checkpoint-500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.9992e-05,
      "loss": 2.3035,
      "step": 1
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.9e-05,
      "loss": 2.1461,
      "step": 125
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.5465,
      "eval_disk_space_total": 78.1898422241211,
      "eval_disk_space_used": 24.584102630615234,
      "eval_f1": 0.4711252488920671,
      "eval_gpu_ram_allocated": 0.3996291160583496,
      "eval_gpu_ram_cached": 12.9296875,
      "eval_gpu_ram_total": 39.56402587890625,
      "eval_gpu_utilization": 28,
      "eval_loss": 1.8486889600753784,
      "eval_precision": 0.5180898369172832,
      "eval_recall": 0.5465,
      "eval_runtime": 1.5234,
      "eval_samples_per_second": 1312.845,
      "eval_steps_per_second": 41.355,
      "eval_system_ram_total": 83.48074722290039,
      "eval_system_ram_used": 3.8797760009765625,
      "step": 125
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.8e-05,
      "loss": 1.6793,
      "step": 250
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.615,
      "eval_disk_space_total": 78.1898422241211,
      "eval_disk_space_used": 24.584190368652344,
      "eval_f1": 0.5799151958404197,
      "eval_gpu_ram_allocated": 0.3996119499206543,
      "eval_gpu_ram_cached": 12.9296875,
      "eval_gpu_ram_total": 39.56402587890625,
      "eval_gpu_utilization": 28,
      "eval_loss": 1.5279773473739624,
      "eval_precision": 0.6206909881233017,
      "eval_recall": 0.615,
      "eval_runtime": 1.5357,
      "eval_samples_per_second": 1302.337,
      "eval_steps_per_second": 41.024,
      "eval_system_ram_total": 83.48074722290039,
      "eval_system_ram_used": 3.8827476501464844,
      "step": 250
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.7e-05,
      "loss": 1.4163,
      "step": 375
    },
    {
      "epoch": 1.5,
      "eval_accuracy": 0.6675,
      "eval_disk_space_total": 78.1898422241211,
      "eval_disk_space_used": 24.584190368652344,
      "eval_f1": 0.6507803054121275,
      "eval_gpu_ram_allocated": 0.3996291160583496,
      "eval_gpu_ram_cached": 12.9296875,
      "eval_gpu_ram_total": 39.56402587890625,
      "eval_gpu_utilization": 28,
      "eval_loss": 1.3395830392837524,
      "eval_precision": 0.6690538200035159,
      "eval_recall": 0.6675,
      "eval_runtime": 1.5175,
      "eval_samples_per_second": 1317.927,
      "eval_steps_per_second": 41.515,
      "eval_system_ram_total": 83.48074722290039,
      "eval_system_ram_used": 3.883075714111328,
      "step": 375
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.2855,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6745,
      "eval_disk_space_total": 78.1898422241211,
      "eval_disk_space_used": 24.584270477294922,
      "eval_f1": 0.6633189544214071,
      "eval_gpu_ram_allocated": 0.3995933532714844,
      "eval_gpu_ram_cached": 12.9296875,
      "eval_gpu_ram_total": 39.56402587890625,
      "eval_gpu_utilization": 30,
      "eval_loss": 1.2413243055343628,
      "eval_precision": 0.6741774761001332,
      "eval_recall": 0.6745,
      "eval_runtime": 1.5166,
      "eval_samples_per_second": 1318.761,
      "eval_steps_per_second": 41.541,
      "eval_system_ram_total": 83.48074722290039,
      "eval_system_ram_used": 3.897541046142578,
      "step": 500
    }
  ],
  "max_steps": 2500,
  "num_train_epochs": 10,
  "total_flos": 252176442301056.0,
  "trial_name": null,
  "trial_params": null
}