aleegis12's picture
Training in progress, step 50, checkpoint
62b0664 verified
raw
history blame
9.96 kB
{
"best_metric": 11.5,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.05178663904712584,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0010357327809425167,
"grad_norm": 0.00022799026919528842,
"learning_rate": 1e-05,
"loss": 46.0,
"step": 1
},
{
"epoch": 0.0010357327809425167,
"eval_loss": 11.5,
"eval_runtime": 7.3616,
"eval_samples_per_second": 220.875,
"eval_steps_per_second": 55.287,
"step": 1
},
{
"epoch": 0.0020714655618850335,
"grad_norm": 0.0003189893322996795,
"learning_rate": 2e-05,
"loss": 46.0,
"step": 2
},
{
"epoch": 0.0031071983428275505,
"grad_norm": 0.00030676033929921687,
"learning_rate": 3e-05,
"loss": 46.0,
"step": 3
},
{
"epoch": 0.004142931123770067,
"grad_norm": 0.0002737623290158808,
"learning_rate": 4e-05,
"loss": 46.0,
"step": 4
},
{
"epoch": 0.005178663904712584,
"grad_norm": 0.00020285221398808062,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 5
},
{
"epoch": 0.006214396685655101,
"grad_norm": 0.00022217661899048835,
"learning_rate": 6e-05,
"loss": 46.0,
"step": 6
},
{
"epoch": 0.0072501294665976174,
"grad_norm": 0.00033399168751202524,
"learning_rate": 7e-05,
"loss": 46.0,
"step": 7
},
{
"epoch": 0.008285862247540134,
"grad_norm": 0.00030777615029364824,
"learning_rate": 8e-05,
"loss": 46.0,
"step": 8
},
{
"epoch": 0.009321595028482652,
"grad_norm": 0.0003417783882468939,
"learning_rate": 9e-05,
"loss": 46.0,
"step": 9
},
{
"epoch": 0.010357327809425169,
"grad_norm": 0.00031432247487828135,
"learning_rate": 0.0001,
"loss": 46.0,
"step": 10
},
{
"epoch": 0.011393060590367685,
"grad_norm": 0.00041850405978038907,
"learning_rate": 9.999316524962345e-05,
"loss": 46.0,
"step": 11
},
{
"epoch": 0.012428793371310202,
"grad_norm": 0.00041423659422434866,
"learning_rate": 9.997266286704631e-05,
"loss": 46.0,
"step": 12
},
{
"epoch": 0.013464526152252718,
"grad_norm": 0.0004432552959769964,
"learning_rate": 9.993849845741524e-05,
"loss": 46.0,
"step": 13
},
{
"epoch": 0.014500258933195235,
"grad_norm": 0.0005180598236620426,
"learning_rate": 9.989068136093873e-05,
"loss": 46.0,
"step": 14
},
{
"epoch": 0.015535991714137753,
"grad_norm": 0.0005157229024916887,
"learning_rate": 9.98292246503335e-05,
"loss": 46.0,
"step": 15
},
{
"epoch": 0.016571724495080268,
"grad_norm": 0.00044451525900512934,
"learning_rate": 9.975414512725057e-05,
"loss": 46.0,
"step": 16
},
{
"epoch": 0.017607457276022784,
"grad_norm": 0.0006396652897819877,
"learning_rate": 9.966546331768191e-05,
"loss": 46.0,
"step": 17
},
{
"epoch": 0.018643190056965304,
"grad_norm": 0.0007490962743759155,
"learning_rate": 9.956320346634876e-05,
"loss": 46.0,
"step": 18
},
{
"epoch": 0.01967892283790782,
"grad_norm": 0.0007005695952102542,
"learning_rate": 9.944739353007344e-05,
"loss": 46.0,
"step": 19
},
{
"epoch": 0.020714655618850338,
"grad_norm": 0.0008960358682088554,
"learning_rate": 9.931806517013612e-05,
"loss": 46.0,
"step": 20
},
{
"epoch": 0.021750388399792854,
"grad_norm": 0.0007888373802416027,
"learning_rate": 9.917525374361912e-05,
"loss": 46.0,
"step": 21
},
{
"epoch": 0.02278612118073537,
"grad_norm": 0.0009302966063842177,
"learning_rate": 9.901899829374047e-05,
"loss": 46.0,
"step": 22
},
{
"epoch": 0.023821853961677887,
"grad_norm": 0.0008068131282925606,
"learning_rate": 9.884934153917997e-05,
"loss": 46.0,
"step": 23
},
{
"epoch": 0.024857586742620404,
"grad_norm": 0.0008582731243222952,
"learning_rate": 9.86663298624003e-05,
"loss": 46.0,
"step": 24
},
{
"epoch": 0.02589331952356292,
"grad_norm": 0.0009067477658390999,
"learning_rate": 9.847001329696653e-05,
"loss": 46.0,
"step": 25
},
{
"epoch": 0.026929052304505437,
"grad_norm": 0.0010893546277657151,
"learning_rate": 9.826044551386744e-05,
"loss": 46.0,
"step": 26
},
{
"epoch": 0.027964785085447953,
"grad_norm": 0.0012705965200439095,
"learning_rate": 9.803768380684242e-05,
"loss": 46.0,
"step": 27
},
{
"epoch": 0.02900051786639047,
"grad_norm": 0.0011961053824052215,
"learning_rate": 9.780178907671789e-05,
"loss": 46.0,
"step": 28
},
{
"epoch": 0.03003625064733299,
"grad_norm": 0.0012201120844110847,
"learning_rate": 9.755282581475769e-05,
"loss": 46.0,
"step": 29
},
{
"epoch": 0.031071983428275506,
"grad_norm": 0.001122495741583407,
"learning_rate": 9.729086208503174e-05,
"loss": 46.0,
"step": 30
},
{
"epoch": 0.03210771620921802,
"grad_norm": 0.0012052401434630156,
"learning_rate": 9.701596950580806e-05,
"loss": 46.0,
"step": 31
},
{
"epoch": 0.033143448990160536,
"grad_norm": 0.0011651843087747693,
"learning_rate": 9.672822322997305e-05,
"loss": 46.0,
"step": 32
},
{
"epoch": 0.03417918177110305,
"grad_norm": 0.001199314254336059,
"learning_rate": 9.642770192448536e-05,
"loss": 46.0,
"step": 33
},
{
"epoch": 0.03521491455204557,
"grad_norm": 0.0013839047169312835,
"learning_rate": 9.611448774886924e-05,
"loss": 46.0,
"step": 34
},
{
"epoch": 0.03625064733298809,
"grad_norm": 0.0015920372679829597,
"learning_rate": 9.578866633275288e-05,
"loss": 46.0,
"step": 35
},
{
"epoch": 0.03728638011393061,
"grad_norm": 0.0015730264130979776,
"learning_rate": 9.545032675245813e-05,
"loss": 46.0,
"step": 36
},
{
"epoch": 0.038322112894873125,
"grad_norm": 0.0017927673179656267,
"learning_rate": 9.509956150664796e-05,
"loss": 46.0,
"step": 37
},
{
"epoch": 0.03935784567581564,
"grad_norm": 0.0019403117476031184,
"learning_rate": 9.473646649103818e-05,
"loss": 46.0,
"step": 38
},
{
"epoch": 0.04039357845675816,
"grad_norm": 0.002109874738380313,
"learning_rate": 9.43611409721806e-05,
"loss": 46.0,
"step": 39
},
{
"epoch": 0.041429311237700675,
"grad_norm": 0.002235481981188059,
"learning_rate": 9.397368756032445e-05,
"loss": 46.0,
"step": 40
},
{
"epoch": 0.04246504401864319,
"grad_norm": 0.002273629419505596,
"learning_rate": 9.357421218136386e-05,
"loss": 46.0,
"step": 41
},
{
"epoch": 0.04350077679958571,
"grad_norm": 0.0018545888597145677,
"learning_rate": 9.316282404787871e-05,
"loss": 46.0,
"step": 42
},
{
"epoch": 0.044536509580528225,
"grad_norm": 0.0020099873654544353,
"learning_rate": 9.273963562927695e-05,
"loss": 46.0,
"step": 43
},
{
"epoch": 0.04557224236147074,
"grad_norm": 0.00231616897508502,
"learning_rate": 9.230476262104677e-05,
"loss": 46.0,
"step": 44
},
{
"epoch": 0.04660797514241326,
"grad_norm": 0.0018780629616230726,
"learning_rate": 9.185832391312644e-05,
"loss": 46.0,
"step": 45
},
{
"epoch": 0.047643707923355774,
"grad_norm": 0.002188002923503518,
"learning_rate": 9.140044155740101e-05,
"loss": 46.0,
"step": 46
},
{
"epoch": 0.04867944070429829,
"grad_norm": 0.0020396774634718895,
"learning_rate": 9.093124073433463e-05,
"loss": 46.0,
"step": 47
},
{
"epoch": 0.04971517348524081,
"grad_norm": 0.002246974967420101,
"learning_rate": 9.045084971874738e-05,
"loss": 46.0,
"step": 48
},
{
"epoch": 0.050750906266183324,
"grad_norm": 0.0026212125085294247,
"learning_rate": 8.995939984474624e-05,
"loss": 46.0,
"step": 49
},
{
"epoch": 0.05178663904712584,
"grad_norm": 0.001977828098461032,
"learning_rate": 8.945702546981969e-05,
"loss": 46.0,
"step": 50
},
{
"epoch": 0.05178663904712584,
"eval_loss": 11.5,
"eval_runtime": 7.3394,
"eval_samples_per_second": 221.544,
"eval_steps_per_second": 55.454,
"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": 8039615692800.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}