aleegis10's picture
Training in progress, step 50, checkpoint
5ed8ab4 verified
raw
history blame
9.95 kB
{
"best_metric": 0.2936895191669464,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.011852554225435581,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00023705108450871164,
"grad_norm": 45.60728073120117,
"learning_rate": 1e-05,
"loss": 7.2208,
"step": 1
},
{
"epoch": 0.00023705108450871164,
"eval_loss": 2.17527437210083,
"eval_runtime": 512.9389,
"eval_samples_per_second": 13.852,
"eval_steps_per_second": 3.464,
"step": 1
},
{
"epoch": 0.0004741021690174233,
"grad_norm": 39.479434967041016,
"learning_rate": 2e-05,
"loss": 5.9475,
"step": 2
},
{
"epoch": 0.0007111532535261348,
"grad_norm": 43.14913558959961,
"learning_rate": 3e-05,
"loss": 6.5429,
"step": 3
},
{
"epoch": 0.0009482043380348466,
"grad_norm": 38.2624626159668,
"learning_rate": 4e-05,
"loss": 4.6751,
"step": 4
},
{
"epoch": 0.0011852554225435582,
"grad_norm": 37.59519577026367,
"learning_rate": 5e-05,
"loss": 3.7288,
"step": 5
},
{
"epoch": 0.0014223065070522697,
"grad_norm": 24.643327713012695,
"learning_rate": 6e-05,
"loss": 2.9582,
"step": 6
},
{
"epoch": 0.0016593575915609814,
"grad_norm": 20.228885650634766,
"learning_rate": 7e-05,
"loss": 2.3467,
"step": 7
},
{
"epoch": 0.001896408676069693,
"grad_norm": 15.846456527709961,
"learning_rate": 8e-05,
"loss": 1.4973,
"step": 8
},
{
"epoch": 0.002133459760578405,
"grad_norm": 14.652710914611816,
"learning_rate": 9e-05,
"loss": 1.5795,
"step": 9
},
{
"epoch": 0.0023705108450871163,
"grad_norm": 22.30735969543457,
"learning_rate": 0.0001,
"loss": 1.6046,
"step": 10
},
{
"epoch": 0.002607561929595828,
"grad_norm": 20.14059066772461,
"learning_rate": 9.999316524962345e-05,
"loss": 2.1066,
"step": 11
},
{
"epoch": 0.0028446130141045393,
"grad_norm": 14.741179466247559,
"learning_rate": 9.997266286704631e-05,
"loss": 1.6849,
"step": 12
},
{
"epoch": 0.0030816640986132513,
"grad_norm": 15.680244445800781,
"learning_rate": 9.993849845741524e-05,
"loss": 1.6815,
"step": 13
},
{
"epoch": 0.0033187151831219628,
"grad_norm": 11.952381134033203,
"learning_rate": 9.989068136093873e-05,
"loss": 1.6821,
"step": 14
},
{
"epoch": 0.0035557662676306743,
"grad_norm": 7.957185745239258,
"learning_rate": 9.98292246503335e-05,
"loss": 0.8576,
"step": 15
},
{
"epoch": 0.003792817352139386,
"grad_norm": 8.777189254760742,
"learning_rate": 9.975414512725057e-05,
"loss": 1.4227,
"step": 16
},
{
"epoch": 0.004029868436648098,
"grad_norm": 15.89772891998291,
"learning_rate": 9.966546331768191e-05,
"loss": 1.3271,
"step": 17
},
{
"epoch": 0.00426691952115681,
"grad_norm": 13.817143440246582,
"learning_rate": 9.956320346634876e-05,
"loss": 1.7801,
"step": 18
},
{
"epoch": 0.004503970605665521,
"grad_norm": 15.342754364013672,
"learning_rate": 9.944739353007344e-05,
"loss": 1.3992,
"step": 19
},
{
"epoch": 0.004741021690174233,
"grad_norm": 9.978917121887207,
"learning_rate": 9.931806517013612e-05,
"loss": 1.1139,
"step": 20
},
{
"epoch": 0.004978072774682945,
"grad_norm": 10.110090255737305,
"learning_rate": 9.917525374361912e-05,
"loss": 1.3036,
"step": 21
},
{
"epoch": 0.005215123859191656,
"grad_norm": 12.066587448120117,
"learning_rate": 9.901899829374047e-05,
"loss": 1.3331,
"step": 22
},
{
"epoch": 0.005452174943700368,
"grad_norm": 15.906118392944336,
"learning_rate": 9.884934153917997e-05,
"loss": 1.6102,
"step": 23
},
{
"epoch": 0.005689226028209079,
"grad_norm": 12.463726997375488,
"learning_rate": 9.86663298624003e-05,
"loss": 1.4063,
"step": 24
},
{
"epoch": 0.005926277112717791,
"grad_norm": 10.469868659973145,
"learning_rate": 9.847001329696653e-05,
"loss": 1.4652,
"step": 25
},
{
"epoch": 0.0061633281972265025,
"grad_norm": 8.34838581085205,
"learning_rate": 9.826044551386744e-05,
"loss": 1.0534,
"step": 26
},
{
"epoch": 0.006400379281735214,
"grad_norm": 7.536215782165527,
"learning_rate": 9.803768380684242e-05,
"loss": 1.2063,
"step": 27
},
{
"epoch": 0.0066374303662439255,
"grad_norm": 7.370880603790283,
"learning_rate": 9.780178907671789e-05,
"loss": 0.9058,
"step": 28
},
{
"epoch": 0.0068744814507526375,
"grad_norm": 9.6860933303833,
"learning_rate": 9.755282581475769e-05,
"loss": 1.1714,
"step": 29
},
{
"epoch": 0.0071115325352613485,
"grad_norm": 13.223746299743652,
"learning_rate": 9.729086208503174e-05,
"loss": 1.2399,
"step": 30
},
{
"epoch": 0.0073485836197700605,
"grad_norm": 10.730929374694824,
"learning_rate": 9.701596950580806e-05,
"loss": 1.1303,
"step": 31
},
{
"epoch": 0.007585634704278772,
"grad_norm": 6.884200096130371,
"learning_rate": 9.672822322997305e-05,
"loss": 0.9594,
"step": 32
},
{
"epoch": 0.007822685788787484,
"grad_norm": 11.763479232788086,
"learning_rate": 9.642770192448536e-05,
"loss": 1.6842,
"step": 33
},
{
"epoch": 0.008059736873296195,
"grad_norm": 10.257864952087402,
"learning_rate": 9.611448774886924e-05,
"loss": 1.4945,
"step": 34
},
{
"epoch": 0.008296787957804906,
"grad_norm": 13.270899772644043,
"learning_rate": 9.578866633275288e-05,
"loss": 1.2097,
"step": 35
},
{
"epoch": 0.00853383904231362,
"grad_norm": 11.5889253616333,
"learning_rate": 9.545032675245813e-05,
"loss": 1.3319,
"step": 36
},
{
"epoch": 0.00877089012682233,
"grad_norm": 11.069531440734863,
"learning_rate": 9.509956150664796e-05,
"loss": 1.564,
"step": 37
},
{
"epoch": 0.009007941211331041,
"grad_norm": 9.586097717285156,
"learning_rate": 9.473646649103818e-05,
"loss": 1.5775,
"step": 38
},
{
"epoch": 0.009244992295839754,
"grad_norm": 9.339739799499512,
"learning_rate": 9.43611409721806e-05,
"loss": 1.2764,
"step": 39
},
{
"epoch": 0.009482043380348465,
"grad_norm": 8.734746932983398,
"learning_rate": 9.397368756032445e-05,
"loss": 1.3781,
"step": 40
},
{
"epoch": 0.009719094464857176,
"grad_norm": 11.1151704788208,
"learning_rate": 9.357421218136386e-05,
"loss": 1.3118,
"step": 41
},
{
"epoch": 0.00995614554936589,
"grad_norm": 10.246061325073242,
"learning_rate": 9.316282404787871e-05,
"loss": 1.5707,
"step": 42
},
{
"epoch": 0.0101931966338746,
"grad_norm": 12.3263521194458,
"learning_rate": 9.273963562927695e-05,
"loss": 1.723,
"step": 43
},
{
"epoch": 0.010430247718383311,
"grad_norm": 8.47308349609375,
"learning_rate": 9.230476262104677e-05,
"loss": 1.1802,
"step": 44
},
{
"epoch": 0.010667298802892022,
"grad_norm": 8.325446128845215,
"learning_rate": 9.185832391312644e-05,
"loss": 1.1147,
"step": 45
},
{
"epoch": 0.010904349887400735,
"grad_norm": 12.091687202453613,
"learning_rate": 9.140044155740101e-05,
"loss": 1.0594,
"step": 46
},
{
"epoch": 0.011141400971909446,
"grad_norm": 7.746819019317627,
"learning_rate": 9.093124073433463e-05,
"loss": 0.797,
"step": 47
},
{
"epoch": 0.011378452056418157,
"grad_norm": 9.007611274719238,
"learning_rate": 9.045084971874738e-05,
"loss": 0.9117,
"step": 48
},
{
"epoch": 0.01161550314092687,
"grad_norm": 12.215007781982422,
"learning_rate": 8.995939984474624e-05,
"loss": 1.7131,
"step": 49
},
{
"epoch": 0.011852554225435581,
"grad_norm": 14.961793899536133,
"learning_rate": 8.945702546981969e-05,
"loss": 1.4138,
"step": 50
},
{
"epoch": 0.011852554225435581,
"eval_loss": 0.2936895191669464,
"eval_runtime": 518.4074,
"eval_samples_per_second": 13.705,
"eval_steps_per_second": 3.428,
"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": 7.190764995162931e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}