checkpoint-10/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10416666666666667,
  "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,
      "eval_loss": 1.7594966888427734,
      "eval_runtime": 8.6735,
      "eval_samples_per_second": 4.727,
      "eval_steps_per_second": 2.421,
      "step": 0
    },
    {
      "epoch": 0.010416666666666666,
      "grad_norm": 0.7218555212020874,
      "learning_rate": 0.0,
      "loss": 1.7446,
      "step": 1
    },
    {
      "epoch": 0.020833333333333332,
      "grad_norm": 0.7277606129646301,
      "learning_rate": 2e-05,
      "loss": 1.5541,
      "step": 2
    },
    {
      "epoch": 0.03125,
      "grad_norm": 0.780460774898529,
      "learning_rate": 4e-05,
      "loss": 2.0334,
      "step": 3
    },
    {
      "epoch": 0.03125,
      "eval_loss": 1.7596561908721924,
      "eval_runtime": 8.4033,
      "eval_samples_per_second": 4.879,
      "eval_steps_per_second": 2.499,
      "step": 3
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 0.6424224376678467,
      "learning_rate": 6e-05,
      "loss": 1.279,
      "step": 4
    },
    {
      "epoch": 0.052083333333333336,
      "grad_norm": 0.7212741374969482,
      "learning_rate": 8e-05,
      "loss": 1.7382,
      "step": 5
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.6658374071121216,
      "learning_rate": 0.0001,
      "loss": 1.4699,
      "step": 6
    },
    {
      "epoch": 0.0625,
      "eval_loss": 1.7542871236801147,
      "eval_runtime": 8.3903,
      "eval_samples_per_second": 4.887,
      "eval_steps_per_second": 2.503,
      "step": 6
    },
    {
      "epoch": 0.07291666666666667,
      "grad_norm": 0.6790383458137512,
      "learning_rate": 0.00012,
      "loss": 1.4455,
      "step": 7
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.5029568076133728,
      "learning_rate": 0.00014,
      "loss": 1.3662,
      "step": 8
    },
    {
      "epoch": 0.09375,
      "grad_norm": 0.958249032497406,
      "learning_rate": 0.00016,
      "loss": 1.4307,
      "step": 9
    },
    {
      "epoch": 0.09375,
      "eval_loss": 1.7402998208999634,
      "eval_runtime": 8.3041,
      "eval_samples_per_second": 4.937,
      "eval_steps_per_second": 2.529,
      "step": 9
    },
    {
      "epoch": 0.10416666666666667,
      "grad_norm": 0.7801684141159058,
      "learning_rate": 0.00018,
      "loss": 2.183,
      "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": 240545515438080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}