trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 18.363699029410846,
      "learning_rate": 1e-05,
      "loss": 1.1139,
      "step": 1
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.1133455038070679,
      "eval_runtime": 2.7908,
      "eval_samples_per_second": 17.199,
      "eval_steps_per_second": 0.358,
      "step": 1
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.2946919202804565,
      "eval_runtime": 2.6849,
      "eval_samples_per_second": 17.878,
      "eval_steps_per_second": 0.372,
      "step": 2
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.084022879600525,
      "eval_runtime": 2.6785,
      "eval_samples_per_second": 17.921,
      "eval_steps_per_second": 0.373,
      "step": 3
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.8533250689506531,
      "eval_runtime": 2.6989,
      "eval_samples_per_second": 17.785,
      "eval_steps_per_second": 0.371,
      "step": 4
    },
    {
      "epoch": 5.0,
      "grad_norm": 20.40164947404992,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 1.0874,
      "step": 5
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.7533825039863586,
      "eval_runtime": 2.6807,
      "eval_samples_per_second": 17.906,
      "eval_steps_per_second": 0.373,
      "step": 5
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.6295236945152283,
      "eval_runtime": 2.68,
      "eval_samples_per_second": 17.911,
      "eval_steps_per_second": 0.373,
      "step": 6
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.567865788936615,
      "eval_runtime": 2.6867,
      "eval_samples_per_second": 17.866,
      "eval_steps_per_second": 0.372,
      "step": 7
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.5224726796150208,
      "eval_runtime": 2.6682,
      "eval_samples_per_second": 17.989,
      "eval_steps_per_second": 0.375,
      "step": 8
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.4935952425003052,
      "eval_runtime": 2.672,
      "eval_samples_per_second": 17.964,
      "eval_steps_per_second": 0.374,
      "step": 9
    },
    {
      "epoch": 10.0,
      "grad_norm": 4.71394718703185,
      "learning_rate": 0.0,
      "loss": 0.5928,
      "step": 10
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.48424649238586426,
      "eval_runtime": 2.6942,
      "eval_samples_per_second": 17.816,
      "eval_steps_per_second": 0.371,
      "step": 10
    },
    {
      "epoch": 10.0,
      "step": 10,
      "total_flos": 8375186227200.0,
      "train_loss": 0.8427552580833435,
      "train_runtime": 304.7513,
      "train_samples_per_second": 1.575,
      "train_steps_per_second": 0.033
    }
  ],
  "logging_steps": 5,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8375186227200.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}