval_samples_per_second": 22.826,
      "eval_steps_per_second": 1.598,
      "step": 71
    },
    {
      "epoch": 0.14219694276573053,
      "grad_norm": 0.9577059149742126,
      "learning_rate": 0.000859375,
      "loss": 6.2445,
      "step": 100
    },
    {
      "epoch": 0.20191965872733736,
      "eval_loss": 1.431077003479004,
      "eval_runtime": 3.7442,
      "eval_samples_per_second": 26.708,
      "eval_steps_per_second": 1.87,
      "step": 142
    },
    {
      "epoch": 0.21329541414859582,
      "grad_norm": 0.9500109553337097,
      "learning_rate": 0.0007883522727272727,
      "loss": 5.999,
      "step": 150
    },
    {
      "epoch": 0.28439388553146105,
      "grad_norm": 0.9268011450767517,
      "learning_rate": 0.0007173295454545454,
      "loss": 5.8782,
      "step": 200
    },
    {
      "epoch": 0.30287948809100607,
      "eval_loss": 1.387271761894226,
      "eval_runtime": 3.7335,
      "eval_samples_per_second": 26.785,
      "eval_steps_per_second": 1.875,
      "step": 213
    },
    {
      "epoch": 0.35549235691432635,
      "grad_norm": 0.9108902215957642,
      "learning_rate": 0.0006463068181818182,
      "loss": 5.8148,
      "step": 250
    },
    {
      "epoch": 0.4038393174546747,
      "eval_loss": 1.363606572151184,
      "eval_runtime": 3.7112,
      "eval_samples_per_second": 26.945,
      "eval_steps_per_second": 1.886,
      "step": 284
    },
    {
      "epoch": 0.42659082829719164,
      "grad_norm": 0.9438243508338928,
      "learning_rate": 0.0005752840909090909,
      "loss": 5.7204,
      "step": 300
    },
    {
      "epoch": 0.4976892996800569,
      "grad_norm": 0.963438868522644,
      "learning_rate": 0.0005042613636363636,
      "loss": 5.6029,
      "step": 350
    },
    {
      "epoch": 0.5047991468183434,
      "eval_loss": 1.3366552591323853,
      "eval_runtime": 3.743,
      "eval_samples_per_second": 26.717,
      "eval_steps_per_second": 1.87,
      "step": 355
    }
  ],
  "logging_steps": 50,
  "max_steps": 704,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 71,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.19719240267989e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}