checkpoint-17/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.25103830179972314,
  "eval_steps": 500,
  "global_step": 17,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014766958929395477,
      "grad_norm": 2.690037488937378,
      "learning_rate": 0.0,
      "loss": 1.6144,
      "memory/device_mem_reserved(gib)": 21.22,
      "memory/max_mem_active(gib)": 20.26,
      "memory/max_mem_allocated(gib)": 20.26,
      "step": 1
    },
    {
      "epoch": 0.029533917858790955,
      "grad_norm": 2.398118257522583,
      "learning_rate": 3.333333333333333e-07,
      "loss": 1.6644,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 2
    },
    {
      "epoch": 0.044300876788186436,
      "grad_norm": 2.5713729858398438,
      "learning_rate": 6.666666666666666e-07,
      "loss": 1.6941,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 3
    },
    {
      "epoch": 0.05906783571758191,
      "grad_norm": 2.2192649841308594,
      "learning_rate": 1e-06,
      "loss": 1.6688,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 4
    },
    {
      "epoch": 0.07383479464697738,
      "grad_norm": 2.3497774600982666,
      "learning_rate": 1.3333333333333332e-06,
      "loss": 1.606,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 5
    },
    {
      "epoch": 0.08860175357637287,
      "grad_norm": 2.2802064418792725,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.7277,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 6
    },
    {
      "epoch": 0.10336871250576835,
      "grad_norm": 2.3159115314483643,
      "learning_rate": 2e-06,
      "loss": 1.7224,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 7
    },
    {
      "epoch": 0.11813567143516382,
      "grad_norm": 2.392916440963745,
      "learning_rate": 1.9986740898848305e-06,
      "loss": 1.6719,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 8
    },
    {
      "epoch": 0.1329026303645593,
      "grad_norm": 2.1091415882110596,
      "learning_rate": 1.994699875614589e-06,
      "loss": 1.6595,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 9
    },
    {
      "epoch": 0.14766958929395477,
      "grad_norm": 1.8049347400665283,
      "learning_rate": 1.988087896091077e-06,
      "loss": 1.5723,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 10
    },
    {
      "epoch": 0.16243654822335024,
      "grad_norm": 1.6561530828475952,
      "learning_rate": 1.9788556850953576e-06,
      "loss": 1.5984,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 11
    },
    {
      "epoch": 0.17720350715274574,
      "grad_norm": 1.3701506853103638,
      "learning_rate": 1.9670277247913204e-06,
      "loss": 1.6334,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 12
    },
    {
      "epoch": 0.19197046608214122,
      "grad_norm": 1.3220688104629517,
      "learning_rate": 1.9526353808033826e-06,
      "loss": 1.6827,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 13
    },
    {
      "epoch": 0.2067374250115367,
      "grad_norm": 1.2383441925048828,
      "learning_rate": 1.9357168190404938e-06,
      "loss": 1.6169,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 14
    },
    {
      "epoch": 0.22150438394093216,
      "grad_norm": 1.103604793548584,
      "learning_rate": 1.9163169044870047e-06,
      "loss": 1.6824,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 15
    },
    {
      "epoch": 0.23627134287032764,
      "grad_norm": 0.9897175431251526,
      "learning_rate": 1.8944870822287954e-06,
      "loss": 1.7108,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 16
    },
    {
      "epoch": 0.25103830179972314,
      "grad_norm": 0.8720229864120483,
      "learning_rate": 1.8702852410301553e-06,
      "loss": 1.5275,
      "memory/device_mem_reserved(gib)": 21.23,
      "memory/max_mem_active(gib)": 20.61,
      "memory/max_mem_allocated(gib)": 20.61,
      "step": 17
    }
  ],
  "logging_steps": 1,
  "max_steps": 67,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 17,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.17292722381783e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}