trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 15.0,
  "eval_steps": 500,
  "global_step": 6705,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1185682326621924,
      "grad_norm": 1.7562521696090698,
      "learning_rate": 4.627889634601044e-05,
      "loss": 1.7047,
      "step": 500
    },
    {
      "epoch": 2.237136465324385,
      "grad_norm": 2.1150481700897217,
      "learning_rate": 4.25503355704698e-05,
      "loss": 1.3195,
      "step": 1000
    },
    {
      "epoch": 3.3557046979865772,
      "grad_norm": 1.773620843887329,
      "learning_rate": 3.882177479492916e-05,
      "loss": 1.1938,
      "step": 1500
    },
    {
      "epoch": 4.47427293064877,
      "grad_norm": 2.1066176891326904,
      "learning_rate": 3.509321401938851e-05,
      "loss": 1.1122,
      "step": 2000
    },
    {
      "epoch": 5.592841163310962,
      "grad_norm": 1.8713332414627075,
      "learning_rate": 3.1364653243847876e-05,
      "loss": 1.0513,
      "step": 2500
    },
    {
      "epoch": 6.7114093959731544,
      "grad_norm": 1.7295632362365723,
      "learning_rate": 2.7636092468307233e-05,
      "loss": 1.0046,
      "step": 3000
    },
    {
      "epoch": 7.829977628635347,
      "grad_norm": 1.7196978330612183,
      "learning_rate": 2.3907531692766593e-05,
      "loss": 0.9671,
      "step": 3500
    },
    {
      "epoch": 8.94854586129754,
      "grad_norm": 1.7857871055603027,
      "learning_rate": 2.017897091722595e-05,
      "loss": 0.9349,
      "step": 4000
    },
    {
      "epoch": 10.06711409395973,
      "grad_norm": 1.7896051406860352,
      "learning_rate": 1.645041014168531e-05,
      "loss": 0.9086,
      "step": 4500
    },
    {
      "epoch": 11.185682326621924,
      "grad_norm": 2.3136727809906006,
      "learning_rate": 1.272184936614467e-05,
      "loss": 0.8844,
      "step": 5000
    },
    {
      "epoch": 12.304250559284116,
      "grad_norm": 2.1995062828063965,
      "learning_rate": 8.993288590604027e-06,
      "loss": 0.877,
      "step": 5500
    },
    {
      "epoch": 13.422818791946309,
      "grad_norm": 1.8003933429718018,
      "learning_rate": 5.264727815063386e-06,
      "loss": 0.8575,
      "step": 6000
    },
    {
      "epoch": 14.5413870246085,
      "grad_norm": 1.9917985200881958,
      "learning_rate": 1.5361670395227442e-06,
      "loss": 0.8476,
      "step": 6500
    },
    {
      "epoch": 15.0,
      "step": 6705,
      "total_flos": 4785148574908416.0,
      "train_loss": 1.044801017653133,
      "train_runtime": 1030.3618,
      "train_samples_per_second": 52.059,
      "train_steps_per_second": 6.507
    }
  ],
  "logging_steps": 500,
  "max_steps": 6705,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4785148574908416.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}