vdos's picture
Training in progress, step 50, checkpoint
add3ed1 verified
raw
history blame
10.3 kB
{
"best_metric": 1.599951148033142,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.061265124827691836,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0012253024965538366,
"grad_norm": 0.38437554240226746,
"learning_rate": 5e-05,
"loss": 1.2256,
"step": 1
},
{
"epoch": 0.0012253024965538366,
"eval_loss": 2.729480504989624,
"eval_runtime": 159.055,
"eval_samples_per_second": 34.567,
"eval_steps_per_second": 4.326,
"step": 1
},
{
"epoch": 0.0024506049931076732,
"grad_norm": 0.7935199737548828,
"learning_rate": 0.0001,
"loss": 1.6149,
"step": 2
},
{
"epoch": 0.00367590748966151,
"grad_norm": 0.8302483558654785,
"learning_rate": 9.989294616193017e-05,
"loss": 1.7008,
"step": 3
},
{
"epoch": 0.0049012099862153465,
"grad_norm": 0.7559549808502197,
"learning_rate": 9.957224306869053e-05,
"loss": 1.6619,
"step": 4
},
{
"epoch": 0.006126512482769184,
"grad_norm": 0.4813291132450104,
"learning_rate": 9.903926402016153e-05,
"loss": 1.4777,
"step": 5
},
{
"epoch": 0.00735181497932302,
"grad_norm": 0.19940398633480072,
"learning_rate": 9.829629131445342e-05,
"loss": 1.3795,
"step": 6
},
{
"epoch": 0.008577117475876857,
"grad_norm": 0.32673880457878113,
"learning_rate": 9.73465064747553e-05,
"loss": 1.3087,
"step": 7
},
{
"epoch": 0.009802419972430693,
"grad_norm": 0.46744921803474426,
"learning_rate": 9.619397662556435e-05,
"loss": 1.6795,
"step": 8
},
{
"epoch": 0.01102772246898453,
"grad_norm": 0.5287789702415466,
"learning_rate": 9.484363707663442e-05,
"loss": 1.8935,
"step": 9
},
{
"epoch": 0.012253024965538368,
"grad_norm": 0.5033717155456543,
"learning_rate": 9.330127018922194e-05,
"loss": 1.9079,
"step": 10
},
{
"epoch": 0.013478327462092205,
"grad_norm": 0.5873647332191467,
"learning_rate": 9.157348061512727e-05,
"loss": 2.0324,
"step": 11
},
{
"epoch": 0.01470362995864604,
"grad_norm": 0.8962656259536743,
"learning_rate": 8.966766701456177e-05,
"loss": 2.4488,
"step": 12
},
{
"epoch": 0.015928932455199878,
"grad_norm": 0.16678322851657867,
"learning_rate": 8.759199037394887e-05,
"loss": 1.1275,
"step": 13
},
{
"epoch": 0.017154234951753715,
"grad_norm": 0.22187885642051697,
"learning_rate": 8.535533905932738e-05,
"loss": 1.3016,
"step": 14
},
{
"epoch": 0.018379537448307552,
"grad_norm": 0.27512508630752563,
"learning_rate": 8.296729075500344e-05,
"loss": 1.4014,
"step": 15
},
{
"epoch": 0.019604839944861386,
"grad_norm": 0.39614734053611755,
"learning_rate": 8.043807145043604e-05,
"loss": 1.6043,
"step": 16
},
{
"epoch": 0.020830142441415223,
"grad_norm": 0.4057166576385498,
"learning_rate": 7.777851165098012e-05,
"loss": 1.4468,
"step": 17
},
{
"epoch": 0.02205544493796906,
"grad_norm": 0.15889322757720947,
"learning_rate": 7.500000000000001e-05,
"loss": 1.1826,
"step": 18
},
{
"epoch": 0.023280747434522898,
"grad_norm": 0.16170313954353333,
"learning_rate": 7.211443451095007e-05,
"loss": 1.2176,
"step": 19
},
{
"epoch": 0.024506049931076735,
"grad_norm": 0.25570419430732727,
"learning_rate": 6.91341716182545e-05,
"loss": 1.4155,
"step": 20
},
{
"epoch": 0.025731352427630572,
"grad_norm": 0.31802138686180115,
"learning_rate": 6.607197326515808e-05,
"loss": 1.5692,
"step": 21
},
{
"epoch": 0.02695665492418441,
"grad_norm": 0.4341036081314087,
"learning_rate": 6.294095225512603e-05,
"loss": 1.7806,
"step": 22
},
{
"epoch": 0.028181957420738243,
"grad_norm": 0.5105137825012207,
"learning_rate": 5.9754516100806423e-05,
"loss": 2.008,
"step": 23
},
{
"epoch": 0.02940725991729208,
"grad_norm": 0.6459643244743347,
"learning_rate": 5.6526309611002594e-05,
"loss": 2.23,
"step": 24
},
{
"epoch": 0.030632562413845918,
"grad_norm": 1.1887092590332031,
"learning_rate": 5.327015646150716e-05,
"loss": 2.4034,
"step": 25
},
{
"epoch": 0.030632562413845918,
"eval_loss": 1.6387038230895996,
"eval_runtime": 159.6801,
"eval_samples_per_second": 34.431,
"eval_steps_per_second": 4.309,
"step": 25
},
{
"epoch": 0.031857864910399755,
"grad_norm": 0.10918952524662018,
"learning_rate": 5e-05,
"loss": 1.0948,
"step": 26
},
{
"epoch": 0.03308316740695359,
"grad_norm": 0.1791597455739975,
"learning_rate": 4.6729843538492847e-05,
"loss": 1.2498,
"step": 27
},
{
"epoch": 0.03430846990350743,
"grad_norm": 0.2935185134410858,
"learning_rate": 4.347369038899744e-05,
"loss": 1.3262,
"step": 28
},
{
"epoch": 0.03553377240006127,
"grad_norm": 0.37032783031463623,
"learning_rate": 4.0245483899193595e-05,
"loss": 1.3698,
"step": 29
},
{
"epoch": 0.036759074896615104,
"grad_norm": 0.2906474769115448,
"learning_rate": 3.705904774487396e-05,
"loss": 1.2198,
"step": 30
},
{
"epoch": 0.03798437739316894,
"grad_norm": 0.2047668993473053,
"learning_rate": 3.392802673484193e-05,
"loss": 1.2105,
"step": 31
},
{
"epoch": 0.03920967988972277,
"grad_norm": 0.1876075118780136,
"learning_rate": 3.086582838174551e-05,
"loss": 1.197,
"step": 32
},
{
"epoch": 0.04043498238627661,
"grad_norm": 0.22366094589233398,
"learning_rate": 2.7885565489049946e-05,
"loss": 1.3892,
"step": 33
},
{
"epoch": 0.041660284882830446,
"grad_norm": 0.2662312090396881,
"learning_rate": 2.500000000000001e-05,
"loss": 1.612,
"step": 34
},
{
"epoch": 0.042885587379384284,
"grad_norm": 0.32836422324180603,
"learning_rate": 2.2221488349019903e-05,
"loss": 1.6611,
"step": 35
},
{
"epoch": 0.04411088987593812,
"grad_norm": 0.4305000603199005,
"learning_rate": 1.9561928549563968e-05,
"loss": 1.9214,
"step": 36
},
{
"epoch": 0.04533619237249196,
"grad_norm": 0.5970643758773804,
"learning_rate": 1.703270924499656e-05,
"loss": 1.9747,
"step": 37
},
{
"epoch": 0.046561494869045796,
"grad_norm": 0.10557608306407928,
"learning_rate": 1.4644660940672627e-05,
"loss": 0.901,
"step": 38
},
{
"epoch": 0.04778679736559963,
"grad_norm": 0.14012107253074646,
"learning_rate": 1.2408009626051137e-05,
"loss": 1.38,
"step": 39
},
{
"epoch": 0.04901209986215347,
"grad_norm": 0.1754305362701416,
"learning_rate": 1.0332332985438248e-05,
"loss": 1.1382,
"step": 40
},
{
"epoch": 0.05023740235870731,
"grad_norm": 0.24448178708553314,
"learning_rate": 8.426519384872733e-06,
"loss": 1.4041,
"step": 41
},
{
"epoch": 0.051462704855261145,
"grad_norm": 0.2805235981941223,
"learning_rate": 6.698729810778065e-06,
"loss": 1.351,
"step": 42
},
{
"epoch": 0.05268800735181498,
"grad_norm": 0.1339372992515564,
"learning_rate": 5.156362923365588e-06,
"loss": 1.3022,
"step": 43
},
{
"epoch": 0.05391330984836882,
"grad_norm": 0.12944447994232178,
"learning_rate": 3.8060233744356633e-06,
"loss": 1.2448,
"step": 44
},
{
"epoch": 0.05513861234492265,
"grad_norm": 0.1557026505470276,
"learning_rate": 2.653493525244721e-06,
"loss": 1.4178,
"step": 45
},
{
"epoch": 0.05636391484147649,
"grad_norm": 0.20143267512321472,
"learning_rate": 1.70370868554659e-06,
"loss": 1.5663,
"step": 46
},
{
"epoch": 0.057589217338030324,
"grad_norm": 0.25110936164855957,
"learning_rate": 9.607359798384785e-07,
"loss": 1.6935,
"step": 47
},
{
"epoch": 0.05881451983458416,
"grad_norm": 0.35833045840263367,
"learning_rate": 4.277569313094809e-07,
"loss": 1.7919,
"step": 48
},
{
"epoch": 0.060039822331138,
"grad_norm": 0.5051993727684021,
"learning_rate": 1.0705383806982606e-07,
"loss": 1.9054,
"step": 49
},
{
"epoch": 0.061265124827691836,
"grad_norm": 1.0000535249710083,
"learning_rate": 0.0,
"loss": 2.3356,
"step": 50
},
{
"epoch": 0.061265124827691836,
"eval_loss": 1.599951148033142,
"eval_runtime": 159.6819,
"eval_samples_per_second": 34.431,
"eval_steps_per_second": 4.309,
"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": 5.270609060482253e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}