{
  "best_metric": 1.147840142250061,
  "best_model_checkpoint": "./mistral/10-04-24-Weni-WeniGPT-Agents-Mistral-1.0.0-SFT_Experiment with SFT and a new tokenizer configuration for chat template of mistral-2_max_steps-312_batch_4_2024-04-10_ppid_9/checkpoint-100",
  "epoch": 0.9569377990430622,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19,
      "grad_norm": 0.6767070889472961,
      "learning_rate": 0.0001993503206718859,
      "loss": 1.421,
      "step": 20
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.7594590783119202,
      "learning_rate": 0.00019487887022684336,
      "loss": 1.1094,
      "step": 40
    },
    {
      "epoch": 0.48,
      "eval_loss": 1.1684353351593018,
      "eval_runtime": 15.9813,
      "eval_samples_per_second": 2.878,
      "eval_steps_per_second": 1.439,
      "step": 50
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.8954619765281677,
      "learning_rate": 0.00018634217048966637,
      "loss": 1.0392,
      "step": 60
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.6521860361099243,
      "learning_rate": 0.0001741059911251997,
      "loss": 0.9187,
      "step": 80
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.869737446308136,
      "learning_rate": 0.0001586946124013354,
      "loss": 0.879,
      "step": 100
    },
    {
      "epoch": 0.96,
      "eval_loss": 1.147840142250061,
      "eval_runtime": 15.9788,
      "eval_samples_per_second": 2.879,
      "eval_steps_per_second": 1.439,
      "step": 100
    }
  ],
  "logging_steps": 20,
  "max_steps": 312,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "total_flos": 5.073493039551283e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}