last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004700720777185835,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015669069257286117,
      "eval_loss": 2.4840877056121826,
      "eval_runtime": 451.2588,
      "eval_samples_per_second": 5.957,
      "eval_steps_per_second": 2.978,
      "step": 1
    },
    {
      "epoch": 0.0004700720777185835,
      "grad_norm": 0.35675525665283203,
      "learning_rate": 6e-05,
      "loss": 2.5651,
      "step": 3
    },
    {
      "epoch": 0.0007834534628643058,
      "eval_loss": 2.4730889797210693,
      "eval_runtime": 452.5563,
      "eval_samples_per_second": 5.94,
      "eval_steps_per_second": 2.97,
      "step": 5
    },
    {
      "epoch": 0.000940144155437167,
      "grad_norm": 0.4222663938999176,
      "learning_rate": 0.00012,
      "loss": 2.2939,
      "step": 6
    },
    {
      "epoch": 0.0014102162331557505,
      "grad_norm": 0.3590506315231323,
      "learning_rate": 0.00018,
      "loss": 2.3442,
      "step": 9
    },
    {
      "epoch": 0.0015669069257286117,
      "eval_loss": 2.3731884956359863,
      "eval_runtime": 452.2685,
      "eval_samples_per_second": 5.943,
      "eval_steps_per_second": 2.972,
      "step": 10
    },
    {
      "epoch": 0.001880288310874334,
      "grad_norm": 0.46846267580986023,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.488,
      "step": 12
    },
    {
      "epoch": 0.0023503603885929175,
      "grad_norm": 0.6831684112548828,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.3226,
      "step": 15
    },
    {
      "epoch": 0.0023503603885929175,
      "eval_loss": 2.313871383666992,
      "eval_runtime": 454.0482,
      "eval_samples_per_second": 5.92,
      "eval_steps_per_second": 2.96,
      "step": 15
    },
    {
      "epoch": 0.002820432466311501,
      "grad_norm": 0.4186990261077881,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.4933,
      "step": 18
    },
    {
      "epoch": 0.0031338138514572234,
      "eval_loss": 2.2869107723236084,
      "eval_runtime": 452.7221,
      "eval_samples_per_second": 5.937,
      "eval_steps_per_second": 2.969,
      "step": 20
    },
    {
      "epoch": 0.0032905045440300845,
      "grad_norm": 0.4401818513870239,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.2597,
      "step": 21
    },
    {
      "epoch": 0.003760576621748668,
      "grad_norm": 0.4133366644382477,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.2031,
      "step": 24
    },
    {
      "epoch": 0.003917267314321529,
      "eval_loss": 2.2778823375701904,
      "eval_runtime": 452.7385,
      "eval_samples_per_second": 5.937,
      "eval_steps_per_second": 2.969,
      "step": 25
    },
    {
      "epoch": 0.0042306486994672515,
      "grad_norm": 0.4584410488605499,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.2624,
      "step": 27
    },
    {
      "epoch": 0.004700720777185835,
      "grad_norm": 0.43087276816368103,
      "learning_rate": 0.0,
      "loss": 2.3631,
      "step": 30
    },
    {
      "epoch": 0.004700720777185835,
      "eval_loss": 2.2758781909942627,
      "eval_runtime": 452.376,
      "eval_samples_per_second": 5.942,
      "eval_steps_per_second": 2.971,
      "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": 1.0572960236568576e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}