{
  "best_metric": 0.9254587155963303,
  "best_model_checkpoint": "./results/checkpoint-6315",
  "epoch": 3.0,
  "global_step": 6315,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 1.9683293745051467e-05,
      "loss": 0.5035,
      "step": 100
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.936658749010293e-05,
      "loss": 0.3283,
      "step": 200
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9049881235154395e-05,
      "loss": 0.2999,
      "step": 300
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.873317498020586e-05,
      "loss": 0.2995,
      "step": 400
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.8416468725257326e-05,
      "loss": 0.2684,
      "step": 500
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.809976247030879e-05,
      "loss": 0.2604,
      "step": 600
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.7783056215360253e-05,
      "loss": 0.2505,
      "step": 700
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.746634996041172e-05,
      "loss": 0.275,
      "step": 800
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.7149643705463184e-05,
      "loss": 0.2649,
      "step": 900
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.6832937450514647e-05,
      "loss": 0.2449,
      "step": 1000
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.6516231195566115e-05,
      "loss": 0.2219,
      "step": 1100
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.6199524940617578e-05,
      "loss": 0.2454,
      "step": 1200
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.5882818685669043e-05,
      "loss": 0.2174,
      "step": 1300
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.556611243072051e-05,
      "loss": 0.2191,
      "step": 1400
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.5249406175771972e-05,
      "loss": 0.2085,
      "step": 1500
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.4932699920823436e-05,
      "loss": 0.2181,
      "step": 1600
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.4615993665874902e-05,
      "loss": 0.2157,
      "step": 1700
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.4299287410926367e-05,
      "loss": 0.2152,
      "step": 1800
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.3982581155977833e-05,
      "loss": 0.2021,
      "step": 1900
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3665874901029297e-05,
      "loss": 0.2079,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.3349168646080762e-05,
      "loss": 0.2149,
      "step": 2100
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9197247706422018,
      "eval_loss": 0.25181546807289124,
      "eval_runtime": 0.5786,
      "eval_samples_per_second": 1507.048,
      "eval_steps_per_second": 24.196,
      "step": 2105
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.3032462391132226e-05,
      "loss": 0.1549,
      "step": 2200
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.271575613618369e-05,
      "loss": 0.1544,
      "step": 2300
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.2399049881235155e-05,
      "loss": 0.1603,
      "step": 2400
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.208234362628662e-05,
      "loss": 0.1552,
      "step": 2500
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.1765637371338086e-05,
      "loss": 0.1694,
      "step": 2600
    },
    {
      "epoch": 1.28,
      "learning_rate": 1.144893111638955e-05,
      "loss": 0.1448,
      "step": 2700
    },
    {
      "epoch": 1.33,
      "learning_rate": 1.1132224861441014e-05,
      "loss": 0.15,
      "step": 2800
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.081551860649248e-05,
      "loss": 0.1641,
      "step": 2900
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.0498812351543943e-05,
      "loss": 0.1598,
      "step": 3000
    },
    {
      "epoch": 1.47,
      "learning_rate": 1.0182106096595407e-05,
      "loss": 0.1587,
      "step": 3100
    },
    {
      "epoch": 1.52,
      "learning_rate": 9.865399841646872e-06,
      "loss": 0.1562,
      "step": 3200
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.548693586698338e-06,
      "loss": 0.1486,
      "step": 3300
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.231987331749803e-06,
      "loss": 0.1493,
      "step": 3400
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.915281076801267e-06,
      "loss": 0.1477,
      "step": 3500
    },
    {
      "epoch": 1.71,
      "learning_rate": 8.598574821852733e-06,
      "loss": 0.1482,
      "step": 3600
    },
    {
      "epoch": 1.76,
      "learning_rate": 8.281868566904197e-06,
      "loss": 0.143,
      "step": 3700
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.965162311955662e-06,
      "loss": 0.1574,
      "step": 3800
    },
    {
      "epoch": 1.85,
      "learning_rate": 7.648456057007126e-06,
      "loss": 0.1496,
      "step": 3900
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.331749802058591e-06,
      "loss": 0.1514,
      "step": 4000
    },
    {
      "epoch": 1.95,
      "learning_rate": 7.015043547110056e-06,
      "loss": 0.144,
      "step": 4100
    },
    {
      "epoch": 2.0,
      "learning_rate": 6.698337292161521e-06,
      "loss": 0.1472,
      "step": 4200
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9185779816513762,
      "eval_loss": 0.2679901719093323,
      "eval_runtime": 0.5778,
      "eval_samples_per_second": 1509.287,
      "eval_steps_per_second": 24.232,
      "step": 4210
    },
    {
      "epoch": 2.04,
      "learning_rate": 6.3816310372129854e-06,
      "loss": 0.1153,
      "step": 4300
    },
    {
      "epoch": 2.09,
      "learning_rate": 6.06492478226445e-06,
      "loss": 0.1184,
      "step": 4400
    },
    {
      "epoch": 2.14,
      "learning_rate": 5.748218527315916e-06,
      "loss": 0.1096,
      "step": 4500
    },
    {
      "epoch": 2.19,
      "learning_rate": 5.431512272367379e-06,
      "loss": 0.1196,
      "step": 4600
    },
    {
      "epoch": 2.23,
      "learning_rate": 5.114806017418844e-06,
      "loss": 0.1246,
      "step": 4700
    },
    {
      "epoch": 2.28,
      "learning_rate": 4.798099762470309e-06,
      "loss": 0.0929,
      "step": 4800
    },
    {
      "epoch": 2.33,
      "learning_rate": 4.481393507521774e-06,
      "loss": 0.1204,
      "step": 4900
    },
    {
      "epoch": 2.38,
      "learning_rate": 4.164687252573238e-06,
      "loss": 0.1113,
      "step": 5000
    },
    {
      "epoch": 2.42,
      "learning_rate": 3.8479809976247036e-06,
      "loss": 0.1169,
      "step": 5100
    },
    {
      "epoch": 2.47,
      "learning_rate": 3.531274742676168e-06,
      "loss": 0.1144,
      "step": 5200
    },
    {
      "epoch": 2.52,
      "learning_rate": 3.214568487727633e-06,
      "loss": 0.1171,
      "step": 5300
    },
    {
      "epoch": 2.57,
      "learning_rate": 2.897862232779098e-06,
      "loss": 0.1031,
      "step": 5400
    },
    {
      "epoch": 2.61,
      "learning_rate": 2.581155977830562e-06,
      "loss": 0.1287,
      "step": 5500
    },
    {
      "epoch": 2.66,
      "learning_rate": 2.264449722882027e-06,
      "loss": 0.12,
      "step": 5600
    },
    {
      "epoch": 2.71,
      "learning_rate": 1.947743467933492e-06,
      "loss": 0.1019,
      "step": 5700
    },
    {
      "epoch": 2.76,
      "learning_rate": 1.6310372129849566e-06,
      "loss": 0.1264,
      "step": 5800
    },
    {
      "epoch": 2.8,
      "learning_rate": 1.3143309580364213e-06,
      "loss": 0.1066,
      "step": 5900
    },
    {
      "epoch": 2.85,
      "learning_rate": 9.976247030878861e-07,
      "loss": 0.1226,
      "step": 6000
    },
    {
      "epoch": 2.9,
      "learning_rate": 6.809184481393508e-07,
      "loss": 0.1027,
      "step": 6100
    },
    {
      "epoch": 2.95,
      "learning_rate": 3.642121931908155e-07,
      "loss": 0.1201,
      "step": 6200
    },
    {
      "epoch": 2.99,
      "learning_rate": 4.750593824228029e-08,
      "loss": 0.1071,
      "step": 6300
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9254587155963303,
      "eval_loss": 0.29632261395454407,
      "eval_runtime": 0.5786,
      "eval_samples_per_second": 1507.184,
      "eval_steps_per_second": 24.198,
      "step": 6315
    }
  ],
  "max_steps": 6315,
  "num_train_epochs": 3,
  "total_flos": 3345580062031104.0,
  "trial_name": null,
  "trial_params": null
}