LLM/checkpoint-600/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7713335796084226,
  "eval_steps": 339,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_loss": 11.850272178649902,
      "eval_runtime": 7.1659,
      "eval_samples_per_second": 19.956,
      "eval_steps_per_second": 19.956,
      "memory/device_reserved (GiB)": 3.2,
      "memory/max_active (GiB)": 3.1,
      "memory/max_allocated (GiB)": 3.1,
      "step": 0
    },
    {
      "epoch": 0.1477650535648319,
      "grad_norm": 9.9116792678833,
      "learning_rate": 0.00019925925947187668,
      "loss": 7.2742,
      "memory/device_reserved (GiB)": 7.67,
      "memory/max_active (GiB)": 7.2,
      "memory/max_allocated (GiB)": 7.2,
      "step": 50,
      "tokens_per_second_per_gpu": 2082.96,
      "total_tokens": 164572
    },
    {
      "epoch": 0.2955301071296638,
      "grad_norm": 12.538771629333496,
      "learning_rate": 0.0001961624298837552,
      "loss": 5.6623,
      "memory/device_reserved (GiB)": 7.67,
      "memory/max_active (GiB)": 7.2,
      "memory/max_allocated (GiB)": 7.2,
      "step": 100,
      "tokens_per_second_per_gpu": 1546.73,
      "total_tokens": 287922
    },
    {
      "epoch": 0.44329516069449576,
      "grad_norm": 25.31467628479004,
      "learning_rate": 0.00019072586525126637,
      "loss": 5.3752,
      "memory/device_reserved (GiB)": 7.67,
      "memory/max_active (GiB)": 7.2,
      "memory/max_allocated (GiB)": 7.2,
      "step": 150,
      "tokens_per_second_per_gpu": 1524.55,
      "total_tokens": 410915
    },
    {
      "epoch": 0.5910602142593276,
      "grad_norm": 25.589689254760742,
      "learning_rate": 0.00018308184302213046,
      "loss": 5.0362,
      "memory/device_reserved (GiB)": 7.67,
      "memory/max_active (GiB)": 7.2,
      "memory/max_allocated (GiB)": 7.2,
      "step": 200,
      "tokens_per_second_per_gpu": 1390.99,
      "total_tokens": 533959
    },
    {
      "epoch": 0.7388252678241596,
      "grad_norm": 26.41189956665039,
      "learning_rate": 0.00017341635045468791,
      "loss": 4.8371,
      "memory/device_reserved (GiB)": 7.67,
      "memory/max_active (GiB)": 7.2,
      "memory/max_allocated (GiB)": 7.2,
      "step": 250,
      "tokens_per_second_per_gpu": 1552.5,
      "total_tokens": 656838
    },
    {
      "epoch": 0.8865903213889915,
      "grad_norm": 23.636552810668945,
      "learning_rate": 0.00016196455934844978,
      "loss": 4.7248,
      "memory/device_reserved (GiB)": 7.67,
      "memory/max_active (GiB)": 7.2,
      "memory/max_allocated (GiB)": 7.2,
      "step": 300,
      "tokens_per_second_per_gpu": 1489.9,
      "total_tokens": 779045
    },
    {
      "epoch": 1.0,
      "eval_loss": 4.642312526702881,
      "eval_runtime": 7.0402,
      "eval_samples_per_second": 20.312,
      "eval_steps_per_second": 20.312,
      "memory/device_reserved (GiB)": 7.67,
      "memory/max_active (GiB)": 7.2,
      "memory/max_allocated (GiB)": 7.2,
      "step": 339
    },
    {
      "epoch": 1.032508311784263,
      "grad_norm": 29.976333618164062,
      "learning_rate": 0.00014900510406201564,
      "loss": 4.6412,
      "memory/device_reserved (GiB)": 7.62,
      "memory/max_active (GiB)": 7.2,
      "memory/max_allocated (GiB)": 7.2,
      "step": 350,
      "tokens_per_second_per_gpu": 346.62,
      "total_tokens": 945548
    },
    {
      "epoch": 1.1802733653490949,
      "grad_norm": 28.489376068115234,
      "learning_rate": 0.00013485330204031937,
      "loss": 4.4916,
      "memory/device_reserved (GiB)": 7.62,
      "memory/max_active (GiB)": 7.2,
      "memory/max_allocated (GiB)": 7.2,
      "step": 400,
      "tokens_per_second_per_gpu": 1511.66,
      "total_tokens": 1067762
    },
    {
      "epoch": 1.328038418913927,
      "grad_norm": 25.01222038269043,
      "learning_rate": 0.0001198534818030452,
      "loss": 4.4404,
      "memory/device_reserved (GiB)": 7.62,
      "memory/max_active (GiB)": 7.2,
      "memory/max_allocated (GiB)": 7.2,
      "step": 450,
      "tokens_per_second_per_gpu": 1375.01,
      "total_tokens": 1188747
    },
    {
      "epoch": 1.4758034724787588,
      "grad_norm": 19.93057632446289,
      "learning_rate": 0.00010437060506248341,
      "loss": 4.4182,
      "memory/device_reserved (GiB)": 7.62,
      "memory/max_active (GiB)": 7.2,
      "memory/max_allocated (GiB)": 7.2,
      "step": 500,
      "tokens_per_second_per_gpu": 1540.13,
      "total_tokens": 1312791
    },
    {
      "epoch": 1.6235685260435906,
      "grad_norm": 20.955829620361328,
      "learning_rate": 8.878138681368239e-05,
      "loss": 4.3869,
      "memory/device_reserved (GiB)": 7.62,
      "memory/max_active (GiB)": 7.2,
      "memory/max_allocated (GiB)": 7.2,
      "step": 550,
      "tokens_per_second_per_gpu": 1544.52,
      "total_tokens": 1437766
    },
    {
      "epoch": 1.7713335796084226,
      "grad_norm": 27.51922035217285,
      "learning_rate": 7.346512945462767e-05,
      "loss": 4.359,
      "memory/device_reserved (GiB)": 7.62,
      "memory/max_active (GiB)": 7.2,
      "memory/max_allocated (GiB)": 7.2,
      "step": 600,
      "tokens_per_second_per_gpu": 1525.07,
      "total_tokens": 1560469
    }
  ],
  "logging_steps": 50,
  "max_steps": 1016,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.054385017061376e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}