training/eval/sweep_lr3e-05.json

{
  "step": [
    1,
    2,
    3,
    4,
    5,
    6,
    7,
    8,
    9,
    10,
    11,
    12,
    13,
    14,
    15,
    16,
    17,
    18,
    19,
    20,
    21,
    22,
    23,
    24,
    25,
    26,
    27,
    28,
    29,
    30,
    31,
    32,
    33,
    34,
    35,
    36,
    37,
    38,
    39,
    40,
    41,
    42
  ],
  "loss": [
    2.929511785507202,
    2.247201919555664,
    2.8281919956207275,
    2.988922119140625,
    2.9579265117645264,
    2.5684621334075928,
    2.780268430709839,
    3.043792963027954,
    2.739168405532837,
    3.1606099605560303,
    2.78983211517334,
    2.7440412044525146,
    3.1741816997528076,
    2.53462553024292,
    2.8028407096862793,
    2.942612409591675,
    3.2238481044769287,
    2.468869924545288,
    3.175896644592285,
    3.166104555130005,
    3.004603147506714,
    2.494501829147339,
    3.6294150352478027,
    3.54898738861084,
    2.914577007293701,
    2.7015793323516846,
    2.7510435581207275,
    3.35261607170105,
    2.443834066390991,
    2.706798553466797,
    2.454486608505249,
    2.99945330619812,
    2.562314748764038,
    2.5577080249786377,
    2.8527939319610596,
    2.624260187149048,
    2.6507158279418945,
    2.745821475982666,
    3.145089864730835,
    3.0858192443847656,
    3.218226194381714,
    3.1568758487701416
  ],
  "grad_norm": [
    0.016382873058319092,
    0.01044374331831932,
    0.014513103291392326,
    0.015878325328230858,
    0.01755627989768982,
    0.01403629221022129,
    0.015126992017030716,
    0.017010418698191643,
    0.017322592437267303,
    0.018153507262468338,
    0.021663852035999298,
    0.020251702517271042,
    0.026083821430802345,
    0.021082837134599686,
    0.021237652748823166,
    0.02275363728404045,
    0.028056206181645393,
    0.025404982268810272,
    0.03324253857135773,
    0.03437183052301407,
    0.03445492312312126,
    0.025799673050642014,
    0.047848328948020935,
    0.04164322465658188,
    0.03566818684339523,
    0.03318743035197258,
    0.03174922242760658,
    0.04117360711097717,
    0.026225894689559937,
    0.03371588885784149,
    0.029318243265151978,
    0.040480468422174454,
    0.03876935690641403,
    0.03223586082458496,
    0.03744722902774811,
    0.032570790499448776,
    0.03520411625504494,
    0.03473634645342827,
    0.050191059708595276,
    0.036559101194143295,
    0.047161854803562164,
    0.03893602266907692
  ],
  "epoch": [
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    1,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2,
    2
  ],
  "eval_step": [
    21,
    42
  ],
  "eval_loss": [
    2.855921506881714,
    2.8544867038726807
  ],
  "skipped_nonfinite": 0,
  "config": {
    "lr": 3e-05,
    "epochs": 2,
    "batch_size": 8,
    "lora_rank": 16,
    "lora_alpha": 32,
    "max_len": 512,
    "grad_clip": 1.0,
    "weight_decay": 0.0,
    "seed": 3407,
    "warmup_frac": 0.1
  },
  "wall_seconds": 118.0,
  "final_loss": 3.1568758487701416,
  "first_loss": 2.929511785507202
}