last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000645682001614205,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.45682001614205e-05,
      "grad_norm": Infinity,
      "learning_rate": 2e-05,
      "loss": 2.635,
      "step": 1
    },
    {
      "epoch": 6.45682001614205e-05,
      "eval_loss": 2.853118419647217,
      "eval_runtime": 1010.3744,
      "eval_samples_per_second": 6.455,
      "eval_steps_per_second": 3.228,
      "step": 1
    },
    {
      "epoch": 0.000129136400322841,
      "grad_norm": Infinity,
      "learning_rate": 4e-05,
      "loss": 2.8469,
      "step": 2
    },
    {
      "epoch": 0.0001937046004842615,
      "grad_norm": Infinity,
      "learning_rate": 6e-05,
      "loss": 2.9541,
      "step": 3
    },
    {
      "epoch": 0.0001937046004842615,
      "eval_loss": 2.853118419647217,
      "eval_runtime": 1010.6212,
      "eval_samples_per_second": 6.453,
      "eval_steps_per_second": 3.227,
      "step": 3
    },
    {
      "epoch": 0.000258272800645682,
      "grad_norm": Infinity,
      "learning_rate": 8e-05,
      "loss": 2.6621,
      "step": 4
    },
    {
      "epoch": 0.0003228410008071025,
      "grad_norm": Infinity,
      "learning_rate": 0.0001,
      "loss": 3.1412,
      "step": 5
    },
    {
      "epoch": 0.000387409200968523,
      "grad_norm": Infinity,
      "learning_rate": 0.00012,
      "loss": 2.9894,
      "step": 6
    },
    {
      "epoch": 0.000387409200968523,
      "eval_loss": 2.853118419647217,
      "eval_runtime": 1010.508,
      "eval_samples_per_second": 6.454,
      "eval_steps_per_second": 3.227,
      "step": 6
    },
    {
      "epoch": 0.0004519774011299435,
      "grad_norm": Infinity,
      "learning_rate": 0.00014,
      "loss": 2.5575,
      "step": 7
    },
    {
      "epoch": 0.000516545601291364,
      "grad_norm": Infinity,
      "learning_rate": 0.00016,
      "loss": 2.3466,
      "step": 8
    },
    {
      "epoch": 0.0005811138014527845,
      "grad_norm": 1.7445339669456749e+19,
      "learning_rate": 0.00018,
      "loss": 2.9283,
      "step": 9
    },
    {
      "epoch": 0.0005811138014527845,
      "eval_loss": 2.8495190143585205,
      "eval_runtime": 1013.3024,
      "eval_samples_per_second": 6.436,
      "eval_steps_per_second": 3.218,
      "step": 9
    },
    {
      "epoch": 0.000645682001614205,
      "grad_norm": Infinity,
      "learning_rate": 0.0002,
      "loss": 2.6989,
      "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
}