DeepDream2045's picture
Training in progress, step 50, checkpoint
71cdf8c verified
{
"best_metric": 1.1787887811660767,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.11283497884344147,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002256699576868829,
"grad_norm": 2.271334648132324,
"learning_rate": 5e-05,
"loss": 4.2202,
"step": 1
},
{
"epoch": 0.002256699576868829,
"eval_loss": 4.576087951660156,
"eval_runtime": 158.443,
"eval_samples_per_second": 18.84,
"eval_steps_per_second": 2.36,
"step": 1
},
{
"epoch": 0.004513399153737658,
"grad_norm": 2.273876428604126,
"learning_rate": 0.0001,
"loss": 4.3923,
"step": 2
},
{
"epoch": 0.006770098730606488,
"grad_norm": 2.266083002090454,
"learning_rate": 9.989294616193017e-05,
"loss": 3.9386,
"step": 3
},
{
"epoch": 0.009026798307475317,
"grad_norm": 2.0494344234466553,
"learning_rate": 9.957224306869053e-05,
"loss": 3.7907,
"step": 4
},
{
"epoch": 0.011283497884344146,
"grad_norm": 1.8673242330551147,
"learning_rate": 9.903926402016153e-05,
"loss": 3.0067,
"step": 5
},
{
"epoch": 0.013540197461212976,
"grad_norm": 2.201956272125244,
"learning_rate": 9.829629131445342e-05,
"loss": 2.9125,
"step": 6
},
{
"epoch": 0.015796897038081806,
"grad_norm": 2.2601053714752197,
"learning_rate": 9.73465064747553e-05,
"loss": 2.3351,
"step": 7
},
{
"epoch": 0.018053596614950634,
"grad_norm": 2.554874897003174,
"learning_rate": 9.619397662556435e-05,
"loss": 1.7008,
"step": 8
},
{
"epoch": 0.020310296191819465,
"grad_norm": 1.5852960348129272,
"learning_rate": 9.484363707663442e-05,
"loss": 1.3767,
"step": 9
},
{
"epoch": 0.022566995768688293,
"grad_norm": 2.140584945678711,
"learning_rate": 9.330127018922194e-05,
"loss": 1.5513,
"step": 10
},
{
"epoch": 0.024823695345557124,
"grad_norm": 1.555256724357605,
"learning_rate": 9.157348061512727e-05,
"loss": 1.4423,
"step": 11
},
{
"epoch": 0.027080394922425952,
"grad_norm": 1.5355030298233032,
"learning_rate": 8.966766701456177e-05,
"loss": 1.5434,
"step": 12
},
{
"epoch": 0.02933709449929478,
"grad_norm": 1.7982749938964844,
"learning_rate": 8.759199037394887e-05,
"loss": 2.2996,
"step": 13
},
{
"epoch": 0.03159379407616361,
"grad_norm": 1.8775335550308228,
"learning_rate": 8.535533905932738e-05,
"loss": 1.6647,
"step": 14
},
{
"epoch": 0.03385049365303244,
"grad_norm": 1.493929386138916,
"learning_rate": 8.296729075500344e-05,
"loss": 1.6185,
"step": 15
},
{
"epoch": 0.03610719322990127,
"grad_norm": 1.1012654304504395,
"learning_rate": 8.043807145043604e-05,
"loss": 1.3674,
"step": 16
},
{
"epoch": 0.0383638928067701,
"grad_norm": 1.2567514181137085,
"learning_rate": 7.777851165098012e-05,
"loss": 1.3151,
"step": 17
},
{
"epoch": 0.04062059238363893,
"grad_norm": 1.2022745609283447,
"learning_rate": 7.500000000000001e-05,
"loss": 1.4862,
"step": 18
},
{
"epoch": 0.042877291960507755,
"grad_norm": 1.0103505849838257,
"learning_rate": 7.211443451095007e-05,
"loss": 1.2479,
"step": 19
},
{
"epoch": 0.045133991537376586,
"grad_norm": 1.2014374732971191,
"learning_rate": 6.91341716182545e-05,
"loss": 1.1638,
"step": 20
},
{
"epoch": 0.04739069111424542,
"grad_norm": 1.050091028213501,
"learning_rate": 6.607197326515808e-05,
"loss": 1.0463,
"step": 21
},
{
"epoch": 0.04964739069111425,
"grad_norm": 1.0348970890045166,
"learning_rate": 6.294095225512603e-05,
"loss": 1.076,
"step": 22
},
{
"epoch": 0.05190409026798307,
"grad_norm": 1.0035017728805542,
"learning_rate": 5.9754516100806423e-05,
"loss": 1.1667,
"step": 23
},
{
"epoch": 0.054160789844851905,
"grad_norm": 0.9342150092124939,
"learning_rate": 5.6526309611002594e-05,
"loss": 1.3069,
"step": 24
},
{
"epoch": 0.056417489421720736,
"grad_norm": 1.2166595458984375,
"learning_rate": 5.327015646150716e-05,
"loss": 1.906,
"step": 25
},
{
"epoch": 0.056417489421720736,
"eval_loss": 1.2338190078735352,
"eval_runtime": 159.0674,
"eval_samples_per_second": 18.766,
"eval_steps_per_second": 2.351,
"step": 25
},
{
"epoch": 0.05867418899858956,
"grad_norm": 1.260665774345398,
"learning_rate": 5e-05,
"loss": 1.5699,
"step": 26
},
{
"epoch": 0.06093088857545839,
"grad_norm": 1.053236961364746,
"learning_rate": 4.6729843538492847e-05,
"loss": 1.4044,
"step": 27
},
{
"epoch": 0.06318758815232722,
"grad_norm": 1.0598998069763184,
"learning_rate": 4.347369038899744e-05,
"loss": 1.2834,
"step": 28
},
{
"epoch": 0.06544428772919605,
"grad_norm": 1.0999733209609985,
"learning_rate": 4.0245483899193595e-05,
"loss": 1.2846,
"step": 29
},
{
"epoch": 0.06770098730606489,
"grad_norm": 0.8835371136665344,
"learning_rate": 3.705904774487396e-05,
"loss": 1.0156,
"step": 30
},
{
"epoch": 0.0699576868829337,
"grad_norm": 0.9244187474250793,
"learning_rate": 3.392802673484193e-05,
"loss": 0.9705,
"step": 31
},
{
"epoch": 0.07221438645980253,
"grad_norm": 0.8493463397026062,
"learning_rate": 3.086582838174551e-05,
"loss": 0.9542,
"step": 32
},
{
"epoch": 0.07447108603667137,
"grad_norm": 0.7597554922103882,
"learning_rate": 2.7885565489049946e-05,
"loss": 1.1698,
"step": 33
},
{
"epoch": 0.0767277856135402,
"grad_norm": 0.7776671051979065,
"learning_rate": 2.500000000000001e-05,
"loss": 1.0893,
"step": 34
},
{
"epoch": 0.07898448519040903,
"grad_norm": 0.852249026298523,
"learning_rate": 2.2221488349019903e-05,
"loss": 1.0481,
"step": 35
},
{
"epoch": 0.08124118476727786,
"grad_norm": 0.7738817930221558,
"learning_rate": 1.9561928549563968e-05,
"loss": 0.9636,
"step": 36
},
{
"epoch": 0.08349788434414669,
"grad_norm": 0.9981914162635803,
"learning_rate": 1.703270924499656e-05,
"loss": 1.436,
"step": 37
},
{
"epoch": 0.08575458392101551,
"grad_norm": 1.1209708452224731,
"learning_rate": 1.4644660940672627e-05,
"loss": 1.9783,
"step": 38
},
{
"epoch": 0.08801128349788434,
"grad_norm": 0.7976085543632507,
"learning_rate": 1.2408009626051137e-05,
"loss": 1.3116,
"step": 39
},
{
"epoch": 0.09026798307475317,
"grad_norm": 0.8048446774482727,
"learning_rate": 1.0332332985438248e-05,
"loss": 1.2387,
"step": 40
},
{
"epoch": 0.092524682651622,
"grad_norm": 0.833931028842926,
"learning_rate": 8.426519384872733e-06,
"loss": 1.1499,
"step": 41
},
{
"epoch": 0.09478138222849083,
"grad_norm": 0.9155600666999817,
"learning_rate": 6.698729810778065e-06,
"loss": 1.154,
"step": 42
},
{
"epoch": 0.09703808180535967,
"grad_norm": 0.9045965671539307,
"learning_rate": 5.156362923365588e-06,
"loss": 1.2816,
"step": 43
},
{
"epoch": 0.0992947813822285,
"grad_norm": 0.9049792289733887,
"learning_rate": 3.8060233744356633e-06,
"loss": 1.145,
"step": 44
},
{
"epoch": 0.10155148095909731,
"grad_norm": 0.7562306523323059,
"learning_rate": 2.653493525244721e-06,
"loss": 0.95,
"step": 45
},
{
"epoch": 0.10380818053596615,
"grad_norm": 0.7610027194023132,
"learning_rate": 1.70370868554659e-06,
"loss": 1.0929,
"step": 46
},
{
"epoch": 0.10606488011283498,
"grad_norm": 0.7419886589050293,
"learning_rate": 9.607359798384785e-07,
"loss": 1.1537,
"step": 47
},
{
"epoch": 0.10832157968970381,
"grad_norm": 0.8622953295707703,
"learning_rate": 4.277569313094809e-07,
"loss": 1.0779,
"step": 48
},
{
"epoch": 0.11057827926657264,
"grad_norm": 0.8365002274513245,
"learning_rate": 1.0705383806982606e-07,
"loss": 1.3221,
"step": 49
},
{
"epoch": 0.11283497884344147,
"grad_norm": 0.9962946772575378,
"learning_rate": 0.0,
"loss": 1.764,
"step": 50
},
{
"epoch": 0.11283497884344147,
"eval_loss": 1.1787887811660767,
"eval_runtime": 158.973,
"eval_samples_per_second": 18.777,
"eval_steps_per_second": 2.353,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"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": true
},
"attributes": {}
}
},
"total_flos": 1.1118514725443338e+18,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}