last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03656307129798903,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003656307129798903,
      "grad_norm": 0.09342558681964874,
      "learning_rate": 2e-05,
      "loss": 10.3625,
      "step": 1
    },
    {
      "epoch": 0.003656307129798903,
      "eval_loss": 10.363628387451172,
      "eval_runtime": 0.9594,
      "eval_samples_per_second": 480.517,
      "eval_steps_per_second": 60.455,
      "step": 1
    },
    {
      "epoch": 0.007312614259597806,
      "grad_norm": 0.09047584235668182,
      "learning_rate": 4e-05,
      "loss": 10.3594,
      "step": 2
    },
    {
      "epoch": 0.010968921389396709,
      "grad_norm": 0.08603765070438385,
      "learning_rate": 6e-05,
      "loss": 10.3705,
      "step": 3
    },
    {
      "epoch": 0.010968921389396709,
      "eval_loss": 10.363529205322266,
      "eval_runtime": 0.9573,
      "eval_samples_per_second": 481.543,
      "eval_steps_per_second": 60.585,
      "step": 3
    },
    {
      "epoch": 0.014625228519195612,
      "grad_norm": 0.06676133722066879,
      "learning_rate": 8e-05,
      "loss": 10.3638,
      "step": 4
    },
    {
      "epoch": 0.018281535648994516,
      "grad_norm": 0.08866722881793976,
      "learning_rate": 0.0001,
      "loss": 10.3619,
      "step": 5
    },
    {
      "epoch": 0.021937842778793418,
      "grad_norm": 0.08508071303367615,
      "learning_rate": 0.00012,
      "loss": 10.361,
      "step": 6
    },
    {
      "epoch": 0.021937842778793418,
      "eval_loss": 10.36319351196289,
      "eval_runtime": 0.9755,
      "eval_samples_per_second": 472.593,
      "eval_steps_per_second": 59.459,
      "step": 6
    },
    {
      "epoch": 0.025594149908592323,
      "grad_norm": 0.09561645984649658,
      "learning_rate": 0.00014,
      "loss": 10.3701,
      "step": 7
    },
    {
      "epoch": 0.029250457038391225,
      "grad_norm": 0.08754566311836243,
      "learning_rate": 0.00016,
      "loss": 10.3637,
      "step": 8
    },
    {
      "epoch": 0.03290676416819013,
      "grad_norm": 0.08271048218011856,
      "learning_rate": 0.00018,
      "loss": 10.3623,
      "step": 9
    },
    {
      "epoch": 0.03290676416819013,
      "eval_loss": 10.36262035369873,
      "eval_runtime": 1.0009,
      "eval_samples_per_second": 460.563,
      "eval_steps_per_second": 57.945,
      "step": 9
    },
    {
      "epoch": 0.03656307129798903,
      "grad_norm": 0.07217925786972046,
      "learning_rate": 0.0002,
      "loss": 10.3636,
      "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": 4184195727360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}