checkpoint-195/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 195,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.2567346394062042,
      "learning_rate": 3.984759689788058e-05,
      "loss": 2.7375,
      "step": 10
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.21736398339271545,
      "learning_rate": 3.923287969397442e-05,
      "loss": 2.5609,
      "step": 20
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.25626686215400696,
      "learning_rate": 3.816256236058198e-05,
      "loss": 2.376,
      "step": 30
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.17514042556285858,
      "learning_rate": 3.6664941776944834e-05,
      "loss": 2.2109,
      "step": 40
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.19688807427883148,
      "learning_rate": 3.477961179759822e-05,
      "loss": 2.0924,
      "step": 50
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.22100670635700226,
      "learning_rate": 3.255641647634906e-05,
      "loss": 1.939,
      "step": 60
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.28523585200309753,
      "learning_rate": 3.005413229711771e-05,
      "loss": 1.7258,
      "step": 70
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.16446594893932343,
      "learning_rate": 2.7338914250614635e-05,
      "loss": 1.5419,
      "step": 80
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.13542944192886353,
      "learning_rate": 2.4482546839229335e-05,
      "loss": 1.4464,
      "step": 90
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.07844964414834976,
      "learning_rate": 2.1560546249785927e-05,
      "loss": 1.4034,
      "step": 100
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.06811417639255524,
      "learning_rate": 1.8650163868619736e-05,
      "loss": 1.4146,
      "step": 110
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.07078027725219727,
      "learning_rate": 1.582834392172553e-05,
      "loss": 1.4064,
      "step": 120
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.06608755141496658,
      "learning_rate": 1.3169689235561926e-05,
      "loss": 1.3229,
      "step": 130
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.06391499936580658,
      "learning_rate": 1.074448889940397e-05,
      "loss": 1.3599,
      "step": 140
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.07549852132797241,
      "learning_rate": 8.616859973592406e-06,
      "loss": 1.3567,
      "step": 150
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.06823641061782837,
      "learning_rate": 6.843052372901353e-06,
      "loss": 1.3428,
      "step": 160
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.08508718013763428,
      "learning_rate": 5.469961740247712e-06,
      "loss": 1.3909,
      "step": 170
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.062366873025894165,
      "learning_rate": 4.533889627150585e-06,
      "loss": 1.3788,
      "step": 180
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.07531938701868057,
      "learning_rate": 4.059583759092255e-06,
      "loss": 1.3351,
      "step": 190
    }
  ],
  "logging_steps": 10,
  "max_steps": 195,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.5016810292412416e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}