last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2176278563656148,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004352557127312296,
      "eval_loss": 0.2532948851585388,
      "eval_runtime": 110.7197,
      "eval_samples_per_second": 3.495,
      "eval_steps_per_second": 1.752,
      "step": 1
    },
    {
      "epoch": 0.04352557127312296,
      "grad_norm": 0.7663939595222473,
      "learning_rate": 2e-05,
      "loss": 3.9326,
      "step": 10
    },
    {
      "epoch": 0.04352557127312296,
      "eval_loss": 0.2527051568031311,
      "eval_runtime": 111.2398,
      "eval_samples_per_second": 3.479,
      "eval_steps_per_second": 1.744,
      "step": 10
    },
    {
      "epoch": 0.08705114254624592,
      "grad_norm": 1.2098848819732666,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 3.9188,
      "step": 20
    },
    {
      "epoch": 0.08705114254624592,
      "eval_loss": 0.24262596666812897,
      "eval_runtime": 111.1971,
      "eval_samples_per_second": 3.48,
      "eval_steps_per_second": 1.745,
      "step": 20
    },
    {
      "epoch": 0.1305767138193689,
      "grad_norm": 2.7661397457122803,
      "learning_rate": 1e-05,
      "loss": 4.2368,
      "step": 30
    },
    {
      "epoch": 0.1305767138193689,
      "eval_loss": 0.22000382840633392,
      "eval_runtime": 111.0485,
      "eval_samples_per_second": 3.485,
      "eval_steps_per_second": 1.747,
      "step": 30
    },
    {
      "epoch": 0.17410228509249184,
      "grad_norm": 1.3489696979522705,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 3.3521,
      "step": 40
    },
    {
      "epoch": 0.17410228509249184,
      "eval_loss": 0.20708845555782318,
      "eval_runtime": 110.1427,
      "eval_samples_per_second": 3.514,
      "eval_steps_per_second": 1.761,
      "step": 40
    },
    {
      "epoch": 0.2176278563656148,
      "grad_norm": 1.763027548789978,
      "learning_rate": 0.0,
      "loss": 3.4624,
      "step": 50
    },
    {
      "epoch": 0.2176278563656148,
      "eval_loss": 0.20506860315799713,
      "eval_runtime": 110.6033,
      "eval_samples_per_second": 3.499,
      "eval_steps_per_second": 1.754,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1651705443713024e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}