checkpoint-150/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.316831683168317,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08800880088008801,
      "grad_norm": 0.008909749798476696,
      "learning_rate": 8.18181797512807e-05,
      "loss": 12.2157,
      "memory/device_mem_reserved(gib)": 2.73,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 10
    },
    {
      "epoch": 0.17601760176017603,
      "grad_norm": 0.007974537089467049,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.2154,
      "memory/device_mem_reserved(gib)": 2.73,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 20
    },
    {
      "epoch": 0.264026402640264,
      "grad_norm": 0.010009167715907097,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.2152,
      "memory/device_mem_reserved(gib)": 2.73,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 30
    },
    {
      "epoch": 0.35203520352035206,
      "grad_norm": 0.010353786870837212,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.2155,
      "memory/device_mem_reserved(gib)": 2.73,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 40
    },
    {
      "epoch": 0.44004400440044006,
      "grad_norm": 0.01487517450004816,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.2151,
      "memory/device_mem_reserved(gib)": 2.73,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 50
    },
    {
      "epoch": 0.528052805280528,
      "grad_norm": 0.011968914419412613,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.215,
      "memory/device_mem_reserved(gib)": 2.73,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 60
    },
    {
      "epoch": 0.6160616061606161,
      "grad_norm": 0.015747424215078354,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.2146,
      "memory/device_mem_reserved(gib)": 2.73,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 70
    },
    {
      "epoch": 0.7040704070407041,
      "grad_norm": 0.01620076224207878,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.2132,
      "memory/device_mem_reserved(gib)": 2.73,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 80
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 0.016200672835111618,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.2131,
      "memory/device_mem_reserved(gib)": 2.73,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 90
    },
    {
      "epoch": 0.8800880088008801,
      "grad_norm": 0.01671593263745308,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.2126,
      "memory/device_mem_reserved(gib)": 2.73,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 100
    },
    {
      "epoch": 0.9680968096809681,
      "grad_norm": 0.019221968948841095,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.2124,
      "memory/device_mem_reserved(gib)": 2.73,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 110
    },
    {
      "epoch": 1.0528052805280528,
      "grad_norm": 0.02141665853559971,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.2117,
      "memory/device_mem_reserved(gib)": 2.73,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 120
    },
    {
      "epoch": 1.140814081408141,
      "grad_norm": 0.015679990872740746,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.2111,
      "memory/device_mem_reserved(gib)": 2.74,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 130
    },
    {
      "epoch": 1.2288228822882288,
      "grad_norm": 0.022765284404158592,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.2093,
      "memory/device_mem_reserved(gib)": 2.74,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 140
    },
    {
      "epoch": 1.316831683168317,
      "grad_norm": 0.01766524650156498,
      "learning_rate": 9.999999747378752e-05,
      "loss": 12.2088,
      "memory/device_mem_reserved(gib)": 2.74,
      "memory/max_mem_active(gib)": 2.34,
      "memory/max_mem_allocated(gib)": 2.34,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 150,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3064545861120.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}