{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9971883786316776,
  "eval_steps": 67,
  "global_step": 266,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0037488284910965324,
      "eval_loss": 2.361954689025879,
      "eval_runtime": 3.5851,
      "eval_samples_per_second": 125.521,
      "eval_steps_per_second": 15.899,
      "step": 1
    },
    {
      "epoch": 0.01874414245548266,
      "grad_norm": 0.1121288314461708,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.0053,
      "step": 5
    },
    {
      "epoch": 0.03748828491096532,
      "grad_norm": 0.2451150268316269,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.2996,
      "step": 10
    },
    {
      "epoch": 0.056232427366447985,
      "grad_norm": 0.10745533555746078,
      "learning_rate": 5e-05,
      "loss": 2.2399,
      "step": 15
    },
    {
      "epoch": 0.07497656982193064,
      "grad_norm": 0.21655316650867462,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.1764,
      "step": 20
    },
    {
      "epoch": 0.09372071227741331,
      "grad_norm": 0.8079115152359009,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.6489,
      "step": 25
    },
    {
      "epoch": 0.11246485473289597,
      "grad_norm": 0.14432325959205627,
      "learning_rate": 0.0001,
      "loss": 2.0175,
      "step": 30
    },
    {
      "epoch": 0.13120899718837864,
      "grad_norm": 0.33471807837486267,
      "learning_rate": 9.989021978333995e-05,
      "loss": 2.1727,
      "step": 35
    },
    {
      "epoch": 0.14995313964386128,
      "grad_norm": 0.18594202399253845,
      "learning_rate": 9.956136120119858e-05,
      "loss": 2.1616,
      "step": 40
    },
    {
      "epoch": 0.16869728209934395,
      "grad_norm": 0.25360578298568726,
      "learning_rate": 9.901486834023182e-05,
      "loss": 2.0248,
      "step": 45
    },
    {
      "epoch": 0.18744142455482662,
      "grad_norm": 0.8163858652114868,
      "learning_rate": 9.825314096462685e-05,
      "loss": 2.3624,
      "step": 50
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.21278133988380432,
      "learning_rate": 9.72795239782369e-05,
      "loss": 1.9549,
      "step": 55
    },
    {
      "epoch": 0.22492970946579194,
      "grad_norm": 0.3845430016517639,
      "learning_rate": 9.609829273641034e-05,
      "loss": 2.1518,
      "step": 60
    },
    {
      "epoch": 0.2436738519212746,
      "grad_norm": 0.20262780785560608,
      "learning_rate": 9.47146342720133e-05,
      "loss": 2.1145,
      "step": 65
    },
    {
      "epoch": 0.2511715089034677,
      "eval_loss": 2.1052558422088623,
      "eval_runtime": 3.565,
      "eval_samples_per_second": 126.226,
      "eval_steps_per_second": 15.989,
      "step": 67
    },
    {
      "epoch": 0.2624179943767573,
      "grad_norm": 0.27742379903793335,
      "learning_rate": 9.3134624518086e-05,
      "loss": 1.9983,
      "step": 70
    },
    {
      "epoch": 0.28116213683223995,
      "grad_norm": 1.399202585220337,
      "learning_rate": 9.136520162715287e-05,
      "loss": 2.3956,
      "step": 75
    },
    {
      "epoch": 0.29990627928772257,
      "grad_norm": 0.2662142813205719,
      "learning_rate": 8.94141355043471e-05,
      "loss": 1.8996,
      "step": 80
    },
    {
      "epoch": 0.31865042174320524,
      "grad_norm": 0.47221991419792175,
      "learning_rate": 8.728999368813591e-05,
      "loss": 2.1171,
      "step": 85
    },
    {
      "epoch": 0.3373945641986879,
      "grad_norm": 0.20478223264217377,
      "learning_rate": 8.500210372847127e-05,
      "loss": 2.0381,
      "step": 90
    },
    {
      "epoch": 0.3561387066541706,
      "grad_norm": 0.3004133105278015,
      "learning_rate": 8.256051222757188e-05,
      "loss": 1.9738,
      "step": 95
    },
    {
      "epoch": 0.37488284910965325,
      "grad_norm": 1.0329713821411133,
      "learning_rate": 7.997594072319625e-05,
      "loss": 2.2227,
      "step": 100
    },
    {
      "epoch": 0.3936269915651359,
      "grad_norm": 0.2629578709602356,
      "learning_rate": 7.725973860813338e-05,
      "loss": 1.8634,
      "step": 105
    },
    {
      "epoch": 0.41237113402061853,
      "grad_norm": 0.46902984380722046,
      "learning_rate": 7.442383329265062e-05,
      "loss": 2.0261,
      "step": 110
    },
    {
      "epoch": 0.4311152764761012,
      "grad_norm": 0.23315371572971344,
      "learning_rate": 7.14806778287464e-05,
      "loss": 2.0076,
      "step": 115
    },
    {
      "epoch": 0.4498594189315839,
      "grad_norm": 0.3503168523311615,
      "learning_rate": 6.844319622620039e-05,
      "loss": 1.9312,
      "step": 120
    },
    {
      "epoch": 0.46860356138706655,
      "grad_norm": 1.228668212890625,
      "learning_rate": 6.532472670054974e-05,
      "loss": 2.2572,
      "step": 125
    },
    {
      "epoch": 0.4873477038425492,
      "grad_norm": 0.27969205379486084,
      "learning_rate": 6.213896310220139e-05,
      "loss": 1.8566,
      "step": 130
    },
    {
      "epoch": 0.5023430178069354,
      "eval_loss": 2.028304100036621,
      "eval_runtime": 3.6808,
      "eval_samples_per_second": 122.257,
      "eval_steps_per_second": 15.486,
      "step": 134
    },
    {
      "epoch": 0.5060918462980318,
      "grad_norm": 0.6361961364746094,
      "learning_rate": 5.889989478387753e-05,
      "loss": 2.02,
      "step": 135
    },
    {
      "epoch": 0.5248359887535146,
      "grad_norm": 0.24769911170005798,
      "learning_rate": 5.5621745170448616e-05,
      "loss": 1.9486,
      "step": 140
    },
    {
      "epoch": 0.5435801312089972,
      "grad_norm": 0.3790437877178192,
      "learning_rate": 5.2318909300906926e-05,
      "loss": 2.012,
      "step": 145
    },
    {
      "epoch": 0.5623242736644799,
      "grad_norm": 1.3477414846420288,
      "learning_rate": 4.900589061674649e-05,
      "loss": 2.1598,
      "step": 150
    },
    {
      "epoch": 0.5810684161199625,
      "grad_norm": 0.3055458664894104,
      "learning_rate": 4.569723727432517e-05,
      "loss": 1.7986,
      "step": 155
    },
    {
      "epoch": 0.5998125585754451,
      "grad_norm": 0.5476722121238708,
      "learning_rate": 4.240747826087429e-05,
      "loss": 2.005,
      "step": 160
    },
    {
      "epoch": 0.6185567010309279,
      "grad_norm": 0.2658919095993042,
      "learning_rate": 3.91510595946841e-05,
      "loss": 1.9485,
      "step": 165
    },
    {
      "epoch": 0.6373008434864105,
      "grad_norm": 0.4225824177265167,
      "learning_rate": 3.5942280889623026e-05,
      "loss": 1.952,
      "step": 170
    },
    {
      "epoch": 0.6560449859418932,
      "grad_norm": 1.3499469757080078,
      "learning_rate": 3.27952325625493e-05,
      "loss": 2.194,
      "step": 175
    },
    {
      "epoch": 0.6747891283973758,
      "grad_norm": 0.3095148801803589,
      "learning_rate": 2.9723733959350307e-05,
      "loss": 1.7729,
      "step": 180
    },
    {
      "epoch": 0.6935332708528584,
      "grad_norm": 0.6386678218841553,
      "learning_rate": 2.674127267131131e-05,
      "loss": 2.0403,
      "step": 185
    },
    {
      "epoch": 0.7122774133083412,
      "grad_norm": 0.2703355848789215,
      "learning_rate": 2.3860945308287552e-05,
      "loss": 1.9099,
      "step": 190
    },
    {
      "epoch": 0.7310215557638238,
      "grad_norm": 0.38986149430274963,
      "learning_rate": 2.1095399988757574e-05,
      "loss": 1.9077,
      "step": 195
    },
    {
      "epoch": 0.7497656982193065,
      "grad_norm": 1.2410173416137695,
      "learning_rate": 1.8456780799295886e-05,
      "loss": 2.1793,
      "step": 200
    },
    {
      "epoch": 0.753514526710403,
      "eval_loss": 1.9828202724456787,
      "eval_runtime": 3.6018,
      "eval_samples_per_second": 124.937,
      "eval_steps_per_second": 15.825,
      "step": 201
    },
    {
      "epoch": 0.7685098406747891,
      "grad_norm": 0.3099184036254883,
      "learning_rate": 1.5956674467354537e-05,
      "loss": 1.7989,
      "step": 205
    },
    {
      "epoch": 0.7872539831302718,
      "grad_norm": 0.6507529616355896,
      "learning_rate": 1.3606059481525296e-05,
      "loss": 1.9024,
      "step": 210
    },
    {
      "epoch": 0.8059981255857545,
      "grad_norm": 0.28235751390457153,
      "learning_rate": 1.1415257882705311e-05,
      "loss": 1.9202,
      "step": 215
    },
    {
      "epoch": 0.8247422680412371,
      "grad_norm": 0.4169105887413025,
      "learning_rate": 9.393889937861694e-06,
      "loss": 1.9481,
      "step": 220
    },
    {
      "epoch": 0.8434864104967198,
      "grad_norm": 1.1425191164016724,
      "learning_rate": 7.550831895431798e-06,
      "loss": 2.0996,
      "step": 225
    },
    {
      "epoch": 0.8622305529522024,
      "grad_norm": 0.3197765052318573,
      "learning_rate": 5.894177007864271e-06,
      "loss": 1.8399,
      "step": 230
    },
    {
      "epoch": 0.8809746954076851,
      "grad_norm": 0.6108065843582153,
      "learning_rate": 4.4311999924586065e-06,
      "loss": 1.9692,
      "step": 235
    },
    {
      "epoch": 0.8997188378631678,
      "grad_norm": 0.2768736779689789,
      "learning_rate": 3.1683250865636114e-06,
      "loss": 1.9613,
      "step": 240
    },
    {
      "epoch": 0.9184629803186504,
      "grad_norm": 0.40607261657714844,
      "learning_rate": 2.1110978374106192e-06,
      "loss": 1.8941,
      "step": 245
    },
    {
      "epoch": 0.9372071227741331,
      "grad_norm": 1.1138426065444946,
      "learning_rate": 1.2641607504584928e-06,
      "loss": 2.0727,
      "step": 250
    },
    {
      "epoch": 0.9559512652296157,
      "grad_norm": 0.32683926820755005,
      "learning_rate": 6.312329031833319e-07,
      "loss": 1.8131,
      "step": 255
    },
    {
      "epoch": 0.9746954076850984,
      "grad_norm": 0.6287037134170532,
      "learning_rate": 2.1509361383330596e-07,
      "loss": 1.9955,
      "step": 260
    },
    {
      "epoch": 0.993439550140581,
      "grad_norm": 0.3499762713909149,
      "learning_rate": 1.7570236862241017e-08,
      "loss": 2.0133,
      "step": 265
    }
  ],
  "logging_steps": 5,
  "max_steps": 267,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.526691379760333e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}