last-checkpoint/trainer_state.json

{
  "best_metric": 1.2919340133666992,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.008592910848549946,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "grad_norm": 0.3312093913555145,
      "learning_rate": 2e-05,
      "loss": 1.4872,
      "step": 1
    },
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 1.3853659629821777,
      "eval_runtime": 85.2778,
      "eval_samples_per_second": 5.746,
      "eval_steps_per_second": 2.873,
      "step": 1
    },
    {
      "epoch": 0.0017185821697099893,
      "grad_norm": 0.2858637273311615,
      "learning_rate": 4e-05,
      "loss": 1.2469,
      "step": 2
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 0.31889280676841736,
      "learning_rate": 6e-05,
      "loss": 1.4095,
      "step": 3
    },
    {
      "epoch": 0.0034371643394199786,
      "grad_norm": 0.250221848487854,
      "learning_rate": 8e-05,
      "loss": 1.2253,
      "step": 4
    },
    {
      "epoch": 0.004296455424274973,
      "grad_norm": 0.29837143421173096,
      "learning_rate": 0.0001,
      "loss": 1.3245,
      "step": 5
    },
    {
      "epoch": 0.004296455424274973,
      "eval_loss": 1.3777861595153809,
      "eval_runtime": 84.8221,
      "eval_samples_per_second": 5.777,
      "eval_steps_per_second": 2.888,
      "step": 5
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 0.3289506435394287,
      "learning_rate": 0.00012,
      "loss": 1.265,
      "step": 6
    },
    {
      "epoch": 0.006015037593984963,
      "grad_norm": 0.3476451635360718,
      "learning_rate": 0.00014,
      "loss": 1.2215,
      "step": 7
    },
    {
      "epoch": 0.006874328678839957,
      "grad_norm": 0.37305933237075806,
      "learning_rate": 0.00016,
      "loss": 1.3076,
      "step": 8
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 0.399949848651886,
      "learning_rate": 0.00018,
      "loss": 1.2704,
      "step": 9
    },
    {
      "epoch": 0.008592910848549946,
      "grad_norm": 0.33795350790023804,
      "learning_rate": 0.0002,
      "loss": 1.4873,
      "step": 10
    },
    {
      "epoch": 0.008592910848549946,
      "eval_loss": 1.2919340133666992,
      "eval_runtime": 89.2938,
      "eval_samples_per_second": 5.488,
      "eval_steps_per_second": 2.744,
      "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": 3013156301438976.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}