checkpoint-62/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.992,
  "eval_steps": 500,
  "global_step": 62,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 0.7084760069847107,
      "learning_rate": 4.920192797165511e-05,
      "loss": 0.8189,
      "num_input_tokens_seen": 54176,
      "step": 5
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.7297347784042358,
      "learning_rate": 4.685866540361456e-05,
      "loss": 0.6742,
      "num_input_tokens_seen": 102528,
      "step": 10
    },
    {
      "epoch": 0.24,
      "grad_norm": 684049.0625,
      "learning_rate": 4.3119819680728e-05,
      "loss": 0.6816,
      "num_input_tokens_seen": 152912,
      "step": 15
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.5369439125061035,
      "learning_rate": 3.822410025817406e-05,
      "loss": 0.6588,
      "num_input_tokens_seen": 204432,
      "step": 20
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.5415367484092712,
      "learning_rate": 3.2484078074333954e-05,
      "loss": 0.5882,
      "num_input_tokens_seen": 254512,
      "step": 25
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.7139325737953186,
      "learning_rate": 2.6266229220967818e-05,
      "loss": 0.6473,
      "num_input_tokens_seen": 298608,
      "step": 30
    },
    {
      "epoch": 0.56,
      "grad_norm": 2127319.0,
      "learning_rate": 1.9967536997783494e-05,
      "loss": 0.6343,
      "num_input_tokens_seen": 348928,
      "step": 35
    },
    {
      "epoch": 0.64,
      "grad_norm": 5908939.5,
      "learning_rate": 1.399014621105914e-05,
      "loss": 0.5067,
      "num_input_tokens_seen": 397216,
      "step": 40
    },
    {
      "epoch": 0.72,
      "grad_norm": 1202378.875,
      "learning_rate": 8.715687931944449e-06,
      "loss": 0.5386,
      "num_input_tokens_seen": 444832,
      "step": 45
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.4307733178138733,
      "learning_rate": 4.480913969818098e-06,
      "loss": 0.563,
      "num_input_tokens_seen": 490640,
      "step": 50
    },
    {
      "epoch": 0.88,
      "grad_norm": 11058075.0,
      "learning_rate": 1.5561966963229924e-06,
      "loss": 0.5484,
      "num_input_tokens_seen": 538400,
      "step": 55
    },
    {
      "epoch": 0.96,
      "grad_norm": 2679230.5,
      "learning_rate": 1.2826691520262114e-07,
      "loss": 0.5979,
      "num_input_tokens_seen": 589856,
      "step": 60
    }
  ],
  "logging_steps": 5,
  "max_steps": 62,
  "num_input_tokens_seen": 610016,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5596354012643328.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}