checkpoint-130/trainer_state.json

{
  "best_metric": 1.2035548686981201,
  "best_model_checkpoint": "/kaggle/working/checkpoint-130",
  "epoch": 14.444444444444445,
  "eval_steps": 10,
  "global_step": 130,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.022282764315605164,
      "learning_rate": 0.0001851851851851852,
      "loss": 2.0424,
      "step": 10
    },
    {
      "epoch": 1.1111111111111112,
      "eval_loss": 1.733155369758606,
      "eval_runtime": 34.5543,
      "eval_samples_per_second": 1.042,
      "eval_steps_per_second": 0.145,
      "step": 10
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.018981408327817917,
      "learning_rate": 0.00017037037037037037,
      "loss": 1.6072,
      "step": 20
    },
    {
      "epoch": 2.2222222222222223,
      "eval_loss": 1.5428930521011353,
      "eval_runtime": 34.6485,
      "eval_samples_per_second": 1.039,
      "eval_steps_per_second": 0.144,
      "step": 20
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.023157037794589996,
      "learning_rate": 0.00015555555555555556,
      "loss": 1.4025,
      "step": 30
    },
    {
      "epoch": 3.3333333333333335,
      "eval_loss": 1.4176721572875977,
      "eval_runtime": 34.5433,
      "eval_samples_per_second": 1.042,
      "eval_steps_per_second": 0.145,
      "step": 30
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.021338749676942825,
      "learning_rate": 0.00014074074074074076,
      "loss": 1.285,
      "step": 40
    },
    {
      "epoch": 4.444444444444445,
      "eval_loss": 1.3449772596359253,
      "eval_runtime": 34.5594,
      "eval_samples_per_second": 1.042,
      "eval_steps_per_second": 0.145,
      "step": 40
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 0.02489505708217621,
      "learning_rate": 0.00012592592592592592,
      "loss": 1.1687,
      "step": 50
    },
    {
      "epoch": 5.555555555555555,
      "eval_loss": 1.2951068878173828,
      "eval_runtime": 34.5896,
      "eval_samples_per_second": 1.041,
      "eval_steps_per_second": 0.145,
      "step": 50
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.028962766751646996,
      "learning_rate": 0.00011111111111111112,
      "loss": 1.0521,
      "step": 60
    },
    {
      "epoch": 6.666666666666667,
      "eval_loss": 1.2674343585968018,
      "eval_runtime": 34.5586,
      "eval_samples_per_second": 1.042,
      "eval_steps_per_second": 0.145,
      "step": 60
    },
    {
      "epoch": 7.777777777777778,
      "grad_norm": 0.033917125314474106,
      "learning_rate": 9.62962962962963e-05,
      "loss": 0.9885,
      "step": 70
    },
    {
      "epoch": 7.777777777777778,
      "eval_loss": 1.2424466609954834,
      "eval_runtime": 34.5412,
      "eval_samples_per_second": 1.042,
      "eval_steps_per_second": 0.145,
      "step": 70
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 0.03393130004405975,
      "learning_rate": 8.148148148148148e-05,
      "loss": 0.8784,
      "step": 80
    },
    {
      "epoch": 8.88888888888889,
      "eval_loss": 1.2252851724624634,
      "eval_runtime": 34.58,
      "eval_samples_per_second": 1.041,
      "eval_steps_per_second": 0.145,
      "step": 80
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.04081139340996742,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.8154,
      "step": 90
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.2115424871444702,
      "eval_runtime": 34.5784,
      "eval_samples_per_second": 1.041,
      "eval_steps_per_second": 0.145,
      "step": 90
    },
    {
      "epoch": 11.11111111111111,
      "grad_norm": 0.04114004969596863,
      "learning_rate": 5.185185185185185e-05,
      "loss": 0.7376,
      "step": 100
    },
    {
      "epoch": 11.11111111111111,
      "eval_loss": 1.2147088050842285,
      "eval_runtime": 34.595,
      "eval_samples_per_second": 1.041,
      "eval_steps_per_second": 0.145,
      "step": 100
    },
    {
      "epoch": 12.222222222222221,
      "grad_norm": 0.04217207431793213,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.6642,
      "step": 110
    },
    {
      "epoch": 12.222222222222221,
      "eval_loss": 1.2141155004501343,
      "eval_runtime": 34.6053,
      "eval_samples_per_second": 1.04,
      "eval_steps_per_second": 0.144,
      "step": 110
    },
    {
      "epoch": 13.333333333333334,
      "grad_norm": 0.04223904013633728,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.6353,
      "step": 120
    },
    {
      "epoch": 13.333333333333334,
      "eval_loss": 1.20501708984375,
      "eval_runtime": 34.6447,
      "eval_samples_per_second": 1.039,
      "eval_steps_per_second": 0.144,
      "step": 120
    },
    {
      "epoch": 14.444444444444445,
      "grad_norm": 0.04531875252723694,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 0.5992,
      "step": 130
    },
    {
      "epoch": 14.444444444444445,
      "eval_loss": 1.2035548686981201,
      "eval_runtime": 34.5919,
      "eval_samples_per_second": 1.041,
      "eval_steps_per_second": 0.145,
      "step": 130
    }
  ],
  "logging_steps": 10,
  "max_steps": 135,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.474229492560691e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}