{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.328711531958065,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.043287115319580655,
      "grad_norm": 1.3075332641601562,
      "learning_rate": 1e-05,
      "loss": 2.6135,
      "step": 1
    },
    {
      "epoch": 0.08657423063916131,
      "grad_norm": 1.331031084060669,
      "learning_rate": 2e-05,
      "loss": 2.6156,
      "step": 2
    },
    {
      "epoch": 0.12986134595874196,
      "grad_norm": 1.182157278060913,
      "learning_rate": 3e-05,
      "loss": 2.6005,
      "step": 3
    },
    {
      "epoch": 0.17314846127832262,
      "grad_norm": 1.057531476020813,
      "learning_rate": 4e-05,
      "loss": 2.5096,
      "step": 4
    },
    {
      "epoch": 0.21643557659790327,
      "grad_norm": 0.9650816917419434,
      "learning_rate": 5e-05,
      "loss": 2.3305,
      "step": 5
    },
    {
      "epoch": 0.2597226919174839,
      "grad_norm": 1.125662922859192,
      "learning_rate": 6e-05,
      "loss": 2.1415,
      "step": 6
    },
    {
      "epoch": 0.3030098072370646,
      "grad_norm": 1.3090826272964478,
      "learning_rate": 7e-05,
      "loss": 2.1103,
      "step": 7
    },
    {
      "epoch": 0.34629692255664524,
      "grad_norm": 0.876710832118988,
      "learning_rate": 8e-05,
      "loss": 2.0032,
      "step": 8
    },
    {
      "epoch": 0.3895840378762259,
      "grad_norm": 0.6368322968482971,
      "learning_rate": 9e-05,
      "loss": 1.941,
      "step": 9
    },
    {
      "epoch": 0.43287115319580655,
      "grad_norm": 0.5906776189804077,
      "learning_rate": 0.0001,
      "loss": 1.9168,
      "step": 10
    },
    {
      "epoch": 0.47615826851538723,
      "grad_norm": 0.4096170663833618,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.8278,
      "step": 11
    },
    {
      "epoch": 0.5194453838349679,
      "grad_norm": 0.5118263363838196,
      "learning_rate": 0.00012,
      "loss": 1.8466,
      "step": 12
    },
    {
      "epoch": 0.5627324991545485,
      "grad_norm": 0.45886170864105225,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.8452,
      "step": 13
    },
    {
      "epoch": 0.6060196144741292,
      "grad_norm": 0.4695449769496918,
      "learning_rate": 0.00014,
      "loss": 1.7073,
      "step": 14
    },
    {
      "epoch": 0.6493067297937098,
      "grad_norm": 0.38605010509490967,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.7525,
      "step": 15
    },
    {
      "epoch": 0.6925938451132905,
      "grad_norm": 0.3754991590976715,
      "learning_rate": 0.00016,
      "loss": 1.7642,
      "step": 16
    },
    {
      "epoch": 0.7358809604328711,
      "grad_norm": 0.3591402769088745,
      "learning_rate": 0.00017,
      "loss": 1.6673,
      "step": 17
    },
    {
      "epoch": 0.7791680757524518,
      "grad_norm": 0.37384992837905884,
      "learning_rate": 0.00018,
      "loss": 1.6268,
      "step": 18
    },
    {
      "epoch": 0.8224551910720325,
      "grad_norm": 0.21681495010852814,
      "learning_rate": 0.00019,
      "loss": 1.5402,
      "step": 19
    },
    {
      "epoch": 0.8657423063916131,
      "grad_norm": 0.3103310763835907,
      "learning_rate": 0.0002,
      "loss": 1.6415,
      "step": 20
    },
    {
      "epoch": 0.9090294217111938,
      "grad_norm": 0.24632440507411957,
      "learning_rate": 0.00019830508474576273,
      "loss": 1.6229,
      "step": 21
    },
    {
      "epoch": 0.9523165370307745,
      "grad_norm": 0.2787884473800659,
      "learning_rate": 0.00019661016949152545,
      "loss": 1.5679,
      "step": 22
    },
    {
      "epoch": 0.9956036523503551,
      "grad_norm": 0.2785838544368744,
      "learning_rate": 0.00019491525423728814,
      "loss": 1.5878,
      "step": 23
    },
    {
      "epoch": 1.0388907676699357,
      "grad_norm": 0.2134454846382141,
      "learning_rate": 0.00019322033898305085,
      "loss": 1.6762,
      "step": 24
    },
    {
      "epoch": 1.0821778829895163,
      "grad_norm": 0.25963786244392395,
      "learning_rate": 0.00019152542372881357,
      "loss": 1.4846,
      "step": 25
    },
    {
      "epoch": 1.125464998309097,
      "grad_norm": 0.17540386319160461,
      "learning_rate": 0.0001898305084745763,
      "loss": 1.5871,
      "step": 26
    },
    {
      "epoch": 1.1687521136286776,
      "grad_norm": 0.2921240031719208,
      "learning_rate": 0.000188135593220339,
      "loss": 1.5098,
      "step": 27
    },
    {
      "epoch": 1.2120392289482584,
      "grad_norm": 0.1676906943321228,
      "learning_rate": 0.0001864406779661017,
      "loss": 1.4752,
      "step": 28
    },
    {
      "epoch": 1.255326344267839,
      "grad_norm": 0.193375363945961,
      "learning_rate": 0.00018474576271186442,
      "loss": 1.6066,
      "step": 29
    },
    {
      "epoch": 1.2986134595874197,
      "grad_norm": 0.20379780232906342,
      "learning_rate": 0.00018305084745762714,
      "loss": 1.4214,
      "step": 30
    },
    {
      "epoch": 1.3419005749070003,
      "grad_norm": 0.16739188134670258,
      "learning_rate": 0.00018135593220338985,
      "loss": 1.4811,
      "step": 31
    },
    {
      "epoch": 1.385187690226581,
      "grad_norm": 0.1727289855480194,
      "learning_rate": 0.00017966101694915257,
      "loss": 1.5107,
      "step": 32
    },
    {
      "epoch": 1.4284748055461616,
      "grad_norm": 0.15966272354125977,
      "learning_rate": 0.00017796610169491526,
      "loss": 1.465,
      "step": 33
    },
    {
      "epoch": 1.4717619208657422,
      "grad_norm": 0.16040155291557312,
      "learning_rate": 0.00017627118644067798,
      "loss": 1.3983,
      "step": 34
    },
    {
      "epoch": 1.515049036185323,
      "grad_norm": 0.176644429564476,
      "learning_rate": 0.0001745762711864407,
      "loss": 1.5164,
      "step": 35
    },
    {
      "epoch": 1.5583361515049035,
      "grad_norm": 0.1550065129995346,
      "learning_rate": 0.00017288135593220342,
      "loss": 1.5667,
      "step": 36
    },
    {
      "epoch": 1.6016232668244843,
      "grad_norm": 0.16012217104434967,
      "learning_rate": 0.0001711864406779661,
      "loss": 1.5848,
      "step": 37
    },
    {
      "epoch": 1.644910382144065,
      "grad_norm": 0.15811151266098022,
      "learning_rate": 0.00016949152542372882,
      "loss": 1.4983,
      "step": 38
    },
    {
      "epoch": 1.6881974974636456,
      "grad_norm": 0.17775847017765045,
      "learning_rate": 0.00016779661016949154,
      "loss": 1.4917,
      "step": 39
    },
    {
      "epoch": 1.7314846127832264,
      "grad_norm": 0.15157213807106018,
      "learning_rate": 0.00016610169491525423,
      "loss": 1.4485,
      "step": 40
    },
    {
      "epoch": 1.7747717281028068,
      "grad_norm": 0.1725074052810669,
      "learning_rate": 0.00016440677966101695,
      "loss": 1.4239,
      "step": 41
    },
    {
      "epoch": 1.8180588434223877,
      "grad_norm": 0.1663850098848343,
      "learning_rate": 0.00016271186440677967,
      "loss": 1.4675,
      "step": 42
    },
    {
      "epoch": 1.861345958741968,
      "grad_norm": 0.1412980854511261,
      "learning_rate": 0.00016101694915254236,
      "loss": 1.5058,
      "step": 43
    },
    {
      "epoch": 1.904633074061549,
      "grad_norm": 0.1626206934452057,
      "learning_rate": 0.00015932203389830508,
      "loss": 1.3938,
      "step": 44
    },
    {
      "epoch": 1.9479201893811295,
      "grad_norm": 0.1704348474740982,
      "learning_rate": 0.0001576271186440678,
      "loss": 1.441,
      "step": 45
    },
    {
      "epoch": 1.9912073047007102,
      "grad_norm": 0.16612422466278076,
      "learning_rate": 0.00015593220338983051,
      "loss": 1.4311,
      "step": 46
    },
    {
      "epoch": 2.034494420020291,
      "grad_norm": 0.1627483069896698,
      "learning_rate": 0.00015423728813559323,
      "loss": 1.4436,
      "step": 47
    },
    {
      "epoch": 2.0777815353398714,
      "grad_norm": 0.164725199341774,
      "learning_rate": 0.00015254237288135592,
      "loss": 1.4396,
      "step": 48
    },
    {
      "epoch": 2.1210686506594523,
      "grad_norm": 0.16077861189842224,
      "learning_rate": 0.00015084745762711864,
      "loss": 1.3553,
      "step": 49
    },
    {
      "epoch": 2.1643557659790327,
      "grad_norm": 0.16761967539787292,
      "learning_rate": 0.00014915254237288136,
      "loss": 1.3419,
      "step": 50
    },
    {
      "epoch": 2.2076428812986135,
      "grad_norm": 0.17950375378131866,
      "learning_rate": 0.00014745762711864408,
      "loss": 1.4441,
      "step": 51
    },
    {
      "epoch": 2.250929996618194,
      "grad_norm": 0.170644611120224,
      "learning_rate": 0.00014576271186440677,
      "loss": 1.2938,
      "step": 52
    },
    {
      "epoch": 2.2942171119377748,
      "grad_norm": 0.14908789098262787,
      "learning_rate": 0.00014406779661016949,
      "loss": 1.4752,
      "step": 53
    },
    {
      "epoch": 2.337504227257355,
      "grad_norm": 0.1823863834142685,
      "learning_rate": 0.0001423728813559322,
      "loss": 1.2808,
      "step": 54
    },
    {
      "epoch": 2.380791342576936,
      "grad_norm": 0.1728678047657013,
      "learning_rate": 0.00014067796610169492,
      "loss": 1.3931,
      "step": 55
    },
    {
      "epoch": 2.424078457896517,
      "grad_norm": 0.1562182605266571,
      "learning_rate": 0.00013898305084745764,
      "loss": 1.3308,
      "step": 56
    },
    {
      "epoch": 2.4673655732160973,
      "grad_norm": 0.17571797966957092,
      "learning_rate": 0.00013728813559322033,
      "loss": 1.4277,
      "step": 57
    },
    {
      "epoch": 2.510652688535678,
      "grad_norm": 0.18452058732509613,
      "learning_rate": 0.00013559322033898305,
      "loss": 1.3371,
      "step": 58
    },
    {
      "epoch": 2.5539398038552585,
      "grad_norm": 0.1646076738834381,
      "learning_rate": 0.00013389830508474577,
      "loss": 1.3057,
      "step": 59
    },
    {
      "epoch": 2.5972269191748394,
      "grad_norm": 0.17110076546669006,
      "learning_rate": 0.00013220338983050849,
      "loss": 1.36,
      "step": 60
    },
    {
      "epoch": 2.6405140344944202,
      "grad_norm": 0.16420727968215942,
      "learning_rate": 0.0001305084745762712,
      "loss": 1.3365,
      "step": 61
    },
    {
      "epoch": 2.6838011498140006,
      "grad_norm": 0.17258888483047485,
      "learning_rate": 0.0001288135593220339,
      "loss": 1.3459,
      "step": 62
    },
    {
      "epoch": 2.7270882651335815,
      "grad_norm": 0.18141889572143555,
      "learning_rate": 0.0001271186440677966,
      "loss": 1.4299,
      "step": 63
    },
    {
      "epoch": 2.770375380453162,
      "grad_norm": 0.16623935103416443,
      "learning_rate": 0.00012542372881355933,
      "loss": 1.4376,
      "step": 64
    },
    {
      "epoch": 2.8136624957727427,
      "grad_norm": 0.17075808346271515,
      "learning_rate": 0.00012372881355932205,
      "loss": 1.3503,
      "step": 65
    },
    {
      "epoch": 2.856949611092323,
      "grad_norm": 0.17947785556316376,
      "learning_rate": 0.00012203389830508477,
      "loss": 1.205,
      "step": 66
    },
    {
      "epoch": 2.900236726411904,
      "grad_norm": 0.17153343558311462,
      "learning_rate": 0.00012033898305084746,
      "loss": 1.2422,
      "step": 67
    },
    {
      "epoch": 2.9435238417314844,
      "grad_norm": 0.16988888382911682,
      "learning_rate": 0.00011864406779661017,
      "loss": 1.4476,
      "step": 68
    },
    {
      "epoch": 2.9868109570510653,
      "grad_norm": 0.16266486048698425,
      "learning_rate": 0.00011694915254237289,
      "loss": 1.304,
      "step": 69
    },
    {
      "epoch": 3.030098072370646,
      "grad_norm": 0.2084127813577652,
      "learning_rate": 0.0001152542372881356,
      "loss": 1.2835,
      "step": 70
    },
    {
      "epoch": 3.0733851876902265,
      "grad_norm": 0.18693631887435913,
      "learning_rate": 0.00011355932203389832,
      "loss": 1.2029,
      "step": 71
    },
    {
      "epoch": 3.1166723030098074,
      "grad_norm": 0.20769809186458588,
      "learning_rate": 0.00011186440677966102,
      "loss": 1.2312,
      "step": 72
    },
    {
      "epoch": 3.1599594183293878,
      "grad_norm": 0.2609138488769531,
      "learning_rate": 0.00011016949152542372,
      "loss": 1.1775,
      "step": 73
    },
    {
      "epoch": 3.2032465336489686,
      "grad_norm": 0.2215770184993744,
      "learning_rate": 0.00010847457627118644,
      "loss": 1.2477,
      "step": 74
    },
    {
      "epoch": 3.246533648968549,
      "grad_norm": 0.19359415769577026,
      "learning_rate": 0.00010677966101694916,
      "loss": 1.3057,
      "step": 75
    },
    {
      "epoch": 3.28982076428813,
      "grad_norm": 0.21368390321731567,
      "learning_rate": 0.00010508474576271188,
      "loss": 1.2199,
      "step": 76
    },
    {
      "epoch": 3.3331078796077107,
      "grad_norm": 0.19992664456367493,
      "learning_rate": 0.00010338983050847457,
      "loss": 1.3003,
      "step": 77
    },
    {
      "epoch": 3.376394994927291,
      "grad_norm": 0.21370652318000793,
      "learning_rate": 0.00010169491525423729,
      "loss": 1.2409,
      "step": 78
    },
    {
      "epoch": 3.419682110246872,
      "grad_norm": 0.23403161764144897,
      "learning_rate": 0.0001,
      "loss": 1.2094,
      "step": 79
    },
    {
      "epoch": 3.4629692255664524,
      "grad_norm": 0.2088824212551117,
      "learning_rate": 9.830508474576272e-05,
      "loss": 1.2024,
      "step": 80
    },
    {
      "epoch": 3.506256340886033,
      "grad_norm": 0.1982620656490326,
      "learning_rate": 9.661016949152543e-05,
      "loss": 1.3191,
      "step": 81
    },
    {
      "epoch": 3.5495434562056136,
      "grad_norm": 0.19635073840618134,
      "learning_rate": 9.491525423728815e-05,
      "loss": 1.2729,
      "step": 82
    },
    {
      "epoch": 3.5928305715251945,
      "grad_norm": 0.21581605076789856,
      "learning_rate": 9.322033898305085e-05,
      "loss": 1.2067,
      "step": 83
    },
    {
      "epoch": 3.6361176868447753,
      "grad_norm": 0.23395930230617523,
      "learning_rate": 9.152542372881357e-05,
      "loss": 1.1732,
      "step": 84
    },
    {
      "epoch": 3.6794048021643557,
      "grad_norm": 0.20725423097610474,
      "learning_rate": 8.983050847457629e-05,
      "loss": 1.2696,
      "step": 85
    },
    {
      "epoch": 3.7226919174839366,
      "grad_norm": 0.2143978476524353,
      "learning_rate": 8.813559322033899e-05,
      "loss": 1.2853,
      "step": 86
    },
    {
      "epoch": 3.765979032803517,
      "grad_norm": 0.20824481546878815,
      "learning_rate": 8.644067796610171e-05,
      "loss": 1.3816,
      "step": 87
    },
    {
      "epoch": 3.809266148123098,
      "grad_norm": 0.2025291919708252,
      "learning_rate": 8.474576271186441e-05,
      "loss": 1.2729,
      "step": 88
    },
    {
      "epoch": 3.8525532634426782,
      "grad_norm": 0.1953839212656021,
      "learning_rate": 8.305084745762712e-05,
      "loss": 1.2137,
      "step": 89
    },
    {
      "epoch": 3.895840378762259,
      "grad_norm": 0.22606025636196136,
      "learning_rate": 8.135593220338983e-05,
      "loss": 1.2075,
      "step": 90
    },
    {
      "epoch": 3.9391274940818395,
      "grad_norm": 0.20046383142471313,
      "learning_rate": 7.966101694915254e-05,
      "loss": 1.3381,
      "step": 91
    },
    {
      "epoch": 3.9824146094014203,
      "grad_norm": 0.21515585482120514,
      "learning_rate": 7.796610169491526e-05,
      "loss": 1.3066,
      "step": 92
    },
    {
      "epoch": 4.025701724721001,
      "grad_norm": 0.21168598532676697,
      "learning_rate": 7.627118644067796e-05,
      "loss": 1.2252,
      "step": 93
    },
    {
      "epoch": 4.068988840040582,
      "grad_norm": 0.22729083895683289,
      "learning_rate": 7.457627118644068e-05,
      "loss": 1.1966,
      "step": 94
    },
    {
      "epoch": 4.112275955360162,
      "grad_norm": 0.2301683872938156,
      "learning_rate": 7.288135593220338e-05,
      "loss": 1.1884,
      "step": 95
    },
    {
      "epoch": 4.155563070679743,
      "grad_norm": 0.2504737973213196,
      "learning_rate": 7.11864406779661e-05,
      "loss": 1.167,
      "step": 96
    },
    {
      "epoch": 4.198850185999324,
      "grad_norm": 0.24270710349082947,
      "learning_rate": 6.949152542372882e-05,
      "loss": 1.2637,
      "step": 97
    },
    {
      "epoch": 4.2421373013189045,
      "grad_norm": 0.2349226176738739,
      "learning_rate": 6.779661016949152e-05,
      "loss": 1.0819,
      "step": 98
    },
    {
      "epoch": 4.2854244166384845,
      "grad_norm": 0.24534264206886292,
      "learning_rate": 6.610169491525424e-05,
      "loss": 1.1141,
      "step": 99
    },
    {
      "epoch": 4.328711531958065,
      "grad_norm": 0.26070985198020935,
      "learning_rate": 6.440677966101695e-05,
      "loss": 1.1362,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 138,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 10,
  "total_flos": 2.2598182449113088e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}