0x1202's picture
Training in progress, step 50, checkpoint
ac778c9 verified
raw
history blame
9.95 kB
{
"best_metric": 1.5559238195419312,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.008104056080068074,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00016208112160136148,
"grad_norm": 21.450843811035156,
"learning_rate": 1e-05,
"loss": 9.9546,
"step": 1
},
{
"epoch": 0.00016208112160136148,
"eval_loss": 2.8611927032470703,
"eval_runtime": 1024.5411,
"eval_samples_per_second": 10.143,
"eval_steps_per_second": 2.536,
"step": 1
},
{
"epoch": 0.00032416224320272295,
"grad_norm": 20.973268508911133,
"learning_rate": 2e-05,
"loss": 10.6012,
"step": 2
},
{
"epoch": 0.00048624336480408443,
"grad_norm": 18.114707946777344,
"learning_rate": 3e-05,
"loss": 10.833,
"step": 3
},
{
"epoch": 0.0006483244864054459,
"grad_norm": 12.959110260009766,
"learning_rate": 4e-05,
"loss": 10.37,
"step": 4
},
{
"epoch": 0.0008104056080068074,
"grad_norm": 14.474491119384766,
"learning_rate": 5e-05,
"loss": 9.5092,
"step": 5
},
{
"epoch": 0.0009724867296081689,
"grad_norm": 14.347698211669922,
"learning_rate": 6e-05,
"loss": 8.3771,
"step": 6
},
{
"epoch": 0.0011345678512095303,
"grad_norm": 11.730208396911621,
"learning_rate": 7e-05,
"loss": 8.6556,
"step": 7
},
{
"epoch": 0.0012966489728108918,
"grad_norm": 10.065325736999512,
"learning_rate": 8e-05,
"loss": 8.7092,
"step": 8
},
{
"epoch": 0.0014587300944122533,
"grad_norm": 8.963871955871582,
"learning_rate": 9e-05,
"loss": 8.0248,
"step": 9
},
{
"epoch": 0.0016208112160136148,
"grad_norm": 9.340985298156738,
"learning_rate": 0.0001,
"loss": 7.8928,
"step": 10
},
{
"epoch": 0.0017828923376149762,
"grad_norm": 7.826351165771484,
"learning_rate": 9.999316524962345e-05,
"loss": 7.7345,
"step": 11
},
{
"epoch": 0.0019449734592163377,
"grad_norm": 7.2508697509765625,
"learning_rate": 9.997266286704631e-05,
"loss": 7.6428,
"step": 12
},
{
"epoch": 0.002107054580817699,
"grad_norm": 6.509117603302002,
"learning_rate": 9.993849845741524e-05,
"loss": 6.6641,
"step": 13
},
{
"epoch": 0.0022691357024190607,
"grad_norm": 7.647972106933594,
"learning_rate": 9.989068136093873e-05,
"loss": 7.2049,
"step": 14
},
{
"epoch": 0.002431216824020422,
"grad_norm": 6.6707000732421875,
"learning_rate": 9.98292246503335e-05,
"loss": 6.8951,
"step": 15
},
{
"epoch": 0.0025932979456217836,
"grad_norm": 6.7753095626831055,
"learning_rate": 9.975414512725057e-05,
"loss": 7.1702,
"step": 16
},
{
"epoch": 0.002755379067223145,
"grad_norm": 5.891744136810303,
"learning_rate": 9.966546331768191e-05,
"loss": 6.3936,
"step": 17
},
{
"epoch": 0.0029174601888245066,
"grad_norm": 6.441070556640625,
"learning_rate": 9.956320346634876e-05,
"loss": 6.748,
"step": 18
},
{
"epoch": 0.003079541310425868,
"grad_norm": 5.625812530517578,
"learning_rate": 9.944739353007344e-05,
"loss": 6.2807,
"step": 19
},
{
"epoch": 0.0032416224320272295,
"grad_norm": 5.964963436126709,
"learning_rate": 9.931806517013612e-05,
"loss": 6.8812,
"step": 20
},
{
"epoch": 0.003403703553628591,
"grad_norm": 6.139531135559082,
"learning_rate": 9.917525374361912e-05,
"loss": 6.2387,
"step": 21
},
{
"epoch": 0.0035657846752299525,
"grad_norm": 5.533466815948486,
"learning_rate": 9.901899829374047e-05,
"loss": 6.1352,
"step": 22
},
{
"epoch": 0.003727865796831314,
"grad_norm": 5.690276622772217,
"learning_rate": 9.884934153917997e-05,
"loss": 6.4498,
"step": 23
},
{
"epoch": 0.0038899469184326754,
"grad_norm": 5.708102703094482,
"learning_rate": 9.86663298624003e-05,
"loss": 6.3784,
"step": 24
},
{
"epoch": 0.004052028040034037,
"grad_norm": 5.579735279083252,
"learning_rate": 9.847001329696653e-05,
"loss": 6.3002,
"step": 25
},
{
"epoch": 0.004214109161635398,
"grad_norm": 5.780838966369629,
"learning_rate": 9.826044551386744e-05,
"loss": 5.8777,
"step": 26
},
{
"epoch": 0.00437619028323676,
"grad_norm": 5.95778226852417,
"learning_rate": 9.803768380684242e-05,
"loss": 6.3759,
"step": 27
},
{
"epoch": 0.004538271404838121,
"grad_norm": 5.736791133880615,
"learning_rate": 9.780178907671789e-05,
"loss": 6.1456,
"step": 28
},
{
"epoch": 0.004700352526439483,
"grad_norm": 5.662046909332275,
"learning_rate": 9.755282581475769e-05,
"loss": 6.1055,
"step": 29
},
{
"epoch": 0.004862433648040844,
"grad_norm": 5.7258806228637695,
"learning_rate": 9.729086208503174e-05,
"loss": 6.2523,
"step": 30
},
{
"epoch": 0.005024514769642206,
"grad_norm": 5.707207202911377,
"learning_rate": 9.701596950580806e-05,
"loss": 5.7521,
"step": 31
},
{
"epoch": 0.005186595891243567,
"grad_norm": 5.748448371887207,
"learning_rate": 9.672822322997305e-05,
"loss": 6.0935,
"step": 32
},
{
"epoch": 0.005348677012844929,
"grad_norm": 5.671350479125977,
"learning_rate": 9.642770192448536e-05,
"loss": 6.2013,
"step": 33
},
{
"epoch": 0.00551075813444629,
"grad_norm": 6.076589584350586,
"learning_rate": 9.611448774886924e-05,
"loss": 6.2627,
"step": 34
},
{
"epoch": 0.005672839256047652,
"grad_norm": 6.076786041259766,
"learning_rate": 9.578866633275288e-05,
"loss": 6.2,
"step": 35
},
{
"epoch": 0.005834920377649013,
"grad_norm": 6.442121982574463,
"learning_rate": 9.545032675245813e-05,
"loss": 6.097,
"step": 36
},
{
"epoch": 0.005997001499250375,
"grad_norm": 6.375777244567871,
"learning_rate": 9.509956150664796e-05,
"loss": 6.3335,
"step": 37
},
{
"epoch": 0.006159082620851736,
"grad_norm": 6.780538558959961,
"learning_rate": 9.473646649103818e-05,
"loss": 6.4989,
"step": 38
},
{
"epoch": 0.006321163742453098,
"grad_norm": 6.880222797393799,
"learning_rate": 9.43611409721806e-05,
"loss": 6.6263,
"step": 39
},
{
"epoch": 0.006483244864054459,
"grad_norm": 6.89586877822876,
"learning_rate": 9.397368756032445e-05,
"loss": 6.6472,
"step": 40
},
{
"epoch": 0.0066453259856558205,
"grad_norm": 7.324431896209717,
"learning_rate": 9.357421218136386e-05,
"loss": 6.9357,
"step": 41
},
{
"epoch": 0.006807407107257182,
"grad_norm": 7.074251174926758,
"learning_rate": 9.316282404787871e-05,
"loss": 6.4737,
"step": 42
},
{
"epoch": 0.0069694882288585435,
"grad_norm": 7.916954040527344,
"learning_rate": 9.273963562927695e-05,
"loss": 6.9543,
"step": 43
},
{
"epoch": 0.007131569350459905,
"grad_norm": 8.427472114562988,
"learning_rate": 9.230476262104677e-05,
"loss": 6.6134,
"step": 44
},
{
"epoch": 0.007293650472061266,
"grad_norm": 8.175810813903809,
"learning_rate": 9.185832391312644e-05,
"loss": 6.5496,
"step": 45
},
{
"epoch": 0.007455731593662628,
"grad_norm": 8.738851547241211,
"learning_rate": 9.140044155740101e-05,
"loss": 6.8652,
"step": 46
},
{
"epoch": 0.007617812715263989,
"grad_norm": 9.828368186950684,
"learning_rate": 9.093124073433463e-05,
"loss": 6.7311,
"step": 47
},
{
"epoch": 0.007779893836865351,
"grad_norm": 10.030229568481445,
"learning_rate": 9.045084971874738e-05,
"loss": 6.7401,
"step": 48
},
{
"epoch": 0.007941974958466713,
"grad_norm": 12.767650604248047,
"learning_rate": 8.995939984474624e-05,
"loss": 7.082,
"step": 49
},
{
"epoch": 0.008104056080068074,
"grad_norm": 14.701695442199707,
"learning_rate": 8.945702546981969e-05,
"loss": 5.9265,
"step": 50
},
{
"epoch": 0.008104056080068074,
"eval_loss": 1.5559238195419312,
"eval_runtime": 1031.1317,
"eval_samples_per_second": 10.078,
"eval_steps_per_second": 2.52,
"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": 9.095305596449587e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}