checkpoint-95676/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 95676,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.8255547054322876,
      "grad_norm": 2.0333640575408936,
      "learning_rate": 4.4961546046144744e-08,
      "loss": 0.8176,
      "step": 5000
    },
    {
      "epoch": 3.827018752391887,
      "grad_norm": 1.769223928451538,
      "learning_rate": 4.458473071611758e-08,
      "loss": 0.4356,
      "step": 10000
    },
    {
      "epoch": 3.826530612244898,
      "grad_norm": 2.0607104301452637,
      "learning_rate": 4.47103688605431e-08,
      "loss": 0.317,
      "step": 15000
    },
    {
      "epoch": 3.827018752391887,
      "grad_norm": 2.4189670085906982,
      "learning_rate": 4.458473071611758e-08,
      "loss": 0.2652,
      "step": 20000
    },
    {
      "epoch": 3.826725853359865,
      "grad_norm": 2.4704151153564453,
      "learning_rate": 4.465835568881174e-08,
      "loss": 0.2326,
      "step": 25000
    },
    {
      "epoch": 3.827018752391887,
      "grad_norm": 2.8222293853759766,
      "learning_rate": 4.458326483642939e-08,
      "loss": 0.2139,
      "step": 30000
    },
    {
      "epoch": 3.826809534222611,
      "grad_norm": 1.4943372011184692,
      "learning_rate": 4.4637321760694354e-08,
      "loss": 0.198,
      "step": 35000
    },
    {
      "epoch": 3.827018752391887,
      "grad_norm": 1.933853030204773,
      "learning_rate": 4.458363129731462e-08,
      "loss": 0.189,
      "step": 40000
    },
    {
      "epoch": 3.8268560251722086,
      "grad_norm": 2.177536725997925,
      "learning_rate": 4.462563563036998e-08,
      "loss": 0.1828,
      "step": 45000
    },
    {
      "epoch": 3.827018752391887,
      "grad_norm": 2.765676498413086,
      "learning_rate": 4.45829716720587e-08,
      "loss": 0.1762,
      "step": 50000
    },
    {
      "epoch": 3.9090262970859984,
      "grad_norm": 2.2480595111846924,
      "learning_rate": 2.3447088347896174e-08,
      "loss": 0.2188,
      "step": 55000
    },
    {
      "epoch": 3.8767202946307426,
      "grad_norm": 1.3450602293014526,
      "learning_rate": 3.177352206494588e-08,
      "loss": 0.2161,
      "step": 60000
    },
    {
      "epoch": 3.849798625918029,
      "grad_norm": 1.3951970338821411,
      "learning_rate": 3.871223801309743e-08,
      "loss": 0.2069,
      "step": 65000
    },
    {
      "epoch": 3.827018752391887,
      "grad_norm": 1.839920997619629,
      "learning_rate": 4.458284603136581e-08,
      "loss": 0.2588,
      "step": 70000
    },
    {
      "epoch": 3.8074931465123365,
      "grad_norm": 1.9440021514892578,
      "learning_rate": 4.961532422672319e-08,
      "loss": 0.2477,
      "step": 75000
    },
    {
      "epoch": 3.7905709547500592,
      "grad_norm": 3.082991361618042,
      "learning_rate": 5.397682171773297e-08,
      "loss": 0.2357,
      "step": 80000
    },
    {
      "epoch": 3.775764036958067,
      "grad_norm": 2.4036500453948975,
      "learning_rate": 5.77931445057587e-08,
      "loss": 0.2354,
      "step": 85000
    },
    {
      "epoch": 3.997867803837953,
      "grad_norm": 3.1487817764282227,
      "learning_rate": 5.495386165365328e-10,
      "loss": 0.2282,
      "step": 90000
    },
    {
      "epoch": 3.9717379489109077,
      "grad_norm": 1.6769729852676392,
      "learning_rate": 7.284090296859005e-09,
      "loss": 0.2206,
      "step": 95000
    }
  ],
  "logging_steps": 5000,
  "max_steps": 95676,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.504777309231514e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}