bbytxt's picture
Training in progress, step 50, checkpoint
f5ce085 verified
raw
history blame
9.99 kB
{
"best_metric": 11.10726547241211,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.7797270955165692,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.015594541910331383,
"grad_norm": 1.3553541898727417,
"learning_rate": 5.000000000000001e-07,
"loss": 88.9667,
"step": 1
},
{
"epoch": 0.015594541910331383,
"eval_loss": 11.111183166503906,
"eval_runtime": 0.2874,
"eval_samples_per_second": 375.846,
"eval_steps_per_second": 93.962,
"step": 1
},
{
"epoch": 0.031189083820662766,
"grad_norm": 1.4310979843139648,
"learning_rate": 1.0000000000000002e-06,
"loss": 88.9521,
"step": 2
},
{
"epoch": 0.04678362573099415,
"grad_norm": 1.448810338973999,
"learning_rate": 1.5e-06,
"loss": 88.9224,
"step": 3
},
{
"epoch": 0.06237816764132553,
"grad_norm": 1.4280792474746704,
"learning_rate": 2.0000000000000003e-06,
"loss": 88.9165,
"step": 4
},
{
"epoch": 0.07797270955165692,
"grad_norm": 1.5008811950683594,
"learning_rate": 2.5e-06,
"loss": 88.9208,
"step": 5
},
{
"epoch": 0.0935672514619883,
"grad_norm": 1.6087157726287842,
"learning_rate": 3e-06,
"loss": 88.9012,
"step": 6
},
{
"epoch": 0.10916179337231968,
"grad_norm": 1.6683207750320435,
"learning_rate": 3.5e-06,
"loss": 88.9475,
"step": 7
},
{
"epoch": 0.12475633528265107,
"grad_norm": 1.747448444366455,
"learning_rate": 4.000000000000001e-06,
"loss": 88.9432,
"step": 8
},
{
"epoch": 0.14035087719298245,
"grad_norm": 1.678775668144226,
"learning_rate": 4.5e-06,
"loss": 88.9057,
"step": 9
},
{
"epoch": 0.15594541910331383,
"grad_norm": 1.823146104812622,
"learning_rate": 5e-06,
"loss": 88.8821,
"step": 10
},
{
"epoch": 0.17153996101364521,
"grad_norm": 1.9624767303466797,
"learning_rate": 4.99847706754774e-06,
"loss": 88.9016,
"step": 11
},
{
"epoch": 0.1871345029239766,
"grad_norm": 1.9462685585021973,
"learning_rate": 4.993910125649561e-06,
"loss": 88.9103,
"step": 12
},
{
"epoch": 0.20272904483430798,
"grad_norm": 2.1563684940338135,
"learning_rate": 4.986304738420684e-06,
"loss": 88.9475,
"step": 13
},
{
"epoch": 0.21832358674463936,
"grad_norm": 2.48010516166687,
"learning_rate": 4.975670171853926e-06,
"loss": 88.932,
"step": 14
},
{
"epoch": 0.23391812865497075,
"grad_norm": 3.1107337474823,
"learning_rate": 4.962019382530521e-06,
"loss": 88.8091,
"step": 15
},
{
"epoch": 0.24951267056530213,
"grad_norm": 5.877386569976807,
"learning_rate": 4.9453690018345144e-06,
"loss": 88.589,
"step": 16
},
{
"epoch": 0.2651072124756335,
"grad_norm": 1.4020336866378784,
"learning_rate": 4.925739315689991e-06,
"loss": 88.9679,
"step": 17
},
{
"epoch": 0.2807017543859649,
"grad_norm": 1.4191652536392212,
"learning_rate": 4.903154239845798e-06,
"loss": 88.9306,
"step": 18
},
{
"epoch": 0.2962962962962963,
"grad_norm": 1.4291287660598755,
"learning_rate": 4.8776412907378845e-06,
"loss": 88.9514,
"step": 19
},
{
"epoch": 0.31189083820662766,
"grad_norm": 1.5101865530014038,
"learning_rate": 4.849231551964771e-06,
"loss": 88.9267,
"step": 20
},
{
"epoch": 0.32748538011695905,
"grad_norm": 1.5891046524047852,
"learning_rate": 4.817959636416969e-06,
"loss": 88.9252,
"step": 21
},
{
"epoch": 0.34307992202729043,
"grad_norm": 1.5987111330032349,
"learning_rate": 4.783863644106502e-06,
"loss": 88.9014,
"step": 22
},
{
"epoch": 0.3586744639376218,
"grad_norm": 1.6611799001693726,
"learning_rate": 4.746985115747918e-06,
"loss": 88.9222,
"step": 23
},
{
"epoch": 0.3742690058479532,
"grad_norm": 1.675337314605713,
"learning_rate": 4.707368982147318e-06,
"loss": 88.9076,
"step": 24
},
{
"epoch": 0.3898635477582846,
"grad_norm": 1.729783058166504,
"learning_rate": 4.665063509461098e-06,
"loss": 88.9013,
"step": 25
},
{
"epoch": 0.40545808966861596,
"grad_norm": 1.9155665636062622,
"learning_rate": 4.620120240391065e-06,
"loss": 88.8678,
"step": 26
},
{
"epoch": 0.42105263157894735,
"grad_norm": 1.9021366834640503,
"learning_rate": 4.572593931387604e-06,
"loss": 88.9318,
"step": 27
},
{
"epoch": 0.43664717348927873,
"grad_norm": 2.0137956142425537,
"learning_rate": 4.522542485937369e-06,
"loss": 88.8439,
"step": 28
},
{
"epoch": 0.4522417153996101,
"grad_norm": 2.1356048583984375,
"learning_rate": 4.470026884016805e-06,
"loss": 88.9014,
"step": 29
},
{
"epoch": 0.4678362573099415,
"grad_norm": 2.3856770992279053,
"learning_rate": 4.415111107797445e-06,
"loss": 88.8764,
"step": 30
},
{
"epoch": 0.4834307992202729,
"grad_norm": 2.872187852859497,
"learning_rate": 4.357862063693486e-06,
"loss": 88.8898,
"step": 31
},
{
"epoch": 0.49902534113060426,
"grad_norm": 4.954247951507568,
"learning_rate": 4.2983495008466285e-06,
"loss": 88.7124,
"step": 32
},
{
"epoch": 0.5146198830409356,
"grad_norm": 1.4366636276245117,
"learning_rate": 4.236645926147493e-06,
"loss": 88.9227,
"step": 33
},
{
"epoch": 0.530214424951267,
"grad_norm": 1.502366304397583,
"learning_rate": 4.172826515897146e-06,
"loss": 88.9448,
"step": 34
},
{
"epoch": 0.5458089668615984,
"grad_norm": 1.4580628871917725,
"learning_rate": 4.106969024216348e-06,
"loss": 88.904,
"step": 35
},
{
"epoch": 0.5614035087719298,
"grad_norm": 1.4254974126815796,
"learning_rate": 4.039153688314146e-06,
"loss": 88.9466,
"step": 36
},
{
"epoch": 0.5769980506822612,
"grad_norm": 1.559779405593872,
"learning_rate": 3.969463130731183e-06,
"loss": 88.8986,
"step": 37
},
{
"epoch": 0.5925925925925926,
"grad_norm": 1.6463968753814697,
"learning_rate": 3.897982258676867e-06,
"loss": 88.915,
"step": 38
},
{
"epoch": 0.6081871345029239,
"grad_norm": 1.7474920749664307,
"learning_rate": 3.824798160583012e-06,
"loss": 88.9155,
"step": 39
},
{
"epoch": 0.6237816764132553,
"grad_norm": 1.8197089433670044,
"learning_rate": 3.7500000000000005e-06,
"loss": 88.871,
"step": 40
},
{
"epoch": 0.6393762183235867,
"grad_norm": 1.8057571649551392,
"learning_rate": 3.6736789069647273e-06,
"loss": 88.9049,
"step": 41
},
{
"epoch": 0.6549707602339181,
"grad_norm": 1.847694754600525,
"learning_rate": 3.595927866972694e-06,
"loss": 88.8932,
"step": 42
},
{
"epoch": 0.6705653021442495,
"grad_norm": 1.9483572244644165,
"learning_rate": 3.516841607689501e-06,
"loss": 88.8755,
"step": 43
},
{
"epoch": 0.6861598440545809,
"grad_norm": 2.0147557258605957,
"learning_rate": 3.436516483539781e-06,
"loss": 88.9301,
"step": 44
},
{
"epoch": 0.7017543859649122,
"grad_norm": 2.302340269088745,
"learning_rate": 3.3550503583141726e-06,
"loss": 88.7964,
"step": 45
},
{
"epoch": 0.7173489278752436,
"grad_norm": 2.700557231903076,
"learning_rate": 3.272542485937369e-06,
"loss": 88.7984,
"step": 46
},
{
"epoch": 0.732943469785575,
"grad_norm": 3.645312547683716,
"learning_rate": 3.189093389542498e-06,
"loss": 88.781,
"step": 47
},
{
"epoch": 0.7485380116959064,
"grad_norm": 5.459611892700195,
"learning_rate": 3.1048047389991693e-06,
"loss": 88.6414,
"step": 48
},
{
"epoch": 0.7641325536062378,
"grad_norm": 1.5512522459030151,
"learning_rate": 3.019779227044398e-06,
"loss": 88.9102,
"step": 49
},
{
"epoch": 0.7797270955165692,
"grad_norm": 1.5456151962280273,
"learning_rate": 2.9341204441673267e-06,
"loss": 88.9206,
"step": 50
},
{
"epoch": 0.7797270955165692,
"eval_loss": 11.10726547241211,
"eval_runtime": 0.2974,
"eval_samples_per_second": 363.086,
"eval_steps_per_second": 90.772,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"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": 4315907358720.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}