trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 12141,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08236553825879252,
      "grad_norm": 2.806833267211914,
      "learning_rate": 1.835268923482415e-05,
      "loss": 7.3233,
      "step": 1000
    },
    {
      "epoch": 0.16473107651758503,
      "grad_norm": 2.414405345916748,
      "learning_rate": 1.67053784696483e-05,
      "loss": 6.428,
      "step": 2000
    },
    {
      "epoch": 0.24709661477637757,
      "grad_norm": 2.7336931228637695,
      "learning_rate": 1.505806770447245e-05,
      "loss": 6.121,
      "step": 3000
    },
    {
      "epoch": 0.32946215303517007,
      "grad_norm": 2.707063674926758,
      "learning_rate": 1.3410756939296599e-05,
      "loss": 5.8761,
      "step": 4000
    },
    {
      "epoch": 0.4118276912939626,
      "grad_norm": 2.918213129043579,
      "learning_rate": 1.176344617412075e-05,
      "loss": 5.7252,
      "step": 5000
    },
    {
      "epoch": 0.49419322955275513,
      "grad_norm": 2.722219944000244,
      "learning_rate": 1.0116135408944898e-05,
      "loss": 5.5951,
      "step": 6000
    },
    {
      "epoch": 0.5765587678115477,
      "grad_norm": 3.1989521980285645,
      "learning_rate": 8.470471954534224e-06,
      "loss": 5.4935,
      "step": 7000
    },
    {
      "epoch": 0.6589243060703401,
      "grad_norm": 3.0108842849731445,
      "learning_rate": 6.823161189358373e-06,
      "loss": 5.4158,
      "step": 8000
    },
    {
      "epoch": 0.7412898443291327,
      "grad_norm": 2.9963932037353516,
      "learning_rate": 5.177497734947698e-06,
      "loss": 5.3553,
      "step": 9000
    },
    {
      "epoch": 0.8236553825879253,
      "grad_norm": 3.4173614978790283,
      "learning_rate": 3.530186969771848e-06,
      "loss": 5.2982,
      "step": 10000
    },
    {
      "epoch": 0.9060209208467177,
      "grad_norm": 2.9771502017974854,
      "learning_rate": 1.884523515361173e-06,
      "loss": 5.2726,
      "step": 11000
    },
    {
      "epoch": 0.9883864591055103,
      "grad_norm": 3.5910282135009766,
      "learning_rate": 2.3721275018532246e-07,
      "loss": 5.2688,
      "step": 12000
    },
    {
      "epoch": 1.0,
      "step": 12141,
      "total_flos": 2.5377466023936e+16,
      "train_loss": 5.757713494451266,
      "train_runtime": 5411.3319,
      "train_samples_per_second": 17.948,
      "train_steps_per_second": 2.244
    }
  ],
  "logging_steps": 1000,
  "max_steps": 12141,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.5377466023936e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}