trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 28178,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10646603733409042,
      "grad_norm": 0.10739253461360931,
      "learning_rate": 4.81935110918419e-05,
      "loss": 1.4731,
      "step": 1500
    },
    {
      "epoch": 0.21293207466818084,
      "grad_norm": 0.12009046971797943,
      "learning_rate": 4.548377772960474e-05,
      "loss": 0.1519,
      "step": 3000
    },
    {
      "epoch": 0.31939811200227125,
      "grad_norm": 0.17752079665660858,
      "learning_rate": 4.277404436736759e-05,
      "loss": 0.1419,
      "step": 4500
    },
    {
      "epoch": 0.4258641493363617,
      "grad_norm": 0.18882086873054504,
      "learning_rate": 4.006431100513043e-05,
      "loss": 0.1371,
      "step": 6000
    },
    {
      "epoch": 0.5323301866704522,
      "grad_norm": 0.13926886022090912,
      "learning_rate": 3.735457764289327e-05,
      "loss": 0.1348,
      "step": 7500
    },
    {
      "epoch": 0.6387962240045425,
      "grad_norm": 0.13389110565185547,
      "learning_rate": 3.464484428065612e-05,
      "loss": 0.1324,
      "step": 9000
    },
    {
      "epoch": 0.7452622613386329,
      "grad_norm": 0.11937592923641205,
      "learning_rate": 3.1935110918418966e-05,
      "loss": 0.1295,
      "step": 10500
    },
    {
      "epoch": 0.8517282986727234,
      "grad_norm": 0.09599358588457108,
      "learning_rate": 2.9225377556181803e-05,
      "loss": 0.1282,
      "step": 12000
    },
    {
      "epoch": 0.9581943360068138,
      "grad_norm": 0.1334109604358673,
      "learning_rate": 2.651564419394465e-05,
      "loss": 0.1287,
      "step": 13500
    },
    {
      "epoch": 1.0646603733409044,
      "grad_norm": 0.14946720004081726,
      "learning_rate": 2.3805910831707495e-05,
      "loss": 0.1282,
      "step": 15000
    },
    {
      "epoch": 1.1711264106749946,
      "grad_norm": 0.12653611600399017,
      "learning_rate": 2.109617746947034e-05,
      "loss": 0.1256,
      "step": 16500
    },
    {
      "epoch": 1.2775924480090852,
      "grad_norm": 0.19287967681884766,
      "learning_rate": 1.8386444107233183e-05,
      "loss": 0.127,
      "step": 18000
    },
    {
      "epoch": 1.3840584853431754,
      "grad_norm": 0.16098152101039886,
      "learning_rate": 1.5676710744996027e-05,
      "loss": 0.1242,
      "step": 19500
    },
    {
      "epoch": 1.4905245226772659,
      "grad_norm": 0.16886812448501587,
      "learning_rate": 1.2966977382758871e-05,
      "loss": 0.1236,
      "step": 21000
    },
    {
      "epoch": 1.5969905600113563,
      "grad_norm": 0.14498655498027802,
      "learning_rate": 1.0257244020521714e-05,
      "loss": 0.124,
      "step": 22500
    },
    {
      "epoch": 1.703456597345447,
      "grad_norm": 0.19877927005290985,
      "learning_rate": 7.547510658284558e-06,
      "loss": 0.1251,
      "step": 24000
    },
    {
      "epoch": 1.8099226346795372,
      "grad_norm": 0.33909276127815247,
      "learning_rate": 4.837777296047403e-06,
      "loss": 0.1242,
      "step": 25500
    },
    {
      "epoch": 1.9163886720136276,
      "grad_norm": 0.14188048243522644,
      "learning_rate": 2.1280439338102465e-06,
      "loss": 0.1222,
      "step": 27000
    }
  ],
  "logging_steps": 1500,
  "max_steps": 28178,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0576304824909824e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}