last-checkpoint/trainer_state.json

{
  "best_metric": 1.364399790763855,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.010598834128245893,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010598834128245894,
      "grad_norm": 0.6467643976211548,
      "learning_rate": 2e-05,
      "loss": 5.9796,
      "step": 1
    },
    {
      "epoch": 0.0010598834128245894,
      "eval_loss": 1.5834020376205444,
      "eval_runtime": 80.3436,
      "eval_samples_per_second": 4.954,
      "eval_steps_per_second": 2.477,
      "step": 1
    },
    {
      "epoch": 0.0021197668256491787,
      "grad_norm": 0.6095791459083557,
      "learning_rate": 4e-05,
      "loss": 7.4113,
      "step": 2
    },
    {
      "epoch": 0.003179650238473768,
      "grad_norm": 0.6075787544250488,
      "learning_rate": 6e-05,
      "loss": 6.0515,
      "step": 3
    },
    {
      "epoch": 0.0042395336512983575,
      "grad_norm": 0.7645446062088013,
      "learning_rate": 8e-05,
      "loss": 6.4815,
      "step": 4
    },
    {
      "epoch": 0.005299417064122946,
      "grad_norm": 0.8007614016532898,
      "learning_rate": 0.0001,
      "loss": 6.2063,
      "step": 5
    },
    {
      "epoch": 0.005299417064122946,
      "eval_loss": 1.5732314586639404,
      "eval_runtime": 80.1038,
      "eval_samples_per_second": 4.969,
      "eval_steps_per_second": 2.484,
      "step": 5
    },
    {
      "epoch": 0.006359300476947536,
      "grad_norm": 0.816467821598053,
      "learning_rate": 0.00012,
      "loss": 6.1399,
      "step": 6
    },
    {
      "epoch": 0.007419183889772125,
      "grad_norm": 1.0349878072738647,
      "learning_rate": 0.00014,
      "loss": 6.3008,
      "step": 7
    },
    {
      "epoch": 0.008479067302596715,
      "grad_norm": 1.3219040632247925,
      "learning_rate": 0.00016,
      "loss": 6.0461,
      "step": 8
    },
    {
      "epoch": 0.009538950715421303,
      "grad_norm": 1.773594856262207,
      "learning_rate": 0.00018,
      "loss": 6.0166,
      "step": 9
    },
    {
      "epoch": 0.010598834128245893,
      "grad_norm": 1.6728031635284424,
      "learning_rate": 0.0002,
      "loss": 5.8041,
      "step": 10
    },
    {
      "epoch": 0.010598834128245893,
      "eval_loss": 1.364399790763855,
      "eval_runtime": 79.9364,
      "eval_samples_per_second": 4.979,
      "eval_steps_per_second": 2.489,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3257498484080640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}