{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.745762711864407,
  "eval_steps": 500,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 3.306018590927124,
      "learning_rate": 9.999125804563732e-05,
      "loss": 2.1358,
      "num_input_tokens_seen": 10896,
      "step": 1
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 2.0162065029144287,
      "learning_rate": 9.996503523941994e-05,
      "loss": 2.3575,
      "num_input_tokens_seen": 20512,
      "step": 2
    },
    {
      "epoch": 0.2033898305084746,
      "grad_norm": 2.1740899085998535,
      "learning_rate": 9.992134075089084e-05,
      "loss": 1.4712,
      "num_input_tokens_seen": 29984,
      "step": 3
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 2.0339269638061523,
      "learning_rate": 9.986018985905901e-05,
      "loss": 2.3124,
      "num_input_tokens_seen": 39760,
      "step": 4
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 1.0339545011520386,
      "learning_rate": 9.978160394705668e-05,
      "loss": 1.8062,
      "num_input_tokens_seen": 49856,
      "step": 5
    },
    {
      "epoch": 0.4067796610169492,
      "grad_norm": 0.6279817819595337,
      "learning_rate": 9.968561049466214e-05,
      "loss": 2.0499,
      "num_input_tokens_seen": 60208,
      "step": 6
    },
    {
      "epoch": 0.4745762711864407,
      "grad_norm": 0.5110039114952087,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.1603,
      "num_input_tokens_seen": 70816,
      "step": 7
    },
    {
      "epoch": 0.5423728813559322,
      "grad_norm": 0.8199847936630249,
      "learning_rate": 9.944154131125642e-05,
      "loss": 1.9923,
      "num_input_tokens_seen": 79968,
      "step": 8
    },
    {
      "epoch": 0.6101694915254238,
      "grad_norm": 0.729006290435791,
      "learning_rate": 9.92935509259118e-05,
      "loss": 1.9688,
      "num_input_tokens_seen": 89472,
      "step": 9
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 1.2717365026474,
      "learning_rate": 9.912832366166442e-05,
      "loss": 2.2878,
      "num_input_tokens_seen": 100336,
      "step": 10
    },
    {
      "epoch": 0.7457627118644068,
      "grad_norm": 0.6771590113639832,
      "learning_rate": 9.894591729488242e-05,
      "loss": 2.001,
      "num_input_tokens_seen": 110640,
      "step": 11
    },
    {
      "epoch": 0.8135593220338984,
      "grad_norm": 0.4566394090652466,
      "learning_rate": 9.874639560909117e-05,
      "loss": 1.8458,
      "num_input_tokens_seen": 120304,
      "step": 12
    },
    {
      "epoch": 0.8813559322033898,
      "grad_norm": 0.6037254929542542,
      "learning_rate": 9.852982837266955e-05,
      "loss": 1.8775,
      "num_input_tokens_seen": 128288,
      "step": 13
    },
    {
      "epoch": 0.9491525423728814,
      "grad_norm": 0.6338982582092285,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.9309,
      "num_input_tokens_seen": 138624,
      "step": 14
    },
    {
      "epoch": 1.0169491525423728,
      "grad_norm": 0.5118916630744934,
      "learning_rate": 9.804586609725499e-05,
      "loss": 1.5507,
      "num_input_tokens_seen": 148208,
      "step": 15
    },
    {
      "epoch": 1.0847457627118644,
      "grad_norm": 0.4119274914264679,
      "learning_rate": 9.777864028930705e-05,
      "loss": 1.6802,
      "num_input_tokens_seen": 159200,
      "step": 16
    },
    {
      "epoch": 1.152542372881356,
      "grad_norm": 0.5065487623214722,
      "learning_rate": 9.74947073336423e-05,
      "loss": 1.5648,
      "num_input_tokens_seen": 166544,
      "step": 17
    },
    {
      "epoch": 1.2203389830508475,
      "grad_norm": 0.47032174468040466,
      "learning_rate": 9.719416651541839e-05,
      "loss": 1.3598,
      "num_input_tokens_seen": 177120,
      "step": 18
    },
    {
      "epoch": 1.288135593220339,
      "grad_norm": 0.38840025663375854,
      "learning_rate": 9.687712292719997e-05,
      "loss": 1.3238,
      "num_input_tokens_seen": 186272,
      "step": 19
    },
    {
      "epoch": 1.3559322033898304,
      "grad_norm": 0.5947024822235107,
      "learning_rate": 9.654368743221022e-05,
      "loss": 1.8704,
      "num_input_tokens_seen": 196480,
      "step": 20
    },
    {
      "epoch": 1.423728813559322,
      "grad_norm": 0.5424012541770935,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.8205,
      "num_input_tokens_seen": 203856,
      "step": 21
    },
    {
      "epoch": 1.4915254237288136,
      "grad_norm": 0.45230892300605774,
      "learning_rate": 9.582811279349882e-05,
      "loss": 1.3595,
      "num_input_tokens_seen": 214512,
      "step": 22
    },
    {
      "epoch": 1.559322033898305,
      "grad_norm": 0.41904568672180176,
      "learning_rate": 9.544622387061055e-05,
      "loss": 2.0797,
      "num_input_tokens_seen": 223792,
      "step": 23
    },
    {
      "epoch": 1.6271186440677967,
      "grad_norm": 0.5474861264228821,
      "learning_rate": 9.504844339512095e-05,
      "loss": 2.15,
      "num_input_tokens_seen": 233776,
      "step": 24
    },
    {
      "epoch": 1.694915254237288,
      "grad_norm": 0.4554285407066345,
      "learning_rate": 9.463491046218058e-05,
      "loss": 2.0059,
      "num_input_tokens_seen": 243600,
      "step": 25
    },
    {
      "epoch": 1.7627118644067796,
      "grad_norm": 0.4554867744445801,
      "learning_rate": 9.420576967523049e-05,
      "loss": 1.2697,
      "num_input_tokens_seen": 254608,
      "step": 26
    },
    {
      "epoch": 1.8305084745762712,
      "grad_norm": 0.44335854053497314,
      "learning_rate": 9.376117109543769e-05,
      "loss": 1.6259,
      "num_input_tokens_seen": 265728,
      "step": 27
    },
    {
      "epoch": 1.8983050847457628,
      "grad_norm": 0.36280569434165955,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0618,
      "num_input_tokens_seen": 276624,
      "step": 28
    },
    {
      "epoch": 1.9661016949152543,
      "grad_norm": 0.4373883306980133,
      "learning_rate": 9.282622777389258e-05,
      "loss": 1.8557,
      "num_input_tokens_seen": 287072,
      "step": 29
    },
    {
      "epoch": 2.0338983050847457,
      "grad_norm": 0.5854040384292603,
      "learning_rate": 9.233620996141421e-05,
      "loss": 1.8077,
      "num_input_tokens_seen": 296248,
      "step": 30
    },
    {
      "epoch": 2.1016949152542375,
      "grad_norm": 0.5168242454528809,
      "learning_rate": 9.183138810032099e-05,
      "loss": 1.767,
      "num_input_tokens_seen": 305560,
      "step": 31
    },
    {
      "epoch": 2.169491525423729,
      "grad_norm": 0.4406554698944092,
      "learning_rate": 9.131193871579975e-05,
      "loss": 1.5561,
      "num_input_tokens_seen": 317176,
      "step": 32
    },
    {
      "epoch": 2.23728813559322,
      "grad_norm": 0.48960959911346436,
      "learning_rate": 9.077804344796302e-05,
      "loss": 1.7631,
      "num_input_tokens_seen": 327352,
      "step": 33
    },
    {
      "epoch": 2.305084745762712,
      "grad_norm": 0.4791744351387024,
      "learning_rate": 9.022988898833342e-05,
      "loss": 1.5754,
      "num_input_tokens_seen": 337384,
      "step": 34
    },
    {
      "epoch": 2.3728813559322033,
      "grad_norm": 0.42596694827079773,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.4501,
      "num_input_tokens_seen": 346952,
      "step": 35
    },
    {
      "epoch": 2.440677966101695,
      "grad_norm": 0.46600142121315,
      "learning_rate": 8.90915741234015e-05,
      "loss": 1.8493,
      "num_input_tokens_seen": 356568,
      "step": 36
    },
    {
      "epoch": 2.5084745762711864,
      "grad_norm": 0.49377578496932983,
      "learning_rate": 8.850181176196315e-05,
      "loss": 1.6969,
      "num_input_tokens_seen": 366504,
      "step": 37
    },
    {
      "epoch": 2.576271186440678,
      "grad_norm": 0.42628544569015503,
      "learning_rate": 8.789858615727265e-05,
      "loss": 1.3998,
      "num_input_tokens_seen": 377512,
      "step": 38
    },
    {
      "epoch": 2.6440677966101696,
      "grad_norm": 0.37030258774757385,
      "learning_rate": 8.728210824415827e-05,
      "loss": 1.1354,
      "num_input_tokens_seen": 388728,
      "step": 39
    },
    {
      "epoch": 2.711864406779661,
      "grad_norm": 0.763684093952179,
      "learning_rate": 8.665259359149132e-05,
      "loss": 1.5526,
      "num_input_tokens_seen": 393800,
      "step": 40
    },
    {
      "epoch": 2.7796610169491527,
      "grad_norm": 0.5274456143379211,
      "learning_rate": 8.601026232680634e-05,
      "loss": 1.671,
      "num_input_tokens_seen": 404072,
      "step": 41
    },
    {
      "epoch": 2.847457627118644,
      "grad_norm": 0.4358402192592621,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1851,
      "num_input_tokens_seen": 415336,
      "step": 42
    },
    {
      "epoch": 2.915254237288136,
      "grad_norm": 0.6406439542770386,
      "learning_rate": 8.468805280142709e-05,
      "loss": 1.8113,
      "num_input_tokens_seen": 425288,
      "step": 43
    },
    {
      "epoch": 2.983050847457627,
      "grad_norm": 0.48384496569633484,
      "learning_rate": 8.400863688854597e-05,
      "loss": 1.2456,
      "num_input_tokens_seen": 436584,
      "step": 44
    },
    {
      "epoch": 3.0508474576271185,
      "grad_norm": 0.6171286702156067,
      "learning_rate": 8.33173288976002e-05,
      "loss": 1.479,
      "num_input_tokens_seen": 445072,
      "step": 45
    },
    {
      "epoch": 3.1186440677966103,
      "grad_norm": 0.5578075051307678,
      "learning_rate": 8.261437056390606e-05,
      "loss": 1.8757,
      "num_input_tokens_seen": 453696,
      "step": 46
    },
    {
      "epoch": 3.1864406779661016,
      "grad_norm": 0.5808205604553223,
      "learning_rate": 8.190000769665044e-05,
      "loss": 1.4613,
      "num_input_tokens_seen": 462976,
      "step": 47
    },
    {
      "epoch": 3.2542372881355934,
      "grad_norm": 0.46899017691612244,
      "learning_rate": 8.117449009293668e-05,
      "loss": 1.2657,
      "num_input_tokens_seen": 474016,
      "step": 48
    },
    {
      "epoch": 3.3220338983050848,
      "grad_norm": 0.677277147769928,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.7769,
      "num_input_tokens_seen": 482960,
      "step": 49
    },
    {
      "epoch": 3.389830508474576,
      "grad_norm": 0.543119490146637,
      "learning_rate": 7.969100927867507e-05,
      "loss": 1.3444,
      "num_input_tokens_seen": 493200,
      "step": 50
    },
    {
      "epoch": 3.457627118644068,
      "grad_norm": 0.5538585782051086,
      "learning_rate": 7.89335648089903e-05,
      "loss": 1.4113,
      "num_input_tokens_seen": 503168,
      "step": 51
    },
    {
      "epoch": 3.5254237288135593,
      "grad_norm": 0.6398975253105164,
      "learning_rate": 7.81660029031811e-05,
      "loss": 1.5596,
      "num_input_tokens_seen": 513776,
      "step": 52
    },
    {
      "epoch": 3.593220338983051,
      "grad_norm": 0.8313115835189819,
      "learning_rate": 7.738859196089358e-05,
      "loss": 1.7417,
      "num_input_tokens_seen": 521376,
      "step": 53
    },
    {
      "epoch": 3.6610169491525424,
      "grad_norm": 0.777786910533905,
      "learning_rate": 7.660160382576683e-05,
      "loss": 1.7439,
      "num_input_tokens_seen": 531504,
      "step": 54
    },
    {
      "epoch": 3.7288135593220337,
      "grad_norm": 0.7124835848808289,
      "learning_rate": 7.580531369037533e-05,
      "loss": 1.2392,
      "num_input_tokens_seen": 542832,
      "step": 55
    },
    {
      "epoch": 3.7966101694915255,
      "grad_norm": 0.7158543467521667,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.4463,
      "num_input_tokens_seen": 554128,
      "step": 56
    },
    {
      "epoch": 3.864406779661017,
      "grad_norm": 0.6232526898384094,
      "learning_rate": 7.4185944355262e-05,
      "loss": 1.1846,
      "num_input_tokens_seen": 564576,
      "step": 57
    },
    {
      "epoch": 3.9322033898305087,
      "grad_norm": 0.6178350448608398,
      "learning_rate": 7.33634314136531e-05,
      "loss": 1.1875,
      "num_input_tokens_seen": 574464,
      "step": 58
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.720112144947052,
      "learning_rate": 7.253274878999727e-05,
      "loss": 1.1346,
      "num_input_tokens_seen": 584192,
      "step": 59
    },
    {
      "epoch": 4.067796610169491,
      "grad_norm": 0.8956817388534546,
      "learning_rate": 7.169418695587791e-05,
      "loss": 1.6462,
      "num_input_tokens_seen": 593440,
      "step": 60
    },
    {
      "epoch": 4.135593220338983,
      "grad_norm": 0.9503009915351868,
      "learning_rate": 7.084803913806641e-05,
      "loss": 1.0892,
      "num_input_tokens_seen": 603168,
      "step": 61
    },
    {
      "epoch": 4.203389830508475,
      "grad_norm": 0.843825101852417,
      "learning_rate": 6.999460121598704e-05,
      "loss": 1.4054,
      "num_input_tokens_seen": 611888,
      "step": 62
    },
    {
      "epoch": 4.271186440677966,
      "grad_norm": 0.7209855318069458,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.9302,
      "num_input_tokens_seen": 623312,
      "step": 63
    },
    {
      "epoch": 4.338983050847458,
      "grad_norm": 0.884834885597229,
      "learning_rate": 6.826705121831976e-05,
      "loss": 1.2218,
      "num_input_tokens_seen": 634768,
      "step": 64
    },
    {
      "epoch": 4.406779661016949,
      "grad_norm": 1.0309629440307617,
      "learning_rate": 6.739354322926136e-05,
      "loss": 1.1605,
      "num_input_tokens_seen": 644848,
      "step": 65
    },
    {
      "epoch": 4.47457627118644,
      "grad_norm": 1.097214698791504,
      "learning_rate": 6.651395309775837e-05,
      "loss": 1.7099,
      "num_input_tokens_seen": 654672,
      "step": 66
    },
    {
      "epoch": 4.5423728813559325,
      "grad_norm": 0.7945898175239563,
      "learning_rate": 6.562858839728223e-05,
      "loss": 0.8147,
      "num_input_tokens_seen": 665584,
      "step": 67
    },
    {
      "epoch": 4.610169491525424,
      "grad_norm": 1.2936004400253296,
      "learning_rate": 6.473775872054521e-05,
      "loss": 1.5787,
      "num_input_tokens_seen": 674096,
      "step": 68
    },
    {
      "epoch": 4.677966101694915,
      "grad_norm": 1.0135834217071533,
      "learning_rate": 6.384177557124247e-05,
      "loss": 1.2265,
      "num_input_tokens_seen": 683968,
      "step": 69
    },
    {
      "epoch": 4.745762711864407,
      "grad_norm": 0.9531109929084778,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.2753,
      "num_input_tokens_seen": 694368,
      "step": 70
    }
  ],
  "logging_steps": 1,
  "max_steps": 168,
  "num_input_tokens_seen": 694368,
  "num_train_epochs": 12,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.1354448922279936e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}