trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9926617745163442,
  "eval_steps": 5,
  "global_step": 93,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0533689126084056,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.66,
      "step": 5
    },
    {
      "epoch": 0.1067378252168112,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.6231,
      "step": 10
    },
    {
      "epoch": 0.1601067378252168,
      "grad_norm": 0.2781398892402649,
      "learning_rate": 0.001414213562373095,
      "loss": 1.6169,
      "step": 15
    },
    {
      "epoch": 0.2134756504336224,
      "grad_norm": 2.027355194091797,
      "learning_rate": 0.001,
      "loss": 1.5934,
      "step": 20
    },
    {
      "epoch": 0.266844563042028,
      "grad_norm": 0.6781024932861328,
      "learning_rate": 0.0006666666666666666,
      "loss": 1.4104,
      "step": 25
    },
    {
      "epoch": 0.3202134756504336,
      "grad_norm": 0.8801289796829224,
      "learning_rate": 0.0005345224838248488,
      "loss": 1.3078,
      "step": 30
    },
    {
      "epoch": 0.3735823882588392,
      "grad_norm": 0.37911781668663025,
      "learning_rate": 0.0004588314677411235,
      "loss": 1.2235,
      "step": 35
    },
    {
      "epoch": 0.4269513008672448,
      "grad_norm": 0.3639412224292755,
      "learning_rate": 0.0004082482904638631,
      "loss": 1.2058,
      "step": 40
    },
    {
      "epoch": 0.48032021347565046,
      "grad_norm": 0.3324061930179596,
      "learning_rate": 0.0003713906763541037,
      "loss": 1.2022,
      "step": 45
    },
    {
      "epoch": 0.533689126084056,
      "grad_norm": 0.3669029772281647,
      "learning_rate": 0.00034299717028501764,
      "loss": 1.1901,
      "step": 50
    },
    {
      "epoch": 0.5870580386924616,
      "grad_norm": 0.3316662013530731,
      "learning_rate": 0.00032025630761017425,
      "loss": 1.1541,
      "step": 55
    },
    {
      "epoch": 0.6404269513008672,
      "grad_norm": 0.36560526490211487,
      "learning_rate": 0.00030151134457776364,
      "loss": 1.1021,
      "step": 60
    },
    {
      "epoch": 0.6937958639092728,
      "grad_norm": 0.36231526732444763,
      "learning_rate": 0.0002857142857142857,
      "loss": 1.1178,
      "step": 65
    },
    {
      "epoch": 0.7471647765176784,
      "grad_norm": 0.3893248438835144,
      "learning_rate": 0.0002721655269759087,
      "loss": 1.1032,
      "step": 70
    },
    {
      "epoch": 0.800533689126084,
      "grad_norm": 0.4164714813232422,
      "learning_rate": 0.0002603778219616478,
      "loss": 1.0781,
      "step": 75
    },
    {
      "epoch": 0.8539026017344896,
      "grad_norm": 0.3659443259239197,
      "learning_rate": 0.00025,
      "loss": 1.0644,
      "step": 80
    },
    {
      "epoch": 0.9072715143428952,
      "grad_norm": 0.3580448031425476,
      "learning_rate": 0.0002407717061715384,
      "loss": 1.0597,
      "step": 85
    },
    {
      "epoch": 0.9606404269513009,
      "grad_norm": 0.4161628186702728,
      "learning_rate": 0.00023249527748763857,
      "loss": 1.0817,
      "step": 90
    },
    {
      "epoch": 0.9926617745163442,
      "step": 93,
      "total_flos": 9.445511318816686e+17,
      "train_loss": 1.2599219224786247,
      "train_runtime": 872.6845,
      "train_samples_per_second": 13.737,
      "train_steps_per_second": 0.107
    }
  ],
  "logging_steps": 5,
  "max_steps": 93,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.445511318816686e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}