last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00019224853891110428,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.922485389111043e-05,
      "grad_norm": 2.3878016471862793,
      "learning_rate": 2e-05,
      "loss": 1.8861,
      "step": 1
    },
    {
      "epoch": 1.922485389111043e-05,
      "eval_loss": 2.2143263816833496,
      "eval_runtime": 831.322,
      "eval_samples_per_second": 26.346,
      "eval_steps_per_second": 13.173,
      "step": 1
    },
    {
      "epoch": 3.844970778222086e-05,
      "grad_norm": 2.8661320209503174,
      "learning_rate": 4e-05,
      "loss": 2.1303,
      "step": 2
    },
    {
      "epoch": 5.767456167333128e-05,
      "grad_norm": 3.176454782485962,
      "learning_rate": 6e-05,
      "loss": 2.0898,
      "step": 3
    },
    {
      "epoch": 5.767456167333128e-05,
      "eval_loss": 2.2025914192199707,
      "eval_runtime": 829.6123,
      "eval_samples_per_second": 26.4,
      "eval_steps_per_second": 13.2,
      "step": 3
    },
    {
      "epoch": 7.689941556444171e-05,
      "grad_norm": 3.8627054691314697,
      "learning_rate": 8e-05,
      "loss": 2.3085,
      "step": 4
    },
    {
      "epoch": 9.612426945555214e-05,
      "grad_norm": 3.1302976608276367,
      "learning_rate": 0.0001,
      "loss": 2.052,
      "step": 5
    },
    {
      "epoch": 0.00011534912334666256,
      "grad_norm": 3.143792152404785,
      "learning_rate": 0.00012,
      "loss": 1.9406,
      "step": 6
    },
    {
      "epoch": 0.00011534912334666256,
      "eval_loss": 2.005070686340332,
      "eval_runtime": 830.0344,
      "eval_samples_per_second": 26.387,
      "eval_steps_per_second": 13.193,
      "step": 6
    },
    {
      "epoch": 0.000134573977237773,
      "grad_norm": 5.530796051025391,
      "learning_rate": 0.00014,
      "loss": 1.8552,
      "step": 7
    },
    {
      "epoch": 0.00015379883112888343,
      "grad_norm": 2.8533973693847656,
      "learning_rate": 0.00016,
      "loss": 1.7328,
      "step": 8
    },
    {
      "epoch": 0.00017302368501999384,
      "grad_norm": 3.86198353767395,
      "learning_rate": 0.00018,
      "loss": 1.4914,
      "step": 9
    },
    {
      "epoch": 0.00017302368501999384,
      "eval_loss": 1.6230554580688477,
      "eval_runtime": 830.058,
      "eval_samples_per_second": 26.386,
      "eval_steps_per_second": 13.193,
      "step": 9
    },
    {
      "epoch": 0.00019224853891110428,
      "grad_norm": 3.6009957790374756,
      "learning_rate": 0.0002,
      "loss": 1.5442,
      "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": 2112182707814400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}