last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.036596523330283626,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036596523330283625,
      "grad_norm": 15.510026931762695,
      "learning_rate": 2e-05,
      "loss": 6.7731,
      "step": 1
    },
    {
      "epoch": 0.007319304666056725,
      "grad_norm": 13.10978889465332,
      "learning_rate": 4e-05,
      "loss": 6.7965,
      "step": 2
    },
    {
      "epoch": 0.010978956999085087,
      "grad_norm": 15.461770057678223,
      "learning_rate": 6e-05,
      "loss": 6.9731,
      "step": 3
    },
    {
      "epoch": 0.010978956999085087,
      "eval_loss": 6.619480609893799,
      "eval_runtime": 5.1632,
      "eval_samples_per_second": 22.273,
      "eval_steps_per_second": 11.233,
      "step": 3
    },
    {
      "epoch": 0.01463860933211345,
      "grad_norm": 15.080842971801758,
      "learning_rate": 8e-05,
      "loss": 6.7537,
      "step": 4
    },
    {
      "epoch": 0.018298261665141813,
      "grad_norm": 18.969974517822266,
      "learning_rate": 0.0001,
      "loss": 6.128,
      "step": 5
    },
    {
      "epoch": 0.021957913998170174,
      "grad_norm": 23.45438003540039,
      "learning_rate": 0.00012,
      "loss": 4.871,
      "step": 6
    },
    {
      "epoch": 0.021957913998170174,
      "eval_loss": 3.074002981185913,
      "eval_runtime": 5.2185,
      "eval_samples_per_second": 22.037,
      "eval_steps_per_second": 11.114,
      "step": 6
    },
    {
      "epoch": 0.025617566331198535,
      "grad_norm": 12.137740135192871,
      "learning_rate": 0.00014,
      "loss": 3.0612,
      "step": 7
    },
    {
      "epoch": 0.0292772186642269,
      "grad_norm": 7.033312797546387,
      "learning_rate": 0.00016,
      "loss": 1.7614,
      "step": 8
    },
    {
      "epoch": 0.03293687099725526,
      "grad_norm": 4.264461994171143,
      "learning_rate": 0.00018,
      "loss": 1.0696,
      "step": 9
    },
    {
      "epoch": 0.03293687099725526,
      "eval_loss": 0.7656844854354858,
      "eval_runtime": 8.1274,
      "eval_samples_per_second": 14.15,
      "eval_steps_per_second": 7.136,
      "step": 9
    },
    {
      "epoch": 0.036596523330283626,
      "grad_norm": 2.800792694091797,
      "learning_rate": 0.0002,
      "loss": 0.6246,
      "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": 1647822923366400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}