last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02007024586051179,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002007024586051179,
      "grad_norm": Infinity,
      "learning_rate": 2e-05,
      "loss": 3.2105,
      "step": 1
    },
    {
      "epoch": 0.002007024586051179,
      "eval_loss": 3.369473695755005,
      "eval_runtime": 33.573,
      "eval_samples_per_second": 6.255,
      "eval_steps_per_second": 3.128,
      "step": 1
    },
    {
      "epoch": 0.004014049172102358,
      "grad_norm": Infinity,
      "learning_rate": 4e-05,
      "loss": 3.0313,
      "step": 2
    },
    {
      "epoch": 0.006021073758153537,
      "grad_norm": Infinity,
      "learning_rate": 6e-05,
      "loss": 3.1503,
      "step": 3
    },
    {
      "epoch": 0.006021073758153537,
      "eval_loss": 3.369473695755005,
      "eval_runtime": 33.4472,
      "eval_samples_per_second": 6.279,
      "eval_steps_per_second": 3.139,
      "step": 3
    },
    {
      "epoch": 0.008028098344204716,
      "grad_norm": Infinity,
      "learning_rate": 8e-05,
      "loss": 3.3801,
      "step": 4
    },
    {
      "epoch": 0.010035122930255895,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 3.1195,
      "step": 5
    },
    {
      "epoch": 0.012042147516307075,
      "grad_norm": Infinity,
      "learning_rate": 0.00012,
      "loss": 3.1796,
      "step": 6
    },
    {
      "epoch": 0.012042147516307075,
      "eval_loss": 3.369473695755005,
      "eval_runtime": 33.6235,
      "eval_samples_per_second": 6.246,
      "eval_steps_per_second": 3.123,
      "step": 6
    },
    {
      "epoch": 0.014049172102358254,
      "grad_norm": Infinity,
      "learning_rate": 0.00014,
      "loss": 3.1369,
      "step": 7
    },
    {
      "epoch": 0.016056196688409432,
      "grad_norm": Infinity,
      "learning_rate": 0.00016,
      "loss": 3.4106,
      "step": 8
    },
    {
      "epoch": 0.01806322127446061,
      "grad_norm": Infinity,
      "learning_rate": 0.00018,
      "loss": 3.3776,
      "step": 9
    },
    {
      "epoch": 0.01806322127446061,
      "eval_loss": 3.369473695755005,
      "eval_runtime": 33.7306,
      "eval_samples_per_second": 6.226,
      "eval_steps_per_second": 3.113,
      "step": 9
    },
    {
      "epoch": 0.02007024586051179,
      "grad_norm": Infinity,
      "learning_rate": 0.0002,
      "loss": 3.1622,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2058737544069120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}