last-checkpoint/trainer_state.json

{
  "best_metric": 1.1784987449645996,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.0013667270304438446,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00013667270304438446,
      "grad_norm": 0.50577712059021,
      "learning_rate": 1e-05,
      "loss": 1.0777,
      "step": 1
    },
    {
      "epoch": 0.00013667270304438446,
      "eval_loss": 1.2357397079467773,
      "eval_runtime": 652.1609,
      "eval_samples_per_second": 4.724,
      "eval_steps_per_second": 2.363,
      "step": 1
    },
    {
      "epoch": 0.00027334540608876893,
      "grad_norm": 0.3678644299507141,
      "learning_rate": 2e-05,
      "loss": 1.2261,
      "step": 2
    },
    {
      "epoch": 0.00041001810913315336,
      "grad_norm": 0.49455997347831726,
      "learning_rate": 3e-05,
      "loss": 1.0898,
      "step": 3
    },
    {
      "epoch": 0.0005466908121775379,
      "grad_norm": 0.4921368658542633,
      "learning_rate": 4e-05,
      "loss": 1.069,
      "step": 4
    },
    {
      "epoch": 0.0006833635152219223,
      "grad_norm": 0.43720000982284546,
      "learning_rate": 5e-05,
      "loss": 1.1512,
      "step": 5
    },
    {
      "epoch": 0.0006833635152219223,
      "eval_loss": 1.2310501337051392,
      "eval_runtime": 649.2905,
      "eval_samples_per_second": 4.745,
      "eval_steps_per_second": 2.373,
      "step": 5
    },
    {
      "epoch": 0.0008200362182663067,
      "grad_norm": 0.5448674559593201,
      "learning_rate": 6e-05,
      "loss": 1.0919,
      "step": 6
    },
    {
      "epoch": 0.0009567089213106913,
      "grad_norm": 0.24378623068332672,
      "learning_rate": 7e-05,
      "loss": 0.7775,
      "step": 7
    },
    {
      "epoch": 0.0010933816243550757,
      "grad_norm": 0.347241073846817,
      "learning_rate": 8e-05,
      "loss": 1.1632,
      "step": 8
    },
    {
      "epoch": 0.0012300543273994601,
      "grad_norm": 0.4972077012062073,
      "learning_rate": 9e-05,
      "loss": 1.0055,
      "step": 9
    },
    {
      "epoch": 0.0013667270304438446,
      "grad_norm": 0.6088771224021912,
      "learning_rate": 0.0001,
      "loss": 1.1217,
      "step": 10
    },
    {
      "epoch": 0.0013667270304438446,
      "eval_loss": 1.1784987449645996,
      "eval_runtime": 649.9639,
      "eval_samples_per_second": 4.74,
      "eval_steps_per_second": 2.371,
      "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": 3007276835143680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}