last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0012322479282831705,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012322479282831706,
      "grad_norm": 1.5896955728530884,
      "learning_rate": 2e-05,
      "loss": 6.981,
      "step": 1
    },
    {
      "epoch": 0.00012322479282831706,
      "eval_loss": 1.7705166339874268,
      "eval_runtime": 112.6936,
      "eval_samples_per_second": 30.321,
      "eval_steps_per_second": 15.165,
      "step": 1
    },
    {
      "epoch": 0.0002464495856566341,
      "grad_norm": 1.6327662467956543,
      "learning_rate": 4e-05,
      "loss": 7.0475,
      "step": 2
    },
    {
      "epoch": 0.0003696743784849512,
      "grad_norm": 1.4530117511749268,
      "learning_rate": 6e-05,
      "loss": 7.0797,
      "step": 3
    },
    {
      "epoch": 0.0003696743784849512,
      "eval_loss": 1.7670907974243164,
      "eval_runtime": 112.4239,
      "eval_samples_per_second": 30.394,
      "eval_steps_per_second": 15.201,
      "step": 3
    },
    {
      "epoch": 0.0004928991713132682,
      "grad_norm": 1.488818645477295,
      "learning_rate": 8e-05,
      "loss": 7.2341,
      "step": 4
    },
    {
      "epoch": 0.0006161239641415853,
      "grad_norm": 1.576625108718872,
      "learning_rate": 0.0001,
      "loss": 7.297,
      "step": 5
    },
    {
      "epoch": 0.0007393487569699024,
      "grad_norm": 1.421807885169983,
      "learning_rate": 0.00012,
      "loss": 7.1019,
      "step": 6
    },
    {
      "epoch": 0.0007393487569699024,
      "eval_loss": 1.743476390838623,
      "eval_runtime": 112.3645,
      "eval_samples_per_second": 30.41,
      "eval_steps_per_second": 15.209,
      "step": 6
    },
    {
      "epoch": 0.0008625735497982194,
      "grad_norm": 1.4673856496810913,
      "learning_rate": 0.00014,
      "loss": 7.2599,
      "step": 7
    },
    {
      "epoch": 0.0009857983426265365,
      "grad_norm": 1.9101917743682861,
      "learning_rate": 0.00016,
      "loss": 6.6899,
      "step": 8
    },
    {
      "epoch": 0.0011090231354548535,
      "grad_norm": 1.9195061922073364,
      "learning_rate": 0.00018,
      "loss": 7.012,
      "step": 9
    },
    {
      "epoch": 0.0011090231354548535,
      "eval_loss": 1.7387100458145142,
      "eval_runtime": 112.4469,
      "eval_samples_per_second": 30.388,
      "eval_steps_per_second": 15.198,
      "step": 9
    },
    {
      "epoch": 0.0012322479282831705,
      "grad_norm": 2.2186131477355957,
      "learning_rate": 0.0002,
      "loss": 6.7451,
      "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": 597144738201600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}