last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0021831677764436196,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021831677764436196,
      "grad_norm": 0.3998178541660309,
      "learning_rate": 2e-05,
      "loss": 3.3873,
      "step": 1
    },
    {
      "epoch": 0.00021831677764436196,
      "eval_loss": 0.9085711240768433,
      "eval_runtime": 123.257,
      "eval_samples_per_second": 15.65,
      "eval_steps_per_second": 7.829,
      "step": 1
    },
    {
      "epoch": 0.00043663355528872393,
      "grad_norm": 0.33427903056144714,
      "learning_rate": 4e-05,
      "loss": 3.2434,
      "step": 2
    },
    {
      "epoch": 0.0006549503329330859,
      "grad_norm": 0.3557869791984558,
      "learning_rate": 6e-05,
      "loss": 4.0315,
      "step": 3
    },
    {
      "epoch": 0.0006549503329330859,
      "eval_loss": 0.9082595705986023,
      "eval_runtime": 123.3262,
      "eval_samples_per_second": 15.641,
      "eval_steps_per_second": 7.825,
      "step": 3
    },
    {
      "epoch": 0.0008732671105774479,
      "grad_norm": 0.3410411477088928,
      "learning_rate": 8e-05,
      "loss": 3.8764,
      "step": 4
    },
    {
      "epoch": 0.0010915838882218098,
      "grad_norm": 0.3806026577949524,
      "learning_rate": 0.0001,
      "loss": 3.9718,
      "step": 5
    },
    {
      "epoch": 0.0013099006658661718,
      "grad_norm": 0.3945617973804474,
      "learning_rate": 0.00012,
      "loss": 3.5815,
      "step": 6
    },
    {
      "epoch": 0.0013099006658661718,
      "eval_loss": 0.9044772386550903,
      "eval_runtime": 123.4111,
      "eval_samples_per_second": 15.631,
      "eval_steps_per_second": 7.819,
      "step": 6
    },
    {
      "epoch": 0.0015282174435105338,
      "grad_norm": 0.5309928059577942,
      "learning_rate": 0.00014,
      "loss": 3.4052,
      "step": 7
    },
    {
      "epoch": 0.0017465342211548957,
      "grad_norm": 0.4780644178390503,
      "learning_rate": 0.00016,
      "loss": 3.3675,
      "step": 8
    },
    {
      "epoch": 0.001964850998799258,
      "grad_norm": 0.5216543078422546,
      "learning_rate": 0.00018,
      "loss": 3.389,
      "step": 9
    },
    {
      "epoch": 0.001964850998799258,
      "eval_loss": 0.8844879269599915,
      "eval_runtime": 123.4319,
      "eval_samples_per_second": 15.628,
      "eval_steps_per_second": 7.818,
      "step": 9
    },
    {
      "epoch": 0.0021831677764436196,
      "grad_norm": 0.9309405088424683,
      "learning_rate": 0.0002,
      "loss": 3.693,
      "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": 3257498484080640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}