{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2741228070175439,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003654970760233918,
      "learning_rate": 6.505149978319905e-07,
      "loss": 1.5211,
      "step": 20
    },
    {
      "epoch": 0.007309941520467836,
      "learning_rate": 8.01029995663981e-07,
      "loss": 1.5142,
      "step": 40
    },
    {
      "epoch": 0.010964912280701754,
      "learning_rate": 8.890756251918216e-07,
      "loss": 1.5057,
      "step": 60
    },
    {
      "epoch": 0.014619883040935672,
      "learning_rate": 9.515449934959715e-07,
      "loss": 1.5015,
      "step": 80
    },
    {
      "epoch": 0.01827485380116959,
      "learning_rate": 9.999999999999997e-07,
      "loss": 1.5142,
      "step": 100
    },
    {
      "epoch": 0.021929824561403508,
      "learning_rate": 9.96779661016949e-07,
      "loss": 1.5057,
      "step": 120
    },
    {
      "epoch": 0.025584795321637425,
      "learning_rate": 9.933898305084746e-07,
      "loss": 1.511,
      "step": 140
    },
    {
      "epoch": 0.029239766081871343,
      "learning_rate": 9.9e-07,
      "loss": 1.493,
      "step": 160
    },
    {
      "epoch": 0.03289473684210526,
      "learning_rate": 9.866101694915253e-07,
      "loss": 1.5048,
      "step": 180
    },
    {
      "epoch": 0.03654970760233918,
      "learning_rate": 9.832203389830508e-07,
      "loss": 1.486,
      "step": 200
    },
    {
      "epoch": 0.0402046783625731,
      "learning_rate": 9.798305084745763e-07,
      "loss": 1.4937,
      "step": 220
    },
    {
      "epoch": 0.043859649122807015,
      "learning_rate": 9.764406779661016e-07,
      "loss": 1.4796,
      "step": 240
    },
    {
      "epoch": 0.04751461988304093,
      "learning_rate": 9.73050847457627e-07,
      "loss": 1.4729,
      "step": 260
    },
    {
      "epoch": 0.05116959064327485,
      "learning_rate": 9.696610169491526e-07,
      "loss": 1.4715,
      "step": 280
    },
    {
      "epoch": 0.05482456140350877,
      "learning_rate": 9.66271186440678e-07,
      "loss": 1.4602,
      "step": 300
    },
    {
      "epoch": 0.05847953216374269,
      "learning_rate": 9.628813559322033e-07,
      "loss": 1.4567,
      "step": 320
    },
    {
      "epoch": 0.062134502923976605,
      "learning_rate": 9.594915254237288e-07,
      "loss": 1.4414,
      "step": 340
    },
    {
      "epoch": 0.06578947368421052,
      "learning_rate": 9.56101694915254e-07,
      "loss": 1.4281,
      "step": 360
    },
    {
      "epoch": 0.06944444444444445,
      "learning_rate": 9.527118644067797e-07,
      "loss": 1.4296,
      "step": 380
    },
    {
      "epoch": 0.07309941520467836,
      "learning_rate": 9.49322033898305e-07,
      "loss": 1.4052,
      "step": 400
    },
    {
      "epoch": 0.07675438596491228,
      "learning_rate": 9.459322033898304e-07,
      "loss": 1.4087,
      "step": 420
    },
    {
      "epoch": 0.0804093567251462,
      "learning_rate": 9.425423728813558e-07,
      "loss": 1.3958,
      "step": 440
    },
    {
      "epoch": 0.08406432748538012,
      "learning_rate": 9.391525423728813e-07,
      "loss": 1.3807,
      "step": 460
    },
    {
      "epoch": 0.08771929824561403,
      "learning_rate": 9.357627118644067e-07,
      "loss": 1.3768,
      "step": 480
    },
    {
      "epoch": 0.09137426900584796,
      "learning_rate": 9.323728813559322e-07,
      "loss": 1.3602,
      "step": 500
    },
    {
      "epoch": 0.09137426900584796,
      "eval_loss": 1.2746659517288208,
      "eval_runtime": 11.7597,
      "eval_samples_per_second": 8.334,
      "eval_steps_per_second": 1.105,
      "step": 500
    },
    {
      "epoch": 0.09502923976608187,
      "learning_rate": 9.289830508474576e-07,
      "loss": 1.354,
      "step": 520
    },
    {
      "epoch": 0.09868421052631579,
      "learning_rate": 9.255932203389831e-07,
      "loss": 1.346,
      "step": 540
    },
    {
      "epoch": 0.1023391812865497,
      "learning_rate": 9.222033898305083e-07,
      "loss": 1.3577,
      "step": 560
    },
    {
      "epoch": 0.10599415204678363,
      "learning_rate": 9.188135593220338e-07,
      "loss": 1.3408,
      "step": 580
    },
    {
      "epoch": 0.10964912280701754,
      "learning_rate": 9.154237288135592e-07,
      "loss": 1.3292,
      "step": 600
    },
    {
      "epoch": 0.11330409356725146,
      "learning_rate": 9.120338983050847e-07,
      "loss": 1.3157,
      "step": 620
    },
    {
      "epoch": 0.11695906432748537,
      "learning_rate": 9.086440677966102e-07,
      "loss": 1.3143,
      "step": 640
    },
    {
      "epoch": 0.1206140350877193,
      "learning_rate": 9.052542372881356e-07,
      "loss": 1.3087,
      "step": 660
    },
    {
      "epoch": 0.12426900584795321,
      "learning_rate": 9.018644067796611e-07,
      "loss": 1.3062,
      "step": 680
    },
    {
      "epoch": 0.12792397660818713,
      "learning_rate": 8.984745762711864e-07,
      "loss": 1.2893,
      "step": 700
    },
    {
      "epoch": 0.13157894736842105,
      "learning_rate": 8.950847457627118e-07,
      "loss": 1.2812,
      "step": 720
    },
    {
      "epoch": 0.13523391812865498,
      "learning_rate": 8.916949152542372e-07,
      "loss": 1.2732,
      "step": 740
    },
    {
      "epoch": 0.1388888888888889,
      "learning_rate": 8.883050847457627e-07,
      "loss": 1.2689,
      "step": 760
    },
    {
      "epoch": 0.1425438596491228,
      "learning_rate": 8.849152542372881e-07,
      "loss": 1.2704,
      "step": 780
    },
    {
      "epoch": 0.14619883040935672,
      "learning_rate": 8.815254237288136e-07,
      "loss": 1.2457,
      "step": 800
    },
    {
      "epoch": 0.14985380116959066,
      "learning_rate": 8.78135593220339e-07,
      "loss": 1.2447,
      "step": 820
    },
    {
      "epoch": 0.15350877192982457,
      "learning_rate": 8.747457627118644e-07,
      "loss": 1.2356,
      "step": 840
    },
    {
      "epoch": 0.15716374269005848,
      "learning_rate": 8.713559322033898e-07,
      "loss": 1.2304,
      "step": 860
    },
    {
      "epoch": 0.1608187134502924,
      "learning_rate": 8.679661016949152e-07,
      "loss": 1.2172,
      "step": 880
    },
    {
      "epoch": 0.16447368421052633,
      "learning_rate": 8.645762711864406e-07,
      "loss": 1.2084,
      "step": 900
    },
    {
      "epoch": 0.16812865497076024,
      "learning_rate": 8.611864406779661e-07,
      "loss": 1.207,
      "step": 920
    },
    {
      "epoch": 0.17178362573099415,
      "learning_rate": 8.577966101694915e-07,
      "loss": 1.2053,
      "step": 940
    },
    {
      "epoch": 0.17543859649122806,
      "learning_rate": 8.544067796610169e-07,
      "loss": 1.1868,
      "step": 960
    },
    {
      "epoch": 0.179093567251462,
      "learning_rate": 8.510169491525423e-07,
      "loss": 1.1834,
      "step": 980
    },
    {
      "epoch": 0.1827485380116959,
      "learning_rate": 8.476271186440678e-07,
      "loss": 1.183,
      "step": 1000
    },
    {
      "epoch": 0.1827485380116959,
      "eval_loss": 1.0988587141036987,
      "eval_runtime": 11.2196,
      "eval_samples_per_second": 8.735,
      "eval_steps_per_second": 1.159,
      "step": 1000
    },
    {
      "epoch": 0.18640350877192982,
      "learning_rate": 8.442372881355931e-07,
      "loss": 1.1698,
      "step": 1020
    },
    {
      "epoch": 0.19005847953216373,
      "learning_rate": 8.408474576271186e-07,
      "loss": 1.164,
      "step": 1040
    },
    {
      "epoch": 0.19371345029239767,
      "learning_rate": 8.37457627118644e-07,
      "loss": 1.1563,
      "step": 1060
    },
    {
      "epoch": 0.19736842105263158,
      "learning_rate": 8.340677966101695e-07,
      "loss": 1.1486,
      "step": 1080
    },
    {
      "epoch": 0.2010233918128655,
      "learning_rate": 8.306779661016948e-07,
      "loss": 1.1411,
      "step": 1100
    },
    {
      "epoch": 0.2046783625730994,
      "learning_rate": 8.272881355932203e-07,
      "loss": 1.14,
      "step": 1120
    },
    {
      "epoch": 0.20833333333333334,
      "learning_rate": 8.238983050847457e-07,
      "loss": 1.1246,
      "step": 1140
    },
    {
      "epoch": 0.21198830409356725,
      "learning_rate": 8.205084745762712e-07,
      "loss": 1.1222,
      "step": 1160
    },
    {
      "epoch": 0.21564327485380116,
      "learning_rate": 8.171186440677966e-07,
      "loss": 1.1125,
      "step": 1180
    },
    {
      "epoch": 0.21929824561403508,
      "learning_rate": 8.13728813559322e-07,
      "loss": 1.1024,
      "step": 1200
    },
    {
      "epoch": 0.22295321637426901,
      "learning_rate": 8.103389830508474e-07,
      "loss": 1.1009,
      "step": 1220
    },
    {
      "epoch": 0.22660818713450293,
      "learning_rate": 8.069491525423728e-07,
      "loss": 1.0901,
      "step": 1240
    },
    {
      "epoch": 0.23026315789473684,
      "learning_rate": 8.035593220338983e-07,
      "loss": 1.0837,
      "step": 1260
    },
    {
      "epoch": 0.23391812865497075,
      "learning_rate": 8.001694915254237e-07,
      "loss": 1.0748,
      "step": 1280
    },
    {
      "epoch": 0.23757309941520469,
      "learning_rate": 7.967796610169492e-07,
      "loss": 1.0639,
      "step": 1300
    },
    {
      "epoch": 0.2412280701754386,
      "learning_rate": 7.933898305084746e-07,
      "loss": 1.0687,
      "step": 1320
    },
    {
      "epoch": 0.2448830409356725,
      "learning_rate": 7.9e-07,
      "loss": 1.0593,
      "step": 1340
    },
    {
      "epoch": 0.24853801169590642,
      "learning_rate": 7.866101694915253e-07,
      "loss": 1.045,
      "step": 1360
    },
    {
      "epoch": 0.25219298245614036,
      "learning_rate": 7.832203389830508e-07,
      "loss": 1.0454,
      "step": 1380
    },
    {
      "epoch": 0.25584795321637427,
      "learning_rate": 7.798305084745762e-07,
      "loss": 1.0309,
      "step": 1400
    },
    {
      "epoch": 0.2595029239766082,
      "learning_rate": 7.764406779661017e-07,
      "loss": 1.0307,
      "step": 1420
    },
    {
      "epoch": 0.2631578947368421,
      "learning_rate": 7.730508474576271e-07,
      "loss": 1.0211,
      "step": 1440
    },
    {
      "epoch": 0.266812865497076,
      "learning_rate": 7.696610169491526e-07,
      "loss": 1.017,
      "step": 1460
    },
    {
      "epoch": 0.27046783625730997,
      "learning_rate": 7.66271186440678e-07,
      "loss": 1.0099,
      "step": 1480
    },
    {
      "epoch": 0.2741228070175439,
      "learning_rate": 7.628813559322033e-07,
      "loss": 0.9921,
      "step": 1500
    },
    {
      "epoch": 0.2741228070175439,
      "eval_loss": 0.9413940906524658,
      "eval_runtime": 11.1818,
      "eval_samples_per_second": 8.764,
      "eval_steps_per_second": 1.163,
      "step": 1500
    }
  ],
  "logging_steps": 20,
  "max_steps": 6000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 2585034596810752.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}