jssky's picture
Training in progress, step 50, checkpoint
ebfa794 verified
{
"best_metric": NaN,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.0398704211313232,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000797408422626464,
"grad_norm": 3.118460178375244,
"learning_rate": 5e-05,
"loss": 3.3129,
"step": 1
},
{
"epoch": 0.000797408422626464,
"eval_loss": NaN,
"eval_runtime": 57.9441,
"eval_samples_per_second": 145.813,
"eval_steps_per_second": 18.242,
"step": 1
},
{
"epoch": 0.001594816845252928,
"grad_norm": 4.203450679779053,
"learning_rate": 0.0001,
"loss": 3.2103,
"step": 2
},
{
"epoch": 0.002392225267879392,
"grad_norm": 4.596311092376709,
"learning_rate": 9.989294616193017e-05,
"loss": 3.7695,
"step": 3
},
{
"epoch": 0.003189633690505856,
"grad_norm": 4.897176265716553,
"learning_rate": 9.957224306869053e-05,
"loss": 3.7375,
"step": 4
},
{
"epoch": 0.00398704211313232,
"grad_norm": 6.114984035491943,
"learning_rate": 9.903926402016153e-05,
"loss": 3.3151,
"step": 5
},
{
"epoch": 0.004784450535758784,
"grad_norm": 4.544273853302002,
"learning_rate": 9.829629131445342e-05,
"loss": 2.8091,
"step": 6
},
{
"epoch": 0.005581858958385248,
"grad_norm": 5.7902045249938965,
"learning_rate": 9.73465064747553e-05,
"loss": 2.8499,
"step": 7
},
{
"epoch": 0.006379267381011712,
"grad_norm": 4.928606033325195,
"learning_rate": 9.619397662556435e-05,
"loss": 1.8564,
"step": 8
},
{
"epoch": 0.0071766758036381755,
"grad_norm": 7.858636379241943,
"learning_rate": 9.484363707663442e-05,
"loss": 2.9428,
"step": 9
},
{
"epoch": 0.00797408422626464,
"grad_norm": 9.078240394592285,
"learning_rate": 9.330127018922194e-05,
"loss": 3.1329,
"step": 10
},
{
"epoch": 0.008771492648891105,
"grad_norm": 7.502594470977783,
"learning_rate": 9.157348061512727e-05,
"loss": 1.5782,
"step": 11
},
{
"epoch": 0.009568901071517567,
"grad_norm": 13.563742637634277,
"learning_rate": 8.966766701456177e-05,
"loss": 1.8071,
"step": 12
},
{
"epoch": 0.010366309494144032,
"grad_norm": 3.1314632892608643,
"learning_rate": 8.759199037394887e-05,
"loss": 2.3669,
"step": 13
},
{
"epoch": 0.011163717916770496,
"grad_norm": 3.0550808906555176,
"learning_rate": 8.535533905932738e-05,
"loss": 2.4571,
"step": 14
},
{
"epoch": 0.01196112633939696,
"grad_norm": 2.894690752029419,
"learning_rate": 8.296729075500344e-05,
"loss": 2.5549,
"step": 15
},
{
"epoch": 0.012758534762023424,
"grad_norm": 2.5987496376037598,
"learning_rate": 8.043807145043604e-05,
"loss": 2.2837,
"step": 16
},
{
"epoch": 0.013555943184649888,
"grad_norm": 3.6536061763763428,
"learning_rate": 7.777851165098012e-05,
"loss": 2.6145,
"step": 17
},
{
"epoch": 0.014353351607276351,
"grad_norm": 3.160776138305664,
"learning_rate": 7.500000000000001e-05,
"loss": 2.4515,
"step": 18
},
{
"epoch": 0.015150760029902816,
"grad_norm": 5.913760662078857,
"learning_rate": 7.211443451095007e-05,
"loss": 2.8022,
"step": 19
},
{
"epoch": 0.01594816845252928,
"grad_norm": 5.53171968460083,
"learning_rate": 6.91341716182545e-05,
"loss": 2.9629,
"step": 20
},
{
"epoch": 0.016745576875155745,
"grad_norm": 3.351043939590454,
"learning_rate": 6.607197326515808e-05,
"loss": 2.362,
"step": 21
},
{
"epoch": 0.01754298529778221,
"grad_norm": 6.70497989654541,
"learning_rate": 6.294095225512603e-05,
"loss": 2.3642,
"step": 22
},
{
"epoch": 0.01834039372040867,
"grad_norm": 5.723726749420166,
"learning_rate": 5.9754516100806423e-05,
"loss": 2.7549,
"step": 23
},
{
"epoch": 0.019137802143035135,
"grad_norm": 3.634131908416748,
"learning_rate": 5.6526309611002594e-05,
"loss": 1.793,
"step": 24
},
{
"epoch": 0.0199352105656616,
"grad_norm": 9.935222625732422,
"learning_rate": 5.327015646150716e-05,
"loss": 2.3597,
"step": 25
},
{
"epoch": 0.0199352105656616,
"eval_loss": NaN,
"eval_runtime": 57.9048,
"eval_samples_per_second": 145.912,
"eval_steps_per_second": 18.254,
"step": 25
},
{
"epoch": 0.020732618988288064,
"grad_norm": 1.758143424987793,
"learning_rate": 5e-05,
"loss": 2.3564,
"step": 26
},
{
"epoch": 0.02153002741091453,
"grad_norm": 1.8171120882034302,
"learning_rate": 4.6729843538492847e-05,
"loss": 2.3386,
"step": 27
},
{
"epoch": 0.022327435833540993,
"grad_norm": 2.4620540142059326,
"learning_rate": 4.347369038899744e-05,
"loss": 2.2566,
"step": 28
},
{
"epoch": 0.023124844256167457,
"grad_norm": 2.1204512119293213,
"learning_rate": 4.0245483899193595e-05,
"loss": 2.3241,
"step": 29
},
{
"epoch": 0.02392225267879392,
"grad_norm": 3.1958048343658447,
"learning_rate": 3.705904774487396e-05,
"loss": 2.2001,
"step": 30
},
{
"epoch": 0.024719661101420383,
"grad_norm": 3.4434661865234375,
"learning_rate": 3.392802673484193e-05,
"loss": 2.1418,
"step": 31
},
{
"epoch": 0.025517069524046847,
"grad_norm": 3.5963659286499023,
"learning_rate": 3.086582838174551e-05,
"loss": 2.5206,
"step": 32
},
{
"epoch": 0.026314477946673312,
"grad_norm": 3.911703586578369,
"learning_rate": 2.7885565489049946e-05,
"loss": 1.9435,
"step": 33
},
{
"epoch": 0.027111886369299776,
"grad_norm": 4.419018745422363,
"learning_rate": 2.500000000000001e-05,
"loss": 2.6252,
"step": 34
},
{
"epoch": 0.02790929479192624,
"grad_norm": 3.8828225135803223,
"learning_rate": 2.2221488349019903e-05,
"loss": 1.6891,
"step": 35
},
{
"epoch": 0.028706703214552702,
"grad_norm": 5.121977806091309,
"learning_rate": 1.9561928549563968e-05,
"loss": 1.4323,
"step": 36
},
{
"epoch": 0.029504111637179167,
"grad_norm": 3.6891393661499023,
"learning_rate": 1.703270924499656e-05,
"loss": 1.7424,
"step": 37
},
{
"epoch": 0.03030152005980563,
"grad_norm": 1.6718828678131104,
"learning_rate": 1.4644660940672627e-05,
"loss": 2.2177,
"step": 38
},
{
"epoch": 0.031098928482432096,
"grad_norm": 1.5160930156707764,
"learning_rate": 1.2408009626051137e-05,
"loss": 2.2251,
"step": 39
},
{
"epoch": 0.03189633690505856,
"grad_norm": 1.7978293895721436,
"learning_rate": 1.0332332985438248e-05,
"loss": 2.2484,
"step": 40
},
{
"epoch": 0.03269374532768502,
"grad_norm": 2.5029444694519043,
"learning_rate": 8.426519384872733e-06,
"loss": 2.3805,
"step": 41
},
{
"epoch": 0.03349115375031149,
"grad_norm": 3.7533793449401855,
"learning_rate": 6.698729810778065e-06,
"loss": 2.1574,
"step": 42
},
{
"epoch": 0.03428856217293795,
"grad_norm": 5.509903907775879,
"learning_rate": 5.156362923365588e-06,
"loss": 2.4423,
"step": 43
},
{
"epoch": 0.03508597059556442,
"grad_norm": 3.371899127960205,
"learning_rate": 3.8060233744356633e-06,
"loss": 2.3273,
"step": 44
},
{
"epoch": 0.03588337901819088,
"grad_norm": 4.512765884399414,
"learning_rate": 2.653493525244721e-06,
"loss": 2.0492,
"step": 45
},
{
"epoch": 0.03668078744081734,
"grad_norm": 6.9926981925964355,
"learning_rate": 1.70370868554659e-06,
"loss": 2.8342,
"step": 46
},
{
"epoch": 0.03747819586344381,
"grad_norm": 5.881093978881836,
"learning_rate": 9.607359798384785e-07,
"loss": 2.3712,
"step": 47
},
{
"epoch": 0.03827560428607027,
"grad_norm": 3.9496421813964844,
"learning_rate": 4.277569313094809e-07,
"loss": 1.7801,
"step": 48
},
{
"epoch": 0.03907301270869674,
"grad_norm": 6.15703010559082,
"learning_rate": 1.0705383806982606e-07,
"loss": 2.0498,
"step": 49
},
{
"epoch": 0.0398704211313232,
"grad_norm": 5.4105987548828125,
"learning_rate": 0.0,
"loss": 1.9125,
"step": 50
},
{
"epoch": 0.0398704211313232,
"eval_loss": NaN,
"eval_runtime": 57.9087,
"eval_samples_per_second": 145.902,
"eval_steps_per_second": 18.253,
"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": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.95300912644096e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}