trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9592760180995477,
  "eval_steps": 500,
  "global_step": 165,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18099547511312217,
      "grad_norm": 0.22652482986450195,
      "learning_rate": 5e-05,
      "loss": 0.4309,
      "step": 10
    },
    {
      "epoch": 0.36199095022624433,
      "grad_norm": 0.14215262234210968,
      "learning_rate": 4.949476630105669e-05,
      "loss": 0.3174,
      "step": 20
    },
    {
      "epoch": 0.5429864253393665,
      "grad_norm": 0.11477602273225784,
      "learning_rate": 4.799948609147061e-05,
      "loss": 0.2812,
      "step": 30
    },
    {
      "epoch": 0.7239819004524887,
      "grad_norm": 0.10571786016225815,
      "learning_rate": 4.557459664734141e-05,
      "loss": 0.2675,
      "step": 40
    },
    {
      "epoch": 0.9049773755656109,
      "grad_norm": 0.10327080637216568,
      "learning_rate": 4.231810883773999e-05,
      "loss": 0.2594,
      "step": 50
    },
    {
      "epoch": 1.0723981900452488,
      "grad_norm": 0.11652153730392456,
      "learning_rate": 3.8361645653195026e-05,
      "loss": 0.2349,
      "step": 60
    },
    {
      "epoch": 1.253393665158371,
      "grad_norm": 0.09489592164754868,
      "learning_rate": 3.386512217606339e-05,
      "loss": 0.1941,
      "step": 70
    },
    {
      "epoch": 1.4343891402714932,
      "grad_norm": 0.12396658211946487,
      "learning_rate": 2.9010282021444008e-05,
      "loss": 0.1889,
      "step": 80
    },
    {
      "epoch": 1.6153846153846154,
      "grad_norm": 0.09647022187709808,
      "learning_rate": 2.399335149726463e-05,
      "loss": 0.185,
      "step": 90
    },
    {
      "epoch": 1.7963800904977374,
      "grad_norm": 0.09202118217945099,
      "learning_rate": 1.9017108392811065e-05,
      "loss": 0.1791,
      "step": 100
    },
    {
      "epoch": 1.9773755656108598,
      "grad_norm": 0.08454926311969757,
      "learning_rate": 1.4282685964923642e-05,
      "loss": 0.1738,
      "step": 110
    },
    {
      "epoch": 2.1447963800904977,
      "grad_norm": 0.1310415267944336,
      "learning_rate": 9.981443394050525e-06,
      "loss": 0.1368,
      "step": 120
    },
    {
      "epoch": 2.32579185520362,
      "grad_norm": 0.09298953413963318,
      "learning_rate": 6.28723129572247e-06,
      "loss": 0.1216,
      "step": 130
    },
    {
      "epoch": 2.506787330316742,
      "grad_norm": 0.08098515123128891,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.1258,
      "step": 140
    },
    {
      "epoch": 2.6877828054298645,
      "grad_norm": 0.08589061349630356,
      "learning_rate": 1.286588951321363e-06,
      "loss": 0.1204,
      "step": 150
    },
    {
      "epoch": 2.8687782805429864,
      "grad_norm": 0.08980952948331833,
      "learning_rate": 1.8227814754865068e-07,
      "loss": 0.1194,
      "step": 160
    },
    {
      "epoch": 2.9592760180995477,
      "step": 165,
      "total_flos": 6047450284425216.0,
      "train_loss": 0.20585341887040573,
      "train_runtime": 94606.623,
      "train_samples_per_second": 0.896,
      "train_steps_per_second": 0.002
    }
  ],
  "logging_steps": 10,
  "max_steps": 165,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 6047450284425216.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}