last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04678362573099415,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004678362573099415,
      "grad_norm": 12.58973503112793,
      "learning_rate": 2e-05,
      "loss": 7.8229,
      "step": 1
    },
    {
      "epoch": 0.004678362573099415,
      "eval_loss": 7.685409069061279,
      "eval_runtime": 1.1679,
      "eval_samples_per_second": 38.532,
      "eval_steps_per_second": 38.532,
      "step": 1
    },
    {
      "epoch": 0.00935672514619883,
      "grad_norm": 13.469074249267578,
      "learning_rate": 4e-05,
      "loss": 7.7073,
      "step": 2
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 13.288359642028809,
      "learning_rate": 6e-05,
      "loss": 7.3078,
      "step": 3
    },
    {
      "epoch": 0.014035087719298246,
      "eval_loss": 7.650800704956055,
      "eval_runtime": 1.1725,
      "eval_samples_per_second": 38.378,
      "eval_steps_per_second": 38.378,
      "step": 3
    },
    {
      "epoch": 0.01871345029239766,
      "grad_norm": 10.393665313720703,
      "learning_rate": 8e-05,
      "loss": 7.893,
      "step": 4
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 10.401045799255371,
      "learning_rate": 0.0001,
      "loss": 7.6955,
      "step": 5
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 12.121800422668457,
      "learning_rate": 0.00012,
      "loss": 6.9641,
      "step": 6
    },
    {
      "epoch": 0.028070175438596492,
      "eval_loss": 7.324780464172363,
      "eval_runtime": 1.2063,
      "eval_samples_per_second": 37.305,
      "eval_steps_per_second": 37.305,
      "step": 6
    },
    {
      "epoch": 0.03274853801169591,
      "grad_norm": 10.740998268127441,
      "learning_rate": 0.00014,
      "loss": 7.112,
      "step": 7
    },
    {
      "epoch": 0.03742690058479532,
      "grad_norm": 9.38088607788086,
      "learning_rate": 0.00016,
      "loss": 7.3835,
      "step": 8
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 9.658013343811035,
      "learning_rate": 0.00018,
      "loss": 6.7257,
      "step": 9
    },
    {
      "epoch": 0.042105263157894736,
      "eval_loss": 6.872171401977539,
      "eval_runtime": 1.2413,
      "eval_samples_per_second": 36.252,
      "eval_steps_per_second": 36.252,
      "step": 9
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 8.201467514038086,
      "learning_rate": 0.0002,
      "loss": 6.6799,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2714952007680.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}