trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08140670791273201,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0040703353956366,
      "grad_norm": 0.8551507592201233,
      "learning_rate": 2.9959296646043635e-05,
      "loss": 1.8278,
      "step": 50
    },
    {
      "epoch": 0.0081406707912732,
      "grad_norm": 0.6171118021011353,
      "learning_rate": 2.991859329208727e-05,
      "loss": 0.0282,
      "step": 100
    },
    {
      "epoch": 0.012211006186909802,
      "grad_norm": 0.04681049659848213,
      "learning_rate": 2.98778899381309e-05,
      "loss": 0.0061,
      "step": 150
    },
    {
      "epoch": 0.0162813415825464,
      "grad_norm": 0.0864928737282753,
      "learning_rate": 2.9837186584174535e-05,
      "loss": 0.0061,
      "step": 200
    },
    {
      "epoch": 0.020351676978183002,
      "grad_norm": 0.09369981288909912,
      "learning_rate": 2.979648323021817e-05,
      "loss": 0.0048,
      "step": 250
    },
    {
      "epoch": 0.024422012373819604,
      "grad_norm": 0.05656412988901138,
      "learning_rate": 2.9755779876261804e-05,
      "loss": 0.0044,
      "step": 300
    },
    {
      "epoch": 0.028492347769456205,
      "grad_norm": 0.06424488872289658,
      "learning_rate": 2.971507652230544e-05,
      "loss": 0.0033,
      "step": 350
    },
    {
      "epoch": 0.0325626831650928,
      "grad_norm": 0.028317060321569443,
      "learning_rate": 2.967437316834907e-05,
      "loss": 0.0034,
      "step": 400
    },
    {
      "epoch": 0.036633018560729404,
      "grad_norm": 0.03844854235649109,
      "learning_rate": 2.9633669814392704e-05,
      "loss": 0.0036,
      "step": 450
    },
    {
      "epoch": 0.040703353956366005,
      "grad_norm": 0.013333266600966454,
      "learning_rate": 2.959296646043634e-05,
      "loss": 0.0026,
      "step": 500
    },
    {
      "epoch": 0.044773689352002606,
      "grad_norm": 0.027189180254936218,
      "learning_rate": 2.9552263106479973e-05,
      "loss": 0.0027,
      "step": 550
    },
    {
      "epoch": 0.04884402474763921,
      "grad_norm": 0.015432504937052727,
      "learning_rate": 2.951155975252361e-05,
      "loss": 0.0021,
      "step": 600
    },
    {
      "epoch": 0.05291436014327581,
      "grad_norm": 0.0909409150481224,
      "learning_rate": 2.9470856398567242e-05,
      "loss": 0.0028,
      "step": 650
    },
    {
      "epoch": 0.05698469553891241,
      "grad_norm": 0.03523814678192139,
      "learning_rate": 2.9430153044610877e-05,
      "loss": 0.0027,
      "step": 700
    },
    {
      "epoch": 0.061055030934549004,
      "grad_norm": 0.037610672414302826,
      "learning_rate": 2.938944969065451e-05,
      "loss": 0.0025,
      "step": 750
    },
    {
      "epoch": 0.0651253663301856,
      "grad_norm": 0.03404204174876213,
      "learning_rate": 2.9348746336698146e-05,
      "loss": 0.0023,
      "step": 800
    },
    {
      "epoch": 0.0691957017258222,
      "grad_norm": 0.0387328565120697,
      "learning_rate": 2.930804298274178e-05,
      "loss": 0.0023,
      "step": 850
    },
    {
      "epoch": 0.07326603712145881,
      "grad_norm": 0.017468873411417007,
      "learning_rate": 2.9267339628785415e-05,
      "loss": 0.0023,
      "step": 900
    },
    {
      "epoch": 0.07733637251709541,
      "grad_norm": 0.025613853707909584,
      "learning_rate": 2.9226636274829046e-05,
      "loss": 0.003,
      "step": 950
    },
    {
      "epoch": 0.08140670791273201,
      "grad_norm": 0.020182810723781586,
      "learning_rate": 2.918593292087268e-05,
      "loss": 0.002,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 36852,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}