last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005792903692976104,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005792903692976104,
      "grad_norm": 0.8005829453468323,
      "learning_rate": 2e-05,
      "loss": 2.9056,
      "step": 1
    },
    {
      "epoch": 0.0005792903692976104,
      "eval_loss": 2.9295616149902344,
      "eval_runtime": 93.9662,
      "eval_samples_per_second": 7.737,
      "eval_steps_per_second": 3.874,
      "step": 1
    },
    {
      "epoch": 0.0011585807385952208,
      "grad_norm": 0.7147985696792603,
      "learning_rate": 4e-05,
      "loss": 2.9177,
      "step": 2
    },
    {
      "epoch": 0.0017378711078928314,
      "grad_norm": 0.8883288502693176,
      "learning_rate": 6e-05,
      "loss": 2.4781,
      "step": 3
    },
    {
      "epoch": 0.0017378711078928314,
      "eval_loss": 2.9244561195373535,
      "eval_runtime": 95.1184,
      "eval_samples_per_second": 7.643,
      "eval_steps_per_second": 3.827,
      "step": 3
    },
    {
      "epoch": 0.0023171614771904415,
      "grad_norm": 0.9748960733413696,
      "learning_rate": 8e-05,
      "loss": 3.1738,
      "step": 4
    },
    {
      "epoch": 0.002896451846488052,
      "grad_norm": 0.7598217725753784,
      "learning_rate": 0.0001,
      "loss": 2.4379,
      "step": 5
    },
    {
      "epoch": 0.0034757422157856628,
      "grad_norm": 1.0207710266113281,
      "learning_rate": 0.00012,
      "loss": 2.9731,
      "step": 6
    },
    {
      "epoch": 0.0034757422157856628,
      "eval_loss": 2.835926055908203,
      "eval_runtime": 95.2842,
      "eval_samples_per_second": 7.63,
      "eval_steps_per_second": 3.82,
      "step": 6
    },
    {
      "epoch": 0.004055032585083273,
      "grad_norm": 1.317775011062622,
      "learning_rate": 0.00014,
      "loss": 2.9932,
      "step": 7
    },
    {
      "epoch": 0.004634322954380883,
      "grad_norm": 1.117720365524292,
      "learning_rate": 0.00016,
      "loss": 2.3084,
      "step": 8
    },
    {
      "epoch": 0.0052136133236784935,
      "grad_norm": 1.2141731977462769,
      "learning_rate": 0.00018,
      "loss": 2.8136,
      "step": 9
    },
    {
      "epoch": 0.0052136133236784935,
      "eval_loss": 2.5741186141967773,
      "eval_runtime": 95.2372,
      "eval_samples_per_second": 7.634,
      "eval_steps_per_second": 3.822,
      "step": 9
    },
    {
      "epoch": 0.005792903692976104,
      "grad_norm": 1.5056668519973755,
      "learning_rate": 0.0002,
      "loss": 2.2225,
      "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": 1849564248145920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}