checkpoint-19/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3318777292576419,
  "eval_steps": 500,
  "global_step": 19,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017467248908296942,
      "grad_norm": 0.12968653440475464,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.3378,
      "step": 1
    },
    {
      "epoch": 0.034934497816593885,
      "grad_norm": 0.1782296746969223,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.2777,
      "step": 2
    },
    {
      "epoch": 0.05240174672489083,
      "grad_norm": 0.1216743066906929,
      "learning_rate": 3e-06,
      "loss": 1.2269,
      "step": 3
    },
    {
      "epoch": 0.06986899563318777,
      "grad_norm": 0.13824662566184998,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.2621,
      "step": 4
    },
    {
      "epoch": 0.08733624454148471,
      "grad_norm": 0.15446175634860992,
      "learning_rate": 5e-06,
      "loss": 1.2518,
      "step": 5
    },
    {
      "epoch": 0.10480349344978165,
      "grad_norm": 0.13843178749084473,
      "learning_rate": 6e-06,
      "loss": 1.2438,
      "step": 6
    },
    {
      "epoch": 0.1222707423580786,
      "grad_norm": 0.15130339562892914,
      "learning_rate": 7e-06,
      "loss": 1.2331,
      "step": 7
    },
    {
      "epoch": 0.13973799126637554,
      "grad_norm": 0.15838982164859772,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.2703,
      "step": 8
    },
    {
      "epoch": 0.1572052401746725,
      "grad_norm": 0.15755866467952728,
      "learning_rate": 9e-06,
      "loss": 1.2603,
      "step": 9
    },
    {
      "epoch": 0.17467248908296942,
      "grad_norm": 0.16667789220809937,
      "learning_rate": 1e-05,
      "loss": 1.2428,
      "step": 10
    },
    {
      "epoch": 0.19213973799126638,
      "grad_norm": 0.1794327050447464,
      "learning_rate": 9.988834393115768e-06,
      "loss": 1.2442,
      "step": 11
    },
    {
      "epoch": 0.2096069868995633,
      "grad_norm": 0.18840420246124268,
      "learning_rate": 9.955387440773902e-06,
      "loss": 1.2562,
      "step": 12
    },
    {
      "epoch": 0.22707423580786026,
      "grad_norm": 0.24771647155284882,
      "learning_rate": 9.899808525182935e-06,
      "loss": 1.2056,
      "step": 13
    },
    {
      "epoch": 0.2445414847161572,
      "grad_norm": 0.2212584763765335,
      "learning_rate": 9.822345875271884e-06,
      "loss": 1.2462,
      "step": 14
    },
    {
      "epoch": 0.26200873362445415,
      "grad_norm": 0.2274945080280304,
      "learning_rate": 9.723345458039595e-06,
      "loss": 1.262,
      "step": 15
    },
    {
      "epoch": 0.2794759825327511,
      "grad_norm": 0.22981807589530945,
      "learning_rate": 9.603249433382145e-06,
      "loss": 1.2918,
      "step": 16
    },
    {
      "epoch": 0.29694323144104806,
      "grad_norm": 0.27434590458869934,
      "learning_rate": 9.462594179299408e-06,
      "loss": 1.2858,
      "step": 17
    },
    {
      "epoch": 0.314410480349345,
      "grad_norm": 0.23107963800430298,
      "learning_rate": 9.302007896300697e-06,
      "loss": 1.1679,
      "step": 18
    },
    {
      "epoch": 0.3318777292576419,
      "grad_norm": 0.23975740373134613,
      "learning_rate": 9.122207801708802e-06,
      "loss": 1.2119,
      "step": 19
    }
  ],
  "logging_steps": 1,
  "max_steps": 57,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 19,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.9698239407086633e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}