last-checkpoint/trainer_state.json

{
  "best_metric": 0.293401837348938,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.18512090709244475,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00046280226773111186,
      "eval_loss": 1.8719569444656372,
      "eval_runtime": 98.5466,
      "eval_samples_per_second": 18.468,
      "eval_steps_per_second": 9.234,
      "step": 1
    },
    {
      "epoch": 0.018512090709244474,
      "grad_norm": 0.9190472960472107,
      "learning_rate": 5e-05,
      "loss": 0.9157,
      "step": 40
    },
    {
      "epoch": 0.023140113386555593,
      "eval_loss": 0.5549266338348389,
      "eval_runtime": 98.6712,
      "eval_samples_per_second": 18.445,
      "eval_steps_per_second": 9.223,
      "step": 50
    },
    {
      "epoch": 0.03702418141848895,
      "grad_norm": 1.004511833190918,
      "learning_rate": 0.0001,
      "loss": 0.4873,
      "step": 80
    },
    {
      "epoch": 0.04628022677311119,
      "eval_loss": 0.4434783458709717,
      "eval_runtime": 98.7605,
      "eval_samples_per_second": 18.428,
      "eval_steps_per_second": 9.214,
      "step": 100
    },
    {
      "epoch": 0.055536272127733426,
      "grad_norm": 0.8885133266448975,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.3716,
      "step": 120
    },
    {
      "epoch": 0.06942034015966678,
      "eval_loss": 0.3885350525379181,
      "eval_runtime": 98.7557,
      "eval_samples_per_second": 18.429,
      "eval_steps_per_second": 9.215,
      "step": 150
    },
    {
      "epoch": 0.0740483628369779,
      "grad_norm": 0.6010408997535706,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.3268,
      "step": 160
    },
    {
      "epoch": 0.09256045354622237,
      "grad_norm": 1.0022616386413574,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.2889,
      "step": 200
    },
    {
      "epoch": 0.09256045354622237,
      "eval_loss": 0.3618102967739105,
      "eval_runtime": 98.327,
      "eval_samples_per_second": 18.51,
      "eval_steps_per_second": 9.255,
      "step": 200
    },
    {
      "epoch": 0.11107254425546685,
      "grad_norm": 0.6008154153823853,
      "learning_rate": 5e-05,
      "loss": 0.3563,
      "step": 240
    },
    {
      "epoch": 0.11570056693277797,
      "eval_loss": 0.33197852969169617,
      "eval_runtime": 98.697,
      "eval_samples_per_second": 18.44,
      "eval_steps_per_second": 9.22,
      "step": 250
    },
    {
      "epoch": 0.12958463496471131,
      "grad_norm": 0.5086503028869629,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.3402,
      "step": 280
    },
    {
      "epoch": 0.13884068031933355,
      "eval_loss": 0.30851373076438904,
      "eval_runtime": 102.8003,
      "eval_samples_per_second": 17.704,
      "eval_steps_per_second": 8.852,
      "step": 300
    },
    {
      "epoch": 0.1480967256739558,
      "grad_norm": 0.43418025970458984,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.3107,
      "step": 320
    },
    {
      "epoch": 0.16198079370588916,
      "eval_loss": 0.2973526120185852,
      "eval_runtime": 98.207,
      "eval_samples_per_second": 18.532,
      "eval_steps_per_second": 9.266,
      "step": 350
    },
    {
      "epoch": 0.16660881638320027,
      "grad_norm": 0.596440851688385,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.286,
      "step": 360
    },
    {
      "epoch": 0.18512090709244475,
      "grad_norm": 0.7190999388694763,
      "learning_rate": 0.0,
      "loss": 0.2512,
      "step": 400
    },
    {
      "epoch": 0.18512090709244475,
      "eval_loss": 0.293401837348938,
      "eval_runtime": 98.1497,
      "eval_samples_per_second": 18.543,
      "eval_steps_per_second": 9.272,
      "step": 400
    }
  ],
  "logging_steps": 40,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.94731890081792e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}