bbytxt's picture
Training in progress, step 50, checkpoint
b80c07c verified
raw
history blame
9.9 kB
{
"best_metric": 4.852181434631348,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 1.415492957746479,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.028169014084507043,
"grad_norm": 5.68193244934082,
"learning_rate": 5.000000000000001e-07,
"loss": 6.4785,
"step": 1
},
{
"epoch": 0.028169014084507043,
"eval_loss": 6.220841884613037,
"eval_runtime": 1.6163,
"eval_samples_per_second": 37.121,
"eval_steps_per_second": 4.949,
"step": 1
},
{
"epoch": 0.056338028169014086,
"grad_norm": 5.4344162940979,
"learning_rate": 1.0000000000000002e-06,
"loss": 6.4907,
"step": 2
},
{
"epoch": 0.08450704225352113,
"grad_norm": 5.336536407470703,
"learning_rate": 1.5e-06,
"loss": 6.6291,
"step": 3
},
{
"epoch": 0.11267605633802817,
"grad_norm": 5.674023628234863,
"learning_rate": 2.0000000000000003e-06,
"loss": 6.5261,
"step": 4
},
{
"epoch": 0.14084507042253522,
"grad_norm": 6.0419111251831055,
"learning_rate": 2.5e-06,
"loss": 6.4708,
"step": 5
},
{
"epoch": 0.16901408450704225,
"grad_norm": 5.955847263336182,
"learning_rate": 3e-06,
"loss": 6.7497,
"step": 6
},
{
"epoch": 0.19718309859154928,
"grad_norm": 7.694795608520508,
"learning_rate": 3.5e-06,
"loss": 6.6166,
"step": 7
},
{
"epoch": 0.22535211267605634,
"grad_norm": 6.317434310913086,
"learning_rate": 4.000000000000001e-06,
"loss": 6.4985,
"step": 8
},
{
"epoch": 0.2535211267605634,
"grad_norm": 5.917690277099609,
"learning_rate": 4.5e-06,
"loss": 6.453,
"step": 9
},
{
"epoch": 0.28169014084507044,
"grad_norm": 5.736076831817627,
"learning_rate": 5e-06,
"loss": 6.7027,
"step": 10
},
{
"epoch": 0.30985915492957744,
"grad_norm": 5.613097190856934,
"learning_rate": 4.99847706754774e-06,
"loss": 5.9373,
"step": 11
},
{
"epoch": 0.3380281690140845,
"grad_norm": 5.329749584197998,
"learning_rate": 4.993910125649561e-06,
"loss": 6.6172,
"step": 12
},
{
"epoch": 0.36619718309859156,
"grad_norm": 6.5323333740234375,
"learning_rate": 4.986304738420684e-06,
"loss": 6.2915,
"step": 13
},
{
"epoch": 0.39436619718309857,
"grad_norm": 6.311445236206055,
"learning_rate": 4.975670171853926e-06,
"loss": 6.5675,
"step": 14
},
{
"epoch": 0.4225352112676056,
"grad_norm": 5.865750789642334,
"learning_rate": 4.962019382530521e-06,
"loss": 6.5465,
"step": 15
},
{
"epoch": 0.4507042253521127,
"grad_norm": 6.167825698852539,
"learning_rate": 4.9453690018345144e-06,
"loss": 6.3649,
"step": 16
},
{
"epoch": 0.4788732394366197,
"grad_norm": 6.63243293762207,
"learning_rate": 4.925739315689991e-06,
"loss": 6.3944,
"step": 17
},
{
"epoch": 0.5070422535211268,
"grad_norm": 5.555633544921875,
"learning_rate": 4.903154239845798e-06,
"loss": 6.3991,
"step": 18
},
{
"epoch": 0.5352112676056338,
"grad_norm": 5.7282867431640625,
"learning_rate": 4.8776412907378845e-06,
"loss": 6.094,
"step": 19
},
{
"epoch": 0.5633802816901409,
"grad_norm": 6.097353935241699,
"learning_rate": 4.849231551964771e-06,
"loss": 6.2897,
"step": 20
},
{
"epoch": 0.5915492957746479,
"grad_norm": 6.4345197677612305,
"learning_rate": 4.817959636416969e-06,
"loss": 6.0746,
"step": 21
},
{
"epoch": 0.6197183098591549,
"grad_norm": 5.89772367477417,
"learning_rate": 4.783863644106502e-06,
"loss": 6.0027,
"step": 22
},
{
"epoch": 0.647887323943662,
"grad_norm": 6.29380989074707,
"learning_rate": 4.746985115747918e-06,
"loss": 5.7046,
"step": 23
},
{
"epoch": 0.676056338028169,
"grad_norm": 6.15521240234375,
"learning_rate": 4.707368982147318e-06,
"loss": 6.1176,
"step": 24
},
{
"epoch": 0.704225352112676,
"grad_norm": 5.841217517852783,
"learning_rate": 4.665063509461098e-06,
"loss": 6.0347,
"step": 25
},
{
"epoch": 0.7323943661971831,
"grad_norm": 5.708609580993652,
"learning_rate": 4.620120240391065e-06,
"loss": 5.7374,
"step": 26
},
{
"epoch": 0.7605633802816901,
"grad_norm": 6.486269474029541,
"learning_rate": 4.572593931387604e-06,
"loss": 5.9866,
"step": 27
},
{
"epoch": 0.7887323943661971,
"grad_norm": 6.278411388397217,
"learning_rate": 4.522542485937369e-06,
"loss": 6.0473,
"step": 28
},
{
"epoch": 0.8169014084507042,
"grad_norm": 6.592667102813721,
"learning_rate": 4.470026884016805e-06,
"loss": 6.0237,
"step": 29
},
{
"epoch": 0.8450704225352113,
"grad_norm": 6.2682414054870605,
"learning_rate": 4.415111107797445e-06,
"loss": 6.0611,
"step": 30
},
{
"epoch": 0.8732394366197183,
"grad_norm": 5.710134029388428,
"learning_rate": 4.357862063693486e-06,
"loss": 5.6585,
"step": 31
},
{
"epoch": 0.9014084507042254,
"grad_norm": 6.120304107666016,
"learning_rate": 4.2983495008466285e-06,
"loss": 6.3488,
"step": 32
},
{
"epoch": 0.9295774647887324,
"grad_norm": 5.738293170928955,
"learning_rate": 4.236645926147493e-06,
"loss": 5.5834,
"step": 33
},
{
"epoch": 0.9577464788732394,
"grad_norm": 6.664410591125488,
"learning_rate": 4.172826515897146e-06,
"loss": 5.7185,
"step": 34
},
{
"epoch": 0.9859154929577465,
"grad_norm": 6.02655553817749,
"learning_rate": 4.106969024216348e-06,
"loss": 5.4995,
"step": 35
},
{
"epoch": 1.0211267605633803,
"grad_norm": 10.034653663635254,
"learning_rate": 4.039153688314146e-06,
"loss": 9.6958,
"step": 36
},
{
"epoch": 1.0492957746478873,
"grad_norm": 6.114748001098633,
"learning_rate": 3.969463130731183e-06,
"loss": 5.6932,
"step": 37
},
{
"epoch": 1.0774647887323943,
"grad_norm": 5.394074440002441,
"learning_rate": 3.897982258676867e-06,
"loss": 5.4438,
"step": 38
},
{
"epoch": 1.1056338028169015,
"grad_norm": 5.475838661193848,
"learning_rate": 3.824798160583012e-06,
"loss": 5.1237,
"step": 39
},
{
"epoch": 1.1338028169014085,
"grad_norm": 5.955112934112549,
"learning_rate": 3.7500000000000005e-06,
"loss": 5.3704,
"step": 40
},
{
"epoch": 1.1619718309859155,
"grad_norm": 6.310902118682861,
"learning_rate": 3.6736789069647273e-06,
"loss": 5.5419,
"step": 41
},
{
"epoch": 1.1901408450704225,
"grad_norm": 6.074863910675049,
"learning_rate": 3.595927866972694e-06,
"loss": 5.2662,
"step": 42
},
{
"epoch": 1.2183098591549295,
"grad_norm": 5.811051845550537,
"learning_rate": 3.516841607689501e-06,
"loss": 5.256,
"step": 43
},
{
"epoch": 1.2464788732394365,
"grad_norm": 6.148581504821777,
"learning_rate": 3.436516483539781e-06,
"loss": 5.0733,
"step": 44
},
{
"epoch": 1.2746478873239437,
"grad_norm": 6.256888389587402,
"learning_rate": 3.3550503583141726e-06,
"loss": 5.1171,
"step": 45
},
{
"epoch": 1.3028169014084507,
"grad_norm": 5.250644683837891,
"learning_rate": 3.272542485937369e-06,
"loss": 5.2975,
"step": 46
},
{
"epoch": 1.3309859154929577,
"grad_norm": 5.596186637878418,
"learning_rate": 3.189093389542498e-06,
"loss": 5.3599,
"step": 47
},
{
"epoch": 1.3591549295774648,
"grad_norm": 5.674249649047852,
"learning_rate": 3.1048047389991693e-06,
"loss": 5.2093,
"step": 48
},
{
"epoch": 1.3873239436619718,
"grad_norm": 6.155755996704102,
"learning_rate": 3.019779227044398e-06,
"loss": 5.1566,
"step": 49
},
{
"epoch": 1.415492957746479,
"grad_norm": 6.356016635894775,
"learning_rate": 2.9341204441673267e-06,
"loss": 5.0461,
"step": 50
},
{
"epoch": 1.415492957746479,
"eval_loss": 4.852181434631348,
"eval_runtime": 1.229,
"eval_samples_per_second": 48.819,
"eval_steps_per_second": 6.509,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 1.06657392623616e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}