last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009284332688588007,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003094777562862669,
      "eval_loss": 10.374013900756836,
      "eval_runtime": 14.2343,
      "eval_samples_per_second": 430.158,
      "eval_steps_per_second": 143.386,
      "step": 1
    },
    {
      "epoch": 0.0009284332688588008,
      "grad_norm": 0.03615349903702736,
      "learning_rate": 8.999999999999999e-05,
      "loss": 10.3744,
      "step": 3
    },
    {
      "epoch": 0.0018568665377176016,
      "grad_norm": 0.04060865938663483,
      "learning_rate": 0.00017999999999999998,
      "loss": 10.3731,
      "step": 6
    },
    {
      "epoch": 0.0024758220502901353,
      "eval_loss": 10.372960090637207,
      "eval_runtime": 14.2469,
      "eval_samples_per_second": 429.779,
      "eval_steps_per_second": 143.26,
      "step": 8
    },
    {
      "epoch": 0.0027852998065764022,
      "grad_norm": 0.04149027168750763,
      "learning_rate": 0.00027,
      "loss": 10.3733,
      "step": 9
    },
    {
      "epoch": 0.003713733075435203,
      "grad_norm": 0.042886920273303986,
      "learning_rate": 0.00029265847744427303,
      "loss": 10.3725,
      "step": 12
    },
    {
      "epoch": 0.0046421663442940036,
      "grad_norm": 0.04727409780025482,
      "learning_rate": 0.00025606601717798207,
      "loss": 10.3698,
      "step": 15
    },
    {
      "epoch": 0.0049516441005802705,
      "eval_loss": 10.369811058044434,
      "eval_runtime": 14.2492,
      "eval_samples_per_second": 429.709,
      "eval_steps_per_second": 143.236,
      "step": 16
    },
    {
      "epoch": 0.0055705996131528044,
      "grad_norm": 0.04473396763205528,
      "learning_rate": 0.0001963525491562421,
      "loss": 10.3694,
      "step": 18
    },
    {
      "epoch": 0.006499032882011605,
      "grad_norm": 0.06059557572007179,
      "learning_rate": 0.00012653483024396533,
      "loss": 10.3673,
      "step": 21
    },
    {
      "epoch": 0.007427466150870406,
      "grad_norm": 0.05967845022678375,
      "learning_rate": 6.183221215612904e-05,
      "loss": 10.3669,
      "step": 24
    },
    {
      "epoch": 0.007427466150870406,
      "eval_loss": 10.367446899414062,
      "eval_runtime": 14.2805,
      "eval_samples_per_second": 428.767,
      "eval_steps_per_second": 142.922,
      "step": 24
    },
    {
      "epoch": 0.008355899419729206,
      "grad_norm": 0.06560368090867996,
      "learning_rate": 1.634902137174483e-05,
      "loss": 10.368,
      "step": 27
    },
    {
      "epoch": 0.009284332688588007,
      "grad_norm": 0.06149117276072502,
      "learning_rate": 0.0,
      "loss": 10.3674,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3530415144960.0,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}