bbytxt's picture
Training in progress, step 50, checkpoint
fa61381 verified
raw
history blame
10 kB
{
"best_metric": 1.5404291152954102,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.16820857863751051,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00336417157275021,
"grad_norm": 3.9489922523498535,
"learning_rate": 5.000000000000001e-07,
"loss": 6.0569,
"step": 1
},
{
"epoch": 0.00336417157275021,
"eval_loss": 2.1594057083129883,
"eval_runtime": 56.5321,
"eval_samples_per_second": 8.862,
"eval_steps_per_second": 2.229,
"step": 1
},
{
"epoch": 0.00672834314550042,
"grad_norm": 4.482152938842773,
"learning_rate": 1.0000000000000002e-06,
"loss": 7.2046,
"step": 2
},
{
"epoch": 0.010092514718250631,
"grad_norm": 5.5263352394104,
"learning_rate": 1.5e-06,
"loss": 8.4916,
"step": 3
},
{
"epoch": 0.01345668629100084,
"grad_norm": 5.707150459289551,
"learning_rate": 2.0000000000000003e-06,
"loss": 8.8524,
"step": 4
},
{
"epoch": 0.01682085786375105,
"grad_norm": 6.016858100891113,
"learning_rate": 2.5e-06,
"loss": 8.9214,
"step": 5
},
{
"epoch": 0.020185029436501262,
"grad_norm": 6.257847309112549,
"learning_rate": 3e-06,
"loss": 9.1536,
"step": 6
},
{
"epoch": 0.023549201009251473,
"grad_norm": 6.696770191192627,
"learning_rate": 3.5e-06,
"loss": 10.0647,
"step": 7
},
{
"epoch": 0.02691337258200168,
"grad_norm": 7.250229835510254,
"learning_rate": 4.000000000000001e-06,
"loss": 11.0152,
"step": 8
},
{
"epoch": 0.030277544154751892,
"grad_norm": 7.7119245529174805,
"learning_rate": 4.5e-06,
"loss": 11.2444,
"step": 9
},
{
"epoch": 0.0336417157275021,
"grad_norm": 7.244583606719971,
"learning_rate": 5e-06,
"loss": 10.8585,
"step": 10
},
{
"epoch": 0.03700588730025231,
"grad_norm": 7.843494415283203,
"learning_rate": 4.99847706754774e-06,
"loss": 10.627,
"step": 11
},
{
"epoch": 0.040370058873002525,
"grad_norm": 8.349863052368164,
"learning_rate": 4.993910125649561e-06,
"loss": 11.6061,
"step": 12
},
{
"epoch": 0.04373423044575273,
"grad_norm": 7.974443435668945,
"learning_rate": 4.986304738420684e-06,
"loss": 10.578,
"step": 13
},
{
"epoch": 0.04709840201850295,
"grad_norm": 8.698466300964355,
"learning_rate": 4.975670171853926e-06,
"loss": 11.2472,
"step": 14
},
{
"epoch": 0.050462573591253154,
"grad_norm": 8.997441291809082,
"learning_rate": 4.962019382530521e-06,
"loss": 11.7005,
"step": 15
},
{
"epoch": 0.05382674516400336,
"grad_norm": 9.786170959472656,
"learning_rate": 4.9453690018345144e-06,
"loss": 12.2871,
"step": 16
},
{
"epoch": 0.057190916736753576,
"grad_norm": 9.312055587768555,
"learning_rate": 4.925739315689991e-06,
"loss": 12.1815,
"step": 17
},
{
"epoch": 0.060555088309503784,
"grad_norm": 9.848001480102539,
"learning_rate": 4.903154239845798e-06,
"loss": 12.2101,
"step": 18
},
{
"epoch": 0.063919259882254,
"grad_norm": 10.315635681152344,
"learning_rate": 4.8776412907378845e-06,
"loss": 12.0979,
"step": 19
},
{
"epoch": 0.0672834314550042,
"grad_norm": 11.100384712219238,
"learning_rate": 4.849231551964771e-06,
"loss": 12.8286,
"step": 20
},
{
"epoch": 0.07064760302775441,
"grad_norm": 11.478273391723633,
"learning_rate": 4.817959636416969e-06,
"loss": 13.5465,
"step": 21
},
{
"epoch": 0.07401177460050462,
"grad_norm": 11.831793785095215,
"learning_rate": 4.783863644106502e-06,
"loss": 13.9233,
"step": 22
},
{
"epoch": 0.07737594617325484,
"grad_norm": 12.055624008178711,
"learning_rate": 4.746985115747918e-06,
"loss": 13.4583,
"step": 23
},
{
"epoch": 0.08074011774600505,
"grad_norm": 12.33119010925293,
"learning_rate": 4.707368982147318e-06,
"loss": 13.772,
"step": 24
},
{
"epoch": 0.08410428931875526,
"grad_norm": 14.89177131652832,
"learning_rate": 4.665063509461098e-06,
"loss": 15.4565,
"step": 25
},
{
"epoch": 0.08746846089150546,
"grad_norm": 14.688849449157715,
"learning_rate": 4.620120240391065e-06,
"loss": 15.1635,
"step": 26
},
{
"epoch": 0.09083263246425567,
"grad_norm": 14.966446876525879,
"learning_rate": 4.572593931387604e-06,
"loss": 15.1824,
"step": 27
},
{
"epoch": 0.0941968040370059,
"grad_norm": 15.037090301513672,
"learning_rate": 4.522542485937369e-06,
"loss": 15.248,
"step": 28
},
{
"epoch": 0.0975609756097561,
"grad_norm": 14.603853225708008,
"learning_rate": 4.470026884016805e-06,
"loss": 16.433,
"step": 29
},
{
"epoch": 0.10092514718250631,
"grad_norm": 16.51859474182129,
"learning_rate": 4.415111107797445e-06,
"loss": 16.8033,
"step": 30
},
{
"epoch": 0.10428931875525652,
"grad_norm": 16.52759552001953,
"learning_rate": 4.357862063693486e-06,
"loss": 16.493,
"step": 31
},
{
"epoch": 0.10765349032800672,
"grad_norm": 17.3706111907959,
"learning_rate": 4.2983495008466285e-06,
"loss": 16.9004,
"step": 32
},
{
"epoch": 0.11101766190075694,
"grad_norm": 17.978242874145508,
"learning_rate": 4.236645926147493e-06,
"loss": 17.7257,
"step": 33
},
{
"epoch": 0.11438183347350715,
"grad_norm": 17.74814224243164,
"learning_rate": 4.172826515897146e-06,
"loss": 15.9999,
"step": 34
},
{
"epoch": 0.11774600504625736,
"grad_norm": 21.516483306884766,
"learning_rate": 4.106969024216348e-06,
"loss": 19.2002,
"step": 35
},
{
"epoch": 0.12111017661900757,
"grad_norm": 21.676025390625,
"learning_rate": 4.039153688314146e-06,
"loss": 19.3753,
"step": 36
},
{
"epoch": 0.12447434819175777,
"grad_norm": 20.633501052856445,
"learning_rate": 3.969463130731183e-06,
"loss": 17.3614,
"step": 37
},
{
"epoch": 0.127838519764508,
"grad_norm": 23.484853744506836,
"learning_rate": 3.897982258676867e-06,
"loss": 18.6916,
"step": 38
},
{
"epoch": 0.1312026913372582,
"grad_norm": 22.21061897277832,
"learning_rate": 3.824798160583012e-06,
"loss": 18.4351,
"step": 39
},
{
"epoch": 0.1345668629100084,
"grad_norm": 22.049198150634766,
"learning_rate": 3.7500000000000005e-06,
"loss": 18.0943,
"step": 40
},
{
"epoch": 0.13793103448275862,
"grad_norm": 24.594404220581055,
"learning_rate": 3.6736789069647273e-06,
"loss": 19.8341,
"step": 41
},
{
"epoch": 0.14129520605550883,
"grad_norm": 23.650936126708984,
"learning_rate": 3.595927866972694e-06,
"loss": 20.1564,
"step": 42
},
{
"epoch": 0.14465937762825903,
"grad_norm": 24.20736312866211,
"learning_rate": 3.516841607689501e-06,
"loss": 19.0633,
"step": 43
},
{
"epoch": 0.14802354920100924,
"grad_norm": 24.75364112854004,
"learning_rate": 3.436516483539781e-06,
"loss": 20.2374,
"step": 44
},
{
"epoch": 0.15138772077375945,
"grad_norm": 25.638423919677734,
"learning_rate": 3.3550503583141726e-06,
"loss": 20.1314,
"step": 45
},
{
"epoch": 0.15475189234650968,
"grad_norm": 24.455801010131836,
"learning_rate": 3.272542485937369e-06,
"loss": 20.3837,
"step": 46
},
{
"epoch": 0.1581160639192599,
"grad_norm": 28.880544662475586,
"learning_rate": 3.189093389542498e-06,
"loss": 20.9076,
"step": 47
},
{
"epoch": 0.1614802354920101,
"grad_norm": 28.061445236206055,
"learning_rate": 3.1048047389991693e-06,
"loss": 21.1376,
"step": 48
},
{
"epoch": 0.1648444070647603,
"grad_norm": 30.0025577545166,
"learning_rate": 3.019779227044398e-06,
"loss": 22.3604,
"step": 49
},
{
"epoch": 0.16820857863751051,
"grad_norm": 32.991703033447266,
"learning_rate": 2.9341204441673267e-06,
"loss": 23.079,
"step": 50
},
{
"epoch": 0.16820857863751051,
"eval_loss": 1.5404291152954102,
"eval_runtime": 57.1121,
"eval_samples_per_second": 8.772,
"eval_steps_per_second": 2.206,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"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": 1.26956599246848e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}