last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005868157178590029,
  "eval_steps": 3,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00011736314357180057,
      "grad_norm": 1.1370474100112915,
      "learning_rate": 1e-05,
      "loss": 1.8185,
      "step": 1
    },
    {
      "epoch": 0.00011736314357180057,
      "eval_loss": 3.281096935272217,
      "eval_runtime": 1575.9695,
      "eval_samples_per_second": 4.553,
      "eval_steps_per_second": 4.553,
      "step": 1
    },
    {
      "epoch": 0.00023472628714360115,
      "grad_norm": 1.9855719804763794,
      "learning_rate": 2e-05,
      "loss": 4.2225,
      "step": 2
    },
    {
      "epoch": 0.0003520894307154017,
      "grad_norm": 1.3053418397903442,
      "learning_rate": 3e-05,
      "loss": 2.4203,
      "step": 3
    },
    {
      "epoch": 0.0003520894307154017,
      "eval_loss": 3.2794156074523926,
      "eval_runtime": 1578.0902,
      "eval_samples_per_second": 4.547,
      "eval_steps_per_second": 4.547,
      "step": 3
    },
    {
      "epoch": 0.0004694525742872023,
      "grad_norm": 1.3151017427444458,
      "learning_rate": 4e-05,
      "loss": 2.5524,
      "step": 4
    },
    {
      "epoch": 0.0005868157178590029,
      "grad_norm": 1.2470061779022217,
      "learning_rate": 5e-05,
      "loss": 2.2495,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1872683801247744.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}