last-checkpoint/trainer_state.json

{
  "best_metric": 1.0966575145721436,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.014847809948032665,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014847809948032665,
      "grad_norm": 4.760746479034424,
      "learning_rate": 2e-05,
      "loss": 11.3863,
      "step": 1
    },
    {
      "epoch": 0.0014847809948032665,
      "eval_loss": 2.8857903480529785,
      "eval_runtime": 52.3524,
      "eval_samples_per_second": 5.425,
      "eval_steps_per_second": 2.712,
      "step": 1
    },
    {
      "epoch": 0.002969561989606533,
      "grad_norm": 3.34657883644104,
      "learning_rate": 4e-05,
      "loss": 11.0456,
      "step": 2
    },
    {
      "epoch": 0.004454342984409799,
      "grad_norm": 3.2356274127960205,
      "learning_rate": 6e-05,
      "loss": 13.5547,
      "step": 3
    },
    {
      "epoch": 0.005939123979213066,
      "grad_norm": 2.6824147701263428,
      "learning_rate": 8e-05,
      "loss": 8.7514,
      "step": 4
    },
    {
      "epoch": 0.007423904974016332,
      "grad_norm": 5.473128318786621,
      "learning_rate": 0.0001,
      "loss": 13.6083,
      "step": 5
    },
    {
      "epoch": 0.007423904974016332,
      "eval_loss": 2.8108508586883545,
      "eval_runtime": 52.1477,
      "eval_samples_per_second": 5.446,
      "eval_steps_per_second": 2.723,
      "step": 5
    },
    {
      "epoch": 0.008908685968819599,
      "grad_norm": 6.155984401702881,
      "learning_rate": 0.00012,
      "loss": 12.4103,
      "step": 6
    },
    {
      "epoch": 0.010393466963622866,
      "grad_norm": 6.005216121673584,
      "learning_rate": 0.00014,
      "loss": 9.9214,
      "step": 7
    },
    {
      "epoch": 0.011878247958426132,
      "grad_norm": 8.351831436157227,
      "learning_rate": 0.00016,
      "loss": 10.4195,
      "step": 8
    },
    {
      "epoch": 0.013363028953229399,
      "grad_norm": 13.200093269348145,
      "learning_rate": 0.00018,
      "loss": 8.6825,
      "step": 9
    },
    {
      "epoch": 0.014847809948032665,
      "grad_norm": 18.01533317565918,
      "learning_rate": 0.0002,
      "loss": 5.6008,
      "step": 10
    },
    {
      "epoch": 0.014847809948032665,
      "eval_loss": 1.0966575145721436,
      "eval_runtime": 53.1328,
      "eval_samples_per_second": 5.345,
      "eval_steps_per_second": 2.673,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3166224305356800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}