last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00014906832298136645,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6563146997929607e-05,
      "grad_norm": 0.3126949369907379,
      "learning_rate": 2e-05,
      "loss": 1.746,
      "step": 1
    },
    {
      "epoch": 1.6563146997929607e-05,
      "eval_loss": 1.7334100008010864,
      "eval_runtime": 1208.818,
      "eval_samples_per_second": 21.03,
      "eval_steps_per_second": 10.515,
      "step": 1
    },
    {
      "epoch": 3.3126293995859214e-05,
      "grad_norm": 0.34097328782081604,
      "learning_rate": 4e-05,
      "loss": 1.8578,
      "step": 2
    },
    {
      "epoch": 4.968944099378882e-05,
      "grad_norm": 0.3534299433231354,
      "learning_rate": 6e-05,
      "loss": 1.8201,
      "step": 3
    },
    {
      "epoch": 4.968944099378882e-05,
      "eval_loss": 1.730895757675171,
      "eval_runtime": 1208.5927,
      "eval_samples_per_second": 21.034,
      "eval_steps_per_second": 10.517,
      "step": 3
    },
    {
      "epoch": 6.625258799171843e-05,
      "grad_norm": 0.33659666776657104,
      "learning_rate": 8e-05,
      "loss": 1.7582,
      "step": 4
    },
    {
      "epoch": 8.281573498964803e-05,
      "grad_norm": 0.33756569027900696,
      "learning_rate": 0.0001,
      "loss": 1.7056,
      "step": 5
    },
    {
      "epoch": 9.937888198757764e-05,
      "grad_norm": 0.46250948309898376,
      "learning_rate": 0.00012,
      "loss": 2.0029,
      "step": 6
    },
    {
      "epoch": 9.937888198757764e-05,
      "eval_loss": 1.706060767173767,
      "eval_runtime": 1209.37,
      "eval_samples_per_second": 21.02,
      "eval_steps_per_second": 10.51,
      "step": 6
    },
    {
      "epoch": 0.00011594202898550724,
      "grad_norm": 0.32047656178474426,
      "learning_rate": 0.00014,
      "loss": 1.4038,
      "step": 7
    },
    {
      "epoch": 0.00013250517598343685,
      "grad_norm": 0.4309922754764557,
      "learning_rate": 0.00016,
      "loss": 1.694,
      "step": 8
    },
    {
      "epoch": 0.00014906832298136645,
      "grad_norm": 0.38406458497047424,
      "learning_rate": 0.00018,
      "loss": 1.7324,
      "step": 9
    },
    {
      "epoch": 0.00014906832298136645,
      "eval_loss": 1.6416521072387695,
      "eval_runtime": 1209.7696,
      "eval_samples_per_second": 21.013,
      "eval_steps_per_second": 10.507,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1271075430727680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}