last-checkpoint/trainer_state.json

{
  "best_metric": 3.275075674057007,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.027932960893854747,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002793296089385475,
      "grad_norm": 1448.4268798828125,
      "learning_rate": 2e-05,
      "loss": 12.7662,
      "step": 1
    },
    {
      "epoch": 0.002793296089385475,
      "eval_loss": 3.3325388431549072,
      "eval_runtime": 6.0267,
      "eval_samples_per_second": 25.055,
      "eval_steps_per_second": 12.611,
      "step": 1
    },
    {
      "epoch": 0.00558659217877095,
      "grad_norm": 1353.778076171875,
      "learning_rate": 4e-05,
      "loss": 12.4396,
      "step": 2
    },
    {
      "epoch": 0.008379888268156424,
      "grad_norm": 806.8947143554688,
      "learning_rate": 6e-05,
      "loss": 13.0645,
      "step": 3
    },
    {
      "epoch": 0.0111731843575419,
      "grad_norm": 999.5733032226562,
      "learning_rate": 8e-05,
      "loss": 12.6938,
      "step": 4
    },
    {
      "epoch": 0.013966480446927373,
      "grad_norm": 1524.6124267578125,
      "learning_rate": 0.0001,
      "loss": 12.2966,
      "step": 5
    },
    {
      "epoch": 0.013966480446927373,
      "eval_loss": 3.323124885559082,
      "eval_runtime": 4.753,
      "eval_samples_per_second": 31.769,
      "eval_steps_per_second": 15.99,
      "step": 5
    },
    {
      "epoch": 0.01675977653631285,
      "grad_norm": 1987.1434326171875,
      "learning_rate": 0.00012,
      "loss": 13.0857,
      "step": 6
    },
    {
      "epoch": 0.019553072625698324,
      "grad_norm": 1016.9581909179688,
      "learning_rate": 0.00014,
      "loss": 12.7557,
      "step": 7
    },
    {
      "epoch": 0.0223463687150838,
      "grad_norm": 847.552490234375,
      "learning_rate": 0.00016,
      "loss": 13.379,
      "step": 8
    },
    {
      "epoch": 0.025139664804469275,
      "grad_norm": 1183.8375244140625,
      "learning_rate": 0.00018,
      "loss": 12.5125,
      "step": 9
    },
    {
      "epoch": 0.027932960893854747,
      "grad_norm": 1316.9891357421875,
      "learning_rate": 0.0002,
      "loss": 12.9677,
      "step": 10
    },
    {
      "epoch": 0.027932960893854747,
      "eval_loss": 3.275075674057007,
      "eval_runtime": 4.8015,
      "eval_samples_per_second": 31.448,
      "eval_steps_per_second": 15.828,
      "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": 30687834931200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}