last-checkpoint/trainer_state.json

{
  "best_metric": 0.8469862937927246,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.02201430930104568,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001100715465052284,
      "eval_loss": 1.6823323965072632,
      "eval_runtime": 60.4068,
      "eval_samples_per_second": 6.34,
      "eval_steps_per_second": 3.178,
      "step": 1
    },
    {
      "epoch": 0.003302146395156852,
      "grad_norm": 0.4217250645160675,
      "learning_rate": 0.00012,
      "loss": 1.2519,
      "step": 3
    },
    {
      "epoch": 0.00550357732526142,
      "eval_loss": 1.4989019632339478,
      "eval_runtime": 66.6709,
      "eval_samples_per_second": 5.745,
      "eval_steps_per_second": 2.88,
      "step": 5
    },
    {
      "epoch": 0.006604292790313704,
      "grad_norm": 0.43674561381340027,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.2706,
      "step": 6
    },
    {
      "epoch": 0.009906439185470555,
      "grad_norm": 0.7715041041374207,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.2818,
      "step": 9
    },
    {
      "epoch": 0.01100715465052284,
      "eval_loss": 1.0318337678909302,
      "eval_runtime": 68.5581,
      "eval_samples_per_second": 5.587,
      "eval_steps_per_second": 2.801,
      "step": 10
    },
    {
      "epoch": 0.013208585580627407,
      "grad_norm": 0.7510042786598206,
      "learning_rate": 0.000163742398974869,
      "loss": 0.9583,
      "step": 12
    },
    {
      "epoch": 0.01651073197578426,
      "grad_norm": 0.24181640148162842,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.7886,
      "step": 15
    },
    {
      "epoch": 0.01651073197578426,
      "eval_loss": 0.9011569619178772,
      "eval_runtime": 68.6475,
      "eval_samples_per_second": 5.579,
      "eval_steps_per_second": 2.797,
      "step": 15
    },
    {
      "epoch": 0.01981287837094111,
      "grad_norm": 0.5233681201934814,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.8176,
      "step": 18
    },
    {
      "epoch": 0.02201430930104568,
      "eval_loss": 0.8469862937927246,
      "eval_runtime": 68.6503,
      "eval_samples_per_second": 5.579,
      "eval_steps_per_second": 2.797,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 6779628844744704.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}