last-checkpoint/trainer_state.json

{
  "best_metric": 0.7292912006378174,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.002463661000246366,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002463661000246366,
      "grad_norm": 0.5469629764556885,
      "learning_rate": 2e-05,
      "loss": 0.9891,
      "step": 1
    },
    {
      "epoch": 0.0002463661000246366,
      "eval_loss": 0.8779290318489075,
      "eval_runtime": 313.0811,
      "eval_samples_per_second": 5.459,
      "eval_steps_per_second": 2.731,
      "step": 1
    },
    {
      "epoch": 0.0004927322000492732,
      "grad_norm": 0.5583520531654358,
      "learning_rate": 4e-05,
      "loss": 0.5833,
      "step": 2
    },
    {
      "epoch": 0.0007390983000739098,
      "grad_norm": 0.41663986444473267,
      "learning_rate": 6e-05,
      "loss": 0.5106,
      "step": 3
    },
    {
      "epoch": 0.0009854644000985464,
      "grad_norm": 0.4580349028110504,
      "learning_rate": 8e-05,
      "loss": 0.7081,
      "step": 4
    },
    {
      "epoch": 0.001231830500123183,
      "grad_norm": 0.3514888882637024,
      "learning_rate": 0.0001,
      "loss": 0.4564,
      "step": 5
    },
    {
      "epoch": 0.001231830500123183,
      "eval_loss": 0.8547623157501221,
      "eval_runtime": 311.5363,
      "eval_samples_per_second": 5.486,
      "eval_steps_per_second": 2.744,
      "step": 5
    },
    {
      "epoch": 0.0014781966001478197,
      "grad_norm": 0.5555539131164551,
      "learning_rate": 0.00012,
      "loss": 0.6882,
      "step": 6
    },
    {
      "epoch": 0.0017245627001724563,
      "grad_norm": 0.3112781345844269,
      "learning_rate": 0.00014,
      "loss": 0.3356,
      "step": 7
    },
    {
      "epoch": 0.001970928800197093,
      "grad_norm": 0.5190461874008179,
      "learning_rate": 0.00016,
      "loss": 0.6538,
      "step": 8
    },
    {
      "epoch": 0.0022172949002217295,
      "grad_norm": 0.4782675504684448,
      "learning_rate": 0.00018,
      "loss": 1.078,
      "step": 9
    },
    {
      "epoch": 0.002463661000246366,
      "grad_norm": 0.42852485179901123,
      "learning_rate": 0.0002,
      "loss": 0.8526,
      "step": 10
    },
    {
      "epoch": 0.002463661000246366,
      "eval_loss": 0.7292912006378174,
      "eval_runtime": 311.1124,
      "eval_samples_per_second": 5.493,
      "eval_steps_per_second": 2.748,
      "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": 3282976540459008.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}