last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0001293259531322746,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2932595313227458e-05,
      "grad_norm": 1.2099701166152954,
      "learning_rate": 2e-05,
      "loss": 1.3488,
      "step": 1
    },
    {
      "epoch": 2.5865190626454916e-05,
      "grad_norm": 1.0312577486038208,
      "learning_rate": 4e-05,
      "loss": 1.2877,
      "step": 2
    },
    {
      "epoch": 3.8797785939682375e-05,
      "grad_norm": 1.3535884618759155,
      "learning_rate": 6e-05,
      "loss": 1.5313,
      "step": 3
    },
    {
      "epoch": 3.8797785939682375e-05,
      "eval_loss": 1.4529240131378174,
      "eval_runtime": 1810.3637,
      "eval_samples_per_second": 17.984,
      "eval_steps_per_second": 8.992,
      "step": 3
    },
    {
      "epoch": 5.173038125290983e-05,
      "grad_norm": 1.1495997905731201,
      "learning_rate": 8e-05,
      "loss": 1.4327,
      "step": 4
    },
    {
      "epoch": 6.46629765661373e-05,
      "grad_norm": 1.257749319076538,
      "learning_rate": 0.0001,
      "loss": 1.2136,
      "step": 5
    },
    {
      "epoch": 7.759557187936475e-05,
      "grad_norm": 1.423362135887146,
      "learning_rate": 0.00012,
      "loss": 1.3854,
      "step": 6
    },
    {
      "epoch": 7.759557187936475e-05,
      "eval_loss": 1.1243104934692383,
      "eval_runtime": 1869.0389,
      "eval_samples_per_second": 17.42,
      "eval_steps_per_second": 8.71,
      "step": 6
    },
    {
      "epoch": 9.052816719259221e-05,
      "grad_norm": 1.0958664417266846,
      "learning_rate": 0.00014,
      "loss": 0.7754,
      "step": 7
    },
    {
      "epoch": 0.00010346076250581966,
      "grad_norm": 1.603328824043274,
      "learning_rate": 0.00016,
      "loss": 0.8923,
      "step": 8
    },
    {
      "epoch": 0.00011639335781904713,
      "grad_norm": 1.5763895511627197,
      "learning_rate": 0.00018,
      "loss": 0.8057,
      "step": 9
    },
    {
      "epoch": 0.00011639335781904713,
      "eval_loss": 0.48591652512550354,
      "eval_runtime": 1827.9834,
      "eval_samples_per_second": 17.811,
      "eval_steps_per_second": 8.905,
      "step": 9
    },
    {
      "epoch": 0.0001293259531322746,
      "grad_norm": 1.1443109512329102,
      "learning_rate": 0.0002,
      "loss": 0.4286,
      "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": 1628734142545920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}