prxy5608's picture
Training in progress, step 50, checkpoint
9efb2bb verified
raw
history blame
9.96 kB
{
"best_metric": 0.6820001602172852,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.014971180477580658,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0002994236095516131,
"grad_norm": 1.5001531839370728,
"learning_rate": 1e-05,
"loss": 0.7045,
"step": 1
},
{
"epoch": 0.0002994236095516131,
"eval_loss": 2.051914691925049,
"eval_runtime": 422.224,
"eval_samples_per_second": 13.322,
"eval_steps_per_second": 3.332,
"step": 1
},
{
"epoch": 0.0005988472191032262,
"grad_norm": 3.2409021854400635,
"learning_rate": 2e-05,
"loss": 1.2576,
"step": 2
},
{
"epoch": 0.0008982708286548395,
"grad_norm": 3.3385164737701416,
"learning_rate": 3e-05,
"loss": 1.4342,
"step": 3
},
{
"epoch": 0.0011976944382064525,
"grad_norm": 2.5048654079437256,
"learning_rate": 4e-05,
"loss": 1.2126,
"step": 4
},
{
"epoch": 0.0014971180477580657,
"grad_norm": 2.4707694053649902,
"learning_rate": 5e-05,
"loss": 1.2135,
"step": 5
},
{
"epoch": 0.001796541657309679,
"grad_norm": 2.2355294227600098,
"learning_rate": 6e-05,
"loss": 1.0944,
"step": 6
},
{
"epoch": 0.002095965266861292,
"grad_norm": 2.022751808166504,
"learning_rate": 7e-05,
"loss": 1.1788,
"step": 7
},
{
"epoch": 0.002395388876412905,
"grad_norm": 2.8048019409179688,
"learning_rate": 8e-05,
"loss": 1.131,
"step": 8
},
{
"epoch": 0.002694812485964518,
"grad_norm": 1.797947645187378,
"learning_rate": 9e-05,
"loss": 0.9426,
"step": 9
},
{
"epoch": 0.0029942360955161314,
"grad_norm": 1.7996845245361328,
"learning_rate": 0.0001,
"loss": 0.9091,
"step": 10
},
{
"epoch": 0.0032936597050677446,
"grad_norm": 1.6557872295379639,
"learning_rate": 9.999316524962345e-05,
"loss": 0.8645,
"step": 11
},
{
"epoch": 0.003593083314619358,
"grad_norm": 1.6052519083023071,
"learning_rate": 9.997266286704631e-05,
"loss": 0.6948,
"step": 12
},
{
"epoch": 0.003892506924170971,
"grad_norm": 1.2952603101730347,
"learning_rate": 9.993849845741524e-05,
"loss": 0.5823,
"step": 13
},
{
"epoch": 0.004191930533722584,
"grad_norm": 1.463269829750061,
"learning_rate": 9.989068136093873e-05,
"loss": 0.6292,
"step": 14
},
{
"epoch": 0.0044913541432741975,
"grad_norm": 1.466579556465149,
"learning_rate": 9.98292246503335e-05,
"loss": 0.7209,
"step": 15
},
{
"epoch": 0.00479077775282581,
"grad_norm": 1.2136961221694946,
"learning_rate": 9.975414512725057e-05,
"loss": 0.639,
"step": 16
},
{
"epoch": 0.005090201362377423,
"grad_norm": 1.3666551113128662,
"learning_rate": 9.966546331768191e-05,
"loss": 0.6686,
"step": 17
},
{
"epoch": 0.005389624971929036,
"grad_norm": 1.357208490371704,
"learning_rate": 9.956320346634876e-05,
"loss": 0.6592,
"step": 18
},
{
"epoch": 0.00568904858148065,
"grad_norm": 1.077374815940857,
"learning_rate": 9.944739353007344e-05,
"loss": 0.5465,
"step": 19
},
{
"epoch": 0.005988472191032263,
"grad_norm": 1.1113899946212769,
"learning_rate": 9.931806517013612e-05,
"loss": 0.6283,
"step": 20
},
{
"epoch": 0.006287895800583876,
"grad_norm": 1.1577091217041016,
"learning_rate": 9.917525374361912e-05,
"loss": 0.6512,
"step": 21
},
{
"epoch": 0.006587319410135489,
"grad_norm": 1.234321117401123,
"learning_rate": 9.901899829374047e-05,
"loss": 0.7452,
"step": 22
},
{
"epoch": 0.0068867430196871025,
"grad_norm": 1.0721598863601685,
"learning_rate": 9.884934153917997e-05,
"loss": 0.5771,
"step": 23
},
{
"epoch": 0.007186166629238716,
"grad_norm": 1.0589637756347656,
"learning_rate": 9.86663298624003e-05,
"loss": 0.5554,
"step": 24
},
{
"epoch": 0.007485590238790329,
"grad_norm": 1.0572690963745117,
"learning_rate": 9.847001329696653e-05,
"loss": 0.6028,
"step": 25
},
{
"epoch": 0.007785013848341942,
"grad_norm": 1.1369898319244385,
"learning_rate": 9.826044551386744e-05,
"loss": 0.7004,
"step": 26
},
{
"epoch": 0.008084437457893555,
"grad_norm": 1.2353670597076416,
"learning_rate": 9.803768380684242e-05,
"loss": 0.7781,
"step": 27
},
{
"epoch": 0.008383861067445169,
"grad_norm": 1.228273868560791,
"learning_rate": 9.780178907671789e-05,
"loss": 0.6891,
"step": 28
},
{
"epoch": 0.008683284676996781,
"grad_norm": 1.5415000915527344,
"learning_rate": 9.755282581475769e-05,
"loss": 0.6284,
"step": 29
},
{
"epoch": 0.008982708286548395,
"grad_norm": 1.2694517374038696,
"learning_rate": 9.729086208503174e-05,
"loss": 0.7427,
"step": 30
},
{
"epoch": 0.009282131896100007,
"grad_norm": 1.0838075876235962,
"learning_rate": 9.701596950580806e-05,
"loss": 0.6549,
"step": 31
},
{
"epoch": 0.00958155550565162,
"grad_norm": 1.1120599508285522,
"learning_rate": 9.672822322997305e-05,
"loss": 0.5431,
"step": 32
},
{
"epoch": 0.009880979115203234,
"grad_norm": 1.1518739461898804,
"learning_rate": 9.642770192448536e-05,
"loss": 0.5033,
"step": 33
},
{
"epoch": 0.010180402724754846,
"grad_norm": 1.096585988998413,
"learning_rate": 9.611448774886924e-05,
"loss": 0.5161,
"step": 34
},
{
"epoch": 0.01047982633430646,
"grad_norm": 1.4382801055908203,
"learning_rate": 9.578866633275288e-05,
"loss": 0.9635,
"step": 35
},
{
"epoch": 0.010779249943858073,
"grad_norm": 1.3973444700241089,
"learning_rate": 9.545032675245813e-05,
"loss": 0.7488,
"step": 36
},
{
"epoch": 0.011078673553409687,
"grad_norm": 1.7564913034439087,
"learning_rate": 9.509956150664796e-05,
"loss": 0.7366,
"step": 37
},
{
"epoch": 0.0113780971629613,
"grad_norm": 2.130863666534424,
"learning_rate": 9.473646649103818e-05,
"loss": 0.9292,
"step": 38
},
{
"epoch": 0.011677520772512913,
"grad_norm": 1.659516453742981,
"learning_rate": 9.43611409721806e-05,
"loss": 0.9802,
"step": 39
},
{
"epoch": 0.011976944382064526,
"grad_norm": 1.8587124347686768,
"learning_rate": 9.397368756032445e-05,
"loss": 0.8617,
"step": 40
},
{
"epoch": 0.01227636799161614,
"grad_norm": 1.5178453922271729,
"learning_rate": 9.357421218136386e-05,
"loss": 0.7172,
"step": 41
},
{
"epoch": 0.012575791601167752,
"grad_norm": 2.470705270767212,
"learning_rate": 9.316282404787871e-05,
"loss": 0.8211,
"step": 42
},
{
"epoch": 0.012875215210719364,
"grad_norm": 1.578737497329712,
"learning_rate": 9.273963562927695e-05,
"loss": 0.8244,
"step": 43
},
{
"epoch": 0.013174638820270979,
"grad_norm": 3.1308135986328125,
"learning_rate": 9.230476262104677e-05,
"loss": 0.7703,
"step": 44
},
{
"epoch": 0.013474062429822591,
"grad_norm": 1.7756150960922241,
"learning_rate": 9.185832391312644e-05,
"loss": 0.8427,
"step": 45
},
{
"epoch": 0.013773486039374205,
"grad_norm": 2.1269168853759766,
"learning_rate": 9.140044155740101e-05,
"loss": 0.7262,
"step": 46
},
{
"epoch": 0.014072909648925817,
"grad_norm": 1.8117233514785767,
"learning_rate": 9.093124073433463e-05,
"loss": 0.722,
"step": 47
},
{
"epoch": 0.014372333258477431,
"grad_norm": 2.315007448196411,
"learning_rate": 9.045084971874738e-05,
"loss": 0.7214,
"step": 48
},
{
"epoch": 0.014671756868029044,
"grad_norm": 2.204045057296753,
"learning_rate": 8.995939984474624e-05,
"loss": 0.5963,
"step": 49
},
{
"epoch": 0.014971180477580658,
"grad_norm": 2.364506483078003,
"learning_rate": 8.945702546981969e-05,
"loss": 0.7147,
"step": 50
},
{
"epoch": 0.014971180477580658,
"eval_loss": 0.6820001602172852,
"eval_runtime": 425.4327,
"eval_samples_per_second": 13.222,
"eval_steps_per_second": 3.307,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 7.580280733197926e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}