last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01862341894932878,
  "eval_steps": 5,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012415612632885853,
      "grad_norm": 0.38651901483535767,
      "learning_rate": 1e-05,
      "loss": 0.8737,
      "step": 1
    },
    {
      "epoch": 0.0012415612632885853,
      "eval_loss": NaN,
      "eval_runtime": 71.5539,
      "eval_samples_per_second": 75.831,
      "eval_steps_per_second": 9.489,
      "step": 1
    },
    {
      "epoch": 0.0024831225265771707,
      "grad_norm": 0.3346116542816162,
      "learning_rate": 2e-05,
      "loss": 0.8453,
      "step": 2
    },
    {
      "epoch": 0.003724683789865756,
      "grad_norm": 0.34337764978408813,
      "learning_rate": 3e-05,
      "loss": 0.7958,
      "step": 3
    },
    {
      "epoch": 0.004966245053154341,
      "grad_norm": 0.4059295952320099,
      "learning_rate": 4e-05,
      "loss": 0.8395,
      "step": 4
    },
    {
      "epoch": 0.006207806316442927,
      "grad_norm": 0.3587191104888916,
      "learning_rate": 5e-05,
      "loss": 0.7908,
      "step": 5
    },
    {
      "epoch": 0.006207806316442927,
      "eval_loss": NaN,
      "eval_runtime": 60.0514,
      "eval_samples_per_second": 90.356,
      "eval_steps_per_second": 11.307,
      "step": 5
    },
    {
      "epoch": 0.007449367579731512,
      "grad_norm": 0.3114588260650635,
      "learning_rate": 6e-05,
      "loss": 0.9081,
      "step": 6
    },
    {
      "epoch": 0.008690928843020097,
      "grad_norm": 0.33595696091651917,
      "learning_rate": 7e-05,
      "loss": 0.8077,
      "step": 7
    },
    {
      "epoch": 0.009932490106308683,
      "grad_norm": 0.32869091629981995,
      "learning_rate": 8e-05,
      "loss": 0.8406,
      "step": 8
    },
    {
      "epoch": 0.011174051369597269,
      "grad_norm": 0.3324941396713257,
      "learning_rate": 9e-05,
      "loss": 0.896,
      "step": 9
    },
    {
      "epoch": 0.012415612632885854,
      "grad_norm": 0.3595397472381592,
      "learning_rate": 0.0001,
      "loss": 0.7572,
      "step": 10
    },
    {
      "epoch": 0.012415612632885854,
      "eval_loss": NaN,
      "eval_runtime": 60.2689,
      "eval_samples_per_second": 90.03,
      "eval_steps_per_second": 11.266,
      "step": 10
    },
    {
      "epoch": 0.01365717389617444,
      "grad_norm": 0.31225091218948364,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8059,
      "step": 11
    },
    {
      "epoch": 0.014898735159463024,
      "grad_norm": 0.33488965034484863,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7773,
      "step": 12
    },
    {
      "epoch": 0.01614029642275161,
      "grad_norm": 1.0021756887435913,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8657,
      "step": 13
    },
    {
      "epoch": 0.017381857686040194,
      "grad_norm": 0.3065239489078522,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.748,
      "step": 14
    },
    {
      "epoch": 0.01862341894932878,
      "grad_norm": 0.3766428828239441,
      "learning_rate": 5e-05,
      "loss": 0.8213,
      "step": 15
    },
    {
      "epoch": 0.01862341894932878,
      "eval_loss": NaN,
      "eval_runtime": 60.2571,
      "eval_samples_per_second": 90.047,
      "eval_steps_per_second": 11.268,
      "step": 15
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.940970105765888e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}