last-checkpoint/trainer_state.json

{
  "best_metric": 0.5411311984062195,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.008998875140607425,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00029996250468691414,
      "eval_loss": 1.0330923795700073,
      "eval_runtime": 330.7833,
      "eval_samples_per_second": 4.244,
      "eval_steps_per_second": 2.122,
      "step": 1
    },
    {
      "epoch": 0.0008998875140607424,
      "grad_norm": 0.2993057370185852,
      "learning_rate": 0.00012,
      "loss": 1.0411,
      "step": 3
    },
    {
      "epoch": 0.0014998125234345708,
      "eval_loss": 0.920964241027832,
      "eval_runtime": 333.8746,
      "eval_samples_per_second": 4.205,
      "eval_steps_per_second": 2.103,
      "step": 5
    },
    {
      "epoch": 0.0017997750281214847,
      "grad_norm": 0.21511536836624146,
      "learning_rate": 0.0001992114701314478,
      "loss": 0.9583,
      "step": 6
    },
    {
      "epoch": 0.0026996625421822273,
      "grad_norm": 0.251980721950531,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.8744,
      "step": 9
    },
    {
      "epoch": 0.0029996250468691415,
      "eval_loss": 0.7666887044906616,
      "eval_runtime": 333.8688,
      "eval_samples_per_second": 4.205,
      "eval_steps_per_second": 2.103,
      "step": 10
    },
    {
      "epoch": 0.0035995500562429695,
      "grad_norm": 0.19681283831596375,
      "learning_rate": 0.000163742398974869,
      "loss": 0.7716,
      "step": 12
    },
    {
      "epoch": 0.0044994375703037125,
      "grad_norm": 0.20338043570518494,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.692,
      "step": 15
    },
    {
      "epoch": 0.0044994375703037125,
      "eval_loss": 0.6406676173210144,
      "eval_runtime": 333.5289,
      "eval_samples_per_second": 4.21,
      "eval_steps_per_second": 2.105,
      "step": 15
    },
    {
      "epoch": 0.005399325084364455,
      "grad_norm": 0.2436366081237793,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.6236,
      "step": 18
    },
    {
      "epoch": 0.005999250093738283,
      "eval_loss": 0.5715872049331665,
      "eval_runtime": 333.2257,
      "eval_samples_per_second": 4.213,
      "eval_steps_per_second": 2.107,
      "step": 20
    },
    {
      "epoch": 0.006299212598425197,
      "grad_norm": 0.20800277590751648,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.5715,
      "step": 21
    },
    {
      "epoch": 0.007199100112485939,
      "grad_norm": 0.20942150056362152,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.5524,
      "step": 24
    },
    {
      "epoch": 0.0074990626171728535,
      "eval_loss": 0.5460241436958313,
      "eval_runtime": 333.1931,
      "eval_samples_per_second": 4.214,
      "eval_steps_per_second": 2.107,
      "step": 25
    },
    {
      "epoch": 0.008098987626546681,
      "grad_norm": 0.18511688709259033,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.545,
      "step": 27
    },
    {
      "epoch": 0.008998875140607425,
      "grad_norm": 0.19074997305870056,
      "learning_rate": 0.0,
      "loss": 0.5388,
      "step": 30
    },
    {
      "epoch": 0.008998875140607425,
      "eval_loss": 0.5411311984062195,
      "eval_runtime": 333.237,
      "eval_samples_per_second": 4.213,
      "eval_steps_per_second": 2.107,
      "step": 30
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.960374605709312e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}