{
  "best_metric": 0.7999999999999999,
  "best_model_checkpoint": "/home/bel3/content/model_folder//finetune/sst2/checkpoint-2000",
  "epoch": 8.10126582278481,
  "global_step": 6400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "eval_accuracy": 0.7637795209884644,
      "eval_f1": 0.7894736842105263,
      "eval_loss": 0.5017877817153931,
      "eval_runtime": 0.8927,
      "eval_samples_per_second": 569.063,
      "eval_steps_per_second": 71.693,
      "step": 200
    },
    {
      "epoch": 0.51,
      "eval_accuracy": 0.8070865869522095,
      "eval_f1": 0.8178438661710037,
      "eval_loss": 0.4368048310279846,
      "eval_runtime": 0.896,
      "eval_samples_per_second": 566.985,
      "eval_steps_per_second": 71.431,
      "step": 400
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.683544303797468e-05,
      "loss": 0.4948,
      "step": 500
    },
    {
      "epoch": 0.76,
      "eval_accuracy": 0.789370059967041,
      "eval_f1": 0.7906066536203523,
      "eval_loss": 0.45398545265197754,
      "eval_runtime": 0.895,
      "eval_samples_per_second": 567.578,
      "eval_steps_per_second": 71.506,
      "step": 600
    },
    {
      "epoch": 1.01,
      "eval_accuracy": 0.8011810779571533,
      "eval_f1": 0.7908902691511387,
      "eval_loss": 0.44997021555900574,
      "eval_runtime": 0.9042,
      "eval_samples_per_second": 561.806,
      "eval_steps_per_second": 70.779,
      "step": 800
    },
    {
      "epoch": 1.27,
      "learning_rate": 4.367088607594937e-05,
      "loss": 0.3027,
      "step": 1000
    },
    {
      "epoch": 1.27,
      "eval_accuracy": 0.8129921555519104,
      "eval_f1": 0.8155339805825244,
      "eval_loss": 0.4525600075721741,
      "eval_runtime": 0.833,
      "eval_samples_per_second": 609.864,
      "eval_steps_per_second": 76.833,
      "step": 1000
    },
    {
      "epoch": 1.52,
      "eval_accuracy": 0.8208661675453186,
      "eval_f1": 0.8253358925143954,
      "eval_loss": 0.4560699462890625,
      "eval_runtime": 0.8459,
      "eval_samples_per_second": 600.52,
      "eval_steps_per_second": 75.656,
      "step": 1200
    },
    {
      "epoch": 1.77,
      "eval_accuracy": 0.8149606585502625,
      "eval_f1": 0.812,
      "eval_loss": 0.4809434413909912,
      "eval_runtime": 0.8476,
      "eval_samples_per_second": 599.306,
      "eval_steps_per_second": 75.503,
      "step": 1400
    },
    {
      "epoch": 1.9,
      "learning_rate": 4.050632911392405e-05,
      "loss": 0.236,
      "step": 1500
    },
    {
      "epoch": 2.03,
      "eval_accuracy": 0.8169291615486145,
      "eval_f1": 0.8228571428571428,
      "eval_loss": 0.6252030730247498,
      "eval_runtime": 0.9277,
      "eval_samples_per_second": 547.599,
      "eval_steps_per_second": 68.989,
      "step": 1600
    },
    {
      "epoch": 2.28,
      "eval_accuracy": 0.8149606585502625,
      "eval_f1": 0.8142292490118577,
      "eval_loss": 0.6088564395904541,
      "eval_runtime": 0.8559,
      "eval_samples_per_second": 593.542,
      "eval_steps_per_second": 74.777,
      "step": 1800
    },
    {
      "epoch": 2.53,
      "learning_rate": 3.7341772151898736e-05,
      "loss": 0.1743,
      "step": 2000
    },
    {
      "epoch": 2.53,
      "eval_accuracy": 0.8070865869522095,
      "eval_f1": 0.7999999999999999,
      "eval_loss": 0.593163251876831,
      "eval_runtime": 0.8297,
      "eval_samples_per_second": 612.294,
      "eval_steps_per_second": 77.139,
      "step": 2000
    },
    {
      "epoch": 2.78,
      "eval_accuracy": 0.8090550899505615,
      "eval_f1": 0.7991718426501037,
      "eval_loss": 0.5563398599624634,
      "eval_runtime": 0.8844,
      "eval_samples_per_second": 574.387,
      "eval_steps_per_second": 72.364,
      "step": 2200
    },
    {
      "epoch": 3.04,
      "eval_accuracy": 0.7972440719604492,
      "eval_f1": 0.8052930056710774,
      "eval_loss": 0.5898112058639526,
      "eval_runtime": 0.9275,
      "eval_samples_per_second": 547.695,
      "eval_steps_per_second": 69.001,
      "step": 2400
    },
    {
      "epoch": 3.16,
      "learning_rate": 3.4177215189873416e-05,
      "loss": 0.1599,
      "step": 2500
    },
    {
      "epoch": 3.29,
      "eval_accuracy": 0.8228346705436707,
      "eval_f1": 0.8228346456692914,
      "eval_loss": 0.538675844669342,
      "eval_runtime": 0.9213,
      "eval_samples_per_second": 551.421,
      "eval_steps_per_second": 69.47,
      "step": 2600
    },
    {
      "epoch": 3.54,
      "eval_accuracy": 0.8110235929489136,
      "eval_f1": 0.8087649402390438,
      "eval_loss": 0.5058029890060425,
      "eval_runtime": 0.9251,
      "eval_samples_per_second": 549.151,
      "eval_steps_per_second": 69.184,
      "step": 2800
    },
    {
      "epoch": 3.8,
      "learning_rate": 3.10126582278481e-05,
      "loss": 0.1218,
      "step": 3000
    },
    {
      "epoch": 3.8,
      "eval_accuracy": 0.8248031735420227,
      "eval_f1": 0.8216432865731464,
      "eval_loss": 0.6525737047195435,
      "eval_runtime": 0.8811,
      "eval_samples_per_second": 576.522,
      "eval_steps_per_second": 72.633,
      "step": 3000
    },
    {
      "epoch": 4.05,
      "eval_accuracy": 0.8110235929489136,
      "eval_f1": 0.8102766798418972,
      "eval_loss": 0.8057999610900879,
      "eval_runtime": 0.8465,
      "eval_samples_per_second": 600.11,
      "eval_steps_per_second": 75.604,
      "step": 3200
    },
    {
      "epoch": 4.3,
      "eval_accuracy": 0.8110235929489136,
      "eval_f1": 0.8032786885245902,
      "eval_loss": 0.7197728753089905,
      "eval_runtime": 0.8474,
      "eval_samples_per_second": 599.485,
      "eval_steps_per_second": 75.526,
      "step": 3400
    },
    {
      "epoch": 4.43,
      "learning_rate": 2.7848101265822786e-05,
      "loss": 0.0955,
      "step": 3500
    },
    {
      "epoch": 4.56,
      "eval_accuracy": 0.8031495809555054,
      "eval_f1": 0.7967479674796747,
      "eval_loss": 0.7408320903778076,
      "eval_runtime": 0.8491,
      "eval_samples_per_second": 598.276,
      "eval_steps_per_second": 75.373,
      "step": 3600
    },
    {
      "epoch": 4.81,
      "eval_accuracy": 0.8011810779571533,
      "eval_f1": 0.8112149532710279,
      "eval_loss": 0.7727562785148621,
      "eval_runtime": 0.8979,
      "eval_samples_per_second": 565.791,
      "eval_steps_per_second": 71.281,
      "step": 3800
    },
    {
      "epoch": 5.06,
      "learning_rate": 2.468354430379747e-05,
      "loss": 0.0858,
      "step": 4000
    },
    {
      "epoch": 5.06,
      "eval_accuracy": 0.8051180839538574,
      "eval_f1": 0.800804828973843,
      "eval_loss": 0.8653830885887146,
      "eval_runtime": 0.8947,
      "eval_samples_per_second": 567.8,
      "eval_steps_per_second": 71.534,
      "step": 4000
    },
    {
      "epoch": 5.32,
      "eval_accuracy": 0.789370059967041,
      "eval_f1": 0.8065099457504521,
      "eval_loss": 0.9238587021827698,
      "eval_runtime": 0.8912,
      "eval_samples_per_second": 570.005,
      "eval_steps_per_second": 71.812,
      "step": 4200
    },
    {
      "epoch": 5.57,
      "eval_accuracy": 0.7814960479736328,
      "eval_f1": 0.7940630797773653,
      "eval_loss": 0.8553095459938049,
      "eval_runtime": 0.8957,
      "eval_samples_per_second": 567.124,
      "eval_steps_per_second": 71.449,
      "step": 4400
    },
    {
      "epoch": 5.7,
      "learning_rate": 2.1518987341772153e-05,
      "loss": 0.0634,
      "step": 4500
    },
    {
      "epoch": 5.82,
      "eval_accuracy": 0.8110235929489136,
      "eval_f1": 0.817490494296578,
      "eval_loss": 0.6774270534515381,
      "eval_runtime": 0.8879,
      "eval_samples_per_second": 572.147,
      "eval_steps_per_second": 72.081,
      "step": 4600
    },
    {
      "epoch": 6.08,
      "eval_accuracy": 0.7992125749588013,
      "eval_f1": 0.8038461538461538,
      "eval_loss": 0.9549906849861145,
      "eval_runtime": 0.9051,
      "eval_samples_per_second": 561.292,
      "eval_steps_per_second": 70.714,
      "step": 4800
    },
    {
      "epoch": 6.33,
      "learning_rate": 1.8354430379746836e-05,
      "loss": 0.0548,
      "step": 5000
    },
    {
      "epoch": 6.33,
      "eval_accuracy": 0.8031495809555054,
      "eval_f1": 0.8091603053435114,
      "eval_loss": 1.1089578866958618,
      "eval_runtime": 0.8777,
      "eval_samples_per_second": 578.768,
      "eval_steps_per_second": 72.916,
      "step": 5000
    },
    {
      "epoch": 6.58,
      "eval_accuracy": 0.8051180839538574,
      "eval_f1": 0.809248554913295,
      "eval_loss": 1.028864860534668,
      "eval_runtime": 0.8922,
      "eval_samples_per_second": 569.357,
      "eval_steps_per_second": 71.73,
      "step": 5200
    },
    {
      "epoch": 6.84,
      "eval_accuracy": 0.7952755689620972,
      "eval_f1": 0.8066914498141264,
      "eval_loss": 0.9950660467147827,
      "eval_runtime": 0.894,
      "eval_samples_per_second": 568.236,
      "eval_steps_per_second": 71.589,
      "step": 5400
    },
    {
      "epoch": 6.96,
      "learning_rate": 1.5189873417721521e-05,
      "loss": 0.0473,
      "step": 5500
    },
    {
      "epoch": 7.09,
      "eval_accuracy": 0.8110235929489136,
      "eval_f1": 0.8117647058823529,
      "eval_loss": 1.1159313917160034,
      "eval_runtime": 0.8468,
      "eval_samples_per_second": 599.932,
      "eval_steps_per_second": 75.582,
      "step": 5600
    },
    {
      "epoch": 7.34,
      "eval_accuracy": 0.8090550899505615,
      "eval_f1": 0.8131021194605009,
      "eval_loss": 1.0203063488006592,
      "eval_runtime": 0.9245,
      "eval_samples_per_second": 549.472,
      "eval_steps_per_second": 69.225,
      "step": 5800
    },
    {
      "epoch": 7.59,
      "learning_rate": 1.2025316455696203e-05,
      "loss": 0.036,
      "step": 6000
    },
    {
      "epoch": 7.59,
      "eval_accuracy": 0.8149606585502625,
      "eval_f1": 0.815686274509804,
      "eval_loss": 1.0656845569610596,
      "eval_runtime": 0.9107,
      "eval_samples_per_second": 557.814,
      "eval_steps_per_second": 70.276,
      "step": 6000
    },
    {
      "epoch": 7.85,
      "eval_accuracy": 0.8129921555519104,
      "eval_f1": 0.8140900195694716,
      "eval_loss": 1.0237640142440796,
      "eval_runtime": 0.85,
      "eval_samples_per_second": 597.63,
      "eval_steps_per_second": 75.292,
      "step": 6200
    },
    {
      "epoch": 8.1,
      "eval_accuracy": 0.8208661675453186,
      "eval_f1": 0.8205128205128205,
      "eval_loss": 1.1597448587417603,
      "eval_runtime": 0.8983,
      "eval_samples_per_second": 565.501,
      "eval_steps_per_second": 71.244,
      "step": 6400
    },
    {
      "epoch": 8.1,
      "step": 6400,
      "total_flos": 1.3556183708860416e+16,
      "train_loss": 0.14836265951395033,
      "train_runtime": 2029.2795,
      "train_samples_per_second": 248.995,
      "train_steps_per_second": 3.893
    }
  ],
  "max_steps": 7900,
  "num_train_epochs": 10,
  "total_flos": 1.3556183708860416e+16,
  "trial_name": null,
  "trial_params": null
}