last-checkpoint/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1080,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.046296296296296294,
      "grad_norm": 3.5503571033477783,
      "learning_rate": 2.2685185185185187e-05,
      "loss": 0.302,
      "step": 50
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 2.7323362827301025,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 0.1737,
      "step": 100
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 2.2092525959014893,
      "learning_rate": 4.7890946502057616e-05,
      "loss": 0.1749,
      "step": 150
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.7028791904449463,
      "learning_rate": 4.531893004115226e-05,
      "loss": 0.1664,
      "step": 200
    },
    {
      "epoch": 0.23148148148148148,
      "grad_norm": 1.235687017440796,
      "learning_rate": 4.2746913580246915e-05,
      "loss": 0.1471,
      "step": 250
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.7896230220794678,
      "learning_rate": 4.017489711934157e-05,
      "loss": 0.1344,
      "step": 300
    },
    {
      "epoch": 0.32407407407407407,
      "grad_norm": 1.2573087215423584,
      "learning_rate": 3.760288065843622e-05,
      "loss": 0.1342,
      "step": 350
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.3279838562011719,
      "learning_rate": 3.503086419753087e-05,
      "loss": 0.1257,
      "step": 400
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 1.5447418689727783,
      "learning_rate": 3.245884773662551e-05,
      "loss": 0.1289,
      "step": 450
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 1.405887484550476,
      "learning_rate": 2.9886831275720166e-05,
      "loss": 0.1096,
      "step": 500
    },
    {
      "epoch": 0.5092592592592593,
      "grad_norm": 1.608939528465271,
      "learning_rate": 2.7314814814814816e-05,
      "loss": 0.1065,
      "step": 550
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.4359056949615479,
      "learning_rate": 2.4742798353909465e-05,
      "loss": 0.0995,
      "step": 600
    },
    {
      "epoch": 0.6018518518518519,
      "grad_norm": 1.5060992240905762,
      "learning_rate": 2.2170781893004118e-05,
      "loss": 0.1042,
      "step": 650
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 1.104844570159912,
      "learning_rate": 1.9598765432098768e-05,
      "loss": 0.1018,
      "step": 700
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 1.426213264465332,
      "learning_rate": 1.7026748971193414e-05,
      "loss": 0.0992,
      "step": 750
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.1723966598510742,
      "learning_rate": 1.4454732510288065e-05,
      "loss": 0.0924,
      "step": 800
    },
    {
      "epoch": 0.7870370370370371,
      "grad_norm": 1.134878158569336,
      "learning_rate": 1.1882716049382716e-05,
      "loss": 0.0909,
      "step": 850
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 1.0749645233154297,
      "learning_rate": 9.310699588477368e-06,
      "loss": 0.0847,
      "step": 900
    },
    {
      "epoch": 0.8796296296296297,
      "grad_norm": 1.171762228012085,
      "learning_rate": 6.7386831275720164e-06,
      "loss": 0.0914,
      "step": 950
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 1.245627522468567,
      "learning_rate": 4.166666666666667e-06,
      "loss": 0.0847,
      "step": 1000
    },
    {
      "epoch": 0.9722222222222222,
      "grad_norm": 1.3060165643692017,
      "learning_rate": 1.5946502057613169e-06,
      "loss": 0.0842,
      "step": 1050
    }
  ],
  "logging_steps": 50,
  "max_steps": 1080,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 512,
  "trial_name": null,
  "trial_params": null
}