nttx's picture
Training in progress, step 50, checkpoint
29ab07a verified
raw
history blame
10 kB
{
"best_metric": 2.229457378387451,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.01681944327642755,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00033638886552855103,
"grad_norm": 0.07795742154121399,
"learning_rate": 3.3333333333333333e-06,
"loss": 2.7769,
"step": 1
},
{
"epoch": 0.00033638886552855103,
"eval_loss": 2.455552101135254,
"eval_runtime": 133.5909,
"eval_samples_per_second": 37.48,
"eval_steps_per_second": 18.744,
"step": 1
},
{
"epoch": 0.0006727777310571021,
"grad_norm": 0.091961570084095,
"learning_rate": 6.666666666666667e-06,
"loss": 2.615,
"step": 2
},
{
"epoch": 0.001009166596585653,
"grad_norm": 0.09707869589328766,
"learning_rate": 1e-05,
"loss": 2.4234,
"step": 3
},
{
"epoch": 0.0013455554621142041,
"grad_norm": 0.09777762740850449,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.4821,
"step": 4
},
{
"epoch": 0.001681944327642755,
"grad_norm": 0.16171760857105255,
"learning_rate": 1.6666666666666667e-05,
"loss": 2.4558,
"step": 5
},
{
"epoch": 0.002018333193171306,
"grad_norm": 0.10559370368719101,
"learning_rate": 2e-05,
"loss": 2.4765,
"step": 6
},
{
"epoch": 0.002354722058699857,
"grad_norm": 0.11369410157203674,
"learning_rate": 2.3333333333333336e-05,
"loss": 2.585,
"step": 7
},
{
"epoch": 0.0026911109242284082,
"grad_norm": 0.1158774346113205,
"learning_rate": 2.6666666666666667e-05,
"loss": 2.4602,
"step": 8
},
{
"epoch": 0.003027499789756959,
"grad_norm": 0.12309759110212326,
"learning_rate": 3e-05,
"loss": 2.4651,
"step": 9
},
{
"epoch": 0.00336388865528551,
"grad_norm": 0.13319513201713562,
"learning_rate": 3.3333333333333335e-05,
"loss": 2.309,
"step": 10
},
{
"epoch": 0.0037002775208140612,
"grad_norm": 0.12856201827526093,
"learning_rate": 3.6666666666666666e-05,
"loss": 2.4663,
"step": 11
},
{
"epoch": 0.004036666386342612,
"grad_norm": 0.12185679376125336,
"learning_rate": 4e-05,
"loss": 2.4488,
"step": 12
},
{
"epoch": 0.004373055251871163,
"grad_norm": 0.12302099913358688,
"learning_rate": 4.3333333333333334e-05,
"loss": 2.3317,
"step": 13
},
{
"epoch": 0.004709444117399714,
"grad_norm": 0.1280185580253601,
"learning_rate": 4.666666666666667e-05,
"loss": 2.3823,
"step": 14
},
{
"epoch": 0.005045832982928265,
"grad_norm": 0.13406257331371307,
"learning_rate": 5e-05,
"loss": 2.3536,
"step": 15
},
{
"epoch": 0.0053822218484568165,
"grad_norm": 0.1333453357219696,
"learning_rate": 5.333333333333333e-05,
"loss": 2.4247,
"step": 16
},
{
"epoch": 0.005718610713985367,
"grad_norm": 0.12794539332389832,
"learning_rate": 5.666666666666667e-05,
"loss": 2.4933,
"step": 17
},
{
"epoch": 0.006054999579513918,
"grad_norm": 0.12640050053596497,
"learning_rate": 6e-05,
"loss": 2.4592,
"step": 18
},
{
"epoch": 0.0063913884450424695,
"grad_norm": 0.1311822533607483,
"learning_rate": 6.333333333333333e-05,
"loss": 2.2846,
"step": 19
},
{
"epoch": 0.00672777731057102,
"grad_norm": 0.13246804475784302,
"learning_rate": 6.666666666666667e-05,
"loss": 2.4061,
"step": 20
},
{
"epoch": 0.007064166176099571,
"grad_norm": 0.15557919442653656,
"learning_rate": 7e-05,
"loss": 2.2899,
"step": 21
},
{
"epoch": 0.0074005550416281225,
"grad_norm": 0.13837924599647522,
"learning_rate": 7.333333333333333e-05,
"loss": 2.5681,
"step": 22
},
{
"epoch": 0.007736943907156673,
"grad_norm": 0.1440717875957489,
"learning_rate": 7.666666666666667e-05,
"loss": 2.3665,
"step": 23
},
{
"epoch": 0.008073332772685224,
"grad_norm": 0.15145528316497803,
"learning_rate": 8e-05,
"loss": 2.2948,
"step": 24
},
{
"epoch": 0.008409721638213775,
"grad_norm": 0.1539720594882965,
"learning_rate": 8.333333333333334e-05,
"loss": 2.3214,
"step": 25
},
{
"epoch": 0.008746110503742325,
"grad_norm": 0.14122752845287323,
"learning_rate": 8.666666666666667e-05,
"loss": 2.2708,
"step": 26
},
{
"epoch": 0.009082499369270877,
"grad_norm": 0.15089313685894012,
"learning_rate": 9e-05,
"loss": 2.3226,
"step": 27
},
{
"epoch": 0.009418888234799428,
"grad_norm": 0.200881689786911,
"learning_rate": 9.333333333333334e-05,
"loss": 2.3429,
"step": 28
},
{
"epoch": 0.00975527710032798,
"grad_norm": 0.1588452160358429,
"learning_rate": 9.666666666666667e-05,
"loss": 2.2316,
"step": 29
},
{
"epoch": 0.01009166596585653,
"grad_norm": 0.18878738582134247,
"learning_rate": 0.0001,
"loss": 2.249,
"step": 30
},
{
"epoch": 0.010428054831385081,
"grad_norm": 0.19466233253479004,
"learning_rate": 9.999146252290264e-05,
"loss": 2.2815,
"step": 31
},
{
"epoch": 0.010764443696913633,
"grad_norm": 0.23344077169895172,
"learning_rate": 9.996585300715116e-05,
"loss": 2.2785,
"step": 32
},
{
"epoch": 0.011100832562442183,
"grad_norm": 0.23798418045043945,
"learning_rate": 9.99231801983717e-05,
"loss": 2.0524,
"step": 33
},
{
"epoch": 0.011437221427970734,
"grad_norm": 0.19358737766742706,
"learning_rate": 9.986345866928941e-05,
"loss": 2.0744,
"step": 34
},
{
"epoch": 0.011773610293499286,
"grad_norm": 0.19671595096588135,
"learning_rate": 9.978670881475172e-05,
"loss": 2.1176,
"step": 35
},
{
"epoch": 0.012109999159027836,
"grad_norm": 0.20317138731479645,
"learning_rate": 9.96929568447637e-05,
"loss": 2.2187,
"step": 36
},
{
"epoch": 0.012446388024556387,
"grad_norm": 0.19243532419204712,
"learning_rate": 9.958223477553714e-05,
"loss": 1.9553,
"step": 37
},
{
"epoch": 0.012782776890084939,
"grad_norm": 0.17963586747646332,
"learning_rate": 9.94545804185573e-05,
"loss": 2.0921,
"step": 38
},
{
"epoch": 0.013119165755613489,
"grad_norm": 0.20728521049022675,
"learning_rate": 9.931003736767013e-05,
"loss": 2.3093,
"step": 39
},
{
"epoch": 0.01345555462114204,
"grad_norm": 0.2048047035932541,
"learning_rate": 9.91486549841951e-05,
"loss": 2.2137,
"step": 40
},
{
"epoch": 0.013791943486670592,
"grad_norm": 0.199965700507164,
"learning_rate": 9.89704883800683e-05,
"loss": 2.1698,
"step": 41
},
{
"epoch": 0.014128332352199142,
"grad_norm": 0.2382458597421646,
"learning_rate": 9.877559839902184e-05,
"loss": 2.1951,
"step": 42
},
{
"epoch": 0.014464721217727693,
"grad_norm": 0.19734260439872742,
"learning_rate": 9.85640515958057e-05,
"loss": 2.118,
"step": 43
},
{
"epoch": 0.014801110083256245,
"grad_norm": 0.23887623846530914,
"learning_rate": 9.833592021345937e-05,
"loss": 2.133,
"step": 44
},
{
"epoch": 0.015137498948784795,
"grad_norm": 0.21855773031711578,
"learning_rate": 9.809128215864097e-05,
"loss": 2.182,
"step": 45
},
{
"epoch": 0.015473887814313346,
"grad_norm": 0.24946734309196472,
"learning_rate": 9.783022097502204e-05,
"loss": 2.2907,
"step": 46
},
{
"epoch": 0.015810276679841896,
"grad_norm": 0.23966045677661896,
"learning_rate": 9.755282581475769e-05,
"loss": 2.1424,
"step": 47
},
{
"epoch": 0.016146665545370448,
"grad_norm": 0.29373985528945923,
"learning_rate": 9.725919140804099e-05,
"loss": 2.2907,
"step": 48
},
{
"epoch": 0.016483054410899,
"grad_norm": 0.2858251631259918,
"learning_rate": 9.694941803075283e-05,
"loss": 1.9196,
"step": 49
},
{
"epoch": 0.01681944327642755,
"grad_norm": 0.44232481718063354,
"learning_rate": 9.662361147021779e-05,
"loss": 2.2586,
"step": 50
},
{
"epoch": 0.01681944327642755,
"eval_loss": 2.229457378387451,
"eval_runtime": 133.8125,
"eval_samples_per_second": 37.418,
"eval_steps_per_second": 18.713,
"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": 3451611968962560.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}