{
"best_metric": 1.9384169578552246,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.7117437722419929,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.014234875444839857,
"grad_norm": 4.127208709716797,
"learning_rate": 5e-05,
"loss": 4.7109,
"step": 1
},
{
"epoch": 0.014234875444839857,
"eval_loss": 5.259206295013428,
"eval_runtime": 22.3441,
"eval_samples_per_second": 21.169,
"eval_steps_per_second": 2.685,
"step": 1
},
{
"epoch": 0.028469750889679714,
"grad_norm": 5.206362724304199,
"learning_rate": 0.0001,
"loss": 4.7682,
"step": 2
},
{
"epoch": 0.042704626334519574,
"grad_norm": 8.270171165466309,
"learning_rate": 9.989294616193017e-05,
"loss": 4.599,
"step": 3
},
{
"epoch": 0.05693950177935943,
"grad_norm": 3.9124391078948975,
"learning_rate": 9.957224306869053e-05,
"loss": 4.4156,
"step": 4
},
{
"epoch": 0.0711743772241993,
"grad_norm": 3.400902032852173,
"learning_rate": 9.903926402016153e-05,
"loss": 3.7391,
"step": 5
},
{
"epoch": 0.08540925266903915,
"grad_norm": 4.260780334472656,
"learning_rate": 9.829629131445342e-05,
"loss": 3.0167,
"step": 6
},
{
"epoch": 0.099644128113879,
"grad_norm": 2.086765766143799,
"learning_rate": 9.73465064747553e-05,
"loss": 2.6469,
"step": 7
},
{
"epoch": 0.11387900355871886,
"grad_norm": 1.7398333549499512,
"learning_rate": 9.619397662556435e-05,
"loss": 2.3918,
"step": 8
},
{
"epoch": 0.12811387900355872,
"grad_norm": 2.3132033348083496,
"learning_rate": 9.484363707663442e-05,
"loss": 2.3496,
"step": 9
},
{
"epoch": 0.1423487544483986,
"grad_norm": 1.6994189023971558,
"learning_rate": 9.330127018922194e-05,
"loss": 2.2287,
"step": 10
},
{
"epoch": 0.15658362989323843,
"grad_norm": 1.3915258646011353,
"learning_rate": 9.157348061512727e-05,
"loss": 2.1647,
"step": 11
},
{
"epoch": 0.1708185053380783,
"grad_norm": 1.4232553243637085,
"learning_rate": 8.966766701456177e-05,
"loss": 2.28,
"step": 12
},
{
"epoch": 0.18505338078291814,
"grad_norm": 1.0158861875534058,
"learning_rate": 8.759199037394887e-05,
"loss": 2.0606,
"step": 13
},
{
"epoch": 0.199288256227758,
"grad_norm": 1.0213874578475952,
"learning_rate": 8.535533905932738e-05,
"loss": 1.8842,
"step": 14
},
{
"epoch": 0.21352313167259787,
"grad_norm": 0.9500750303268433,
"learning_rate": 8.296729075500344e-05,
"loss": 1.7835,
"step": 15
},
{
"epoch": 0.2277580071174377,
"grad_norm": 0.8292347192764282,
"learning_rate": 8.043807145043604e-05,
"loss": 1.7693,
"step": 16
},
{
"epoch": 0.24199288256227758,
"grad_norm": 0.8554771542549133,
"learning_rate": 7.777851165098012e-05,
"loss": 1.8696,
"step": 17
},
{
"epoch": 0.25622775800711745,
"grad_norm": 0.840994656085968,
"learning_rate": 7.500000000000001e-05,
"loss": 1.9225,
"step": 18
},
{
"epoch": 0.2704626334519573,
"grad_norm": 1.0327759981155396,
"learning_rate": 7.211443451095007e-05,
"loss": 2.0754,
"step": 19
},
{
"epoch": 0.2846975088967972,
"grad_norm": 0.8893172144889832,
"learning_rate": 6.91341716182545e-05,
"loss": 2.1191,
"step": 20
},
{
"epoch": 0.298932384341637,
"grad_norm": 0.7258279919624329,
"learning_rate": 6.607197326515808e-05,
"loss": 2.0286,
"step": 21
},
{
"epoch": 0.31316725978647686,
"grad_norm": 0.9243592619895935,
"learning_rate": 6.294095225512603e-05,
"loss": 2.0714,
"step": 22
},
{
"epoch": 0.3274021352313167,
"grad_norm": 0.9329895377159119,
"learning_rate": 5.9754516100806423e-05,
"loss": 2.0226,
"step": 23
},
{
"epoch": 0.3416370106761566,
"grad_norm": 0.9377391338348389,
"learning_rate": 5.6526309611002594e-05,
"loss": 1.9961,
"step": 24
},
{
"epoch": 0.35587188612099646,
"grad_norm": 0.9633881449699402,
"learning_rate": 5.327015646150716e-05,
"loss": 2.3204,
"step": 25
},
{
"epoch": 0.35587188612099646,
"eval_loss": 1.9744657278060913,
"eval_runtime": 22.4898,
"eval_samples_per_second": 21.032,
"eval_steps_per_second": 2.668,
"step": 25
},
{
"epoch": 0.3701067615658363,
"grad_norm": 0.9666065573692322,
"learning_rate": 5e-05,
"loss": 1.8401,
"step": 26
},
{
"epoch": 0.38434163701067614,
"grad_norm": 0.9301469326019287,
"learning_rate": 4.6729843538492847e-05,
"loss": 1.7366,
"step": 27
},
{
"epoch": 0.398576512455516,
"grad_norm": 0.7510563135147095,
"learning_rate": 4.347369038899744e-05,
"loss": 1.8588,
"step": 28
},
{
"epoch": 0.4128113879003559,
"grad_norm": 0.8679802417755127,
"learning_rate": 4.0245483899193595e-05,
"loss": 1.859,
"step": 29
},
{
"epoch": 0.42704626334519574,
"grad_norm": 0.7821605801582336,
"learning_rate": 3.705904774487396e-05,
"loss": 1.8511,
"step": 30
},
{
"epoch": 0.4412811387900356,
"grad_norm": 0.8082809448242188,
"learning_rate": 3.392802673484193e-05,
"loss": 1.8725,
"step": 31
},
{
"epoch": 0.4555160142348754,
"grad_norm": 0.869269609451294,
"learning_rate": 3.086582838174551e-05,
"loss": 1.9881,
"step": 32
},
{
"epoch": 0.4697508896797153,
"grad_norm": 0.8141599893569946,
"learning_rate": 2.7885565489049946e-05,
"loss": 1.9531,
"step": 33
},
{
"epoch": 0.48398576512455516,
"grad_norm": 0.7377688884735107,
"learning_rate": 2.500000000000001e-05,
"loss": 1.9266,
"step": 34
},
{
"epoch": 0.498220640569395,
"grad_norm": 0.8427651524543762,
"learning_rate": 2.2221488349019903e-05,
"loss": 2.0421,
"step": 35
},
{
"epoch": 0.5124555160142349,
"grad_norm": 0.7727118134498596,
"learning_rate": 1.9561928549563968e-05,
"loss": 2.1763,
"step": 36
},
{
"epoch": 0.5266903914590747,
"grad_norm": 1.126348853111267,
"learning_rate": 1.703270924499656e-05,
"loss": 2.2711,
"step": 37
},
{
"epoch": 0.5409252669039146,
"grad_norm": 0.7392522096633911,
"learning_rate": 1.4644660940672627e-05,
"loss": 2.0126,
"step": 38
},
{
"epoch": 0.5551601423487544,
"grad_norm": 0.7053424119949341,
"learning_rate": 1.2408009626051137e-05,
"loss": 1.8244,
"step": 39
},
{
"epoch": 0.5693950177935944,
"grad_norm": 0.6880508065223694,
"learning_rate": 1.0332332985438248e-05,
"loss": 1.7971,
"step": 40
},
{
"epoch": 0.5836298932384342,
"grad_norm": 0.6148623824119568,
"learning_rate": 8.426519384872733e-06,
"loss": 1.8143,
"step": 41
},
{
"epoch": 0.597864768683274,
"grad_norm": 0.6629939079284668,
"learning_rate": 6.698729810778065e-06,
"loss": 1.9547,
"step": 42
},
{
"epoch": 0.6120996441281139,
"grad_norm": 0.6230815052986145,
"learning_rate": 5.156362923365588e-06,
"loss": 1.7457,
"step": 43
},
{
"epoch": 0.6263345195729537,
"grad_norm": 0.6868031024932861,
"learning_rate": 3.8060233744356633e-06,
"loss": 1.7492,
"step": 44
},
{
"epoch": 0.6405693950177936,
"grad_norm": 0.6768158078193665,
"learning_rate": 2.653493525244721e-06,
"loss": 1.8826,
"step": 45
},
{
"epoch": 0.6548042704626335,
"grad_norm": 0.7183138728141785,
"learning_rate": 1.70370868554659e-06,
"loss": 1.9686,
"step": 46
},
{
"epoch": 0.6690391459074733,
"grad_norm": 0.7213199734687805,
"learning_rate": 9.607359798384785e-07,
"loss": 2.0478,
"step": 47
},
{
"epoch": 0.6832740213523132,
"grad_norm": 0.7075734734535217,
"learning_rate": 4.277569313094809e-07,
"loss": 1.9768,
"step": 48
},
{
"epoch": 0.697508896797153,
"grad_norm": 0.779909074306488,
"learning_rate": 1.0705383806982606e-07,
"loss": 2.1713,
"step": 49
},
{
"epoch": 0.7117437722419929,
"grad_norm": 0.9000588655471802,
"learning_rate": 0.0,
"loss": 2.2541,
"step": 50
},
{
"epoch": 0.7117437722419929,
"eval_loss": 1.9384169578552246,
"eval_runtime": 22.4329,
"eval_samples_per_second": 21.085,
"eval_steps_per_second": 2.675,
"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": 1.0228361536208896e+18,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}