last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.40816326530612246,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 2.541314125061035,
      "learning_rate": 2e-05,
      "loss": 1.7373,
      "step": 1
    },
    {
      "epoch": 0.04081632653061224,
      "eval_loss": 2.7169904708862305,
      "eval_runtime": 1.7579,
      "eval_samples_per_second": 6.257,
      "eval_steps_per_second": 3.413,
      "step": 1
    },
    {
      "epoch": 0.08163265306122448,
      "grad_norm": 1.641190767288208,
      "learning_rate": 4e-05,
      "loss": 1.2073,
      "step": 2
    },
    {
      "epoch": 0.12244897959183673,
      "grad_norm": 1.9342085123062134,
      "learning_rate": 6e-05,
      "loss": 1.4465,
      "step": 3
    },
    {
      "epoch": 0.12244897959183673,
      "eval_loss": 2.6776387691497803,
      "eval_runtime": 0.3767,
      "eval_samples_per_second": 29.201,
      "eval_steps_per_second": 15.928,
      "step": 3
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 2.0054235458374023,
      "learning_rate": 8e-05,
      "loss": 1.3989,
      "step": 4
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 2.624239206314087,
      "learning_rate": 0.0001,
      "loss": 1.2946,
      "step": 5
    },
    {
      "epoch": 0.24489795918367346,
      "grad_norm": 3.491370916366577,
      "learning_rate": 0.00012,
      "loss": 1.2136,
      "step": 6
    },
    {
      "epoch": 0.24489795918367346,
      "eval_loss": 1.9611179828643799,
      "eval_runtime": 0.3833,
      "eval_samples_per_second": 28.695,
      "eval_steps_per_second": 15.652,
      "step": 6
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 3.4276037216186523,
      "learning_rate": 0.00014,
      "loss": 1.1283,
      "step": 7
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 3.7004971504211426,
      "learning_rate": 0.00016,
      "loss": 0.888,
      "step": 8
    },
    {
      "epoch": 0.3673469387755102,
      "grad_norm": 3.3266162872314453,
      "learning_rate": 0.00018,
      "loss": 0.5917,
      "step": 9
    },
    {
      "epoch": 0.3673469387755102,
      "eval_loss": 0.5113109946250916,
      "eval_runtime": 0.3774,
      "eval_samples_per_second": 29.148,
      "eval_steps_per_second": 15.899,
      "step": 9
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 6.337663173675537,
      "learning_rate": 0.0002,
      "loss": 0.5944,
      "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": 1647822923366400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}