{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008510276158461342,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.510276158461342e-05,
      "eval_loss": 1.4265342950820923,
      "eval_runtime": 1422.7176,
      "eval_samples_per_second": 13.911,
      "eval_steps_per_second": 1.739,
      "step": 1
    },
    {
      "epoch": 0.0002553082847538403,
      "grad_norm": 7.908364295959473,
      "learning_rate": 1.5e-05,
      "loss": 5.6974,
      "step": 3
    },
    {
      "epoch": 0.0005106165695076806,
      "grad_norm": 6.230061054229736,
      "learning_rate": 3e-05,
      "loss": 5.4338,
      "step": 6
    },
    {
      "epoch": 0.0007659248542615208,
      "grad_norm": 3.978466272354126,
      "learning_rate": 4.5e-05,
      "loss": 5.2112,
      "step": 9
    },
    {
      "epoch": 0.0007659248542615208,
      "eval_loss": 1.2634788751602173,
      "eval_runtime": 1429.6296,
      "eval_samples_per_second": 13.843,
      "eval_steps_per_second": 1.731,
      "step": 9
    },
    {
      "epoch": 0.0010212331390153612,
      "grad_norm": 4.294009685516357,
      "learning_rate": 4.993910125649561e-05,
      "loss": 5.0675,
      "step": 12
    },
    {
      "epoch": 0.0012765414237692013,
      "grad_norm": 2.9980828762054443,
      "learning_rate": 4.962019382530521e-05,
      "loss": 4.8171,
      "step": 15
    },
    {
      "epoch": 0.0015318497085230415,
      "grad_norm": 3.0869834423065186,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 4.7292,
      "step": 18
    },
    {
      "epoch": 0.0015318497085230415,
      "eval_loss": 1.1791282892227173,
      "eval_runtime": 1430.0647,
      "eval_samples_per_second": 13.839,
      "eval_steps_per_second": 1.73,
      "step": 18
    },
    {
      "epoch": 0.001787157993276882,
      "grad_norm": 2.754807949066162,
      "learning_rate": 4.817959636416969e-05,
      "loss": 4.6937,
      "step": 21
    },
    {
      "epoch": 0.0020424662780307223,
      "grad_norm": 2.638349771499634,
      "learning_rate": 4.707368982147318e-05,
      "loss": 4.5978,
      "step": 24
    },
    {
      "epoch": 0.0022977745627845623,
      "grad_norm": 2.762077569961548,
      "learning_rate": 4.572593931387604e-05,
      "loss": 4.6333,
      "step": 27
    },
    {
      "epoch": 0.0022977745627845623,
      "eval_loss": 1.1523500680923462,
      "eval_runtime": 1430.0767,
      "eval_samples_per_second": 13.839,
      "eval_steps_per_second": 1.73,
      "step": 27
    },
    {
      "epoch": 0.0025530828475384027,
      "grad_norm": 2.646472692489624,
      "learning_rate": 4.415111107797445e-05,
      "loss": 4.5757,
      "step": 30
    },
    {
      "epoch": 0.002808391132292243,
      "grad_norm": 2.671572685241699,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 4.6269,
      "step": 33
    },
    {
      "epoch": 0.003063699417046083,
      "grad_norm": 2.880744218826294,
      "learning_rate": 4.039153688314145e-05,
      "loss": 4.5438,
      "step": 36
    },
    {
      "epoch": 0.003063699417046083,
      "eval_loss": 1.1377136707305908,
      "eval_runtime": 1429.7895,
      "eval_samples_per_second": 13.842,
      "eval_steps_per_second": 1.73,
      "step": 36
    },
    {
      "epoch": 0.0033190077017999234,
      "grad_norm": 2.7430524826049805,
      "learning_rate": 3.824798160583012e-05,
      "loss": 4.627,
      "step": 39
    },
    {
      "epoch": 0.003574315986553764,
      "grad_norm": 2.8961098194122314,
      "learning_rate": 3.5959278669726935e-05,
      "loss": 4.5318,
      "step": 42
    },
    {
      "epoch": 0.0038296242713076038,
      "grad_norm": 2.7629406452178955,
      "learning_rate": 3.355050358314172e-05,
      "loss": 4.4218,
      "step": 45
    },
    {
      "epoch": 0.0038296242713076038,
      "eval_loss": 1.129303216934204,
      "eval_runtime": 1430.1322,
      "eval_samples_per_second": 13.839,
      "eval_steps_per_second": 1.73,
      "step": 45
    },
    {
      "epoch": 0.004084932556061445,
      "grad_norm": 2.760894536972046,
      "learning_rate": 3.104804738999169e-05,
      "loss": 4.3762,
      "step": 48
    },
    {
      "epoch": 0.004340240840815284,
      "grad_norm": 2.6783533096313477,
      "learning_rate": 2.8479327524001636e-05,
      "loss": 4.559,
      "step": 51
    },
    {
      "epoch": 0.0045955491255691245,
      "grad_norm": 2.5721302032470703,
      "learning_rate": 2.587248741756253e-05,
      "loss": 4.5641,
      "step": 54
    },
    {
      "epoch": 0.0045955491255691245,
      "eval_loss": 1.1213735342025757,
      "eval_runtime": 1430.3753,
      "eval_samples_per_second": 13.836,
      "eval_steps_per_second": 1.73,
      "step": 54
    },
    {
      "epoch": 0.004850857410322965,
      "grad_norm": 2.695680618286133,
      "learning_rate": 2.3256088156396868e-05,
      "loss": 4.4795,
      "step": 57
    },
    {
      "epoch": 0.005106165695076805,
      "grad_norm": 2.6988542079925537,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 4.433,
      "step": 60
    },
    {
      "epoch": 0.005361473979830646,
      "grad_norm": 2.7334961891174316,
      "learning_rate": 1.8109066104575023e-05,
      "loss": 4.4115,
      "step": 63
    },
    {
      "epoch": 0.005361473979830646,
      "eval_loss": 1.1170847415924072,
      "eval_runtime": 1430.6721,
      "eval_samples_per_second": 13.833,
      "eval_steps_per_second": 1.729,
      "step": 63
    },
    {
      "epoch": 0.005616782264584486,
      "grad_norm": 2.718637704849243,
      "learning_rate": 1.56348351646022e-05,
      "loss": 4.4666,
      "step": 66
    },
    {
      "epoch": 0.005872090549338326,
      "grad_norm": 2.9299156665802,
      "learning_rate": 1.3263210930352737e-05,
      "loss": 4.4289,
      "step": 69
    },
    {
      "epoch": 0.006127398834092166,
      "grad_norm": 2.732020616531372,
      "learning_rate": 1.1020177413231334e-05,
      "loss": 4.3213,
      "step": 72
    },
    {
      "epoch": 0.006127398834092166,
      "eval_loss": 1.1137700080871582,
      "eval_runtime": 1430.87,
      "eval_samples_per_second": 13.831,
      "eval_steps_per_second": 1.729,
      "step": 72
    },
    {
      "epoch": 0.0063827071188460064,
      "grad_norm": 2.8953986167907715,
      "learning_rate": 8.930309757836517e-06,
      "loss": 4.4973,
      "step": 75
    },
    {
      "epoch": 0.006638015403599847,
      "grad_norm": 2.6640074253082275,
      "learning_rate": 7.016504991533726e-06,
      "loss": 4.3667,
      "step": 78
    },
    {
      "epoch": 0.006893323688353687,
      "grad_norm": 2.7051126956939697,
      "learning_rate": 5.299731159831953e-06,
      "loss": 4.3751,
      "step": 81
    },
    {
      "epoch": 0.006893323688353687,
      "eval_loss": 1.1114040613174438,
      "eval_runtime": 1430.9038,
      "eval_samples_per_second": 13.831,
      "eval_steps_per_second": 1.729,
      "step": 81
    },
    {
      "epoch": 0.007148631973107528,
      "grad_norm": 2.845485210418701,
      "learning_rate": 3.798797596089351e-06,
      "loss": 4.537,
      "step": 84
    },
    {
      "epoch": 0.007403940257861368,
      "grad_norm": 2.637657642364502,
      "learning_rate": 2.5301488425208296e-06,
      "loss": 4.4016,
      "step": 87
    },
    {
      "epoch": 0.0076592485426152076,
      "grad_norm": 2.7435178756713867,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 4.399,
      "step": 90
    },
    {
      "epoch": 0.0076592485426152076,
      "eval_loss": 1.1104978322982788,
      "eval_runtime": 1430.9556,
      "eval_samples_per_second": 13.831,
      "eval_steps_per_second": 1.729,
      "step": 90
    },
    {
      "epoch": 0.007914556827369048,
      "grad_norm": 2.8266332149505615,
      "learning_rate": 7.426068431000882e-07,
      "loss": 4.5159,
      "step": 93
    },
    {
      "epoch": 0.00816986511212289,
      "grad_norm": 2.816528081893921,
      "learning_rate": 2.4329828146074095e-07,
      "loss": 4.5103,
      "step": 96
    },
    {
      "epoch": 0.008425173396876729,
      "grad_norm": 2.7482688426971436,
      "learning_rate": 1.522932452260595e-08,
      "loss": 4.4013,
      "step": 99
    },
    {
      "epoch": 0.008425173396876729,
      "eval_loss": 1.1102831363677979,
      "eval_runtime": 1430.7905,
      "eval_samples_per_second": 13.832,
      "eval_steps_per_second": 1.729,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.406260607975424e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}