aleegis12's picture
Training in progress, step 50, checkpoint
17fcc7d verified
raw
history blame
10 kB
{
"best_metric": 11.5,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.005646367973800853,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00011292735947601705,
"grad_norm": 3.614788147388026e-05,
"learning_rate": 1e-05,
"loss": 46.0,
"step": 1
},
{
"epoch": 0.00011292735947601705,
"eval_loss": 11.5,
"eval_runtime": 67.3019,
"eval_samples_per_second": 221.613,
"eval_steps_per_second": 55.407,
"step": 1
},
{
"epoch": 0.0002258547189520341,
"grad_norm": 3.123121496173553e-05,
"learning_rate": 2e-05,
"loss": 46.0,
"step": 2
},
{
"epoch": 0.00033878207842805115,
"grad_norm": 2.8957145332242362e-05,
"learning_rate": 3e-05,
"loss": 46.0,
"step": 3
},
{
"epoch": 0.0004517094379040682,
"grad_norm": 3.201327854185365e-05,
"learning_rate": 4e-05,
"loss": 46.0,
"step": 4
},
{
"epoch": 0.0005646367973800852,
"grad_norm": 3.30324619426392e-05,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 5
},
{
"epoch": 0.0006775641568561023,
"grad_norm": 1.9614395569078624e-05,
"learning_rate": 6e-05,
"loss": 46.0,
"step": 6
},
{
"epoch": 0.0007904915163321194,
"grad_norm": 2.3348015020019375e-05,
"learning_rate": 7e-05,
"loss": 46.0,
"step": 7
},
{
"epoch": 0.0009034188758081364,
"grad_norm": 3.713077967404388e-05,
"learning_rate": 8e-05,
"loss": 46.0,
"step": 8
},
{
"epoch": 0.0010163462352841535,
"grad_norm": 2.811581907735672e-05,
"learning_rate": 9e-05,
"loss": 46.0,
"step": 9
},
{
"epoch": 0.0011292735947601704,
"grad_norm": 2.1962290702504106e-05,
"learning_rate": 0.0001,
"loss": 46.0,
"step": 10
},
{
"epoch": 0.0012422009542361876,
"grad_norm": 3.7259764212649316e-05,
"learning_rate": 9.999316524962345e-05,
"loss": 46.0,
"step": 11
},
{
"epoch": 0.0013551283137122046,
"grad_norm": 1.6783784303697757e-05,
"learning_rate": 9.997266286704631e-05,
"loss": 46.0,
"step": 12
},
{
"epoch": 0.0014680556731882218,
"grad_norm": 4.028781768283807e-05,
"learning_rate": 9.993849845741524e-05,
"loss": 46.0,
"step": 13
},
{
"epoch": 0.0015809830326642387,
"grad_norm": 3.867182749672793e-05,
"learning_rate": 9.989068136093873e-05,
"loss": 46.0,
"step": 14
},
{
"epoch": 0.0016939103921402557,
"grad_norm": 3.935163840651512e-05,
"learning_rate": 9.98292246503335e-05,
"loss": 46.0,
"step": 15
},
{
"epoch": 0.0018068377516162728,
"grad_norm": 3.734438359970227e-05,
"learning_rate": 9.975414512725057e-05,
"loss": 46.0,
"step": 16
},
{
"epoch": 0.0019197651110922898,
"grad_norm": 3.779438338824548e-05,
"learning_rate": 9.966546331768191e-05,
"loss": 46.0,
"step": 17
},
{
"epoch": 0.002032692470568307,
"grad_norm": 3.9759692299412563e-05,
"learning_rate": 9.956320346634876e-05,
"loss": 46.0,
"step": 18
},
{
"epoch": 0.002145619830044324,
"grad_norm": 5.707326272386126e-05,
"learning_rate": 9.944739353007344e-05,
"loss": 46.0,
"step": 19
},
{
"epoch": 0.002258547189520341,
"grad_norm": 4.848073876928538e-05,
"learning_rate": 9.931806517013612e-05,
"loss": 46.0,
"step": 20
},
{
"epoch": 0.002371474548996358,
"grad_norm": 4.8901285481406376e-05,
"learning_rate": 9.917525374361912e-05,
"loss": 46.0,
"step": 21
},
{
"epoch": 0.0024844019084723752,
"grad_norm": 5.652082109008916e-05,
"learning_rate": 9.901899829374047e-05,
"loss": 46.0,
"step": 22
},
{
"epoch": 0.002597329267948392,
"grad_norm": 9.701135422801599e-05,
"learning_rate": 9.884934153917997e-05,
"loss": 46.0,
"step": 23
},
{
"epoch": 0.002710256627424409,
"grad_norm": 5.8126366639044136e-05,
"learning_rate": 9.86663298624003e-05,
"loss": 46.0,
"step": 24
},
{
"epoch": 0.0028231839869004263,
"grad_norm": 6.462896999437362e-05,
"learning_rate": 9.847001329696653e-05,
"loss": 46.0,
"step": 25
},
{
"epoch": 0.0029361113463764435,
"grad_norm": 5.241742110229097e-05,
"learning_rate": 9.826044551386744e-05,
"loss": 46.0,
"step": 26
},
{
"epoch": 0.0030490387058524603,
"grad_norm": 5.914594657951966e-05,
"learning_rate": 9.803768380684242e-05,
"loss": 46.0,
"step": 27
},
{
"epoch": 0.0031619660653284774,
"grad_norm": 5.9205271099926904e-05,
"learning_rate": 9.780178907671789e-05,
"loss": 46.0,
"step": 28
},
{
"epoch": 0.0032748934248044946,
"grad_norm": 8.066185546340421e-05,
"learning_rate": 9.755282581475769e-05,
"loss": 46.0,
"step": 29
},
{
"epoch": 0.0033878207842805113,
"grad_norm": 8.380277722608298e-05,
"learning_rate": 9.729086208503174e-05,
"loss": 46.0,
"step": 30
},
{
"epoch": 0.0035007481437565285,
"grad_norm": 5.8457095292396843e-05,
"learning_rate": 9.701596950580806e-05,
"loss": 46.0,
"step": 31
},
{
"epoch": 0.0036136755032325457,
"grad_norm": 8.569472265662625e-05,
"learning_rate": 9.672822322997305e-05,
"loss": 46.0,
"step": 32
},
{
"epoch": 0.003726602862708563,
"grad_norm": 8.675931894686073e-05,
"learning_rate": 9.642770192448536e-05,
"loss": 46.0,
"step": 33
},
{
"epoch": 0.0038395302221845796,
"grad_norm": 6.944208143977448e-05,
"learning_rate": 9.611448774886924e-05,
"loss": 46.0,
"step": 34
},
{
"epoch": 0.003952457581660597,
"grad_norm": 6.330825272016227e-05,
"learning_rate": 9.578866633275288e-05,
"loss": 46.0,
"step": 35
},
{
"epoch": 0.004065384941136614,
"grad_norm": 8.716557931620628e-05,
"learning_rate": 9.545032675245813e-05,
"loss": 46.0,
"step": 36
},
{
"epoch": 0.004178312300612631,
"grad_norm": 8.742913632886484e-05,
"learning_rate": 9.509956150664796e-05,
"loss": 46.0,
"step": 37
},
{
"epoch": 0.004291239660088648,
"grad_norm": 8.630647062091157e-05,
"learning_rate": 9.473646649103818e-05,
"loss": 46.0,
"step": 38
},
{
"epoch": 0.004404167019564665,
"grad_norm": 0.00016223177954088897,
"learning_rate": 9.43611409721806e-05,
"loss": 46.0,
"step": 39
},
{
"epoch": 0.004517094379040682,
"grad_norm": 0.00011058787640649825,
"learning_rate": 9.397368756032445e-05,
"loss": 46.0,
"step": 40
},
{
"epoch": 0.004630021738516699,
"grad_norm": 8.163695019902661e-05,
"learning_rate": 9.357421218136386e-05,
"loss": 46.0,
"step": 41
},
{
"epoch": 0.004742949097992716,
"grad_norm": 0.00010987564746756107,
"learning_rate": 9.316282404787871e-05,
"loss": 46.0,
"step": 42
},
{
"epoch": 0.004855876457468733,
"grad_norm": 0.0001059857604559511,
"learning_rate": 9.273963562927695e-05,
"loss": 46.0,
"step": 43
},
{
"epoch": 0.0049688038169447505,
"grad_norm": 9.816615784075111e-05,
"learning_rate": 9.230476262104677e-05,
"loss": 46.0,
"step": 44
},
{
"epoch": 0.005081731176420768,
"grad_norm": 0.00014900887617841363,
"learning_rate": 9.185832391312644e-05,
"loss": 46.0,
"step": 45
},
{
"epoch": 0.005194658535896784,
"grad_norm": 0.00011268858361290768,
"learning_rate": 9.140044155740101e-05,
"loss": 46.0,
"step": 46
},
{
"epoch": 0.005307585895372801,
"grad_norm": 7.1711816417519e-05,
"learning_rate": 9.093124073433463e-05,
"loss": 46.0,
"step": 47
},
{
"epoch": 0.005420513254848818,
"grad_norm": 9.647711704019457e-05,
"learning_rate": 9.045084971874738e-05,
"loss": 46.0,
"step": 48
},
{
"epoch": 0.0055334406143248355,
"grad_norm": 0.00010786413622554392,
"learning_rate": 8.995939984474624e-05,
"loss": 46.0,
"step": 49
},
{
"epoch": 0.005646367973800853,
"grad_norm": 0.00016665902512613684,
"learning_rate": 8.945702546981969e-05,
"loss": 46.0,
"step": 50
},
{
"epoch": 0.005646367973800853,
"eval_loss": 11.5,
"eval_runtime": 67.5491,
"eval_samples_per_second": 220.802,
"eval_steps_per_second": 55.204,
"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
}