{
  "best_global_step": 1000,
  "best_metric": 0.4028251022017164,
  "best_model_checkpoint": "checkpoints/med-ruri-v3-70m-v2-from-ruri/checkpoint-1000",
  "epoch": 0.1623640201331385,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008118201006656925,
      "grad_norm": 21.997957229614258,
      "learning_rate": 1.590909090909091e-06,
      "loss": 2.7372756958007813,
      "step": 50
    },
    {
      "epoch": 0.01623640201331385,
      "grad_norm": 21.73430824279785,
      "learning_rate": 3.2142857142857147e-06,
      "loss": 1.9263325500488282,
      "step": 100
    },
    {
      "epoch": 0.024354603019970774,
      "grad_norm": 20.49755859375,
      "learning_rate": 4.837662337662339e-06,
      "loss": 1.7200509643554687,
      "step": 150
    },
    {
      "epoch": 0.0324728040266277,
      "grad_norm": 21.036407470703125,
      "learning_rate": 6.461038961038961e-06,
      "loss": 1.5285859680175782,
      "step": 200
    },
    {
      "epoch": 0.040591005033284625,
      "grad_norm": 21.67646026611328,
      "learning_rate": 8.084415584415586e-06,
      "loss": 1.4216513061523437,
      "step": 250
    },
    {
      "epoch": 0.04870920603994155,
      "grad_norm": 30.95376205444336,
      "learning_rate": 9.707792207792209e-06,
      "loss": 1.382916259765625,
      "step": 300
    },
    {
      "epoch": 0.05682740704659847,
      "grad_norm": 22.470050811767578,
      "learning_rate": 9.929926508289183e-06,
      "loss": 1.316688995361328,
      "step": 350
    },
    {
      "epoch": 0.0649456080532554,
      "grad_norm": 31.66095733642578,
      "learning_rate": 9.84447103059306e-06,
      "loss": 1.284674072265625,
      "step": 400
    },
    {
      "epoch": 0.07306380905991232,
      "grad_norm": 20.316326141357422,
      "learning_rate": 9.759015552896942e-06,
      "loss": 1.18936767578125,
      "step": 450
    },
    {
      "epoch": 0.08118201006656925,
      "grad_norm": 23.299427032470703,
      "learning_rate": 9.67356007520082e-06,
      "loss": 1.1284925842285156,
      "step": 500
    },
    {
      "epoch": 0.08118201006656925,
      "eval_med-ir_cosine_accuracy@1": 0.2215,
      "eval_med-ir_cosine_accuracy@10": 0.5745,
      "eval_med-ir_cosine_accuracy@5": 0.4715,
      "eval_med-ir_cosine_map@10": 0.32694821428571424,
      "eval_med-ir_cosine_mrr@10": 0.3269482142857145,
      "eval_med-ir_cosine_ndcg@10": 0.3859062398415415,
      "eval_med-ir_cosine_precision@1": 0.2215,
      "eval_med-ir_cosine_precision@10": 0.057449999999999994,
      "eval_med-ir_cosine_precision@5": 0.0943,
      "eval_med-ir_cosine_recall@1": 0.2215,
      "eval_med-ir_cosine_recall@10": 0.5745,
      "eval_med-ir_cosine_recall@5": 0.4715,
      "eval_runtime": 53.6164,
      "eval_samples_per_second": 0.0,
      "eval_steps_per_second": 0.0,
      "step": 500
    },
    {
      "epoch": 0.08930021107322618,
      "grad_norm": 22.585927963256836,
      "learning_rate": 9.5881045975047e-06,
      "loss": 1.1239456176757812,
      "step": 550
    },
    {
      "epoch": 0.0974184120798831,
      "grad_norm": 23.06036949157715,
      "learning_rate": 9.50264911980858e-06,
      "loss": 1.0830574035644531,
      "step": 600
    },
    {
      "epoch": 0.10553661308654003,
      "grad_norm": 23.491195678710938,
      "learning_rate": 9.41719364211246e-06,
      "loss": 1.0685610961914063,
      "step": 650
    },
    {
      "epoch": 0.11365481409319694,
      "grad_norm": 21.600292205810547,
      "learning_rate": 9.33173816441634e-06,
      "loss": 1.018815460205078,
      "step": 700
    },
    {
      "epoch": 0.12177301509985387,
      "grad_norm": 28.022537231445312,
      "learning_rate": 9.24628268672022e-06,
      "loss": 0.9987781524658204,
      "step": 750
    },
    {
      "epoch": 0.1298912161065108,
      "grad_norm": 23.952239990234375,
      "learning_rate": 9.160827209024098e-06,
      "loss": 0.9764260864257812,
      "step": 800
    },
    {
      "epoch": 0.13800941711316772,
      "grad_norm": 22.52235984802246,
      "learning_rate": 9.07537173132798e-06,
      "loss": 0.9670017242431641,
      "step": 850
    },
    {
      "epoch": 0.14612761811982464,
      "grad_norm": 24.34895896911621,
      "learning_rate": 8.989916253631858e-06,
      "loss": 0.9470697021484376,
      "step": 900
    },
    {
      "epoch": 0.15424581912648158,
      "grad_norm": 22.89519500732422,
      "learning_rate": 8.904460775935739e-06,
      "loss": 0.9199741363525391,
      "step": 950
    },
    {
      "epoch": 0.1623640201331385,
      "grad_norm": 22.926559448242188,
      "learning_rate": 8.819005298239618e-06,
      "loss": 0.8991819000244141,
      "step": 1000
    },
    {
      "epoch": 0.1623640201331385,
      "eval_med-ir_cosine_accuracy@1": 0.223,
      "eval_med-ir_cosine_accuracy@10": 0.609,
      "eval_med-ir_cosine_accuracy@5": 0.497,
      "eval_med-ir_cosine_map@10": 0.3382640873015873,
      "eval_med-ir_cosine_mrr@10": 0.3382640873015877,
      "eval_med-ir_cosine_ndcg@10": 0.4028251022017164,
      "eval_med-ir_cosine_precision@1": 0.223,
      "eval_med-ir_cosine_precision@10": 0.060899999999999996,
      "eval_med-ir_cosine_precision@5": 0.09939999999999999,
      "eval_med-ir_cosine_recall@1": 0.223,
      "eval_med-ir_cosine_recall@10": 0.609,
      "eval_med-ir_cosine_recall@5": 0.497,
      "eval_runtime": 53.4694,
      "eval_samples_per_second": 0.0,
      "eval_steps_per_second": 0.0,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 6159,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 192,
  "trial_name": null,
  "trial_params": null
}