last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0434782608695652,
  "eval_steps": 4,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06956521739130435,
      "grad_norm": 7.7945876121521,
      "learning_rate": 1e-05,
      "loss": 177.4688,
      "step": 1
    },
    {
      "epoch": 0.06956521739130435,
      "eval_loss": 11.082473754882812,
      "eval_runtime": 7.3657,
      "eval_samples_per_second": 13.169,
      "eval_steps_per_second": 1.765,
      "step": 1
    },
    {
      "epoch": 0.1391304347826087,
      "grad_norm": 7.366751194000244,
      "learning_rate": 2e-05,
      "loss": 177.3516,
      "step": 2
    },
    {
      "epoch": 0.20869565217391303,
      "grad_norm": 6.917609214782715,
      "learning_rate": 3e-05,
      "loss": 177.4609,
      "step": 3
    },
    {
      "epoch": 0.2782608695652174,
      "grad_norm": 7.315999984741211,
      "learning_rate": 4e-05,
      "loss": 177.3516,
      "step": 4
    },
    {
      "epoch": 0.2782608695652174,
      "eval_loss": 11.079252243041992,
      "eval_runtime": 0.1082,
      "eval_samples_per_second": 896.219,
      "eval_steps_per_second": 120.112,
      "step": 4
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 7.8040056228637695,
      "learning_rate": 5e-05,
      "loss": 177.4141,
      "step": 5
    },
    {
      "epoch": 0.41739130434782606,
      "grad_norm": 8.207115173339844,
      "learning_rate": 6e-05,
      "loss": 177.3047,
      "step": 6
    },
    {
      "epoch": 0.48695652173913045,
      "grad_norm": 7.859698295593262,
      "learning_rate": 7e-05,
      "loss": 177.2422,
      "step": 7
    },
    {
      "epoch": 0.5565217391304348,
      "grad_norm": 7.5123820304870605,
      "learning_rate": 8e-05,
      "loss": 177.1875,
      "step": 8
    },
    {
      "epoch": 0.5565217391304348,
      "eval_loss": 11.06894302368164,
      "eval_runtime": 0.1066,
      "eval_samples_per_second": 909.671,
      "eval_steps_per_second": 121.915,
      "step": 8
    },
    {
      "epoch": 0.6260869565217392,
      "grad_norm": 7.649663925170898,
      "learning_rate": 9e-05,
      "loss": 177.1172,
      "step": 9
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 7.564890384674072,
      "learning_rate": 0.0001,
      "loss": 177.0859,
      "step": 10
    },
    {
      "epoch": 0.7652173913043478,
      "grad_norm": 8.557611465454102,
      "learning_rate": 9.045084971874738e-05,
      "loss": 177.0078,
      "step": 11
    },
    {
      "epoch": 0.8347826086956521,
      "grad_norm": 7.719607353210449,
      "learning_rate": 6.545084971874738e-05,
      "loss": 176.9453,
      "step": 12
    },
    {
      "epoch": 0.8347826086956521,
      "eval_loss": 11.049612998962402,
      "eval_runtime": 0.1071,
      "eval_samples_per_second": 905.76,
      "eval_steps_per_second": 121.391,
      "step": 12
    },
    {
      "epoch": 0.9043478260869565,
      "grad_norm": 8.3920259475708,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 176.8594,
      "step": 13
    },
    {
      "epoch": 0.9739130434782609,
      "grad_norm": 8.231620788574219,
      "learning_rate": 9.549150281252633e-06,
      "loss": 176.8672,
      "step": 14
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 8.611029624938965,
      "learning_rate": 0.0,
      "loss": 176.7188,
      "step": 15
    }
  ],
  "logging_steps": 1,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 4,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 19967571394560.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}