prxy5604's picture
Training in progress, step 50, checkpoint
a13a15d verified
raw
history blame
9.97 kB
{
"best_metric": 0.7931326031684875,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.035143208574942894,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0007028641714988579,
"grad_norm": 3.985713005065918,
"learning_rate": 3.3333333333333333e-06,
"loss": 0.9101,
"step": 1
},
{
"epoch": 0.0007028641714988579,
"eval_loss": 1.2333168983459473,
"eval_runtime": 329.6451,
"eval_samples_per_second": 7.271,
"eval_steps_per_second": 3.637,
"step": 1
},
{
"epoch": 0.0014057283429977157,
"grad_norm": 3.467237710952759,
"learning_rate": 6.666666666666667e-06,
"loss": 0.8645,
"step": 2
},
{
"epoch": 0.0021085925144965737,
"grad_norm": 4.0260396003723145,
"learning_rate": 1e-05,
"loss": 0.8497,
"step": 3
},
{
"epoch": 0.0028114566859954314,
"grad_norm": 3.5175299644470215,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.8297,
"step": 4
},
{
"epoch": 0.003514320857494289,
"grad_norm": 3.0513343811035156,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.9402,
"step": 5
},
{
"epoch": 0.004217185028993147,
"grad_norm": 2.0091588497161865,
"learning_rate": 2e-05,
"loss": 0.9226,
"step": 6
},
{
"epoch": 0.004920049200492005,
"grad_norm": 1.5375112295150757,
"learning_rate": 2.3333333333333336e-05,
"loss": 0.8269,
"step": 7
},
{
"epoch": 0.005622913371990863,
"grad_norm": 1.1322797536849976,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.8076,
"step": 8
},
{
"epoch": 0.0063257775434897206,
"grad_norm": 0.6666527390480042,
"learning_rate": 3e-05,
"loss": 0.7947,
"step": 9
},
{
"epoch": 0.007028641714988578,
"grad_norm": 0.49241289496421814,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.8479,
"step": 10
},
{
"epoch": 0.007731505886487436,
"grad_norm": 0.38597196340560913,
"learning_rate": 3.6666666666666666e-05,
"loss": 0.8584,
"step": 11
},
{
"epoch": 0.008434370057986295,
"grad_norm": 0.38379645347595215,
"learning_rate": 4e-05,
"loss": 0.9209,
"step": 12
},
{
"epoch": 0.009137234229485152,
"grad_norm": 0.3469511866569519,
"learning_rate": 4.3333333333333334e-05,
"loss": 0.9364,
"step": 13
},
{
"epoch": 0.00984009840098401,
"grad_norm": 0.37990155816078186,
"learning_rate": 4.666666666666667e-05,
"loss": 0.9295,
"step": 14
},
{
"epoch": 0.010542962572482868,
"grad_norm": 0.39598187804222107,
"learning_rate": 5e-05,
"loss": 0.98,
"step": 15
},
{
"epoch": 0.011245826743981726,
"grad_norm": 0.5101740956306458,
"learning_rate": 5.333333333333333e-05,
"loss": 0.869,
"step": 16
},
{
"epoch": 0.011948690915480583,
"grad_norm": 0.4814358651638031,
"learning_rate": 5.666666666666667e-05,
"loss": 0.8725,
"step": 17
},
{
"epoch": 0.012651555086979441,
"grad_norm": 0.4803312420845032,
"learning_rate": 6e-05,
"loss": 0.8974,
"step": 18
},
{
"epoch": 0.013354419258478299,
"grad_norm": 0.5351816415786743,
"learning_rate": 6.333333333333333e-05,
"loss": 0.8547,
"step": 19
},
{
"epoch": 0.014057283429977157,
"grad_norm": 0.3521532416343689,
"learning_rate": 6.666666666666667e-05,
"loss": 0.8167,
"step": 20
},
{
"epoch": 0.014760147601476014,
"grad_norm": 0.3495865762233734,
"learning_rate": 7e-05,
"loss": 0.8601,
"step": 21
},
{
"epoch": 0.015463011772974872,
"grad_norm": 0.32179948687553406,
"learning_rate": 7.333333333333333e-05,
"loss": 0.9306,
"step": 22
},
{
"epoch": 0.01616587594447373,
"grad_norm": 0.31504809856414795,
"learning_rate": 7.666666666666667e-05,
"loss": 0.9073,
"step": 23
},
{
"epoch": 0.01686874011597259,
"grad_norm": 0.29273295402526855,
"learning_rate": 8e-05,
"loss": 0.9163,
"step": 24
},
{
"epoch": 0.017571604287471447,
"grad_norm": 0.29041165113449097,
"learning_rate": 8.333333333333334e-05,
"loss": 0.9695,
"step": 25
},
{
"epoch": 0.018274468458970305,
"grad_norm": 0.27887824177742004,
"learning_rate": 8.666666666666667e-05,
"loss": 0.9974,
"step": 26
},
{
"epoch": 0.018977332630469163,
"grad_norm": 0.2727268934249878,
"learning_rate": 9e-05,
"loss": 0.9174,
"step": 27
},
{
"epoch": 0.01968019680196802,
"grad_norm": 0.32749247550964355,
"learning_rate": 9.333333333333334e-05,
"loss": 1.0012,
"step": 28
},
{
"epoch": 0.020383060973466878,
"grad_norm": 0.3218176066875458,
"learning_rate": 9.666666666666667e-05,
"loss": 0.9661,
"step": 29
},
{
"epoch": 0.021085925144965736,
"grad_norm": 0.29646337032318115,
"learning_rate": 0.0001,
"loss": 0.9915,
"step": 30
},
{
"epoch": 0.021788789316464593,
"grad_norm": 0.34624406695365906,
"learning_rate": 9.999146252290264e-05,
"loss": 0.8692,
"step": 31
},
{
"epoch": 0.02249165348796345,
"grad_norm": 0.768728494644165,
"learning_rate": 9.996585300715116e-05,
"loss": 0.8271,
"step": 32
},
{
"epoch": 0.02319451765946231,
"grad_norm": 0.3600139617919922,
"learning_rate": 9.99231801983717e-05,
"loss": 0.887,
"step": 33
},
{
"epoch": 0.023897381830961167,
"grad_norm": 0.4439491033554077,
"learning_rate": 9.986345866928941e-05,
"loss": 0.8287,
"step": 34
},
{
"epoch": 0.024600246002460024,
"grad_norm": 0.5002362132072449,
"learning_rate": 9.978670881475172e-05,
"loss": 1.0547,
"step": 35
},
{
"epoch": 0.025303110173958882,
"grad_norm": 0.36719855666160583,
"learning_rate": 9.96929568447637e-05,
"loss": 0.9393,
"step": 36
},
{
"epoch": 0.02600597434545774,
"grad_norm": 0.4160923659801483,
"learning_rate": 9.958223477553714e-05,
"loss": 0.985,
"step": 37
},
{
"epoch": 0.026708838516956598,
"grad_norm": 0.48960939049720764,
"learning_rate": 9.94545804185573e-05,
"loss": 0.9871,
"step": 38
},
{
"epoch": 0.027411702688455455,
"grad_norm": 0.406502366065979,
"learning_rate": 9.931003736767013e-05,
"loss": 0.9413,
"step": 39
},
{
"epoch": 0.028114566859954313,
"grad_norm": 0.3597155511379242,
"learning_rate": 9.91486549841951e-05,
"loss": 0.9638,
"step": 40
},
{
"epoch": 0.02881743103145317,
"grad_norm": 0.3127121925354004,
"learning_rate": 9.89704883800683e-05,
"loss": 0.962,
"step": 41
},
{
"epoch": 0.02952029520295203,
"grad_norm": 0.3300633430480957,
"learning_rate": 9.877559839902184e-05,
"loss": 0.9166,
"step": 42
},
{
"epoch": 0.030223159374450886,
"grad_norm": 0.3021150827407837,
"learning_rate": 9.85640515958057e-05,
"loss": 0.8592,
"step": 43
},
{
"epoch": 0.030926023545949744,
"grad_norm": 0.33230969309806824,
"learning_rate": 9.833592021345937e-05,
"loss": 0.8466,
"step": 44
},
{
"epoch": 0.0316288877174486,
"grad_norm": 0.3447709381580353,
"learning_rate": 9.809128215864097e-05,
"loss": 0.8761,
"step": 45
},
{
"epoch": 0.03233175188894746,
"grad_norm": 0.3439708948135376,
"learning_rate": 9.783022097502204e-05,
"loss": 0.8295,
"step": 46
},
{
"epoch": 0.03303461606044632,
"grad_norm": 0.3578321933746338,
"learning_rate": 9.755282581475769e-05,
"loss": 0.8659,
"step": 47
},
{
"epoch": 0.03373748023194518,
"grad_norm": 0.4063121974468231,
"learning_rate": 9.725919140804099e-05,
"loss": 0.9674,
"step": 48
},
{
"epoch": 0.03444034440344403,
"grad_norm": 0.41490623354911804,
"learning_rate": 9.694941803075283e-05,
"loss": 0.9979,
"step": 49
},
{
"epoch": 0.035143208574942894,
"grad_norm": 0.6388435959815979,
"learning_rate": 9.662361147021779e-05,
"loss": 1.0037,
"step": 50
},
{
"epoch": 0.035143208574942894,
"eval_loss": 0.7931326031684875,
"eval_runtime": 332.4888,
"eval_samples_per_second": 7.209,
"eval_steps_per_second": 3.606,
"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": 1.22128410083328e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}