8035 lines
219 KiB
JSON
8035 lines
219 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.08937848436435139,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 4000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.74203462600708,
|
||
|
|
"epoch": 0.00011172310545543924,
|
||
|
|
"grad_norm": 7.40625,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.545,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 4264.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.74201259613037,
|
||
|
|
"epoch": 0.00022344621091087847,
|
||
|
|
"grad_norm": 6.84375,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.5105,
|
||
|
|
"mean_token_accuracy": 0.0002816901309415698,
|
||
|
|
"num_tokens": 8413.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742000961303711,
|
||
|
|
"epoch": 0.0003351693163663177,
|
||
|
|
"grad_norm": 6.78125,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.4826,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 12394.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742033767700196,
|
||
|
|
"epoch": 0.00044689242182175694,
|
||
|
|
"grad_norm": 5.90625,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.4451,
|
||
|
|
"mean_token_accuracy": 0.0004269361263141036,
|
||
|
|
"num_tokens": 16610.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.742008590698243,
|
||
|
|
"epoch": 0.0005586155272771962,
|
||
|
|
"grad_norm": 5.9375,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 10.3813,
|
||
|
|
"mean_token_accuracy": 0.0017635513795539737,
|
||
|
|
"num_tokens": 21243.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.74174461364746,
|
||
|
|
"epoch": 0.0006703386327326354,
|
||
|
|
"grad_norm": 5.1875,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 10.2219,
|
||
|
|
"mean_token_accuracy": 0.019105370296165346,
|
||
|
|
"num_tokens": 25571.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.741024494171143,
|
||
|
|
"epoch": 0.0007820617381880747,
|
||
|
|
"grad_norm": 4.75,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 10.0233,
|
||
|
|
"mean_token_accuracy": 0.0476666621863842,
|
||
|
|
"num_tokens": 29412.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.739530563354492,
|
||
|
|
"epoch": 0.0008937848436435139,
|
||
|
|
"grad_norm": 3.75,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 9.943,
|
||
|
|
"mean_token_accuracy": 0.04776074178516865,
|
||
|
|
"num_tokens": 33893.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.736891174316407,
|
||
|
|
"epoch": 0.0010055079490989532,
|
||
|
|
"grad_norm": 3.09375,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 9.7721,
|
||
|
|
"mean_token_accuracy": 0.05200008656829595,
|
||
|
|
"num_tokens": 38043.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.733825874328613,
|
||
|
|
"epoch": 0.0011172310545543925,
|
||
|
|
"grad_norm": 2.75,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 9.7095,
|
||
|
|
"mean_token_accuracy": 0.05134744010865688,
|
||
|
|
"num_tokens": 42222.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.731979370117188,
|
||
|
|
"epoch": 0.0012289541600098315,
|
||
|
|
"grad_norm": 2.765625,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.6035,
|
||
|
|
"mean_token_accuracy": 0.05346306636929512,
|
||
|
|
"num_tokens": 46321.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.729666996002198,
|
||
|
|
"epoch": 0.0013406772654652708,
|
||
|
|
"grad_norm": 2.515625,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.5985,
|
||
|
|
"mean_token_accuracy": 0.053918526880443095,
|
||
|
|
"num_tokens": 50816.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.726247787475586,
|
||
|
|
"epoch": 0.0014524003709207101,
|
||
|
|
"grad_norm": 2.453125,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.5526,
|
||
|
|
"mean_token_accuracy": 0.05777559094130993,
|
||
|
|
"num_tokens": 55331.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.722254943847656,
|
||
|
|
"epoch": 0.0015641234763761494,
|
||
|
|
"grad_norm": 2.296875,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.4754,
|
||
|
|
"mean_token_accuracy": 0.060246657207608224,
|
||
|
|
"num_tokens": 59379.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.717647266387939,
|
||
|
|
"epoch": 0.0016758465818315885,
|
||
|
|
"grad_norm": 2.375,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.3716,
|
||
|
|
"mean_token_accuracy": 0.05563458241522312,
|
||
|
|
"num_tokens": 63463.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.709985065460206,
|
||
|
|
"epoch": 0.0017875696872870278,
|
||
|
|
"grad_norm": 2.234375,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.4054,
|
||
|
|
"mean_token_accuracy": 0.04782464448362589,
|
||
|
|
"num_tokens": 67897.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.698591709136963,
|
||
|
|
"epoch": 0.001899292792742467,
|
||
|
|
"grad_norm": 2.703125,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.2081,
|
||
|
|
"mean_token_accuracy": 0.05416969805955887,
|
||
|
|
"num_tokens": 71995.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.679736518859864,
|
||
|
|
"epoch": 0.0020110158981979064,
|
||
|
|
"grad_norm": 2.453125,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.0655,
|
||
|
|
"mean_token_accuracy": 0.06419909372925758,
|
||
|
|
"num_tokens": 75745.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.639767360687255,
|
||
|
|
"epoch": 0.0021227390036533456,
|
||
|
|
"grad_norm": 2.296875,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 9.0156,
|
||
|
|
"mean_token_accuracy": 0.06227423809468746,
|
||
|
|
"num_tokens": 79641.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.604651832580567,
|
||
|
|
"epoch": 0.002234462109108785,
|
||
|
|
"grad_norm": 2.328125,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 8.9827,
|
||
|
|
"mean_token_accuracy": 0.07007253468036652,
|
||
|
|
"num_tokens": 84368.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.576740074157716,
|
||
|
|
"epoch": 0.0023461852145642242,
|
||
|
|
"grad_norm": 3.0,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 8.9633,
|
||
|
|
"mean_token_accuracy": 0.06716309636831283,
|
||
|
|
"num_tokens": 89177.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.532594108581543,
|
||
|
|
"epoch": 0.002457908320019663,
|
||
|
|
"grad_norm": 2.171875,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 8.7625,
|
||
|
|
"mean_token_accuracy": 0.06927448399364948,
|
||
|
|
"num_tokens": 93266.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.469588470458984,
|
||
|
|
"epoch": 0.0025696314254751024,
|
||
|
|
"grad_norm": 1.9921875,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 8.6738,
|
||
|
|
"mean_token_accuracy": 0.0684173908084631,
|
||
|
|
"num_tokens": 97385.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.414745044708251,
|
||
|
|
"epoch": 0.0026813545309305417,
|
||
|
|
"grad_norm": 2.203125,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.4918,
|
||
|
|
"mean_token_accuracy": 0.06782151162624359,
|
||
|
|
"num_tokens": 100911.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.343620300292969,
|
||
|
|
"epoch": 0.002793077636385981,
|
||
|
|
"grad_norm": 1.8359375,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 8.4104,
|
||
|
|
"mean_token_accuracy": 0.07619427219033241,
|
||
|
|
"num_tokens": 104785.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.282330799102784,
|
||
|
|
"epoch": 0.0029048007418414202,
|
||
|
|
"grad_norm": 2.09375,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.3421,
|
||
|
|
"mean_token_accuracy": 0.0715565849095583,
|
||
|
|
"num_tokens": 109434.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.177853965759278,
|
||
|
|
"epoch": 0.0030165238472968595,
|
||
|
|
"grad_norm": 1.7578125,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 8.3045,
|
||
|
|
"mean_token_accuracy": 0.07821577228605747,
|
||
|
|
"num_tokens": 113869.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.01875,
|
||
|
|
"epoch": 0.003128246952752299,
|
||
|
|
"grad_norm": 1.640625,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 8.2069,
|
||
|
|
"mean_token_accuracy": 0.07112646363675594,
|
||
|
|
"num_tokens": 118332.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.93814001083374,
|
||
|
|
"epoch": 0.003239970058207738,
|
||
|
|
"grad_norm": 1.65625,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 8.0893,
|
||
|
|
"mean_token_accuracy": 0.06839369647204877,
|
||
|
|
"num_tokens": 122140.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.799712753295898,
|
||
|
|
"epoch": 0.003351693163663177,
|
||
|
|
"grad_norm": 1.6875,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 7.9249,
|
||
|
|
"mean_token_accuracy": 0.067073168233037,
|
||
|
|
"num_tokens": 126515.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.603694915771484,
|
||
|
|
"epoch": 0.0034634162691186163,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 7.897,
|
||
|
|
"mean_token_accuracy": 0.07342451699078083,
|
||
|
|
"num_tokens": 130397.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.402643203735352,
|
||
|
|
"epoch": 0.0035751393745740555,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 7.815,
|
||
|
|
"mean_token_accuracy": 0.07550931498408317,
|
||
|
|
"num_tokens": 134428.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.27815113067627,
|
||
|
|
"epoch": 0.003686862480029495,
|
||
|
|
"grad_norm": 1.5546875,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.6921,
|
||
|
|
"mean_token_accuracy": 0.08235657699406147,
|
||
|
|
"num_tokens": 138294.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.126440715789794,
|
||
|
|
"epoch": 0.003798585585484934,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.6466,
|
||
|
|
"mean_token_accuracy": 0.0780983179807663,
|
||
|
|
"num_tokens": 142750.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.904253101348877,
|
||
|
|
"epoch": 0.003910308690940373,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.5833,
|
||
|
|
"mean_token_accuracy": 0.06832590401172638,
|
||
|
|
"num_tokens": 147220.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.704329586029052,
|
||
|
|
"epoch": 0.004022031796395813,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.464,
|
||
|
|
"mean_token_accuracy": 0.08249393478035927,
|
||
|
|
"num_tokens": 151396.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.544238567352295,
|
||
|
|
"epoch": 0.0041337549018512516,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.4503,
|
||
|
|
"mean_token_accuracy": 0.07549951747059822,
|
||
|
|
"num_tokens": 155336.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.501252269744873,
|
||
|
|
"epoch": 0.004245478007306691,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.4842,
|
||
|
|
"mean_token_accuracy": 0.07688803523778916,
|
||
|
|
"num_tokens": 159752.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.432751655578613,
|
||
|
|
"epoch": 0.00435720111276213,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.5426,
|
||
|
|
"mean_token_accuracy": 0.07533748783171176,
|
||
|
|
"num_tokens": 163895.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.257897663116456,
|
||
|
|
"epoch": 0.00446892421821757,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.3421,
|
||
|
|
"mean_token_accuracy": 0.08197390548884868,
|
||
|
|
"num_tokens": 168312.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.259009075164794,
|
||
|
|
"epoch": 0.004580647323673009,
|
||
|
|
"grad_norm": 1.546875,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.3701,
|
||
|
|
"mean_token_accuracy": 0.08555959761142731,
|
||
|
|
"num_tokens": 172358.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.100054454803466,
|
||
|
|
"epoch": 0.0046923704291284484,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.357,
|
||
|
|
"mean_token_accuracy": 0.08119111023843288,
|
||
|
|
"num_tokens": 177085.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.163977813720702,
|
||
|
|
"epoch": 0.004804093534583887,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.4691,
|
||
|
|
"mean_token_accuracy": 0.07897469773888588,
|
||
|
|
"num_tokens": 181410.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.064214897155761,
|
||
|
|
"epoch": 0.004915816640039326,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.2085,
|
||
|
|
"mean_token_accuracy": 0.08347514495253563,
|
||
|
|
"num_tokens": 185649.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.9723944664001465,
|
||
|
|
"epoch": 0.005027539745494766,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 7.2571,
|
||
|
|
"mean_token_accuracy": 0.08833960294723511,
|
||
|
|
"num_tokens": 190055.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.958705711364746,
|
||
|
|
"epoch": 0.005139262850950205,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.2784,
|
||
|
|
"mean_token_accuracy": 0.08142814487218857,
|
||
|
|
"num_tokens": 194267.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.980498743057251,
|
||
|
|
"epoch": 0.0052509859564056445,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.2042,
|
||
|
|
"mean_token_accuracy": 0.08119908273220063,
|
||
|
|
"num_tokens": 198483.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.903439283370972,
|
||
|
|
"epoch": 0.005362709061861083,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.1137,
|
||
|
|
"mean_token_accuracy": 0.09260561317205429,
|
||
|
|
"num_tokens": 202514.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.820244312286377,
|
||
|
|
"epoch": 0.005474432167316523,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 7.2591,
|
||
|
|
"mean_token_accuracy": 0.08432262316346169,
|
||
|
|
"num_tokens": 206748.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.817278146743774,
|
||
|
|
"epoch": 0.005586155272771962,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.1337,
|
||
|
|
"mean_token_accuracy": 0.08795059770345688,
|
||
|
|
"num_tokens": 210981.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.902036476135254,
|
||
|
|
"epoch": 0.005697878378227402,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.2718,
|
||
|
|
"mean_token_accuracy": 0.08792312145233154,
|
||
|
|
"num_tokens": 215551.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.720875978469849,
|
||
|
|
"epoch": 0.0058096014836828405,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.0933,
|
||
|
|
"mean_token_accuracy": 0.09327159300446511,
|
||
|
|
"num_tokens": 219677.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8553773880004885,
|
||
|
|
"epoch": 0.005921324589138279,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 7.1915,
|
||
|
|
"mean_token_accuracy": 0.08988388553261757,
|
||
|
|
"num_tokens": 223457.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.8154174327850345,
|
||
|
|
"epoch": 0.006033047694593719,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 7.026,
|
||
|
|
"mean_token_accuracy": 0.10610299035906792,
|
||
|
|
"num_tokens": 227135.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.805374622344971,
|
||
|
|
"epoch": 0.006144770800049158,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.2242,
|
||
|
|
"mean_token_accuracy": 0.0845766805112362,
|
||
|
|
"num_tokens": 231393.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.793313646316529,
|
||
|
|
"epoch": 0.006256493905504598,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 7.2039,
|
||
|
|
"mean_token_accuracy": 0.09036076590418815,
|
||
|
|
"num_tokens": 235959.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.797818899154663,
|
||
|
|
"epoch": 0.0063682170109600365,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.0391,
|
||
|
|
"mean_token_accuracy": 0.10008666068315505,
|
||
|
|
"num_tokens": 239875.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.643310832977295,
|
||
|
|
"epoch": 0.006479940116415476,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 7.1816,
|
||
|
|
"mean_token_accuracy": 0.10088859647512435,
|
||
|
|
"num_tokens": 244397.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.749200963973999,
|
||
|
|
"epoch": 0.006591663221870915,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 7.1022,
|
||
|
|
"mean_token_accuracy": 0.09432346150279045,
|
||
|
|
"num_tokens": 248441.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.724449968338012,
|
||
|
|
"epoch": 0.006703386327326354,
|
||
|
|
"grad_norm": 1.6328125,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 7.1223,
|
||
|
|
"mean_token_accuracy": 0.09665866494178772,
|
||
|
|
"num_tokens": 252693.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.719059801101684,
|
||
|
|
"epoch": 0.006815109432781794,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 7.0852,
|
||
|
|
"mean_token_accuracy": 0.0973274439573288,
|
||
|
|
"num_tokens": 257135.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.689913558959961,
|
||
|
|
"epoch": 0.0069268325382372325,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 7.1788,
|
||
|
|
"mean_token_accuracy": 0.09386017993092537,
|
||
|
|
"num_tokens": 261919.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.723158597946167,
|
||
|
|
"epoch": 0.007038555643692672,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 7.0899,
|
||
|
|
"mean_token_accuracy": 0.10055064782500267,
|
||
|
|
"num_tokens": 266656.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.58135347366333,
|
||
|
|
"epoch": 0.007150278749148111,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 7.0484,
|
||
|
|
"mean_token_accuracy": 0.0989685259759426,
|
||
|
|
"num_tokens": 270879.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.633032703399659,
|
||
|
|
"epoch": 0.007262001854603551,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 7.0017,
|
||
|
|
"mean_token_accuracy": 0.11045164242386818,
|
||
|
|
"num_tokens": 274884.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.55345048904419,
|
||
|
|
"epoch": 0.00737372496005899,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 6.9434,
|
||
|
|
"mean_token_accuracy": 0.10104935392737388,
|
||
|
|
"num_tokens": 279096.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.626837635040284,
|
||
|
|
"epoch": 0.007485448065514429,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 7.0338,
|
||
|
|
"mean_token_accuracy": 0.10009614899754524,
|
||
|
|
"num_tokens": 282923.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.528380966186523,
|
||
|
|
"epoch": 0.007597171170969868,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 6.99,
|
||
|
|
"mean_token_accuracy": 0.10532780215144158,
|
||
|
|
"num_tokens": 287283.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.572710466384888,
|
||
|
|
"epoch": 0.007708894276425307,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 6.9504,
|
||
|
|
"mean_token_accuracy": 0.10530123338103295,
|
||
|
|
"num_tokens": 291409.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.547561979293823,
|
||
|
|
"epoch": 0.007820617381880746,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 6.9732,
|
||
|
|
"mean_token_accuracy": 0.10650015398859977,
|
||
|
|
"num_tokens": 295157.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.669625616073608,
|
||
|
|
"epoch": 0.007932340487336187,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 7.0005,
|
||
|
|
"mean_token_accuracy": 0.10243007764220238,
|
||
|
|
"num_tokens": 299370.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.543743228912353,
|
||
|
|
"epoch": 0.008044063592791625,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 7.0093,
|
||
|
|
"mean_token_accuracy": 0.11244696080684662,
|
||
|
|
"num_tokens": 303955.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.570756626129151,
|
||
|
|
"epoch": 0.008155786698247064,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 6.9899,
|
||
|
|
"mean_token_accuracy": 0.10562622845172882,
|
||
|
|
"num_tokens": 308047.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.594445466995239,
|
||
|
|
"epoch": 0.008267509803702503,
|
||
|
|
"grad_norm": 1.609375,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 6.9313,
|
||
|
|
"mean_token_accuracy": 0.11213268861174583,
|
||
|
|
"num_tokens": 312050.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.5787379264831545,
|
||
|
|
"epoch": 0.008379232909157944,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 6.9007,
|
||
|
|
"mean_token_accuracy": 0.11451447457075119,
|
||
|
|
"num_tokens": 315901.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.617064571380615,
|
||
|
|
"epoch": 0.008490956014613383,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 6.9233,
|
||
|
|
"mean_token_accuracy": 0.11718286573886871,
|
||
|
|
"num_tokens": 320077.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.479556846618652,
|
||
|
|
"epoch": 0.008602679120068821,
|
||
|
|
"grad_norm": 1.546875,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 6.8783,
|
||
|
|
"mean_token_accuracy": 0.11937321722507477,
|
||
|
|
"num_tokens": 324365.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.485933542251587,
|
||
|
|
"epoch": 0.00871440222552426,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 6.8292,
|
||
|
|
"mean_token_accuracy": 0.11517802253365517,
|
||
|
|
"num_tokens": 327971.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.489345073699951,
|
||
|
|
"epoch": 0.0088261253309797,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 6.8634,
|
||
|
|
"mean_token_accuracy": 0.12188869342207909,
|
||
|
|
"num_tokens": 331791.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.405192232131958,
|
||
|
|
"epoch": 0.00893784843643514,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 6.9151,
|
||
|
|
"mean_token_accuracy": 0.11866991743445396,
|
||
|
|
"num_tokens": 335616.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.442100572586059,
|
||
|
|
"epoch": 0.009049571541890579,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 6.8337,
|
||
|
|
"mean_token_accuracy": 0.1216049998998642,
|
||
|
|
"num_tokens": 339815.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.466716241836548,
|
||
|
|
"epoch": 0.009161294647346017,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 6.8153,
|
||
|
|
"mean_token_accuracy": 0.11885289028286934,
|
||
|
|
"num_tokens": 344045.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.439525604248047,
|
||
|
|
"epoch": 0.009273017752801456,
|
||
|
|
"grad_norm": 1.5859375,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 6.9127,
|
||
|
|
"mean_token_accuracy": 0.1201499916613102,
|
||
|
|
"num_tokens": 348726.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.421639108657837,
|
||
|
|
"epoch": 0.009384740858256897,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 6.8973,
|
||
|
|
"mean_token_accuracy": 0.11855003610253334,
|
||
|
|
"num_tokens": 353228.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.533071041107178,
|
||
|
|
"epoch": 0.009496463963712336,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 6.8732,
|
||
|
|
"mean_token_accuracy": 0.12777991741895675,
|
||
|
|
"num_tokens": 357379.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.404365539550781,
|
||
|
|
"epoch": 0.009608187069167775,
|
||
|
|
"grad_norm": 1.78125,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 6.8237,
|
||
|
|
"mean_token_accuracy": 0.11873817816376686,
|
||
|
|
"num_tokens": 361347.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3829724311828615,
|
||
|
|
"epoch": 0.009719910174623213,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 6.8001,
|
||
|
|
"mean_token_accuracy": 0.12097886875271797,
|
||
|
|
"num_tokens": 365364.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.4662988662719725,
|
||
|
|
"epoch": 0.009831633280078652,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 6.8435,
|
||
|
|
"mean_token_accuracy": 0.1184915505349636,
|
||
|
|
"num_tokens": 369648.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.550151824951172,
|
||
|
|
"epoch": 0.009943356385534093,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 6.8211,
|
||
|
|
"mean_token_accuracy": 0.1224476382136345,
|
||
|
|
"num_tokens": 373734.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.477874803543091,
|
||
|
|
"epoch": 0.010055079490989532,
|
||
|
|
"grad_norm": 1.6328125,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 6.8174,
|
||
|
|
"mean_token_accuracy": 0.12541017457842826,
|
||
|
|
"num_tokens": 378184.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.454969882965088,
|
||
|
|
"epoch": 0.01016680259644497,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 6.9275,
|
||
|
|
"mean_token_accuracy": 0.11591533869504929,
|
||
|
|
"num_tokens": 382686.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.344128131866455,
|
||
|
|
"epoch": 0.01027852570190041,
|
||
|
|
"grad_norm": 1.6640625,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 6.8348,
|
||
|
|
"mean_token_accuracy": 0.12774229273200036,
|
||
|
|
"num_tokens": 387210.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.421209812164307,
|
||
|
|
"epoch": 0.01039024880735585,
|
||
|
|
"grad_norm": 1.484375,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 6.8216,
|
||
|
|
"mean_token_accuracy": 0.12031811997294425,
|
||
|
|
"num_tokens": 391247.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.465836143493652,
|
||
|
|
"epoch": 0.010501971912811289,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 6.6907,
|
||
|
|
"mean_token_accuracy": 0.13249015137553216,
|
||
|
|
"num_tokens": 395188.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.280446100234985,
|
||
|
|
"epoch": 0.010613695018266728,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 6.7666,
|
||
|
|
"mean_token_accuracy": 0.12789778113365174,
|
||
|
|
"num_tokens": 399513.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.51575026512146,
|
||
|
|
"epoch": 0.010725418123722167,
|
||
|
|
"grad_norm": 1.59375,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 6.8438,
|
||
|
|
"mean_token_accuracy": 0.12305677309632301,
|
||
|
|
"num_tokens": 404052.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.260741233825684,
|
||
|
|
"epoch": 0.010837141229177606,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 6.6724,
|
||
|
|
"mean_token_accuracy": 0.13464880287647246,
|
||
|
|
"num_tokens": 408299.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3084382057189945,
|
||
|
|
"epoch": 0.010948864334633046,
|
||
|
|
"grad_norm": 1.5859375,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 6.6808,
|
||
|
|
"mean_token_accuracy": 0.12868183255195617,
|
||
|
|
"num_tokens": 412376.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.318713665008545,
|
||
|
|
"epoch": 0.011060587440088485,
|
||
|
|
"grad_norm": 1.484375,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 6.7365,
|
||
|
|
"mean_token_accuracy": 0.12830623611807823,
|
||
|
|
"num_tokens": 417010.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.343731689453125,
|
||
|
|
"epoch": 0.011172310545543924,
|
||
|
|
"grad_norm": 1.734375,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 6.615,
|
||
|
|
"mean_token_accuracy": 0.1360365241765976,
|
||
|
|
"num_tokens": 421167.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.227418041229248,
|
||
|
|
"epoch": 0.011284033650999363,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 6.715,
|
||
|
|
"mean_token_accuracy": 0.1310766190290451,
|
||
|
|
"num_tokens": 425942.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.354942321777344,
|
||
|
|
"epoch": 0.011395756756454803,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 6.7458,
|
||
|
|
"mean_token_accuracy": 0.13017034903168678,
|
||
|
|
"num_tokens": 430529.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.211854124069214,
|
||
|
|
"epoch": 0.011507479861910242,
|
||
|
|
"grad_norm": 1.515625,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 6.6012,
|
||
|
|
"mean_token_accuracy": 0.12464086860418319,
|
||
|
|
"num_tokens": 434464.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.229535865783691,
|
||
|
|
"epoch": 0.011619202967365681,
|
||
|
|
"grad_norm": 1.578125,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 6.72,
|
||
|
|
"mean_token_accuracy": 0.13534524589776992,
|
||
|
|
"num_tokens": 438763.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.300835609436035,
|
||
|
|
"epoch": 0.01173092607282112,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 6.67,
|
||
|
|
"mean_token_accuracy": 0.12867324203252792,
|
||
|
|
"num_tokens": 442945.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.314332723617554,
|
||
|
|
"epoch": 0.011842649178276559,
|
||
|
|
"grad_norm": 1.5859375,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 6.7556,
|
||
|
|
"mean_token_accuracy": 0.12306396216154099,
|
||
|
|
"num_tokens": 447301.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.266288375854492,
|
||
|
|
"epoch": 0.011954372283732,
|
||
|
|
"grad_norm": 1.5625,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 6.6174,
|
||
|
|
"mean_token_accuracy": 0.13486616015434266,
|
||
|
|
"num_tokens": 451365.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.152557897567749,
|
||
|
|
"epoch": 0.012066095389187438,
|
||
|
|
"grad_norm": 1.671875,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 6.6467,
|
||
|
|
"mean_token_accuracy": 0.13019582405686378,
|
||
|
|
"num_tokens": 455469.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.219053745269775,
|
||
|
|
"epoch": 0.012177818494642877,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.7099,
|
||
|
|
"mean_token_accuracy": 0.13144526258111,
|
||
|
|
"num_tokens": 459641.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.226452398300171,
|
||
|
|
"epoch": 0.012289541600098316,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.6922,
|
||
|
|
"mean_token_accuracy": 0.13080282509326935,
|
||
|
|
"num_tokens": 463866.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.169753932952881,
|
||
|
|
"epoch": 0.012401264705553756,
|
||
|
|
"grad_norm": 1.578125,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 6.5534,
|
||
|
|
"mean_token_accuracy": 0.14116353392601014,
|
||
|
|
"num_tokens": 467692.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.142725467681885,
|
||
|
|
"epoch": 0.012512987811009195,
|
||
|
|
"grad_norm": 1.625,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.706,
|
||
|
|
"mean_token_accuracy": 0.13806632682681083,
|
||
|
|
"num_tokens": 471719.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.179370450973511,
|
||
|
|
"epoch": 0.012624710916464634,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.6323,
|
||
|
|
"mean_token_accuracy": 0.12942282631993293,
|
||
|
|
"num_tokens": 475978.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.241915130615235,
|
||
|
|
"epoch": 0.012736434021920073,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 6.7049,
|
||
|
|
"mean_token_accuracy": 0.13150753006339072,
|
||
|
|
"num_tokens": 480538.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.216012620925904,
|
||
|
|
"epoch": 0.012848157127375512,
|
||
|
|
"grad_norm": 1.53125,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.6041,
|
||
|
|
"mean_token_accuracy": 0.13532499819993973,
|
||
|
|
"num_tokens": 484604.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.280426120758056,
|
||
|
|
"epoch": 0.012959880232830952,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.6293,
|
||
|
|
"mean_token_accuracy": 0.13353263586759567,
|
||
|
|
"num_tokens": 489117.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.161381196975708,
|
||
|
|
"epoch": 0.013071603338286391,
|
||
|
|
"grad_norm": 1.640625,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.5337,
|
||
|
|
"mean_token_accuracy": 0.14060464650392532,
|
||
|
|
"num_tokens": 493020.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.130830383300781,
|
||
|
|
"epoch": 0.01318332644374183,
|
||
|
|
"grad_norm": 1.6171875,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.688,
|
||
|
|
"mean_token_accuracy": 0.1310403361916542,
|
||
|
|
"num_tokens": 497224.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2293980598449705,
|
||
|
|
"epoch": 0.013295049549197269,
|
||
|
|
"grad_norm": 1.578125,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.6199,
|
||
|
|
"mean_token_accuracy": 0.13552179485559462,
|
||
|
|
"num_tokens": 501323.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.092097234725952,
|
||
|
|
"epoch": 0.013406772654652708,
|
||
|
|
"grad_norm": 1.59375,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.6871,
|
||
|
|
"mean_token_accuracy": 0.1318632557988167,
|
||
|
|
"num_tokens": 505544.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2185986042022705,
|
||
|
|
"epoch": 0.013518495760108148,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.624,
|
||
|
|
"mean_token_accuracy": 0.14037465676665306,
|
||
|
|
"num_tokens": 509980.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0673870086669925,
|
||
|
|
"epoch": 0.013630218865563587,
|
||
|
|
"grad_norm": 1.84375,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.4906,
|
||
|
|
"mean_token_accuracy": 0.1455707758665085,
|
||
|
|
"num_tokens": 514264.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.061304330825806,
|
||
|
|
"epoch": 0.013741941971019026,
|
||
|
|
"grad_norm": 1.6875,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.573,
|
||
|
|
"mean_token_accuracy": 0.14321403577923775,
|
||
|
|
"num_tokens": 518482.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.22766146659851,
|
||
|
|
"epoch": 0.013853665076474465,
|
||
|
|
"grad_norm": 1.515625,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.6066,
|
||
|
|
"mean_token_accuracy": 0.1336400181055069,
|
||
|
|
"num_tokens": 522765.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.029418087005615,
|
||
|
|
"epoch": 0.013965388181929906,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.4457,
|
||
|
|
"mean_token_accuracy": 0.14515347853302957,
|
||
|
|
"num_tokens": 526794.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.065269136428833,
|
||
|
|
"epoch": 0.014077111287385344,
|
||
|
|
"grad_norm": 1.53125,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.5766,
|
||
|
|
"mean_token_accuracy": 0.14270118325948716,
|
||
|
|
"num_tokens": 531070.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.208616876602173,
|
||
|
|
"epoch": 0.014188834392840783,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.6389,
|
||
|
|
"mean_token_accuracy": 0.13457323089241982,
|
||
|
|
"num_tokens": 535655.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.065006256103516,
|
||
|
|
"epoch": 0.014300557498296222,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.666,
|
||
|
|
"mean_token_accuracy": 0.13108374997973443,
|
||
|
|
"num_tokens": 540231.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.094880771636963,
|
||
|
|
"epoch": 0.014412280603751661,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.5078,
|
||
|
|
"mean_token_accuracy": 0.14435381516814233,
|
||
|
|
"num_tokens": 544180.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.076756286621094,
|
||
|
|
"epoch": 0.014524003709207102,
|
||
|
|
"grad_norm": 1.640625,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.4786,
|
||
|
|
"mean_token_accuracy": 0.13342859596014023,
|
||
|
|
"num_tokens": 547905.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.96412615776062,
|
||
|
|
"epoch": 0.01463572681466254,
|
||
|
|
"grad_norm": 1.53125,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.5565,
|
||
|
|
"mean_token_accuracy": 0.14217662066221237,
|
||
|
|
"num_tokens": 552248.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.046826982498169,
|
||
|
|
"epoch": 0.01474744992011798,
|
||
|
|
"grad_norm": 1.6875,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.3918,
|
||
|
|
"mean_token_accuracy": 0.14909711182117463,
|
||
|
|
"num_tokens": 556430.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.026239967346191,
|
||
|
|
"epoch": 0.014859173025573418,
|
||
|
|
"grad_norm": 1.6875,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.4678,
|
||
|
|
"mean_token_accuracy": 0.15065777227282523,
|
||
|
|
"num_tokens": 560114.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.857525396347046,
|
||
|
|
"epoch": 0.014970896131028859,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.4711,
|
||
|
|
"mean_token_accuracy": 0.14087381735444068,
|
||
|
|
"num_tokens": 564624.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.029787588119507,
|
||
|
|
"epoch": 0.015082619236484298,
|
||
|
|
"grad_norm": 1.6015625,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.4073,
|
||
|
|
"mean_token_accuracy": 0.14824407249689103,
|
||
|
|
"num_tokens": 568918.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.077581787109375,
|
||
|
|
"epoch": 0.015194342341939737,
|
||
|
|
"grad_norm": 1.59375,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.4725,
|
||
|
|
"mean_token_accuracy": 0.15365976840257645,
|
||
|
|
"num_tokens": 572972.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.980326414108276,
|
||
|
|
"epoch": 0.015306065447395175,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.4873,
|
||
|
|
"mean_token_accuracy": 0.15378629714250563,
|
||
|
|
"num_tokens": 577250.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.116094398498535,
|
||
|
|
"epoch": 0.015417788552850614,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.4245,
|
||
|
|
"mean_token_accuracy": 0.1488552987575531,
|
||
|
|
"num_tokens": 581418.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.932662296295166,
|
||
|
|
"epoch": 0.015529511658306055,
|
||
|
|
"grad_norm": 1.6015625,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.5042,
|
||
|
|
"mean_token_accuracy": 0.15049396306276322,
|
||
|
|
"num_tokens": 585675.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.966062307357788,
|
||
|
|
"epoch": 0.015641234763761492,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.392,
|
||
|
|
"mean_token_accuracy": 0.1462944969534874,
|
||
|
|
"num_tokens": 590032.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.915396404266358,
|
||
|
|
"epoch": 0.015752957869216933,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.3949,
|
||
|
|
"mean_token_accuracy": 0.1510719522833824,
|
||
|
|
"num_tokens": 594185.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.896506881713867,
|
||
|
|
"epoch": 0.015864680974672373,
|
||
|
|
"grad_norm": 1.5546875,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.3488,
|
||
|
|
"mean_token_accuracy": 0.15710561126470565,
|
||
|
|
"num_tokens": 598246.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.905340528488159,
|
||
|
|
"epoch": 0.01597640408012781,
|
||
|
|
"grad_norm": 1.515625,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.4826,
|
||
|
|
"mean_token_accuracy": 0.14725056737661363,
|
||
|
|
"num_tokens": 602676.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.877582645416259,
|
||
|
|
"epoch": 0.01608812718558325,
|
||
|
|
"grad_norm": 1.5546875,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.3352,
|
||
|
|
"mean_token_accuracy": 0.16034641861915588,
|
||
|
|
"num_tokens": 606693.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.880430507659912,
|
||
|
|
"epoch": 0.01619985029103869,
|
||
|
|
"grad_norm": 1.6484375,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.3591,
|
||
|
|
"mean_token_accuracy": 0.14268538355827332,
|
||
|
|
"num_tokens": 610780.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.902221918106079,
|
||
|
|
"epoch": 0.01631157339649413,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.4226,
|
||
|
|
"mean_token_accuracy": 0.1481914848089218,
|
||
|
|
"num_tokens": 614746.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.847220468521118,
|
||
|
|
"epoch": 0.01642329650194957,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.3719,
|
||
|
|
"mean_token_accuracy": 0.15163339525461197,
|
||
|
|
"num_tokens": 619222.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.968106889724732,
|
||
|
|
"epoch": 0.016535019607405006,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.5165,
|
||
|
|
"mean_token_accuracy": 0.14626363143324853,
|
||
|
|
"num_tokens": 623746.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9071704864501955,
|
||
|
|
"epoch": 0.016646742712860447,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.366,
|
||
|
|
"mean_token_accuracy": 0.15544869527220725,
|
||
|
|
"num_tokens": 628392.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.845142030715943,
|
||
|
|
"epoch": 0.016758465818315887,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.3775,
|
||
|
|
"mean_token_accuracy": 0.14660717099905013,
|
||
|
|
"num_tokens": 632439.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.813414907455444,
|
||
|
|
"epoch": 0.016870188923771325,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.4088,
|
||
|
|
"mean_token_accuracy": 0.1431469090282917,
|
||
|
|
"num_tokens": 636801.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.88551287651062,
|
||
|
|
"epoch": 0.016981912029226765,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.2173,
|
||
|
|
"mean_token_accuracy": 0.16097238063812255,
|
||
|
|
"num_tokens": 640818.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7791321754455565,
|
||
|
|
"epoch": 0.017093635134682202,
|
||
|
|
"grad_norm": 1.6171875,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.3784,
|
||
|
|
"mean_token_accuracy": 0.14307227358222008,
|
||
|
|
"num_tokens": 644914.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.967279005050659,
|
||
|
|
"epoch": 0.017205358240137643,
|
||
|
|
"grad_norm": 1.5625,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.4658,
|
||
|
|
"mean_token_accuracy": 0.14935086220502852,
|
||
|
|
"num_tokens": 649368.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.788582992553711,
|
||
|
|
"epoch": 0.017317081345593083,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.2984,
|
||
|
|
"mean_token_accuracy": 0.15846630781888962,
|
||
|
|
"num_tokens": 653537.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.87021164894104,
|
||
|
|
"epoch": 0.01742880445104852,
|
||
|
|
"grad_norm": 1.5625,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.4177,
|
||
|
|
"mean_token_accuracy": 0.13871796652674676,
|
||
|
|
"num_tokens": 658232.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.85303897857666,
|
||
|
|
"epoch": 0.01754052755650396,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.3841,
|
||
|
|
"mean_token_accuracy": 0.14893919229507446,
|
||
|
|
"num_tokens": 662512.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.839845895767212,
|
||
|
|
"epoch": 0.0176522506619594,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.372,
|
||
|
|
"mean_token_accuracy": 0.15011741518974303,
|
||
|
|
"num_tokens": 666759.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.646692132949829,
|
||
|
|
"epoch": 0.01776397376741484,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.2896,
|
||
|
|
"mean_token_accuracy": 0.1571863681077957,
|
||
|
|
"num_tokens": 670870.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.806870698928833,
|
||
|
|
"epoch": 0.01787569687287028,
|
||
|
|
"grad_norm": 1.515625,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.2513,
|
||
|
|
"mean_token_accuracy": 0.158031065762043,
|
||
|
|
"num_tokens": 675150.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.714898729324341,
|
||
|
|
"epoch": 0.017987419978325717,
|
||
|
|
"grad_norm": 1.6875,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.1745,
|
||
|
|
"mean_token_accuracy": 0.1610417976975441,
|
||
|
|
"num_tokens": 679083.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.70656795501709,
|
||
|
|
"epoch": 0.018099143083781157,
|
||
|
|
"grad_norm": 1.65625,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.371,
|
||
|
|
"mean_token_accuracy": 0.15746122524142264,
|
||
|
|
"num_tokens": 683477.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.743958902359009,
|
||
|
|
"epoch": 0.018210866189236594,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.1656,
|
||
|
|
"mean_token_accuracy": 0.16271859258413315,
|
||
|
|
"num_tokens": 687819.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8285057067871096,
|
||
|
|
"epoch": 0.018322589294692035,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.3924,
|
||
|
|
"mean_token_accuracy": 0.15080199763178825,
|
||
|
|
"num_tokens": 692017.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8905205726623535,
|
||
|
|
"epoch": 0.018434312400147475,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.3853,
|
||
|
|
"mean_token_accuracy": 0.14643741324543952,
|
||
|
|
"num_tokens": 696853.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.839770412445068,
|
||
|
|
"epoch": 0.018546035505602913,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.4221,
|
||
|
|
"mean_token_accuracy": 0.1416957326233387,
|
||
|
|
"num_tokens": 701131.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.750663423538208,
|
||
|
|
"epoch": 0.018657758611058353,
|
||
|
|
"grad_norm": 1.5546875,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.3757,
|
||
|
|
"mean_token_accuracy": 0.1462937667965889,
|
||
|
|
"num_tokens": 705428.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.672054672241211,
|
||
|
|
"epoch": 0.018769481716513794,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.2377,
|
||
|
|
"mean_token_accuracy": 0.16088497787714004,
|
||
|
|
"num_tokens": 709760.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.700072860717773,
|
||
|
|
"epoch": 0.01888120482196923,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.2073,
|
||
|
|
"mean_token_accuracy": 0.1617395505309105,
|
||
|
|
"num_tokens": 713964.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.665010023117065,
|
||
|
|
"epoch": 0.01899292792742467,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.3575,
|
||
|
|
"mean_token_accuracy": 0.15287077873945237,
|
||
|
|
"num_tokens": 718305.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.806714677810669,
|
||
|
|
"epoch": 0.01910465103288011,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.2661,
|
||
|
|
"mean_token_accuracy": 0.15892615169286728,
|
||
|
|
"num_tokens": 722705.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.528658866882324,
|
||
|
|
"epoch": 0.01921637413833555,
|
||
|
|
"grad_norm": 1.5703125,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.1765,
|
||
|
|
"mean_token_accuracy": 0.16424758732318878,
|
||
|
|
"num_tokens": 726529.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.659326124191284,
|
||
|
|
"epoch": 0.01932809724379099,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.2522,
|
||
|
|
"mean_token_accuracy": 0.15339272618293762,
|
||
|
|
"num_tokens": 730535.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.74210753440857,
|
||
|
|
"epoch": 0.019439820349246427,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.2117,
|
||
|
|
"mean_token_accuracy": 0.15879523605108262,
|
||
|
|
"num_tokens": 734836.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.65736346244812,
|
||
|
|
"epoch": 0.019551543454701868,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.2891,
|
||
|
|
"mean_token_accuracy": 0.15371360629796982,
|
||
|
|
"num_tokens": 739176.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.574539995193481,
|
||
|
|
"epoch": 0.019663266560157305,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.2674,
|
||
|
|
"mean_token_accuracy": 0.15556667894124984,
|
||
|
|
"num_tokens": 743497.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.720397853851319,
|
||
|
|
"epoch": 0.019774989665612745,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.2818,
|
||
|
|
"mean_token_accuracy": 0.16183461248874664,
|
||
|
|
"num_tokens": 747185.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.739978790283203,
|
||
|
|
"epoch": 0.019886712771068186,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.4179,
|
||
|
|
"mean_token_accuracy": 0.1448575735092163,
|
||
|
|
"num_tokens": 751345.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7309082508087155,
|
||
|
|
"epoch": 0.019998435876523623,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.2944,
|
||
|
|
"mean_token_accuracy": 0.15704837888479234,
|
||
|
|
"num_tokens": 755618.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.653637266159057,
|
||
|
|
"epoch": 0.020110158981979064,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.2788,
|
||
|
|
"mean_token_accuracy": 0.15478281527757645,
|
||
|
|
"num_tokens": 759583.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.644137716293335,
|
||
|
|
"epoch": 0.0202218820874345,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.1758,
|
||
|
|
"mean_token_accuracy": 0.1591601625084877,
|
||
|
|
"num_tokens": 763861.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.53189525604248,
|
||
|
|
"epoch": 0.02033360519288994,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.1717,
|
||
|
|
"mean_token_accuracy": 0.16117519289255142,
|
||
|
|
"num_tokens": 768046.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.686648035049439,
|
||
|
|
"epoch": 0.020445328298345382,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.1927,
|
||
|
|
"mean_token_accuracy": 0.15583422034978867,
|
||
|
|
"num_tokens": 772570.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.651849317550659,
|
||
|
|
"epoch": 0.02055705140380082,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.3181,
|
||
|
|
"mean_token_accuracy": 0.15458481013774872,
|
||
|
|
"num_tokens": 777324.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.669686937332154,
|
||
|
|
"epoch": 0.02066877450925626,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.3017,
|
||
|
|
"mean_token_accuracy": 0.14780564680695535,
|
||
|
|
"num_tokens": 781829.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.655124092102051,
|
||
|
|
"epoch": 0.0207804976147117,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.1719,
|
||
|
|
"mean_token_accuracy": 0.15766340345144272,
|
||
|
|
"num_tokens": 786089.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.433820819854736,
|
||
|
|
"epoch": 0.020892220720167137,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.1607,
|
||
|
|
"mean_token_accuracy": 0.16852562725543976,
|
||
|
|
"num_tokens": 790273.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.675999402999878,
|
||
|
|
"epoch": 0.021003943825622578,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.1583,
|
||
|
|
"mean_token_accuracy": 0.17233449518680571,
|
||
|
|
"num_tokens": 794600.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.556878328323364,
|
||
|
|
"epoch": 0.021115666931078015,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.149,
|
||
|
|
"mean_token_accuracy": 0.16213736683130264,
|
||
|
|
"num_tokens": 798756.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6472193717956545,
|
||
|
|
"epoch": 0.021227390036533456,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.1599,
|
||
|
|
"mean_token_accuracy": 0.16358468383550645,
|
||
|
|
"num_tokens": 803122.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.386259412765503,
|
||
|
|
"epoch": 0.021339113141988896,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.1891,
|
||
|
|
"mean_token_accuracy": 0.15860249921679498,
|
||
|
|
"num_tokens": 807393.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.601777124404907,
|
||
|
|
"epoch": 0.021450836247444333,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.1289,
|
||
|
|
"mean_token_accuracy": 0.16311845034360886,
|
||
|
|
"num_tokens": 811735.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.646067714691162,
|
||
|
|
"epoch": 0.021562559352899774,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.3186,
|
||
|
|
"mean_token_accuracy": 0.15336783230304718,
|
||
|
|
"num_tokens": 816327.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.546494245529175,
|
||
|
|
"epoch": 0.02167428245835521,
|
||
|
|
"grad_norm": 1.578125,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.1048,
|
||
|
|
"mean_token_accuracy": 0.1641931340098381,
|
||
|
|
"num_tokens": 820476.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.502486848831177,
|
||
|
|
"epoch": 0.02178600556381065,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.1289,
|
||
|
|
"mean_token_accuracy": 0.16595971435308457,
|
||
|
|
"num_tokens": 824563.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.51844539642334,
|
||
|
|
"epoch": 0.021897728669266092,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.2249,
|
||
|
|
"mean_token_accuracy": 0.15903169065713882,
|
||
|
|
"num_tokens": 829307.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.48329792022705,
|
||
|
|
"epoch": 0.02200945177472153,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.2234,
|
||
|
|
"mean_token_accuracy": 0.16081805527210236,
|
||
|
|
"num_tokens": 833876.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.577699089050293,
|
||
|
|
"epoch": 0.02212117488017697,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.3108,
|
||
|
|
"mean_token_accuracy": 0.15140475034713746,
|
||
|
|
"num_tokens": 838484.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.628869199752808,
|
||
|
|
"epoch": 0.022232897985632407,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.1561,
|
||
|
|
"mean_token_accuracy": 0.1592697098851204,
|
||
|
|
"num_tokens": 842813.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.393803596496582,
|
||
|
|
"epoch": 0.022344621091087848,
|
||
|
|
"grad_norm": 1.515625,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.0899,
|
||
|
|
"mean_token_accuracy": 0.16069612354040147,
|
||
|
|
"num_tokens": 846638.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4989090919494625,
|
||
|
|
"epoch": 0.022456344196543288,
|
||
|
|
"grad_norm": 1.578125,
|
||
|
|
"learning_rate": 0.000499998026082006,
|
||
|
|
"loss": 6.0626,
|
||
|
|
"mean_token_accuracy": 0.17749472558498383,
|
||
|
|
"num_tokens": 850577.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.439338541030883,
|
||
|
|
"epoch": 0.022568067301998725,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0004999900070995136,
|
||
|
|
"loss": 6.0906,
|
||
|
|
"mean_token_accuracy": 0.16202376335859298,
|
||
|
|
"num_tokens": 854904.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5132981300354,
|
||
|
|
"epoch": 0.022679790407454166,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0004999758199023239,
|
||
|
|
"loss": 6.1076,
|
||
|
|
"mean_token_accuracy": 0.17384408712387084,
|
||
|
|
"num_tokens": 858859.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.43322901725769,
|
||
|
|
"epoch": 0.022791513512909607,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 0.0004999554648793858,
|
||
|
|
"loss": 6.055,
|
||
|
|
"mean_token_accuracy": 0.16654047518968582,
|
||
|
|
"num_tokens": 863121.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.506139421463013,
|
||
|
|
"epoch": 0.022903236618365044,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.0004999289425887425,
|
||
|
|
"loss": 6.1709,
|
||
|
|
"mean_token_accuracy": 0.15935743749141693,
|
||
|
|
"num_tokens": 867805.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.488983964920044,
|
||
|
|
"epoch": 0.023014959723820484,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004998962537575161,
|
||
|
|
"loss": 6.1244,
|
||
|
|
"mean_token_accuracy": 0.1593026451766491,
|
||
|
|
"num_tokens": 871988.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.497362184524536,
|
||
|
|
"epoch": 0.02312668282927592,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.0004998573992818874,
|
||
|
|
"loss": 6.0959,
|
||
|
|
"mean_token_accuracy": 0.16356074959039688,
|
||
|
|
"num_tokens": 876181.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.301354026794433,
|
||
|
|
"epoch": 0.023238405934731362,
|
||
|
|
"grad_norm": 1.7265625,
|
||
|
|
"learning_rate": 0.0004998123802270715,
|
||
|
|
"loss": 5.9669,
|
||
|
|
"mean_token_accuracy": 0.18099125623703002,
|
||
|
|
"num_tokens": 880521.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.322625303268433,
|
||
|
|
"epoch": 0.023350129040186803,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0004997611978272886,
|
||
|
|
"loss": 6.1019,
|
||
|
|
"mean_token_accuracy": 0.16592444032430648,
|
||
|
|
"num_tokens": 885006.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.541764831542968,
|
||
|
|
"epoch": 0.02346185214564224,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0004997038534857298,
|
||
|
|
"loss": 6.1038,
|
||
|
|
"mean_token_accuracy": 0.15975722372531892,
|
||
|
|
"num_tokens": 889184.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.410001420974732,
|
||
|
|
"epoch": 0.02357357525109768,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.0004996403487745194,
|
||
|
|
"loss": 6.0039,
|
||
|
|
"mean_token_accuracy": 0.17406690418720244,
|
||
|
|
"num_tokens": 893806.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.391436147689819,
|
||
|
|
"epoch": 0.023685298356553117,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.000499570685434671,
|
||
|
|
"loss": 6.0131,
|
||
|
|
"mean_token_accuracy": 0.17006947249174117,
|
||
|
|
"num_tokens": 897578.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.47973518371582,
|
||
|
|
"epoch": 0.023797021462008558,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0004994948653760405,
|
||
|
|
"loss": 6.2734,
|
||
|
|
"mean_token_accuracy": 0.15798939615488053,
|
||
|
|
"num_tokens": 902225.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.551846933364868,
|
||
|
|
"epoch": 0.023908744567464,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004994128906772729,
|
||
|
|
"loss": 6.1246,
|
||
|
|
"mean_token_accuracy": 0.1635009005665779,
|
||
|
|
"num_tokens": 906477.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.386241388320923,
|
||
|
|
"epoch": 0.024020467672919436,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000499324763585746,
|
||
|
|
"loss": 6.1123,
|
||
|
|
"mean_token_accuracy": 0.15879142582416533,
|
||
|
|
"num_tokens": 910948.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.503281879425049,
|
||
|
|
"epoch": 0.024132190778374876,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0004992304865175085,
|
||
|
|
"loss": 6.2186,
|
||
|
|
"mean_token_accuracy": 0.14976079761981964,
|
||
|
|
"num_tokens": 915157.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.450709199905395,
|
||
|
|
"epoch": 0.024243913883830313,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0004991300620572138,
|
||
|
|
"loss": 6.0396,
|
||
|
|
"mean_token_accuracy": 0.16553105041384697,
|
||
|
|
"num_tokens": 920251.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.222010898590088,
|
||
|
|
"epoch": 0.024355636989285754,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0004990234929580494,
|
||
|
|
"loss": 6.1224,
|
||
|
|
"mean_token_accuracy": 0.16098514199256897,
|
||
|
|
"num_tokens": 924510.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.347459030151367,
|
||
|
|
"epoch": 0.024467360094741195,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0004989107821416609,
|
||
|
|
"loss": 6.0245,
|
||
|
|
"mean_token_accuracy": 0.1654239609837532,
|
||
|
|
"num_tokens": 928925.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.316383314132691,
|
||
|
|
"epoch": 0.02457908320019663,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004987919326980723,
|
||
|
|
"loss": 6.0384,
|
||
|
|
"mean_token_accuracy": 0.17247851192951202,
|
||
|
|
"num_tokens": 933211.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.317654371261597,
|
||
|
|
"epoch": 0.024690806305652072,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.0004986669478856011,
|
||
|
|
"loss": 6.1915,
|
||
|
|
"mean_token_accuracy": 0.15772637948393822,
|
||
|
|
"num_tokens": 937621.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.42638087272644,
|
||
|
|
"epoch": 0.024802529411107513,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0004985358311307688,
|
||
|
|
"loss": 6.0898,
|
||
|
|
"mean_token_accuracy": 0.1647167555987835,
|
||
|
|
"num_tokens": 941629.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.330166149139404,
|
||
|
|
"epoch": 0.02491425251656295,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0004983985860282081,
|
||
|
|
"loss": 6.0709,
|
||
|
|
"mean_token_accuracy": 0.16174031496047975,
|
||
|
|
"num_tokens": 945853.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.225450944900513,
|
||
|
|
"epoch": 0.02502597562201839,
|
||
|
|
"grad_norm": 1.5703125,
|
||
|
|
"learning_rate": 0.0004982552163405623,
|
||
|
|
"loss": 5.9055,
|
||
|
|
"mean_token_accuracy": 0.17898752093315123,
|
||
|
|
"num_tokens": 949758.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.182316493988037,
|
||
|
|
"epoch": 0.025137698727473828,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.0004981057259983839,
|
||
|
|
"loss": 6.0268,
|
||
|
|
"mean_token_accuracy": 0.17987219095230103,
|
||
|
|
"num_tokens": 954028.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.319781017303467,
|
||
|
|
"epoch": 0.02524942183292927,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.0004979501191000262,
|
||
|
|
"loss": 6.0393,
|
||
|
|
"mean_token_accuracy": 0.16309117376804352,
|
||
|
|
"num_tokens": 958006.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.320125341415405,
|
||
|
|
"epoch": 0.02536114493838471,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 0.0004977883999115311,
|
||
|
|
"loss": 5.9716,
|
||
|
|
"mean_token_accuracy": 0.17731243520975112,
|
||
|
|
"num_tokens": 962637.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.350974798202515,
|
||
|
|
"epoch": 0.025472868043840146,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004976205728665113,
|
||
|
|
"loss": 5.9456,
|
||
|
|
"mean_token_accuracy": 0.17742093056440353,
|
||
|
|
"num_tokens": 966770.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1780962467193605,
|
||
|
|
"epoch": 0.025584591149295587,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.0004974466425660307,
|
||
|
|
"loss": 5.9758,
|
||
|
|
"mean_token_accuracy": 0.1761695474386215,
|
||
|
|
"num_tokens": 970976.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.276739263534546,
|
||
|
|
"epoch": 0.025696314254751024,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.0004972666137784759,
|
||
|
|
"loss": 6.0095,
|
||
|
|
"mean_token_accuracy": 0.16108598709106445,
|
||
|
|
"num_tokens": 975253.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.226910066604614,
|
||
|
|
"epoch": 0.025808037360206464,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004970804914394271,
|
||
|
|
"loss": 5.998,
|
||
|
|
"mean_token_accuracy": 0.1661012887954712,
|
||
|
|
"num_tokens": 979388.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.162249755859375,
|
||
|
|
"epoch": 0.025919760465661905,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.0004968882806515225,
|
||
|
|
"loss": 5.9613,
|
||
|
|
"mean_token_accuracy": 0.1830698937177658,
|
||
|
|
"num_tokens": 983216.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.258333396911621,
|
||
|
|
"epoch": 0.026031483571117342,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004966899866843177,
|
||
|
|
"loss": 6.061,
|
||
|
|
"mean_token_accuracy": 0.16143736988306046,
|
||
|
|
"num_tokens": 987850.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.322597026824951,
|
||
|
|
"epoch": 0.026143206676572783,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000496485614974142,
|
||
|
|
"loss": 5.9894,
|
||
|
|
"mean_token_accuracy": 0.17105733901262282,
|
||
|
|
"num_tokens": 992232.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.21760311126709,
|
||
|
|
"epoch": 0.02625492978202822,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0004962751711239492,
|
||
|
|
"loss": 6.0848,
|
||
|
|
"mean_token_accuracy": 0.1664736032485962,
|
||
|
|
"num_tokens": 996428.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.334726476669312,
|
||
|
|
"epoch": 0.02636665288748366,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.0004960586609031636,
|
||
|
|
"loss": 5.9449,
|
||
|
|
"mean_token_accuracy": 0.17343248575925826,
|
||
|
|
"num_tokens": 1000336.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3395665168762205,
|
||
|
|
"epoch": 0.0264783759929391,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.0004958360902475224,
|
||
|
|
"loss": 5.9253,
|
||
|
|
"mean_token_accuracy": 0.17060509622097014,
|
||
|
|
"num_tokens": 1004312.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.365295124053955,
|
||
|
|
"epoch": 0.026590099098394538,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0004956074652589125,
|
||
|
|
"loss": 6.1563,
|
||
|
|
"mean_token_accuracy": 0.16267625764012336,
|
||
|
|
"num_tokens": 1008728.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.270880270004272,
|
||
|
|
"epoch": 0.02670182220384998,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0004953727922052035,
|
||
|
|
"loss": 6.0663,
|
||
|
|
"mean_token_accuracy": 0.16970421522855758,
|
||
|
|
"num_tokens": 1013385.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.310678911209107,
|
||
|
|
"epoch": 0.026813545309305416,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004951320775200756,
|
||
|
|
"loss": 6.0449,
|
||
|
|
"mean_token_accuracy": 0.16335367113351823,
|
||
|
|
"num_tokens": 1017537.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093309450149536,
|
||
|
|
"epoch": 0.026925268414760856,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.0004948853278028436,
|
||
|
|
"loss": 5.9362,
|
||
|
|
"mean_token_accuracy": 0.17884828001260758,
|
||
|
|
"num_tokens": 1021753.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.228685140609741,
|
||
|
|
"epoch": 0.027036991520216297,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0004946325498182755,
|
||
|
|
"loss": 6.0468,
|
||
|
|
"mean_token_accuracy": 0.16449340134859086,
|
||
|
|
"num_tokens": 1026248.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.192647790908813,
|
||
|
|
"epoch": 0.027148714625671734,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.0004943737504964076,
|
||
|
|
"loss": 5.838,
|
||
|
|
"mean_token_accuracy": 0.18312328010797502,
|
||
|
|
"num_tokens": 1030284.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.250751209259033,
|
||
|
|
"epoch": 0.027260437731127175,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.000494108936932354,
|
||
|
|
"loss": 6.1342,
|
||
|
|
"mean_token_accuracy": 0.16936966106295587,
|
||
|
|
"num_tokens": 1034444.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.304910802841187,
|
||
|
|
"epoch": 0.027372160836582615,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0004938381163861124,
|
||
|
|
"loss": 5.9104,
|
||
|
|
"mean_token_accuracy": 0.18955854922533036,
|
||
|
|
"num_tokens": 1038819.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.332531595230103,
|
||
|
|
"epoch": 0.027483883942038052,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004935612962823645,
|
||
|
|
"loss": 6.1242,
|
||
|
|
"mean_token_accuracy": 0.16566465348005294,
|
||
|
|
"num_tokens": 1043303.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.162945175170899,
|
||
|
|
"epoch": 0.027595607047493493,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.0004932784842102739,
|
||
|
|
"loss": 5.9639,
|
||
|
|
"mean_token_accuracy": 0.1748690575361252,
|
||
|
|
"num_tokens": 1047451.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.292677593231201,
|
||
|
|
"epoch": 0.02770733015294893,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004929896879232758,
|
||
|
|
"loss": 6.0031,
|
||
|
|
"mean_token_accuracy": 0.17595543414354325,
|
||
|
|
"num_tokens": 1052370.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.406116533279419,
|
||
|
|
"epoch": 0.02781905325840437,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.0004926949153388668,
|
||
|
|
"loss": 6.1119,
|
||
|
|
"mean_token_accuracy": 0.1625329688191414,
|
||
|
|
"num_tokens": 1056755.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.257381248474121,
|
||
|
|
"epoch": 0.02793077636385981,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004923941745383859,
|
||
|
|
"loss": 5.9983,
|
||
|
|
"mean_token_accuracy": 0.16609450280666352,
|
||
|
|
"num_tokens": 1061380.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.04865870475769,
|
||
|
|
"epoch": 0.02804249946931525,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000492087473766794,
|
||
|
|
"loss": 5.8919,
|
||
|
|
"mean_token_accuracy": 0.18033342361450194,
|
||
|
|
"num_tokens": 1065633.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.278530168533325,
|
||
|
|
"epoch": 0.02815422257477069,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.000491774821432448,
|
||
|
|
"loss": 6.0283,
|
||
|
|
"mean_token_accuracy": 0.16999331265687942,
|
||
|
|
"num_tokens": 1070131.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.240628862380982,
|
||
|
|
"epoch": 0.028265945680226126,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0004914562261068693,
|
||
|
|
"loss": 5.9501,
|
||
|
|
"mean_token_accuracy": 0.16984693259000777,
|
||
|
|
"num_tokens": 1074465.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.062196207046509,
|
||
|
|
"epoch": 0.028377668785681567,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.0004911316965245098,
|
||
|
|
"loss": 5.828,
|
||
|
|
"mean_token_accuracy": 0.17757159918546678,
|
||
|
|
"num_tokens": 1078738.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.12146635055542,
|
||
|
|
"epoch": 0.028489391891137007,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.000490801241582512,
|
||
|
|
"loss": 5.9453,
|
||
|
|
"mean_token_accuracy": 0.17620262503623962,
|
||
|
|
"num_tokens": 1082529.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.328038311004638,
|
||
|
|
"epoch": 0.028601114996592444,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.000490464870340465,
|
||
|
|
"loss": 6.0216,
|
||
|
|
"mean_token_accuracy": 0.16488975435495376,
|
||
|
|
"num_tokens": 1087043.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.050336456298828,
|
||
|
|
"epoch": 0.028712838102047885,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.0004901225920201563,
|
||
|
|
"loss": 5.9187,
|
||
|
|
"mean_token_accuracy": 0.18301421254873276,
|
||
|
|
"num_tokens": 1091045.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1567244052886965,
|
||
|
|
"epoch": 0.028824561207503322,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.000489774416005319,
|
||
|
|
"loss": 5.8778,
|
||
|
|
"mean_token_accuracy": 0.18505997806787491,
|
||
|
|
"num_tokens": 1094949.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.193764543533325,
|
||
|
|
"epoch": 0.028936284312958763,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0004894203518413742,
|
||
|
|
"loss": 5.942,
|
||
|
|
"mean_token_accuracy": 0.17170550525188447,
|
||
|
|
"num_tokens": 1099131.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.024008512496948,
|
||
|
|
"epoch": 0.029048007418414203,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0004890604092351701,
|
||
|
|
"loss": 5.8863,
|
||
|
|
"mean_token_accuracy": 0.18198106437921524,
|
||
|
|
"num_tokens": 1102967.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.191930198669434,
|
||
|
|
"epoch": 0.02915973052386964,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.000488694598054715,
|
||
|
|
"loss": 5.8698,
|
||
|
|
"mean_token_accuracy": 0.18373733162879943,
|
||
|
|
"num_tokens": 1106777.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.126851320266724,
|
||
|
|
"epoch": 0.02927145362932508,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0004883229283289071,
|
||
|
|
"loss": 5.9212,
|
||
|
|
"mean_token_accuracy": 0.17913941144943238,
|
||
|
|
"num_tokens": 1111184.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.192364168167114,
|
||
|
|
"epoch": 0.02938317673478052,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00048794541024725993,
|
||
|
|
"loss": 5.9298,
|
||
|
|
"mean_token_accuracy": 0.17791166305541992,
|
||
|
|
"num_tokens": 1115651.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.26938943862915,
|
||
|
|
"epoch": 0.02949489984023596,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0004875620541596221,
|
||
|
|
"loss": 5.955,
|
||
|
|
"mean_token_accuracy": 0.1659138545393944,
|
||
|
|
"num_tokens": 1120012.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.076159715652466,
|
||
|
|
"epoch": 0.0296066229456914,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00048717287057589454,
|
||
|
|
"loss": 5.8588,
|
||
|
|
"mean_token_accuracy": 0.17886159271001817,
|
||
|
|
"num_tokens": 1124549.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.182869958877563,
|
||
|
|
"epoch": 0.029718346051146836,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0004867778701657417,
|
||
|
|
"loss": 5.9345,
|
||
|
|
"mean_token_accuracy": 0.17838005125522613,
|
||
|
|
"num_tokens": 1128968.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.133463668823242,
|
||
|
|
"epoch": 0.029830069156602277,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00048637706375829955,
|
||
|
|
"loss": 5.9933,
|
||
|
|
"mean_token_accuracy": 0.17328195571899413,
|
||
|
|
"num_tokens": 1133396.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.253204965591431,
|
||
|
|
"epoch": 0.029941792262057718,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.000485970462341878,
|
||
|
|
"loss": 5.9025,
|
||
|
|
"mean_token_accuracy": 0.170744127035141,
|
||
|
|
"num_tokens": 1137577.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.061755275726318,
|
||
|
|
"epoch": 0.030053515367513155,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00048555807706366044,
|
||
|
|
"loss": 5.7801,
|
||
|
|
"mean_token_accuracy": 0.18417277485132216,
|
||
|
|
"num_tokens": 1141551.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.116015100479126,
|
||
|
|
"epoch": 0.030165238472968595,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.00048513991922939756,
|
||
|
|
"loss": 5.8398,
|
||
|
|
"mean_token_accuracy": 0.17423712015151976,
|
||
|
|
"num_tokens": 1145295.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.067533349990844,
|
||
|
|
"epoch": 0.030276961578424032,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00048471600030309744,
|
||
|
|
"loss": 6.0567,
|
||
|
|
"mean_token_accuracy": 0.16484877467155457,
|
||
|
|
"num_tokens": 1149946.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1512785911560055,
|
||
|
|
"epoch": 0.030388684683879473,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.00048428633190671186,
|
||
|
|
"loss": 5.9399,
|
||
|
|
"mean_token_accuracy": 0.18146816939115523,
|
||
|
|
"num_tokens": 1153955.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.143903684616089,
|
||
|
|
"epoch": 0.030500407789334914,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0004838509258198167,
|
||
|
|
"loss": 5.849,
|
||
|
|
"mean_token_accuracy": 0.18261384814977646,
|
||
|
|
"num_tokens": 1158568.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.127876806259155,
|
||
|
|
"epoch": 0.03061213089479035,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.00048340979397929,
|
||
|
|
"loss": 5.7759,
|
||
|
|
"mean_token_accuracy": 0.18599571883678437,
|
||
|
|
"num_tokens": 1162217.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.076024913787842,
|
||
|
|
"epoch": 0.03072385400024579,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.00048296294847898386,
|
||
|
|
"loss": 5.8861,
|
||
|
|
"mean_token_accuracy": 0.17389037311077118,
|
||
|
|
"num_tokens": 1165905.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.11526198387146,
|
||
|
|
"epoch": 0.03083557710570123,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.0004825104015693934,
|
||
|
|
"loss": 5.8432,
|
||
|
|
"mean_token_accuracy": 0.17682357281446456,
|
||
|
|
"num_tokens": 1170352.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.046456527709961,
|
||
|
|
"epoch": 0.03094730021115667,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004820521656573208,
|
||
|
|
"loss": 5.9274,
|
||
|
|
"mean_token_accuracy": 0.17616797983646393,
|
||
|
|
"num_tokens": 1174560.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.11228313446045,
|
||
|
|
"epoch": 0.03105902331661211,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00048158825330553505,
|
||
|
|
"loss": 5.8708,
|
||
|
|
"mean_token_accuracy": 0.17557800114154815,
|
||
|
|
"num_tokens": 1178544.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.975264167785644,
|
||
|
|
"epoch": 0.031170746422067547,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.00048111867723242763,
|
||
|
|
"loss": 5.6949,
|
||
|
|
"mean_token_accuracy": 0.19889509081840515,
|
||
|
|
"num_tokens": 1182541.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.97807993888855,
|
||
|
|
"epoch": 0.031282469527522984,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004806434503116637,
|
||
|
|
"loss": 5.7847,
|
||
|
|
"mean_token_accuracy": 0.1825215622782707,
|
||
|
|
"num_tokens": 1186684.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.036240196228027,
|
||
|
|
"epoch": 0.03139419263297843,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004801625855718296,
|
||
|
|
"loss": 5.7286,
|
||
|
|
"mean_token_accuracy": 0.1909311071038246,
|
||
|
|
"num_tokens": 1190785.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.977891159057617,
|
||
|
|
"epoch": 0.031505915738433865,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00047967609619607477,
|
||
|
|
"loss": 5.7739,
|
||
|
|
"mean_token_accuracy": 0.17418278902769088,
|
||
|
|
"num_tokens": 1194940.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.920260810852051,
|
||
|
|
"epoch": 0.0316176388438893,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0004791839955217513,
|
||
|
|
"loss": 5.7381,
|
||
|
|
"mean_token_accuracy": 0.18921381384134292,
|
||
|
|
"num_tokens": 1198765.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.071567487716675,
|
||
|
|
"epoch": 0.031729361949344746,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00047868629704004786,
|
||
|
|
"loss": 5.9463,
|
||
|
|
"mean_token_accuracy": 0.17053111791610717,
|
||
|
|
"num_tokens": 1203266.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.066260862350464,
|
||
|
|
"epoch": 0.03184108505480018,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00047818301439561965,
|
||
|
|
"loss": 5.7346,
|
||
|
|
"mean_token_accuracy": 0.19455005526542662,
|
||
|
|
"num_tokens": 1207414.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.978516721725464,
|
||
|
|
"epoch": 0.03195280816025562,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00047767416138621454,
|
||
|
|
"loss": 5.7596,
|
||
|
|
"mean_token_accuracy": 0.1821496695280075,
|
||
|
|
"num_tokens": 1211325.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.088147068023682,
|
||
|
|
"epoch": 0.032064531265711065,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.000477159751962295,
|
||
|
|
"loss": 5.7876,
|
||
|
|
"mean_token_accuracy": 0.17757320106029512,
|
||
|
|
"num_tokens": 1215866.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.105999946594238,
|
||
|
|
"epoch": 0.0321762543711665,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00047663980022665507,
|
||
|
|
"loss": 5.8637,
|
||
|
|
"mean_token_accuracy": 0.16661322563886644,
|
||
|
|
"num_tokens": 1220241.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943767118453979,
|
||
|
|
"epoch": 0.03228797747662194,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00047611432043403437,
|
||
|
|
"loss": 5.8393,
|
||
|
|
"mean_token_accuracy": 0.17783186137676238,
|
||
|
|
"num_tokens": 1224330.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.21411657333374,
|
||
|
|
"epoch": 0.03239970058207738,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004755833269907267,
|
||
|
|
"loss": 5.9352,
|
||
|
|
"mean_token_accuracy": 0.16817386895418168,
|
||
|
|
"num_tokens": 1228518.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.985192489624024,
|
||
|
|
"epoch": 0.03251142368753282,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004750468344541857,
|
||
|
|
"loss": 5.8087,
|
||
|
|
"mean_token_accuracy": 0.1855456992983818,
|
||
|
|
"num_tokens": 1232556.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.902926826477051,
|
||
|
|
"epoch": 0.03262314679298826,
|
||
|
|
"grad_norm": 1.5546875,
|
||
|
|
"learning_rate": 0.00047450485753262525,
|
||
|
|
"loss": 5.8417,
|
||
|
|
"mean_token_accuracy": 0.17538347840309143,
|
||
|
|
"num_tokens": 1236464.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1002099990844725,
|
||
|
|
"epoch": 0.032734869898443694,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00047395741108461633,
|
||
|
|
"loss": 5.8552,
|
||
|
|
"mean_token_accuracy": 0.1877426788210869,
|
||
|
|
"num_tokens": 1240478.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.054091215133667,
|
||
|
|
"epoch": 0.03284659300389914,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.00047340451011867985,
|
||
|
|
"loss": 5.8806,
|
||
|
|
"mean_token_accuracy": 0.1829858422279358,
|
||
|
|
"num_tokens": 1244149.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.208575963973999,
|
||
|
|
"epoch": 0.032958316109354575,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.00047284616979287515,
|
||
|
|
"loss": 5.9965,
|
||
|
|
"mean_token_accuracy": 0.15834348127245904,
|
||
|
|
"num_tokens": 1248617.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.053374433517456,
|
||
|
|
"epoch": 0.03307003921481001,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00047228240541438433,
|
||
|
|
"loss": 5.8381,
|
||
|
|
"mean_token_accuracy": 0.18422103077173232,
|
||
|
|
"num_tokens": 1253044.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.099059247970581,
|
||
|
|
"epoch": 0.03318176232026546,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.00047171323243909257,
|
||
|
|
"loss": 5.8787,
|
||
|
|
"mean_token_accuracy": 0.1814146339893341,
|
||
|
|
"num_tokens": 1257651.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0209493160247805,
|
||
|
|
"epoch": 0.033293485425720894,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00047113866647116457,
|
||
|
|
"loss": 5.8113,
|
||
|
|
"mean_token_accuracy": 0.19222917556762695,
|
||
|
|
"num_tokens": 1261805.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.859741830825806,
|
||
|
|
"epoch": 0.03340520853117633,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0004705587232626164,
|
||
|
|
"loss": 5.6211,
|
||
|
|
"mean_token_accuracy": 0.20293725579977034,
|
||
|
|
"num_tokens": 1265625.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.956333827972412,
|
||
|
|
"epoch": 0.033516931636631775,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00046997341871288424,
|
||
|
|
"loss": 5.7941,
|
||
|
|
"mean_token_accuracy": 0.18911935687065123,
|
||
|
|
"num_tokens": 1269876.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.947610187530517,
|
||
|
|
"epoch": 0.03362865474208721,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004693827688683879,
|
||
|
|
"loss": 5.7585,
|
||
|
|
"mean_token_accuracy": 0.18911905884742736,
|
||
|
|
"num_tokens": 1273821.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.978272771835327,
|
||
|
|
"epoch": 0.03374037784754265,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004687867899220914,
|
||
|
|
"loss": 5.8581,
|
||
|
|
"mean_token_accuracy": 0.1890767216682434,
|
||
|
|
"num_tokens": 1278574.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.054383754730225,
|
||
|
|
"epoch": 0.033852100952998086,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.00046818549821305846,
|
||
|
|
"loss": 5.8519,
|
||
|
|
"mean_token_accuracy": 0.17416736483573914,
|
||
|
|
"num_tokens": 1283271.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.997065925598145,
|
||
|
|
"epoch": 0.03396382405845353,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.00046757891022600494,
|
||
|
|
"loss": 5.6877,
|
||
|
|
"mean_token_accuracy": 0.1906101658940315,
|
||
|
|
"num_tokens": 1287633.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.85000958442688,
|
||
|
|
"epoch": 0.03407554716390897,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.0004669670425908471,
|
||
|
|
"loss": 5.6926,
|
||
|
|
"mean_token_accuracy": 0.19665769934654237,
|
||
|
|
"num_tokens": 1291796.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.956004524230957,
|
||
|
|
"epoch": 0.034187270269364405,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.0004663499120822451,
|
||
|
|
"loss": 5.8535,
|
||
|
|
"mean_token_accuracy": 0.18395211100578307,
|
||
|
|
"num_tokens": 1296086.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.935553312301636,
|
||
|
|
"epoch": 0.03429899337481985,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004657275356191437,
|
||
|
|
"loss": 5.7859,
|
||
|
|
"mean_token_accuracy": 0.1771954283118248,
|
||
|
|
"num_tokens": 1300651.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.98644380569458,
|
||
|
|
"epoch": 0.034410716480275286,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.00046509993026430804,
|
||
|
|
"loss": 5.7857,
|
||
|
|
"mean_token_accuracy": 0.18615951985120774,
|
||
|
|
"num_tokens": 1304930.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.049903631210327,
|
||
|
|
"epoch": 0.03452243958573072,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0004644671132238558,
|
||
|
|
"loss": 5.9064,
|
||
|
|
"mean_token_accuracy": 0.17017292976379395,
|
||
|
|
"num_tokens": 1308950.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.011875438690185,
|
||
|
|
"epoch": 0.03463416269118617,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.00046382910184678585,
|
||
|
|
"loss": 5.7646,
|
||
|
|
"mean_token_accuracy": 0.18291668146848677,
|
||
|
|
"num_tokens": 1313059.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.82340407371521,
|
||
|
|
"epoch": 0.034745885796641604,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.0004631859136245025,
|
||
|
|
"loss": 5.653,
|
||
|
|
"mean_token_accuracy": 0.20044284611940383,
|
||
|
|
"num_tokens": 1316756.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.832498359680176,
|
||
|
|
"epoch": 0.03485760890209704,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0004625375661903357,
|
||
|
|
"loss": 5.9377,
|
||
|
|
"mean_token_accuracy": 0.1717216596007347,
|
||
|
|
"num_tokens": 1320834.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.000537538528443,
|
||
|
|
"epoch": 0.034969332007552485,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.00046188407731905787,
|
||
|
|
"loss": 5.7466,
|
||
|
|
"mean_token_accuracy": 0.179401932656765,
|
||
|
|
"num_tokens": 1324484.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9155961036682125,
|
||
|
|
"epoch": 0.03508105511300792,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00046122546492639643,
|
||
|
|
"loss": 5.7167,
|
||
|
|
"mean_token_accuracy": 0.18550520837306977,
|
||
|
|
"num_tokens": 1328935.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.872024726867676,
|
||
|
|
"epoch": 0.03519277821846336,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.000460561747068543,
|
||
|
|
"loss": 5.712,
|
||
|
|
"mean_token_accuracy": 0.18719355762004852,
|
||
|
|
"num_tokens": 1333225.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.869159507751465,
|
||
|
|
"epoch": 0.0353045013239188,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.0004598929419416578,
|
||
|
|
"loss": 5.651,
|
||
|
|
"mean_token_accuracy": 0.18982717245817185,
|
||
|
|
"num_tokens": 1337234.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.923066091537476,
|
||
|
|
"epoch": 0.03541622442937424,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.00045921906788137123,
|
||
|
|
"loss": 5.9007,
|
||
|
|
"mean_token_accuracy": 0.1787141427397728,
|
||
|
|
"num_tokens": 1341765.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0253113269805905,
|
||
|
|
"epoch": 0.03552794753482968,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00045854014336228115,
|
||
|
|
"loss": 5.7594,
|
||
|
|
"mean_token_accuracy": 0.18375371396541595,
|
||
|
|
"num_tokens": 1346087.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.957542037963867,
|
||
|
|
"epoch": 0.035639670640285115,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00045785618699744615,
|
||
|
|
"loss": 5.8163,
|
||
|
|
"mean_token_accuracy": 0.17815666794776916,
|
||
|
|
"num_tokens": 1350443.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.926890325546265,
|
||
|
|
"epoch": 0.03575139374574056,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00045716721753787543,
|
||
|
|
"loss": 5.816,
|
||
|
|
"mean_token_accuracy": 0.18130575716495514,
|
||
|
|
"num_tokens": 1355092.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.974433660507202,
|
||
|
|
"epoch": 0.035863116851195996,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004564732538720148,
|
||
|
|
"loss": 5.835,
|
||
|
|
"mean_token_accuracy": 0.18347030133008957,
|
||
|
|
"num_tokens": 1359379.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.953034782409668,
|
||
|
|
"epoch": 0.03597483995665143,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00045577431502522877,
|
||
|
|
"loss": 5.6628,
|
||
|
|
"mean_token_accuracy": 0.19076226502656937,
|
||
|
|
"num_tokens": 1363346.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8596611499786375,
|
||
|
|
"epoch": 0.03608656306210688,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0004550704201592787,
|
||
|
|
"loss": 5.7542,
|
||
|
|
"mean_token_accuracy": 0.18018715232610702,
|
||
|
|
"num_tokens": 1367322.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.794494342803955,
|
||
|
|
"epoch": 0.036198286167562314,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0004543615885717981,
|
||
|
|
"loss": 5.6992,
|
||
|
|
"mean_token_accuracy": 0.17892082631587983,
|
||
|
|
"num_tokens": 1371165.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.782205438613891,
|
||
|
|
"epoch": 0.03631000927301775,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00045364783969576296,
|
||
|
|
"loss": 5.7294,
|
||
|
|
"mean_token_accuracy": 0.18963399678468704,
|
||
|
|
"num_tokens": 1375119.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001317644119263,
|
||
|
|
"epoch": 0.03642173237847319,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0004529291930989592,
|
||
|
|
"loss": 5.6411,
|
||
|
|
"mean_token_accuracy": 0.18632617145776748,
|
||
|
|
"num_tokens": 1379268.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.849557733535766,
|
||
|
|
"epoch": 0.03653345548392863,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0004522056684834464,
|
||
|
|
"loss": 5.7699,
|
||
|
|
"mean_token_accuracy": 0.1743351399898529,
|
||
|
|
"num_tokens": 1383477.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.865782070159912,
|
||
|
|
"epoch": 0.03664517858938407,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.0004514772856850173,
|
||
|
|
"loss": 5.6866,
|
||
|
|
"mean_token_accuracy": 0.18341614156961442,
|
||
|
|
"num_tokens": 1387138.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.977947139739991,
|
||
|
|
"epoch": 0.03675690169483951,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004507440646726542,
|
||
|
|
"loss": 5.8143,
|
||
|
|
"mean_token_accuracy": 0.172549207508564,
|
||
|
|
"num_tokens": 1391758.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8711779594421385,
|
||
|
|
"epoch": 0.03686862480029495,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0004500060255479818,
|
||
|
|
"loss": 5.723,
|
||
|
|
"mean_token_accuracy": 0.17711774334311486,
|
||
|
|
"num_tokens": 1395517.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.922771453857422,
|
||
|
|
"epoch": 0.03698034790575039,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0004492631885447151,
|
||
|
|
"loss": 5.7544,
|
||
|
|
"mean_token_accuracy": 0.19050031006336213,
|
||
|
|
"num_tokens": 1400021.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1255439758300785,
|
||
|
|
"epoch": 0.037092071011205825,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00044851557402810616,
|
||
|
|
"loss": 5.9007,
|
||
|
|
"mean_token_accuracy": 0.17477723360061645,
|
||
|
|
"num_tokens": 1404456.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.92813024520874,
|
||
|
|
"epoch": 0.03720379411666127,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00044776320249438444,
|
||
|
|
"loss": 5.7934,
|
||
|
|
"mean_token_accuracy": 0.1815376475453377,
|
||
|
|
"num_tokens": 1408612.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.931152248382569,
|
||
|
|
"epoch": 0.037315517222116706,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00044700609457019565,
|
||
|
|
"loss": 5.7709,
|
||
|
|
"mean_token_accuracy": 0.18026064932346345,
|
||
|
|
"num_tokens": 1412688.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.978479957580566,
|
||
|
|
"epoch": 0.037427240327572144,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004462442710120359,
|
||
|
|
"loss": 5.8158,
|
||
|
|
"mean_token_accuracy": 0.1856473058462143,
|
||
|
|
"num_tokens": 1417273.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.903031873703003,
|
||
|
|
"epoch": 0.03753896343302759,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.000445477752705683,
|
||
|
|
"loss": 5.7375,
|
||
|
|
"mean_token_accuracy": 0.1884758025407791,
|
||
|
|
"num_tokens": 1421737.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8098523139953615,
|
||
|
|
"epoch": 0.037650686538483025,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00044470656066562336,
|
||
|
|
"loss": 5.5071,
|
||
|
|
"mean_token_accuracy": 0.21041337251663209,
|
||
|
|
"num_tokens": 1426154.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.780639505386352,
|
||
|
|
"epoch": 0.03776240964393846,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0004439307160344765,
|
||
|
|
"loss": 5.7721,
|
||
|
|
"mean_token_accuracy": 0.17714227586984635,
|
||
|
|
"num_tokens": 1430270.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.961412334442139,
|
||
|
|
"epoch": 0.0378741327493939,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00044315024008241473,
|
||
|
|
"loss": 5.643,
|
||
|
|
"mean_token_accuracy": 0.19645272940397263,
|
||
|
|
"num_tokens": 1434877.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.815417146682739,
|
||
|
|
"epoch": 0.03798585585484934,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0004423651542065806,
|
||
|
|
"loss": 5.7024,
|
||
|
|
"mean_token_accuracy": 0.19412025362253188,
|
||
|
|
"num_tokens": 1438690.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.813020801544189,
|
||
|
|
"epoch": 0.03809757896030478,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.00044157547993050006,
|
||
|
|
"loss": 5.666,
|
||
|
|
"mean_token_accuracy": 0.18868900388479232,
|
||
|
|
"num_tokens": 1443085.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.746577167510987,
|
||
|
|
"epoch": 0.03820930206576022,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.00044078123890349227,
|
||
|
|
"loss": 5.5337,
|
||
|
|
"mean_token_accuracy": 0.20610977411270143,
|
||
|
|
"num_tokens": 1447280.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.846112585067749,
|
||
|
|
"epoch": 0.03832102517121566,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00043998245290007606,
|
||
|
|
"loss": 5.7143,
|
||
|
|
"mean_token_accuracy": 0.1895755797624588,
|
||
|
|
"num_tokens": 1451639.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9104358673095705,
|
||
|
|
"epoch": 0.0384327482766711,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00043917914381937323,
|
||
|
|
"loss": 5.6867,
|
||
|
|
"mean_token_accuracy": 0.18838332891464232,
|
||
|
|
"num_tokens": 1455473.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.924994277954101,
|
||
|
|
"epoch": 0.038544471382126536,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00043837133368450815,
|
||
|
|
"loss": 5.7771,
|
||
|
|
"mean_token_accuracy": 0.17980068176984787,
|
||
|
|
"num_tokens": 1460332.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.907491636276245,
|
||
|
|
"epoch": 0.03865619448758198,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004375590446420037,
|
||
|
|
"loss": 5.658,
|
||
|
|
"mean_token_accuracy": 0.19679046124219896,
|
||
|
|
"num_tokens": 1465013.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.766436243057251,
|
||
|
|
"epoch": 0.03876791759303742,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0004367422989611743,
|
||
|
|
"loss": 5.5845,
|
||
|
|
"mean_token_accuracy": 0.1921959325671196,
|
||
|
|
"num_tokens": 1469070.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.966058731079102,
|
||
|
|
"epoch": 0.038879640698492854,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004359211190335153,
|
||
|
|
"loss": 5.6631,
|
||
|
|
"mean_token_accuracy": 0.18933282941579818,
|
||
|
|
"num_tokens": 1473426.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8712715148925785,
|
||
|
|
"epoch": 0.0389913638039483,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.00043509552737208923,
|
||
|
|
"loss": 5.7692,
|
||
|
|
"mean_token_accuracy": 0.18656760305166245,
|
||
|
|
"num_tokens": 1477631.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.809204721450806,
|
||
|
|
"epoch": 0.039103086909403735,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00043426554661090853,
|
||
|
|
"loss": 5.7989,
|
||
|
|
"mean_token_accuracy": 0.1808011546730995,
|
||
|
|
"num_tokens": 1481921.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.959576177597046,
|
||
|
|
"epoch": 0.03921481001485917,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00043343119950431516,
|
||
|
|
"loss": 5.7858,
|
||
|
|
"mean_token_accuracy": 0.18863923847675323,
|
||
|
|
"num_tokens": 1486571.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01992974281311,
|
||
|
|
"epoch": 0.03932653312031461,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00043259250892635644,
|
||
|
|
"loss": 5.7733,
|
||
|
|
"mean_token_accuracy": 0.17147145718336104,
|
||
|
|
"num_tokens": 1490952.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.805021715164185,
|
||
|
|
"epoch": 0.03943825622577005,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004317494978701582,
|
||
|
|
"loss": 5.5844,
|
||
|
|
"mean_token_accuracy": 0.20293330252170563,
|
||
|
|
"num_tokens": 1495144.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.851907777786255,
|
||
|
|
"epoch": 0.03954997933122549,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0004309021894472943,
|
||
|
|
"loss": 5.7049,
|
||
|
|
"mean_token_accuracy": 0.1867707759141922,
|
||
|
|
"num_tokens": 1499386.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.924546384811402,
|
||
|
|
"epoch": 0.03966170243668093,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.0004300506068871534,
|
||
|
|
"loss": 5.6447,
|
||
|
|
"mean_token_accuracy": 0.196545746922493,
|
||
|
|
"num_tokens": 1503583.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.851029920578003,
|
||
|
|
"epoch": 0.03977342554213637,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.00042919477353630135,
|
||
|
|
"loss": 5.6454,
|
||
|
|
"mean_token_accuracy": 0.18555532693862914,
|
||
|
|
"num_tokens": 1507680.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.900534915924072,
|
||
|
|
"epoch": 0.03988514864759181,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.000428334712857842,
|
||
|
|
"loss": 5.7511,
|
||
|
|
"mean_token_accuracy": 0.18316335380077362,
|
||
|
|
"num_tokens": 1511856.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.938773584365845,
|
||
|
|
"epoch": 0.039996871753047246,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00042747044843077304,
|
||
|
|
"loss": 5.6779,
|
||
|
|
"mean_token_accuracy": 0.18426842391490936,
|
||
|
|
"num_tokens": 1516176.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.897777462005616,
|
||
|
|
"epoch": 0.04010859485850269,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00042660200394934047,
|
||
|
|
"loss": 5.6167,
|
||
|
|
"mean_token_accuracy": 0.19120081663131713,
|
||
|
|
"num_tokens": 1520060.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.674463272094727,
|
||
|
|
"epoch": 0.04022031796395813,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00042572940322238844,
|
||
|
|
"loss": 5.6891,
|
||
|
|
"mean_token_accuracy": 0.1935557708144188,
|
||
|
|
"num_tokens": 1524165.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.897950935363769,
|
||
|
|
"epoch": 0.040332041069413564,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00042485267017270664,
|
||
|
|
"loss": 5.873,
|
||
|
|
"mean_token_accuracy": 0.1720517948269844,
|
||
|
|
"num_tokens": 1528065.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.998282623291016,
|
||
|
|
"epoch": 0.040443764174869,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004239718288363745,
|
||
|
|
"loss": 5.6418,
|
||
|
|
"mean_token_accuracy": 0.19317266643047332,
|
||
|
|
"num_tokens": 1532618.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.780726480484009,
|
||
|
|
"epoch": 0.040555487280324445,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004230869033621023,
|
||
|
|
"loss": 5.6881,
|
||
|
|
"mean_token_accuracy": 0.18989397287368776,
|
||
|
|
"num_tokens": 1536965.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.810385847091675,
|
||
|
|
"epoch": 0.04066721038577988,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0004221979180105688,
|
||
|
|
"loss": 5.81,
|
||
|
|
"mean_token_accuracy": 0.17670476138591767,
|
||
|
|
"num_tokens": 1541332.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.831990575790405,
|
||
|
|
"epoch": 0.04077893349123532,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00042130489715375645,
|
||
|
|
"loss": 5.5056,
|
||
|
|
"mean_token_accuracy": 0.20245466083288194,
|
||
|
|
"num_tokens": 1545324.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.938973903656006,
|
||
|
|
"epoch": 0.040890656596690764,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00042040786527428335,
|
||
|
|
"loss": 5.718,
|
||
|
|
"mean_token_accuracy": 0.1829439416527748,
|
||
|
|
"num_tokens": 1549409.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.827459383010864,
|
||
|
|
"epoch": 0.0410023797021462,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0004195068469647315,
|
||
|
|
"loss": 5.722,
|
||
|
|
"mean_token_accuracy": 0.18134666085243226,
|
||
|
|
"num_tokens": 1553526.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.846643352508545,
|
||
|
|
"epoch": 0.04111410280760164,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00041860186692697297,
|
||
|
|
"loss": 5.8215,
|
||
|
|
"mean_token_accuracy": 0.18818144947290422,
|
||
|
|
"num_tokens": 1558475.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.911942195892334,
|
||
|
|
"epoch": 0.04122582591305708,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00041769294997149264,
|
||
|
|
"loss": 5.6244,
|
||
|
|
"mean_token_accuracy": 0.18921684920787812,
|
||
|
|
"num_tokens": 1562702.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.760951137542724,
|
||
|
|
"epoch": 0.04133754901851252,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004167801210167081,
|
||
|
|
"loss": 5.6199,
|
||
|
|
"mean_token_accuracy": 0.2041267544031143,
|
||
|
|
"num_tokens": 1566706.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.749172258377075,
|
||
|
|
"epoch": 0.041449272123967956,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0004158634050882861,
|
||
|
|
"loss": 5.6459,
|
||
|
|
"mean_token_accuracy": 0.1950855016708374,
|
||
|
|
"num_tokens": 1570843.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.89965443611145,
|
||
|
|
"epoch": 0.0415609952294234,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004149428273184569,
|
||
|
|
"loss": 5.6739,
|
||
|
|
"mean_token_accuracy": 0.18709891736507417,
|
||
|
|
"num_tokens": 1575308.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.850597333908081,
|
||
|
|
"epoch": 0.04167271833487884,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0004140184129453253,
|
||
|
|
"loss": 5.8073,
|
||
|
|
"mean_token_accuracy": 0.1735033169388771,
|
||
|
|
"num_tokens": 1579397.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.788528537750244,
|
||
|
|
"epoch": 0.041784441440334275,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.000413090187312178,
|
||
|
|
"loss": 5.5974,
|
||
|
|
"mean_token_accuracy": 0.1987029194831848,
|
||
|
|
"num_tokens": 1583464.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.821397066116333,
|
||
|
|
"epoch": 0.04189616454578971,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004121581758667898,
|
||
|
|
"loss": 5.6181,
|
||
|
|
"mean_token_accuracy": 0.18513045012950896,
|
||
|
|
"num_tokens": 1587948.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.83982481956482,
|
||
|
|
"epoch": 0.042007887651245156,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.00041122240416072533,
|
||
|
|
"loss": 5.5384,
|
||
|
|
"mean_token_accuracy": 0.2091333582997322,
|
||
|
|
"num_tokens": 1591855.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8791999340057375,
|
||
|
|
"epoch": 0.04211961075670059,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004102828978486385,
|
||
|
|
"loss": 5.6762,
|
||
|
|
"mean_token_accuracy": 0.19092029482126235,
|
||
|
|
"num_tokens": 1595951.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.779487609863281,
|
||
|
|
"epoch": 0.04223133386215603,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0004093396826875695,
|
||
|
|
"loss": 5.6041,
|
||
|
|
"mean_token_accuracy": 0.19690629988908767,
|
||
|
|
"num_tokens": 1600091.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.929903554916382,
|
||
|
|
"epoch": 0.042343056967611474,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00040839278453623837,
|
||
|
|
"loss": 5.6967,
|
||
|
|
"mean_token_accuracy": 0.18317292779684066,
|
||
|
|
"num_tokens": 1604093.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.816547489166259,
|
||
|
|
"epoch": 0.04245478007306691,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0004074422293543363,
|
||
|
|
"loss": 5.6041,
|
||
|
|
"mean_token_accuracy": 0.19519466310739517,
|
||
|
|
"num_tokens": 1608254.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.730870199203491,
|
||
|
|
"epoch": 0.04256650317852235,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004064880432018137,
|
||
|
|
"loss": 5.7094,
|
||
|
|
"mean_token_accuracy": 0.18937533646821975,
|
||
|
|
"num_tokens": 1612064.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.835119581222534,
|
||
|
|
"epoch": 0.04267822628397779,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00040553025223816615,
|
||
|
|
"loss": 5.7613,
|
||
|
|
"mean_token_accuracy": 0.18858376294374465,
|
||
|
|
"num_tokens": 1616494.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.779830884933472,
|
||
|
|
"epoch": 0.04278994938943323,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00040456888272171653,
|
||
|
|
"loss": 5.4725,
|
||
|
|
"mean_token_accuracy": 0.20619394183158873,
|
||
|
|
"num_tokens": 1620432.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.958911371231079,
|
||
|
|
"epoch": 0.04290167249488867,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00040360396100889577,
|
||
|
|
"loss": 5.7467,
|
||
|
|
"mean_token_accuracy": 0.17847216576337815,
|
||
|
|
"num_tokens": 1625170.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.828932857513427,
|
||
|
|
"epoch": 0.043013395600344104,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004026355135535202,
|
||
|
|
"loss": 5.6647,
|
||
|
|
"mean_token_accuracy": 0.18227333724498748,
|
||
|
|
"num_tokens": 1629487.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.734749698638916,
|
||
|
|
"epoch": 0.04312511870579955,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.000401663566906066,
|
||
|
|
"loss": 5.6037,
|
||
|
|
"mean_token_accuracy": 0.19136299937963486,
|
||
|
|
"num_tokens": 1633868.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.85823073387146,
|
||
|
|
"epoch": 0.043236841811254985,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00040068814771294134,
|
||
|
|
"loss": 5.725,
|
||
|
|
"mean_token_accuracy": 0.18341838121414183,
|
||
|
|
"num_tokens": 1638153.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7378229141235355,
|
||
|
|
"epoch": 0.04334856491671042,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0003997092827157562,
|
||
|
|
"loss": 5.5213,
|
||
|
|
"mean_token_accuracy": 0.21243593096733093,
|
||
|
|
"num_tokens": 1642365.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021594619750976,
|
||
|
|
"epoch": 0.043460288022165866,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.000398726998750589,
|
||
|
|
"loss": 5.6583,
|
||
|
|
"mean_token_accuracy": 0.18683991432189942,
|
||
|
|
"num_tokens": 1646202.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.737234687805175,
|
||
|
|
"epoch": 0.0435720111276213,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00039774132274725076,
|
||
|
|
"loss": 5.5423,
|
||
|
|
"mean_token_accuracy": 0.20251974761486052,
|
||
|
|
"num_tokens": 1650542.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.632225704193115,
|
||
|
|
"epoch": 0.04368373423307674,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00039675228172854707,
|
||
|
|
"loss": 5.4996,
|
||
|
|
"mean_token_accuracy": 0.20376336723566055,
|
||
|
|
"num_tokens": 1654386.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.716553688049316,
|
||
|
|
"epoch": 0.043795457338532184,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0003957599028095371,
|
||
|
|
"loss": 5.4805,
|
||
|
|
"mean_token_accuracy": 0.20812955051660537,
|
||
|
|
"num_tokens": 1658211.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.847964096069336,
|
||
|
|
"epoch": 0.04390718044398762,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.00039476421319679017,
|
||
|
|
"loss": 5.6714,
|
||
|
|
"mean_token_accuracy": 0.183257956802845,
|
||
|
|
"num_tokens": 1662757.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.93111743927002,
|
||
|
|
"epoch": 0.04401890354944306,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.00039376524018764,
|
||
|
|
"loss": 5.671,
|
||
|
|
"mean_token_accuracy": 0.18319940865039824,
|
||
|
|
"num_tokens": 1666714.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.817181968688965,
|
||
|
|
"epoch": 0.0441306266548985,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00039276301116943616,
|
||
|
|
"loss": 5.6546,
|
||
|
|
"mean_token_accuracy": 0.18562693744897843,
|
||
|
|
"num_tokens": 1671029.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8121912479400635,
|
||
|
|
"epoch": 0.04424234976035394,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0003917575536187936,
|
||
|
|
"loss": 5.6513,
|
||
|
|
"mean_token_accuracy": 0.1900311678647995,
|
||
|
|
"num_tokens": 1675366.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.853685092926026,
|
||
|
|
"epoch": 0.04435407286580938,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.00039074889510083894,
|
||
|
|
"loss": 5.5223,
|
||
|
|
"mean_token_accuracy": 0.21142301857471466,
|
||
|
|
"num_tokens": 1679657.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.725562191009521,
|
||
|
|
"epoch": 0.044465795971264814,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00038973706326845495,
|
||
|
|
"loss": 5.5366,
|
||
|
|
"mean_token_accuracy": 0.19422180354595184,
|
||
|
|
"num_tokens": 1683676.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.668733263015747,
|
||
|
|
"epoch": 0.04457751907672026,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0003887220858615225,
|
||
|
|
"loss": 5.5311,
|
||
|
|
"mean_token_accuracy": 0.20603107661008835,
|
||
|
|
"num_tokens": 1687718.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6940343379974365,
|
||
|
|
"epoch": 0.044689242182175695,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0003877039907061597,
|
||
|
|
"loss": 5.5685,
|
||
|
|
"mean_token_accuracy": 0.18587933331727982,
|
||
|
|
"num_tokens": 1691434.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.721743106842041,
|
||
|
|
"epoch": 0.04480096528763113,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0003866828057139598,
|
||
|
|
"loss": 5.6397,
|
||
|
|
"mean_token_accuracy": 0.18485358059406282,
|
||
|
|
"num_tokens": 1695714.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.784295082092285,
|
||
|
|
"epoch": 0.044912688393086576,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00038565855888122503,
|
||
|
|
"loss": 5.4378,
|
||
|
|
"mean_token_accuracy": 0.20242598354816438,
|
||
|
|
"num_tokens": 1700245.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.62515549659729,
|
||
|
|
"epoch": 0.045024411498542014,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.00038463127828819975,
|
||
|
|
"loss": 5.5494,
|
||
|
|
"mean_token_accuracy": 0.20422022193670272,
|
||
|
|
"num_tokens": 1704329.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.733830881118775,
|
||
|
|
"epoch": 0.04513613460399745,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00038360099209830043,
|
||
|
|
"loss": 5.5726,
|
||
|
|
"mean_token_accuracy": 0.19276565164327622,
|
||
|
|
"num_tokens": 1708387.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.789889287948609,
|
||
|
|
"epoch": 0.045247857709452895,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.0003825677285573433,
|
||
|
|
"loss": 5.5658,
|
||
|
|
"mean_token_accuracy": 0.1929836466908455,
|
||
|
|
"num_tokens": 1712620.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.746649646759034,
|
||
|
|
"epoch": 0.04535958081490833,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00038153151599277027,
|
||
|
|
"loss": 5.5775,
|
||
|
|
"mean_token_accuracy": 0.19831744730472564,
|
||
|
|
"num_tokens": 1716862.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.86361927986145,
|
||
|
|
"epoch": 0.04547130392036377,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0003804923828128723,
|
||
|
|
"loss": 5.6553,
|
||
|
|
"mean_token_accuracy": 0.18186011761426926,
|
||
|
|
"num_tokens": 1721121.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.826954174041748,
|
||
|
|
"epoch": 0.04558302702581921,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0003794503575060104,
|
||
|
|
"loss": 5.4734,
|
||
|
|
"mean_token_accuracy": 0.20993418246507645,
|
||
|
|
"num_tokens": 1725307.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.828565216064453,
|
||
|
|
"epoch": 0.04569475013127465,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00037840546863983484,
|
||
|
|
"loss": 5.6917,
|
||
|
|
"mean_token_accuracy": 0.18647813200950622,
|
||
|
|
"num_tokens": 1729931.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.691795730590821,
|
||
|
|
"epoch": 0.04580647323673009,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0003773577448605015,
|
||
|
|
"loss": 5.677,
|
||
|
|
"mean_token_accuracy": 0.18873957991600038,
|
||
|
|
"num_tokens": 1734117.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.802150058746338,
|
||
|
|
"epoch": 0.045918196342185524,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0003763072148918872,
|
||
|
|
"loss": 5.6918,
|
||
|
|
"mean_token_accuracy": 0.1806354731321335,
|
||
|
|
"num_tokens": 1738246.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.928330421447754,
|
||
|
|
"epoch": 0.04602991944764097,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0003752539075348017,
|
||
|
|
"loss": 5.634,
|
||
|
|
"mean_token_accuracy": 0.1888989970088005,
|
||
|
|
"num_tokens": 1742557.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.763717365264893,
|
||
|
|
"epoch": 0.046141642553096406,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00037419785166619817,
|
||
|
|
"loss": 5.5667,
|
||
|
|
"mean_token_accuracy": 0.19592652171850206,
|
||
|
|
"num_tokens": 1746639.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.832269716262817,
|
||
|
|
"epoch": 0.04625336565855184,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0003731390762383818,
|
||
|
|
"loss": 5.6515,
|
||
|
|
"mean_token_accuracy": 0.18419942110776902,
|
||
|
|
"num_tokens": 1751528.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7962113380432125,
|
||
|
|
"epoch": 0.04636508876400729,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0003720776102782158,
|
||
|
|
"loss": 5.4677,
|
||
|
|
"mean_token_accuracy": 0.20580795109272004,
|
||
|
|
"num_tokens": 1755734.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7612978458404545,
|
||
|
|
"epoch": 0.046476811869462724,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00037101348288632555,
|
||
|
|
"loss": 5.6062,
|
||
|
|
"mean_token_accuracy": 0.19590772986412047,
|
||
|
|
"num_tokens": 1760188.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.779658651351928,
|
||
|
|
"epoch": 0.04658853497491816,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0003699467232363012,
|
||
|
|
"loss": 5.5658,
|
||
|
|
"mean_token_accuracy": 0.20426930040121077,
|
||
|
|
"num_tokens": 1764469.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.796822643280029,
|
||
|
|
"epoch": 0.046700258080373605,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0003688773605738973,
|
||
|
|
"loss": 5.6241,
|
||
|
|
"mean_token_accuracy": 0.1935473784804344,
|
||
|
|
"num_tokens": 1768946.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.739144229888916,
|
||
|
|
"epoch": 0.04681198118582904,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.00036780542421623134,
|
||
|
|
"loss": 5.452,
|
||
|
|
"mean_token_accuracy": 0.20726609230041504,
|
||
|
|
"num_tokens": 1772806.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.762845706939697,
|
||
|
|
"epoch": 0.04692370429128448,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0003667309435509802,
|
||
|
|
"loss": 5.7521,
|
||
|
|
"mean_token_accuracy": 0.1798543617129326,
|
||
|
|
"num_tokens": 1777333.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.788598918914795,
|
||
|
|
"epoch": 0.047035427396739916,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.0003656539480355741,
|
||
|
|
"loss": 5.5277,
|
||
|
|
"mean_token_accuracy": 0.19866943806409837,
|
||
|
|
"num_tokens": 1781232.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.829206132888794,
|
||
|
|
"epoch": 0.04714715050219536,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0003645744671963891,
|
||
|
|
"loss": 5.6079,
|
||
|
|
"mean_token_accuracy": 0.18846295773983002,
|
||
|
|
"num_tokens": 1785543.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.724898433685302,
|
||
|
|
"epoch": 0.0472588736076508,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0003634925306279376,
|
||
|
|
"loss": 5.601,
|
||
|
|
"mean_token_accuracy": 0.18806510120630265,
|
||
|
|
"num_tokens": 1789926.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.709711313247681,
|
||
|
|
"epoch": 0.047370596713106235,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0003624081679920574,
|
||
|
|
"loss": 5.5505,
|
||
|
|
"mean_token_accuracy": 0.19849662482738495,
|
||
|
|
"num_tokens": 1794307.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.706761646270752,
|
||
|
|
"epoch": 0.04748231981856168,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0003613214090170977,
|
||
|
|
"loss": 5.473,
|
||
|
|
"mean_token_accuracy": 0.20660974830389023,
|
||
|
|
"num_tokens": 1798553.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.782987308502197,
|
||
|
|
"epoch": 0.047594042924017116,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0003602322834971048,
|
||
|
|
"loss": 5.4317,
|
||
|
|
"mean_token_accuracy": 0.21588237285614015,
|
||
|
|
"num_tokens": 1802795.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.62813401222229,
|
||
|
|
"epoch": 0.04770576602947255,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0003591408212910051,
|
||
|
|
"loss": 5.4229,
|
||
|
|
"mean_token_accuracy": 0.20910920351743698,
|
||
|
|
"num_tokens": 1806762.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.61645393371582,
|
||
|
|
"epoch": 0.047817489134928,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0003580470523217863,
|
||
|
|
"loss": 5.4807,
|
||
|
|
"mean_token_accuracy": 0.20365458726882935,
|
||
|
|
"num_tokens": 1811067.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.593378210067749,
|
||
|
|
"epoch": 0.047929212240383434,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0003569510065756771,
|
||
|
|
"loss": 5.4525,
|
||
|
|
"mean_token_accuracy": 0.20863720178604125,
|
||
|
|
"num_tokens": 1815180.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.623372507095337,
|
||
|
|
"epoch": 0.04804093534583887,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0003558527141013254,
|
||
|
|
"loss": 5.5856,
|
||
|
|
"mean_token_accuracy": 0.1915388822555542,
|
||
|
|
"num_tokens": 1819564.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.802288627624511,
|
||
|
|
"epoch": 0.048152658451294315,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0003547522050089742,
|
||
|
|
"loss": 5.535,
|
||
|
|
"mean_token_accuracy": 0.20326677560806275,
|
||
|
|
"num_tokens": 1823974.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.881820392608643,
|
||
|
|
"epoch": 0.04826438155674975,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00035364950946963606,
|
||
|
|
"loss": 5.6065,
|
||
|
|
"mean_token_accuracy": 0.1908256970345974,
|
||
|
|
"num_tokens": 1828532.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.701642608642578,
|
||
|
|
"epoch": 0.04837610466220519,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0003525446577142663,
|
||
|
|
"loss": 5.5115,
|
||
|
|
"mean_token_accuracy": 0.20846942365169524,
|
||
|
|
"num_tokens": 1832678.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.717232418060303,
|
||
|
|
"epoch": 0.04848782776766063,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00035143768003293395,
|
||
|
|
"loss": 5.5227,
|
||
|
|
"mean_token_accuracy": 0.20353641510009765,
|
||
|
|
"num_tokens": 1837118.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7132915496826175,
|
||
|
|
"epoch": 0.04859955087311607,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0003503286067739913,
|
||
|
|
"loss": 5.4338,
|
||
|
|
"mean_token_accuracy": 0.20535381585359574,
|
||
|
|
"num_tokens": 1841348.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.668986082077026,
|
||
|
|
"epoch": 0.04871127397857151,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00034921746834324193,
|
||
|
|
"loss": 5.5611,
|
||
|
|
"mean_token_accuracy": 0.1910241276025772,
|
||
|
|
"num_tokens": 1845715.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.724797916412354,
|
||
|
|
"epoch": 0.048822997084026945,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0003481042952031072,
|
||
|
|
"loss": 5.5269,
|
||
|
|
"mean_token_accuracy": 0.1976793333888054,
|
||
|
|
"num_tokens": 1850028.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.77208890914917,
|
||
|
|
"epoch": 0.04893472018948239,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0003469891178717911,
|
||
|
|
"loss": 5.5548,
|
||
|
|
"mean_token_accuracy": 0.1952129825949669,
|
||
|
|
"num_tokens": 1854331.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.690452289581299,
|
||
|
|
"epoch": 0.049046443294937826,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0003458719669224436,
|
||
|
|
"loss": 5.4759,
|
||
|
|
"mean_token_accuracy": 0.21617792248725892,
|
||
|
|
"num_tokens": 1858740.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.787473392486572,
|
||
|
|
"epoch": 0.04915816640039326,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0003447528729823221,
|
||
|
|
"loss": 5.6273,
|
||
|
|
"mean_token_accuracy": 0.19919337928295136,
|
||
|
|
"num_tokens": 1863091.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.811230134963989,
|
||
|
|
"epoch": 0.04926988950584871,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0003436318667319525,
|
||
|
|
"loss": 5.5562,
|
||
|
|
"mean_token_accuracy": 0.1929182305932045,
|
||
|
|
"num_tokens": 1867164.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.705197381973266,
|
||
|
|
"epoch": 0.049381612611304145,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00034250897890428716,
|
||
|
|
"loss": 5.6218,
|
||
|
|
"mean_token_accuracy": 0.18770090788602828,
|
||
|
|
"num_tokens": 1871614.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.780409431457519,
|
||
|
|
"epoch": 0.04949333571675958,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0003413842402838633,
|
||
|
|
"loss": 5.6555,
|
||
|
|
"mean_token_accuracy": 0.18250572085380554,
|
||
|
|
"num_tokens": 1876315.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.786741590499878,
|
||
|
|
"epoch": 0.049605058822215026,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00034025768170595834,
|
||
|
|
"loss": 5.5971,
|
||
|
|
"mean_token_accuracy": 0.19007931649684906,
|
||
|
|
"num_tokens": 1880404.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8036340236663815,
|
||
|
|
"epoch": 0.04971678192767046,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0003391293340557446,
|
||
|
|
"loss": 5.5786,
|
||
|
|
"mean_token_accuracy": 0.1949792042374611,
|
||
|
|
"num_tokens": 1885056.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.699591016769409,
|
||
|
|
"epoch": 0.0498285050331259,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0003379992282674431,
|
||
|
|
"loss": 5.486,
|
||
|
|
"mean_token_accuracy": 0.19173632711172103,
|
||
|
|
"num_tokens": 1889170.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.668955135345459,
|
||
|
|
"epoch": 0.04994022813858134,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0003368673953234749,
|
||
|
|
"loss": 5.4143,
|
||
|
|
"mean_token_accuracy": 0.203122578561306,
|
||
|
|
"num_tokens": 1893344.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6577390193939205,
|
||
|
|
"epoch": 0.05005195124403678,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.00033573386625361176,
|
||
|
|
"loss": 5.5016,
|
||
|
|
"mean_token_accuracy": 0.20062802582979203,
|
||
|
|
"num_tokens": 1897399.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.685666561126709,
|
||
|
|
"epoch": 0.05016367434949222,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00033459867213412567,
|
||
|
|
"loss": 5.5944,
|
||
|
|
"mean_token_accuracy": 0.19337151050567628,
|
||
|
|
"num_tokens": 1901687.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.606955575942993,
|
||
|
|
"epoch": 0.050275397454947655,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.000333461844086937,
|
||
|
|
"loss": 5.3316,
|
||
|
|
"mean_token_accuracy": 0.20973291248083115,
|
||
|
|
"num_tokens": 1905556.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.688958406448364,
|
||
|
|
"epoch": 0.0503871205604031,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.00033232341327876097,
|
||
|
|
"loss": 5.4847,
|
||
|
|
"mean_token_accuracy": 0.20489684492349625,
|
||
|
|
"num_tokens": 1909477.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.79883189201355,
|
||
|
|
"epoch": 0.05049884366585854,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0003311834109202531,
|
||
|
|
"loss": 5.5427,
|
||
|
|
"mean_token_accuracy": 0.19271014332771302,
|
||
|
|
"num_tokens": 1913593.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.727897787094117,
|
||
|
|
"epoch": 0.050610566771313974,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.00033004186826515416,
|
||
|
|
"loss": 5.6088,
|
||
|
|
"mean_token_accuracy": 0.19398681819438934,
|
||
|
|
"num_tokens": 1917853.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.713510322570801,
|
||
|
|
"epoch": 0.05072228987676942,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.0003288988166094324,
|
||
|
|
"loss": 5.4865,
|
||
|
|
"mean_token_accuracy": 0.19069691747426987,
|
||
|
|
"num_tokens": 1922075.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.742081880569458,
|
||
|
|
"epoch": 0.050834012982224855,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00032775428729042656,
|
||
|
|
"loss": 5.5265,
|
||
|
|
"mean_token_accuracy": 0.19670794606208802,
|
||
|
|
"num_tokens": 1926595.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.659421730041504,
|
||
|
|
"epoch": 0.05094573608768029,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000326608311685986,
|
||
|
|
"loss": 5.4308,
|
||
|
|
"mean_token_accuracy": 0.21417462676763535,
|
||
|
|
"num_tokens": 1930748.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7727135181427,
|
||
|
|
"epoch": 0.05105745919313573,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0003254609212136108,
|
||
|
|
"loss": 5.5924,
|
||
|
|
"mean_token_accuracy": 0.19971541166305543,
|
||
|
|
"num_tokens": 1935243.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.814140462875367,
|
||
|
|
"epoch": 0.05116918229859117,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00032431214732959036,
|
||
|
|
"loss": 5.6066,
|
||
|
|
"mean_token_accuracy": 0.18658054620027542,
|
||
|
|
"num_tokens": 1939932.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.821799945831299,
|
||
|
|
"epoch": 0.05128090540404661,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.000323162021528141,
|
||
|
|
"loss": 5.5663,
|
||
|
|
"mean_token_accuracy": 0.19208056181669236,
|
||
|
|
"num_tokens": 1944021.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.667191028594971,
|
||
|
|
"epoch": 0.05139262850950205,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00032201057534054264,
|
||
|
|
"loss": 5.4898,
|
||
|
|
"mean_token_accuracy": 0.19366947710514068,
|
||
|
|
"num_tokens": 1948339.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.712211561203003,
|
||
|
|
"epoch": 0.05150435161495749,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00032085784033427414,
|
||
|
|
"loss": 5.641,
|
||
|
|
"mean_token_accuracy": 0.1895766705274582,
|
||
|
|
"num_tokens": 1952489.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.688895845413208,
|
||
|
|
"epoch": 0.05161607472041293,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0003197038481121478,
|
||
|
|
"loss": 5.4639,
|
||
|
|
"mean_token_accuracy": 0.19564596861600875,
|
||
|
|
"num_tokens": 1956765.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.784148550033569,
|
||
|
|
"epoch": 0.051727797825868366,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0003185486303114436,
|
||
|
|
"loss": 5.5065,
|
||
|
|
"mean_token_accuracy": 0.19699872732162477,
|
||
|
|
"num_tokens": 1960490.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.768551969528199,
|
||
|
|
"epoch": 0.05183952093132381,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.0003173922186030409,
|
||
|
|
"loss": 5.5974,
|
||
|
|
"mean_token_accuracy": 0.18267382681369781,
|
||
|
|
"num_tokens": 1964452.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.775525951385498,
|
||
|
|
"epoch": 0.05195124403677925,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.000316234644690551,
|
||
|
|
"loss": 5.5279,
|
||
|
|
"mean_token_accuracy": 0.20707689225673676,
|
||
|
|
"num_tokens": 1968765.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.656964111328125,
|
||
|
|
"epoch": 0.052062967142234684,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0003150759403094473,
|
||
|
|
"loss": 5.3023,
|
||
|
|
"mean_token_accuracy": 0.20677033066749573,
|
||
|
|
"num_tokens": 1972696.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.731927442550659,
|
||
|
|
"epoch": 0.05217469024769013,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00031391613722619587,
|
||
|
|
"loss": 5.6455,
|
||
|
|
"mean_token_accuracy": 0.1690948113799095,
|
||
|
|
"num_tokens": 1976873.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.701600790023804,
|
||
|
|
"epoch": 0.052286413353145565,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000312755267237384,
|
||
|
|
"loss": 5.4535,
|
||
|
|
"mean_token_accuracy": 0.20874593853950502,
|
||
|
|
"num_tokens": 1981203.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.716491413116455,
|
||
|
|
"epoch": 0.052398136458601,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0003115933621688488,
|
||
|
|
"loss": 5.4959,
|
||
|
|
"mean_token_accuracy": 0.19572610706090926,
|
||
|
|
"num_tokens": 1985311.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.722491359710693,
|
||
|
|
"epoch": 0.05250985956405644,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00031043045387480487,
|
||
|
|
"loss": 5.487,
|
||
|
|
"mean_token_accuracy": 0.19076797217130662,
|
||
|
|
"num_tokens": 1989525.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.713915491104126,
|
||
|
|
"epoch": 0.052621582669511884,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.0003092665742369703,
|
||
|
|
"loss": 5.5469,
|
||
|
|
"mean_token_accuracy": 0.19271685034036637,
|
||
|
|
"num_tokens": 1993322.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.756639909744263,
|
||
|
|
"epoch": 0.05273330577496732,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00030810175516369343,
|
||
|
|
"loss": 5.5986,
|
||
|
|
"mean_token_accuracy": 0.19009712785482408,
|
||
|
|
"num_tokens": 1997360.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.864648628234863,
|
||
|
|
"epoch": 0.05284502888042276,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0003069360285890775,
|
||
|
|
"loss": 5.4436,
|
||
|
|
"mean_token_accuracy": 0.20150963515043258,
|
||
|
|
"num_tokens": 2001867.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.802446031570435,
|
||
|
|
"epoch": 0.0529567519858782,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00030576942647210547,
|
||
|
|
"loss": 5.6381,
|
||
|
|
"mean_token_accuracy": 0.19385351836681367,
|
||
|
|
"num_tokens": 2005729.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.738719177246094,
|
||
|
|
"epoch": 0.05306847509133364,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00030460198079576355,
|
||
|
|
"loss": 5.5142,
|
||
|
|
"mean_token_accuracy": 0.1945842370390892,
|
||
|
|
"num_tokens": 2009839.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.718826341629028,
|
||
|
|
"epoch": 0.053180198196789076,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0003034337235661648,
|
||
|
|
"loss": 5.4732,
|
||
|
|
"mean_token_accuracy": 0.1891820028424263,
|
||
|
|
"num_tokens": 2013967.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.774100112915039,
|
||
|
|
"epoch": 0.05329192130224452,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.0003022646868116714,
|
||
|
|
"loss": 5.5776,
|
||
|
|
"mean_token_accuracy": 0.19752005487680435,
|
||
|
|
"num_tokens": 2018353.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8372434139251705,
|
||
|
|
"epoch": 0.05340364440769996,
|
||
|
|
"grad_norm": 1.4765625,
|
||
|
|
"learning_rate": 0.0003010949025820163,
|
||
|
|
"loss": 5.641,
|
||
|
|
"mean_token_accuracy": 0.18861606419086457,
|
||
|
|
"num_tokens": 2022171.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.75879545211792,
|
||
|
|
"epoch": 0.053515367513155394,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0002999244029474252,
|
||
|
|
"loss": 5.547,
|
||
|
|
"mean_token_accuracy": 0.20157204419374466,
|
||
|
|
"num_tokens": 2026341.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.830027294158936,
|
||
|
|
"epoch": 0.05362709061861083,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00029875321999773684,
|
||
|
|
"loss": 5.588,
|
||
|
|
"mean_token_accuracy": 0.19347797334194183,
|
||
|
|
"num_tokens": 2031021.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.816708278656006,
|
||
|
|
"epoch": 0.053738813724066276,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00029758138584152333,
|
||
|
|
"loss": 5.6899,
|
||
|
|
"mean_token_accuracy": 0.18223569244146348,
|
||
|
|
"num_tokens": 2035653.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.729998159408569,
|
||
|
|
"epoch": 0.05385053682952171,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0002964089326052102,
|
||
|
|
"loss": 5.6188,
|
||
|
|
"mean_token_accuracy": 0.20222849845886232,
|
||
|
|
"num_tokens": 2039728.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.713871240615845,
|
||
|
|
"epoch": 0.05396225993497715,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.0002952358924321949,
|
||
|
|
"loss": 5.4909,
|
||
|
|
"mean_token_accuracy": 0.19180112928152085,
|
||
|
|
"num_tokens": 2044078.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.726597166061401,
|
||
|
|
"epoch": 0.054073983040432594,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00029406229748196657,
|
||
|
|
"loss": 5.3667,
|
||
|
|
"mean_token_accuracy": 0.21022001802921295,
|
||
|
|
"num_tokens": 2048138.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.739075231552124,
|
||
|
|
"epoch": 0.05418570614588803,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0002928881799292235,
|
||
|
|
"loss": 5.6663,
|
||
|
|
"mean_token_accuracy": 0.188392074406147,
|
||
|
|
"num_tokens": 2052837.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.754153871536255,
|
||
|
|
"epoch": 0.05429742925134347,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.00029171357196299154,
|
||
|
|
"loss": 5.5659,
|
||
|
|
"mean_token_accuracy": 0.20061070024967192,
|
||
|
|
"num_tokens": 2056715.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.690628623962402,
|
||
|
|
"epoch": 0.05440915235679891,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0002905385057857414,
|
||
|
|
"loss": 5.5361,
|
||
|
|
"mean_token_accuracy": 0.1939275875687599,
|
||
|
|
"num_tokens": 2060508.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.781807994842529,
|
||
|
|
"epoch": 0.05452087546225435,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0002893630136125058,
|
||
|
|
"loss": 5.5752,
|
||
|
|
"mean_token_accuracy": 0.18510538935661316,
|
||
|
|
"num_tokens": 2065050.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.740582275390625,
|
||
|
|
"epoch": 0.054632598567709786,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0002881871276699967,
|
||
|
|
"loss": 5.4727,
|
||
|
|
"mean_token_accuracy": 0.1987502843141556,
|
||
|
|
"num_tokens": 2069488.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.70595965385437,
|
||
|
|
"epoch": 0.05474432167316523,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00028701088019572114,
|
||
|
|
"loss": 5.5521,
|
||
|
|
"mean_token_accuracy": 0.19443101733922957,
|
||
|
|
"num_tokens": 2073605.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.707414436340332,
|
||
|
|
"epoch": 0.05485604477862067,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0002858343034370977,
|
||
|
|
"loss": 5.4163,
|
||
|
|
"mean_token_accuracy": 0.20107322484254836,
|
||
|
|
"num_tokens": 2077721.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.679768180847168,
|
||
|
|
"epoch": 0.054967767884076105,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00028465742965057267,
|
||
|
|
"loss": 5.5498,
|
||
|
|
"mean_token_accuracy": 0.19062326103448868,
|
||
|
|
"num_tokens": 2081945.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.776157379150391,
|
||
|
|
"epoch": 0.05507949098953154,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00028348029110073533,
|
||
|
|
"loss": 5.6399,
|
||
|
|
"mean_token_accuracy": 0.189193694293499,
|
||
|
|
"num_tokens": 2086184.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.761434888839721,
|
||
|
|
"epoch": 0.055191214094986986,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00028230292005943365,
|
||
|
|
"loss": 5.4473,
|
||
|
|
"mean_token_accuracy": 0.20474444925785065,
|
||
|
|
"num_tokens": 2090271.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.625124883651734,
|
||
|
|
"epoch": 0.05530293720044242,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00028112534880488945,
|
||
|
|
"loss": 5.4348,
|
||
|
|
"mean_token_accuracy": 0.19888102859258652,
|
||
|
|
"num_tokens": 2094427.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.551406145095825,
|
||
|
|
"epoch": 0.05541466030589786,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0002799476096208137,
|
||
|
|
"loss": 5.2503,
|
||
|
|
"mean_token_accuracy": 0.22414482980966569,
|
||
|
|
"num_tokens": 2098795.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.698645448684692,
|
||
|
|
"epoch": 0.055526383411353304,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00027876973479552087,
|
||
|
|
"loss": 5.4507,
|
||
|
|
"mean_token_accuracy": 0.21797254532575608,
|
||
|
|
"num_tokens": 2103190.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7277178287506105,
|
||
|
|
"epoch": 0.05563810651680874,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00027759175662104424,
|
||
|
|
"loss": 5.3879,
|
||
|
|
"mean_token_accuracy": 0.2203633740544319,
|
||
|
|
"num_tokens": 2107253.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6748926639556885,
|
||
|
|
"epoch": 0.05574982962226418,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0002764137073922508,
|
||
|
|
"loss": 5.572,
|
||
|
|
"mean_token_accuracy": 0.19839244335889816,
|
||
|
|
"num_tokens": 2111361.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.68821496963501,
|
||
|
|
"epoch": 0.05586155272771962,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00027523561940595505,
|
||
|
|
"loss": 5.4097,
|
||
|
|
"mean_token_accuracy": 0.2047291651368141,
|
||
|
|
"num_tokens": 2115586.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.779299640655518,
|
||
|
|
"epoch": 0.05597327583317506,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0002740575249600342,
|
||
|
|
"loss": 5.5373,
|
||
|
|
"mean_token_accuracy": 0.1977283999323845,
|
||
|
|
"num_tokens": 2119746.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.650565814971924,
|
||
|
|
"epoch": 0.0560849989386305,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00027287945635254263,
|
||
|
|
"loss": 5.5265,
|
||
|
|
"mean_token_accuracy": 0.19489531219005585,
|
||
|
|
"num_tokens": 2124367.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.795668697357177,
|
||
|
|
"epoch": 0.05619672204408594,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00027170144588082635,
|
||
|
|
"loss": 5.5271,
|
||
|
|
"mean_token_accuracy": 0.19151871800422668,
|
||
|
|
"num_tokens": 2128772.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.783979797363282,
|
||
|
|
"epoch": 0.05630844514954138,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00027052352584063763,
|
||
|
|
"loss": 5.4057,
|
||
|
|
"mean_token_accuracy": 0.20860070288181304,
|
||
|
|
"num_tokens": 2132943.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.579121398925781,
|
||
|
|
"epoch": 0.056420168254996815,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00026934572852524907,
|
||
|
|
"loss": 5.3935,
|
||
|
|
"mean_token_accuracy": 0.2062055453658104,
|
||
|
|
"num_tokens": 2137332.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.585285711288452,
|
||
|
|
"epoch": 0.05653189136045225,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00026816808622456937,
|
||
|
|
"loss": 5.4183,
|
||
|
|
"mean_token_accuracy": 0.20738962888717652,
|
||
|
|
"num_tokens": 2141459.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.581014633178711,
|
||
|
|
"epoch": 0.056643614465907696,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0002669906312242569,
|
||
|
|
"loss": 5.3718,
|
||
|
|
"mean_token_accuracy": 0.20966480523347855,
|
||
|
|
"num_tokens": 2145450.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.709204387664795,
|
||
|
|
"epoch": 0.05675533757136313,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00026581339580483525,
|
||
|
|
"loss": 5.5215,
|
||
|
|
"mean_token_accuracy": 0.19486008882522582,
|
||
|
|
"num_tokens": 2149908.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.81135311126709,
|
||
|
|
"epoch": 0.05686706067681857,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0002646364122408082,
|
||
|
|
"loss": 5.6473,
|
||
|
|
"mean_token_accuracy": 0.18592869490385056,
|
||
|
|
"num_tokens": 2154641.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.743757867813111,
|
||
|
|
"epoch": 0.056978783782274015,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.0002634597127997749,
|
||
|
|
"loss": 5.4325,
|
||
|
|
"mean_token_accuracy": 0.20286497473716736,
|
||
|
|
"num_tokens": 2158558.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.736222839355468,
|
||
|
|
"epoch": 0.05709050688772945,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0002622833297415445,
|
||
|
|
"loss": 5.4822,
|
||
|
|
"mean_token_accuracy": 0.20705748796463014,
|
||
|
|
"num_tokens": 2162953.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.728305435180664,
|
||
|
|
"epoch": 0.05720222999318489,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.0002611072953172531,
|
||
|
|
"loss": 5.5456,
|
||
|
|
"mean_token_accuracy": 0.19390425831079483,
|
||
|
|
"num_tokens": 2167438.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.734443330764771,
|
||
|
|
"epoch": 0.05731395309864033,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00025993164176847845,
|
||
|
|
"loss": 5.464,
|
||
|
|
"mean_token_accuracy": 0.20087790936231614,
|
||
|
|
"num_tokens": 2171603.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.737977695465088,
|
||
|
|
"epoch": 0.05742567620409577,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.0002587564013263564,
|
||
|
|
"loss": 5.498,
|
||
|
|
"mean_token_accuracy": 0.19558269530534744,
|
||
|
|
"num_tokens": 2175976.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.766001796722412,
|
||
|
|
"epoch": 0.05753739930955121,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.0002575816062106974,
|
||
|
|
"loss": 5.3427,
|
||
|
|
"mean_token_accuracy": 0.2205933377146721,
|
||
|
|
"num_tokens": 2179626.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.643783760070801,
|
||
|
|
"epoch": 0.057649122415006644,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00025640728862910293,
|
||
|
|
"loss": 5.4789,
|
||
|
|
"mean_token_accuracy": 0.20106479972600938,
|
||
|
|
"num_tokens": 2183903.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.61820912361145,
|
||
|
|
"epoch": 0.05776084552046209,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.00025523348077608285,
|
||
|
|
"loss": 5.5113,
|
||
|
|
"mean_token_accuracy": 0.1954667776823044,
|
||
|
|
"num_tokens": 2188232.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.654152536392212,
|
||
|
|
"epoch": 0.057872568625917525,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00025406021483217225,
|
||
|
|
"loss": 5.4086,
|
||
|
|
"mean_token_accuracy": 0.2141653209924698,
|
||
|
|
"num_tokens": 2192465.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7762407779693605,
|
||
|
|
"epoch": 0.05798429173137296,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00025288752296304963,
|
||
|
|
"loss": 5.4788,
|
||
|
|
"mean_token_accuracy": 0.19897868633270263,
|
||
|
|
"num_tokens": 2196597.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.663915967941284,
|
||
|
|
"epoch": 0.05809601483682841,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.000251715437318655,
|
||
|
|
"loss": 5.4153,
|
||
|
|
"mean_token_accuracy": 0.19493801891803741,
|
||
|
|
"num_tokens": 2200590.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.633232975006104,
|
||
|
|
"epoch": 0.058207737942283844,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.0002505439900323084,
|
||
|
|
"loss": 5.3918,
|
||
|
|
"mean_token_accuracy": 0.204731585085392,
|
||
|
|
"num_tokens": 2204897.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.740216207504273,
|
||
|
|
"epoch": 0.05831946104773928,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00024937321321982894,
|
||
|
|
"loss": 5.5004,
|
||
|
|
"mean_token_accuracy": 0.1938529819250107,
|
||
|
|
"num_tokens": 2209187.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.715686464309693,
|
||
|
|
"epoch": 0.058431184153194725,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.00024820313897865433,
|
||
|
|
"loss": 5.5595,
|
||
|
|
"mean_token_accuracy": 0.20210601687431334,
|
||
|
|
"num_tokens": 2213496.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.646053171157837,
|
||
|
|
"epoch": 0.05854290725865016,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00024703379938696105,
|
||
|
|
"loss": 5.3267,
|
||
|
|
"mean_token_accuracy": 0.2136288985610008,
|
||
|
|
"num_tokens": 2217612.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.582569265365601,
|
||
|
|
"epoch": 0.0586546303641056,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00024586522650278447,
|
||
|
|
"loss": 5.3083,
|
||
|
|
"mean_token_accuracy": 0.2052677869796753,
|
||
|
|
"num_tokens": 2221830.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.684707498550415,
|
||
|
|
"epoch": 0.05876635346956104,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00024469745236314064,
|
||
|
|
"loss": 5.3923,
|
||
|
|
"mean_token_accuracy": 0.2086835339665413,
|
||
|
|
"num_tokens": 2226552.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.722059297561645,
|
||
|
|
"epoch": 0.05887807657501648,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 0.00024353050898314767,
|
||
|
|
"loss": 5.498,
|
||
|
|
"mean_token_accuracy": 0.20146586149930953,
|
||
|
|
"num_tokens": 2230785.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.678656578063965,
|
||
|
|
"epoch": 0.05898979968047192,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.00024236442835514743,
|
||
|
|
"loss": 5.3457,
|
||
|
|
"mean_token_accuracy": 0.20883162021636964,
|
||
|
|
"num_tokens": 2235103.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.732641696929932,
|
||
|
|
"epoch": 0.059101522785927355,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00024119924244782965,
|
||
|
|
"loss": 5.4506,
|
||
|
|
"mean_token_accuracy": 0.20166707560420036,
|
||
|
|
"num_tokens": 2239699.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.742127323150635,
|
||
|
|
"epoch": 0.0592132458913828,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00024003498320535462,
|
||
|
|
"loss": 5.5482,
|
||
|
|
"mean_token_accuracy": 0.18562940657138824,
|
||
|
|
"num_tokens": 2244112.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.637723159790039,
|
||
|
|
"epoch": 0.059324968996838236,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.00023887168254647727,
|
||
|
|
"loss": 5.3385,
|
||
|
|
"mean_token_accuracy": 0.21312180608510972,
|
||
|
|
"num_tokens": 2247902.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.600325059890747,
|
||
|
|
"epoch": 0.05943669210229367,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00023770937236367308,
|
||
|
|
"loss": 5.4058,
|
||
|
|
"mean_token_accuracy": 0.1909279465675354,
|
||
|
|
"num_tokens": 2251966.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.647561836242676,
|
||
|
|
"epoch": 0.05954841520774912,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00023654808452226278,
|
||
|
|
"loss": 5.4118,
|
||
|
|
"mean_token_accuracy": 0.20381290316581727,
|
||
|
|
"num_tokens": 2256579.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.709055614471436,
|
||
|
|
"epoch": 0.059660138313204554,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00023538785085953912,
|
||
|
|
"loss": 5.4918,
|
||
|
|
"mean_token_accuracy": 0.20567824095487594,
|
||
|
|
"num_tokens": 2261466.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.651337146759033,
|
||
|
|
"epoch": 0.05977186141865999,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00023422870318389404,
|
||
|
|
"loss": 5.4168,
|
||
|
|
"mean_token_accuracy": 0.20561701506376268,
|
||
|
|
"num_tokens": 2266547.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.723851871490479,
|
||
|
|
"epoch": 0.059883584524115435,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0002330706732739468,
|
||
|
|
"loss": 5.5041,
|
||
|
|
"mean_token_accuracy": 0.1933462366461754,
|
||
|
|
"num_tokens": 2270686.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.628253173828125,
|
||
|
|
"epoch": 0.05999530762957087,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00023191379287767211,
|
||
|
|
"loss": 5.3672,
|
||
|
|
"mean_token_accuracy": 0.21610769629478455,
|
||
|
|
"num_tokens": 2274819.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6342497825622555,
|
||
|
|
"epoch": 0.06010703073502631,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0002307580937115305,
|
||
|
|
"loss": 5.3348,
|
||
|
|
"mean_token_accuracy": 0.21631180346012116,
|
||
|
|
"num_tokens": 2278991.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7209268569946286,
|
||
|
|
"epoch": 0.06021875384048175,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00022960360745959846,
|
||
|
|
"loss": 5.4823,
|
||
|
|
"mean_token_accuracy": 0.2016025885939598,
|
||
|
|
"num_tokens": 2283300.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7764557838439945,
|
||
|
|
"epoch": 0.06033047694593719,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00022845036577269972,
|
||
|
|
"loss": 5.5319,
|
||
|
|
"mean_token_accuracy": 0.19847869277000427,
|
||
|
|
"num_tokens": 2288263.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.787051963806152,
|
||
|
|
"epoch": 0.06044220005139263,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00022729840026753777,
|
||
|
|
"loss": 5.4309,
|
||
|
|
"mean_token_accuracy": 0.1996562197804451,
|
||
|
|
"num_tokens": 2292413.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.728420066833496,
|
||
|
|
"epoch": 0.060553923156848065,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0002261477425258287,
|
||
|
|
"loss": 5.444,
|
||
|
|
"mean_token_accuracy": 0.20907077044248581,
|
||
|
|
"num_tokens": 2297154.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6644935131073,
|
||
|
|
"epoch": 0.06066564626230351,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0002249984240934358,
|
||
|
|
"loss": 5.4308,
|
||
|
|
"mean_token_accuracy": 0.2125580057501793,
|
||
|
|
"num_tokens": 2301162.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.746449279785156,
|
||
|
|
"epoch": 0.060777369367758946,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00022385047647950464,
|
||
|
|
"loss": 5.4339,
|
||
|
|
"mean_token_accuracy": 0.1966474771499634,
|
||
|
|
"num_tokens": 2305827.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.712580442428589,
|
||
|
|
"epoch": 0.06088909247321438,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0002227039311555986,
|
||
|
|
"loss": 5.4109,
|
||
|
|
"mean_token_accuracy": 0.1991946816444397,
|
||
|
|
"num_tokens": 2310167.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.612943077087403,
|
||
|
|
"epoch": 0.06100081557866983,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0002215588195548372,
|
||
|
|
"loss": 5.3646,
|
||
|
|
"mean_token_accuracy": 0.21367968916893004,
|
||
|
|
"num_tokens": 2314324.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.602614831924439,
|
||
|
|
"epoch": 0.061112538684125264,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.00022041517307103337,
|
||
|
|
"loss": 5.4077,
|
||
|
|
"mean_token_accuracy": 0.1989472836256027,
|
||
|
|
"num_tokens": 2318316.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.596106052398682,
|
||
|
|
"epoch": 0.0612242617895807,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0002192730230578331,
|
||
|
|
"loss": 5.3815,
|
||
|
|
"mean_token_accuracy": 0.21190638095140457,
|
||
|
|
"num_tokens": 2322450.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6977253437042235,
|
||
|
|
"epoch": 0.061335984895036146,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0002181324008278559,
|
||
|
|
"loss": 5.5464,
|
||
|
|
"mean_token_accuracy": 0.20245341062545777,
|
||
|
|
"num_tokens": 2326849.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6974265575408936,
|
||
|
|
"epoch": 0.06144770800049158,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00021699333765183655,
|
||
|
|
"loss": 5.3075,
|
||
|
|
"mean_token_accuracy": 0.21131206750869752,
|
||
|
|
"num_tokens": 2331326.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.609620380401611,
|
||
|
|
"epoch": 0.06155943110594702,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.0002158558647577673,
|
||
|
|
"loss": 5.301,
|
||
|
|
"mean_token_accuracy": 0.21574847102165223,
|
||
|
|
"num_tokens": 2335443.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.723866319656372,
|
||
|
|
"epoch": 0.06167115421140246,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00021472001333004215,
|
||
|
|
"loss": 5.5859,
|
||
|
|
"mean_token_accuracy": 0.19365599304437636,
|
||
|
|
"num_tokens": 2339836.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.684416246414185,
|
||
|
|
"epoch": 0.0617828773168579,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00021358581450860186,
|
||
|
|
"loss": 5.417,
|
||
|
|
"mean_token_accuracy": 0.2063658282160759,
|
||
|
|
"num_tokens": 2344125.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6221246242523195,
|
||
|
|
"epoch": 0.06189460042231334,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0002124532993880799,
|
||
|
|
"loss": 5.3519,
|
||
|
|
"mean_token_accuracy": 0.20936380624771117,
|
||
|
|
"num_tokens": 2348375.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.616058301925659,
|
||
|
|
"epoch": 0.062006323527768775,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00021132249901695044,
|
||
|
|
"loss": 5.26,
|
||
|
|
"mean_token_accuracy": 0.22578572183847428,
|
||
|
|
"num_tokens": 2352315.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6582283020019535,
|
||
|
|
"epoch": 0.06211804663322422,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.00021019344439667705,
|
||
|
|
"loss": 5.3208,
|
||
|
|
"mean_token_accuracy": 0.22070808410644532,
|
||
|
|
"num_tokens": 2356351.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.663221788406372,
|
||
|
|
"epoch": 0.062229769738679656,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00020906616648086213,
|
||
|
|
"loss": 5.3256,
|
||
|
|
"mean_token_accuracy": 0.20464612394571305,
|
||
|
|
"num_tokens": 2360690.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.712641191482544,
|
||
|
|
"epoch": 0.062341492844135094,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00020794069617439942,
|
||
|
|
"loss": 5.3701,
|
||
|
|
"mean_token_accuracy": 0.2112012192606926,
|
||
|
|
"num_tokens": 2364581.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.671883583068848,
|
||
|
|
"epoch": 0.06245321594959054,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.00020681706433262593,
|
||
|
|
"loss": 5.4907,
|
||
|
|
"mean_token_accuracy": 0.21165458709001542,
|
||
|
|
"num_tokens": 2368799.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.652011823654175,
|
||
|
|
"epoch": 0.06256493905504597,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.00020569530176047602,
|
||
|
|
"loss": 5.3811,
|
||
|
|
"mean_token_accuracy": 0.2047820582985878,
|
||
|
|
"num_tokens": 2372843.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.629188394546508,
|
||
|
|
"epoch": 0.06267666216050141,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0002045754392116374,
|
||
|
|
"loss": 5.2659,
|
||
|
|
"mean_token_accuracy": 0.22178127020597457,
|
||
|
|
"num_tokens": 2376998.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.74638090133667,
|
||
|
|
"epoch": 0.06278838526595686,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00020345750738770757,
|
||
|
|
"loss": 5.4709,
|
||
|
|
"mean_token_accuracy": 0.20035234242677688,
|
||
|
|
"num_tokens": 2381511.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.746858596801758,
|
||
|
|
"epoch": 0.06290010837141229,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00020234153693735214,
|
||
|
|
"loss": 5.4442,
|
||
|
|
"mean_token_accuracy": 0.21169123500585557,
|
||
|
|
"num_tokens": 2385352.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.596214485168457,
|
||
|
|
"epoch": 0.06301183147686773,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0002012275584554647,
|
||
|
|
"loss": 5.3718,
|
||
|
|
"mean_token_accuracy": 0.20885302722454072,
|
||
|
|
"num_tokens": 2389631.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.635304594039917,
|
||
|
|
"epoch": 0.06312355458232317,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00020011560248232803,
|
||
|
|
"loss": 5.5109,
|
||
|
|
"mean_token_accuracy": 0.19816787391901017,
|
||
|
|
"num_tokens": 2394253.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.660125255584717,
|
||
|
|
"epoch": 0.0632352776877786,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00019900569950277692,
|
||
|
|
"loss": 5.3589,
|
||
|
|
"mean_token_accuracy": 0.21076688766479493,
|
||
|
|
"num_tokens": 2398397.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.612528276443482,
|
||
|
|
"epoch": 0.06334700079323405,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00019789787994536228,
|
||
|
|
"loss": 5.3586,
|
||
|
|
"mean_token_accuracy": 0.21716920733451844,
|
||
|
|
"num_tokens": 2402624.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.602710866928101,
|
||
|
|
"epoch": 0.06345872389868949,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.00019679217418151667,
|
||
|
|
"loss": 5.3197,
|
||
|
|
"mean_token_accuracy": 0.20867802053689957,
|
||
|
|
"num_tokens": 2406841.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7144159317016605,
|
||
|
|
"epoch": 0.06357044700414492,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.00019568861252472236,
|
||
|
|
"loss": 5.3641,
|
||
|
|
"mean_token_accuracy": 0.20947953015565873,
|
||
|
|
"num_tokens": 2410760.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.546571922302246,
|
||
|
|
"epoch": 0.06368217010960037,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00019458722522967952,
|
||
|
|
"loss": 5.2964,
|
||
|
|
"mean_token_accuracy": 0.21963961869478227,
|
||
|
|
"num_tokens": 2415022.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6442108154296875,
|
||
|
|
"epoch": 0.06379389321505581,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00019348804249147723,
|
||
|
|
"loss": 5.4682,
|
||
|
|
"mean_token_accuracy": 0.2053038701415062,
|
||
|
|
"num_tokens": 2419569.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.556906986236572,
|
||
|
|
"epoch": 0.06390561632051124,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0001923910944447655,
|
||
|
|
"loss": 5.387,
|
||
|
|
"mean_token_accuracy": 0.217524017393589,
|
||
|
|
"num_tokens": 2423979.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.622811889648437,
|
||
|
|
"epoch": 0.06401733942596669,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00019129641116292928,
|
||
|
|
"loss": 5.34,
|
||
|
|
"mean_token_accuracy": 0.21249400526285173,
|
||
|
|
"num_tokens": 2428714.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.612063026428222,
|
||
|
|
"epoch": 0.06412906253142213,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00019020402265726343,
|
||
|
|
"loss": 5.3926,
|
||
|
|
"mean_token_accuracy": 0.21560358256101608,
|
||
|
|
"num_tokens": 2433133.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.733652210235595,
|
||
|
|
"epoch": 0.06424078563687756,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.0001891139588761509,
|
||
|
|
"loss": 5.3896,
|
||
|
|
"mean_token_accuracy": 0.20228823721408845,
|
||
|
|
"num_tokens": 2436934.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.791445779800415,
|
||
|
|
"epoch": 0.064352508742333,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.00018802624970424076,
|
||
|
|
"loss": 5.4891,
|
||
|
|
"mean_token_accuracy": 0.19218750596046447,
|
||
|
|
"num_tokens": 2441569.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7009679794311525,
|
||
|
|
"epoch": 0.06446423184778845,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00018694092496162945,
|
||
|
|
"loss": 5.4602,
|
||
|
|
"mean_token_accuracy": 0.2004503607749939,
|
||
|
|
"num_tokens": 2445672.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.695861387252807,
|
||
|
|
"epoch": 0.06457595495324388,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00018585801440304306,
|
||
|
|
"loss": 5.3984,
|
||
|
|
"mean_token_accuracy": 0.21129112392663957,
|
||
|
|
"num_tokens": 2449608.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.610105514526367,
|
||
|
|
"epoch": 0.06468767805869932,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.00018477754771702165,
|
||
|
|
"loss": 5.3041,
|
||
|
|
"mean_token_accuracy": 0.21272615641355513,
|
||
|
|
"num_tokens": 2453604.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.785283613204956,
|
||
|
|
"epoch": 0.06479940116415477,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00018369955452510506,
|
||
|
|
"loss": 5.542,
|
||
|
|
"mean_token_accuracy": 0.19543841928243638,
|
||
|
|
"num_tokens": 2457973.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.576959562301636,
|
||
|
|
"epoch": 0.0649111242696102,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0001826240643810212,
|
||
|
|
"loss": 5.2954,
|
||
|
|
"mean_token_accuracy": 0.21963100880384445,
|
||
|
|
"num_tokens": 2462123.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5987739086151125,
|
||
|
|
"epoch": 0.06502284737506564,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.0001815511067698758,
|
||
|
|
"loss": 5.3741,
|
||
|
|
"mean_token_accuracy": 0.20394418984651566,
|
||
|
|
"num_tokens": 2466404.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.599570846557617,
|
||
|
|
"epoch": 0.06513457048052107,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0001804807111073436,
|
||
|
|
"loss": 5.4111,
|
||
|
|
"mean_token_accuracy": 0.2101197898387909,
|
||
|
|
"num_tokens": 2471086.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.728887939453125,
|
||
|
|
"epoch": 0.06524629358597651,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0001794129067388625,
|
||
|
|
"loss": 5.4369,
|
||
|
|
"mean_token_accuracy": 0.19458499997854234,
|
||
|
|
"num_tokens": 2475411.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.772345447540284,
|
||
|
|
"epoch": 0.06535801669143196,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00017834772293882868,
|
||
|
|
"loss": 5.5032,
|
||
|
|
"mean_token_accuracy": 0.19811111837625503,
|
||
|
|
"num_tokens": 2479742.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.731832504272461,
|
||
|
|
"epoch": 0.06546973979688739,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.000177285188909794,
|
||
|
|
"loss": 5.5256,
|
||
|
|
"mean_token_accuracy": 0.19889512807130813,
|
||
|
|
"num_tokens": 2484339.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6758034229278564,
|
||
|
|
"epoch": 0.06558146290234283,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0001762253337816656,
|
||
|
|
"loss": 5.4664,
|
||
|
|
"mean_token_accuracy": 0.20579820573329927,
|
||
|
|
"num_tokens": 2488619.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.765306663513184,
|
||
|
|
"epoch": 0.06569318600779828,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00017516818661090738,
|
||
|
|
"loss": 5.5043,
|
||
|
|
"mean_token_accuracy": 0.19775743186473846,
|
||
|
|
"num_tokens": 2493068.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.652463054656982,
|
||
|
|
"epoch": 0.0658049091132537,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0001741137763797428,
|
||
|
|
"loss": 5.2482,
|
||
|
|
"mean_token_accuracy": 0.23082863986492158,
|
||
|
|
"num_tokens": 2497322.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.812825775146484,
|
||
|
|
"epoch": 0.06591663221870915,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.00017306213199536115,
|
||
|
|
"loss": 5.5222,
|
||
|
|
"mean_token_accuracy": 0.18363130688667298,
|
||
|
|
"num_tokens": 2501476.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.639954090118408,
|
||
|
|
"epoch": 0.0660283553241646,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0001720132822891243,
|
||
|
|
"loss": 5.3021,
|
||
|
|
"mean_token_accuracy": 0.21535781025886536,
|
||
|
|
"num_tokens": 2505520.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.607745599746704,
|
||
|
|
"epoch": 0.06614007842962003,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0001709672560157769,
|
||
|
|
"loss": 5.2646,
|
||
|
|
"mean_token_accuracy": 0.21338043361902237,
|
||
|
|
"num_tokens": 2509912.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.706130886077881,
|
||
|
|
"epoch": 0.06625180153507547,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00016992408185265758,
|
||
|
|
"loss": 5.5395,
|
||
|
|
"mean_token_accuracy": 0.19716476798057556,
|
||
|
|
"num_tokens": 2514342.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.630351114273071,
|
||
|
|
"epoch": 0.06636352464053091,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00016888378839891298,
|
||
|
|
"loss": 5.2632,
|
||
|
|
"mean_token_accuracy": 0.21412647962570192,
|
||
|
|
"num_tokens": 2518771.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.680066061019898,
|
||
|
|
"epoch": 0.06647524774598634,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0001678464041747137,
|
||
|
|
"loss": 5.3748,
|
||
|
|
"mean_token_accuracy": 0.19917938560247422,
|
||
|
|
"num_tokens": 2522908.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.595112133026123,
|
||
|
|
"epoch": 0.06658697085144179,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00016681195762047223,
|
||
|
|
"loss": 5.3649,
|
||
|
|
"mean_token_accuracy": 0.21546784788370132,
|
||
|
|
"num_tokens": 2527150.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.624182558059692,
|
||
|
|
"epoch": 0.06669869395689723,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00016578047709606337,
|
||
|
|
"loss": 5.2446,
|
||
|
|
"mean_token_accuracy": 0.21532990038394928,
|
||
|
|
"num_tokens": 2531708.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.688130235671997,
|
||
|
|
"epoch": 0.06681041706235266,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00016475199088004678,
|
||
|
|
"loss": 5.3917,
|
||
|
|
"mean_token_accuracy": 0.20507018119096757,
|
||
|
|
"num_tokens": 2536403.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.59664306640625,
|
||
|
|
"epoch": 0.0669221401678081,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.00016372652716889163,
|
||
|
|
"loss": 5.2967,
|
||
|
|
"mean_token_accuracy": 0.21951241195201873,
|
||
|
|
"num_tokens": 2540527.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.678198194503784,
|
||
|
|
"epoch": 0.06703386327326355,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.0001627041140762035,
|
||
|
|
"loss": 5.3924,
|
||
|
|
"mean_token_accuracy": 0.20448053181171416,
|
||
|
|
"num_tokens": 2544603.0,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.622107076644897,
|
||
|
|
"epoch": 0.06714558637871898,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.00016168477963195382,
|
||
|
|
"loss": 5.3918,
|
||
|
|
"mean_token_accuracy": 0.20578134208917617,
|
||
|
|
"num_tokens": 2548211.0,
|
||
|
|
"step": 3005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5697588443756105,
|
||
|
|
"epoch": 0.06725730948417442,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0001606685517817114,
|
||
|
|
"loss": 5.3427,
|
||
|
|
"mean_token_accuracy": 0.21928378343582153,
|
||
|
|
"num_tokens": 2552772.0,
|
||
|
|
"step": 3010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.638986587524414,
|
||
|
|
"epoch": 0.06736903258962987,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.00015965545838587592,
|
||
|
|
"loss": 5.3433,
|
||
|
|
"mean_token_accuracy": 0.2137608751654625,
|
||
|
|
"num_tokens": 2557221.0,
|
||
|
|
"step": 3015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.617996072769165,
|
||
|
|
"epoch": 0.0674807556950853,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00015864552721891467,
|
||
|
|
"loss": 5.2909,
|
||
|
|
"mean_token_accuracy": 0.22195946127176286,
|
||
|
|
"num_tokens": 2561383.0,
|
||
|
|
"step": 3020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.660844516754151,
|
||
|
|
"epoch": 0.06759247880054074,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00015763878596860076,
|
||
|
|
"loss": 5.4319,
|
||
|
|
"mean_token_accuracy": 0.2059861347079277,
|
||
|
|
"num_tokens": 2565688.0,
|
||
|
|
"step": 3025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.734495162963867,
|
||
|
|
"epoch": 0.06770420190599617,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00015663526223525412,
|
||
|
|
"loss": 5.4203,
|
||
|
|
"mean_token_accuracy": 0.20661102682352067,
|
||
|
|
"num_tokens": 2569677.0,
|
||
|
|
"step": 3030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.668662261962891,
|
||
|
|
"epoch": 0.06781592501145162,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.0001556349835309848,
|
||
|
|
"loss": 5.3722,
|
||
|
|
"mean_token_accuracy": 0.2033245787024498,
|
||
|
|
"num_tokens": 2573507.0,
|
||
|
|
"step": 3035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6115399360656735,
|
||
|
|
"epoch": 0.06792764811690706,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0001546379772789389,
|
||
|
|
"loss": 5.3547,
|
||
|
|
"mean_token_accuracy": 0.2055089771747589,
|
||
|
|
"num_tokens": 2578069.0,
|
||
|
|
"step": 3040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.711817598342895,
|
||
|
|
"epoch": 0.06803937122236249,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00015364427081254622,
|
||
|
|
"loss": 5.4195,
|
||
|
|
"mean_token_accuracy": 0.1933088108897209,
|
||
|
|
"num_tokens": 2582054.0,
|
||
|
|
"step": 3045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6535242080688475,
|
||
|
|
"epoch": 0.06815109432781793,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00015265389137477165,
|
||
|
|
"loss": 5.2475,
|
||
|
|
"mean_token_accuracy": 0.20738670974969864,
|
||
|
|
"num_tokens": 2585729.0,
|
||
|
|
"step": 3050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.589264392852783,
|
||
|
|
"epoch": 0.06826281743327338,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00015166686611736786,
|
||
|
|
"loss": 5.3462,
|
||
|
|
"mean_token_accuracy": 0.21424128711223603,
|
||
|
|
"num_tokens": 2589872.0,
|
||
|
|
"step": 3055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.560762739181518,
|
||
|
|
"epoch": 0.06837454053872881,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00015068322210013064,
|
||
|
|
"loss": 5.2998,
|
||
|
|
"mean_token_accuracy": 0.21292162388563157,
|
||
|
|
"num_tokens": 2593616.0,
|
||
|
|
"step": 3060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6391003131866455,
|
||
|
|
"epoch": 0.06848626364418425,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0001497029862901578,
|
||
|
|
"loss": 5.3307,
|
||
|
|
"mean_token_accuracy": 0.20281794518232346,
|
||
|
|
"num_tokens": 2597907.0,
|
||
|
|
"step": 3065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.628227758407593,
|
||
|
|
"epoch": 0.0685979867496397,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00014872618556110905,
|
||
|
|
"loss": 5.341,
|
||
|
|
"mean_token_accuracy": 0.20735297352075577,
|
||
|
|
"num_tokens": 2602051.0,
|
||
|
|
"step": 3070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.568817281723023,
|
||
|
|
"epoch": 0.06870970985509513,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00014775284669246992,
|
||
|
|
"loss": 5.3085,
|
||
|
|
"mean_token_accuracy": 0.2230152130126953,
|
||
|
|
"num_tokens": 2606214.0,
|
||
|
|
"step": 3075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.699526786804199,
|
||
|
|
"epoch": 0.06882143296055057,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00014678299636881716,
|
||
|
|
"loss": 5.4604,
|
||
|
|
"mean_token_accuracy": 0.2045097067952156,
|
||
|
|
"num_tokens": 2610766.0,
|
||
|
|
"step": 3080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.720143032073975,
|
||
|
|
"epoch": 0.06893315606600602,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0001458166611790873,
|
||
|
|
"loss": 5.4899,
|
||
|
|
"mean_token_accuracy": 0.19933217763900757,
|
||
|
|
"num_tokens": 2614715.0,
|
||
|
|
"step": 3085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.722377920150757,
|
||
|
|
"epoch": 0.06904487917146145,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.00014485386761584773,
|
||
|
|
"loss": 5.3442,
|
||
|
|
"mean_token_accuracy": 0.2098390132188797,
|
||
|
|
"num_tokens": 2618750.0,
|
||
|
|
"step": 3090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.585204696655273,
|
||
|
|
"epoch": 0.06915660227691689,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00014389464207457042,
|
||
|
|
"loss": 5.2674,
|
||
|
|
"mean_token_accuracy": 0.21748966127634048,
|
||
|
|
"num_tokens": 2623692.0,
|
||
|
|
"step": 3095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.645673656463623,
|
||
|
|
"epoch": 0.06926832538237233,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00014293901085290795,
|
||
|
|
"loss": 5.3308,
|
||
|
|
"mean_token_accuracy": 0.21164227575063704,
|
||
|
|
"num_tokens": 2628797.0,
|
||
|
|
"step": 3100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.58236780166626,
|
||
|
|
"epoch": 0.06938004848782776,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00014198700014997307,
|
||
|
|
"loss": 5.366,
|
||
|
|
"mean_token_accuracy": 0.1984266683459282,
|
||
|
|
"num_tokens": 2633246.0,
|
||
|
|
"step": 3105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.616124296188355,
|
||
|
|
"epoch": 0.06949177159328321,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00014103863606562016,
|
||
|
|
"loss": 5.281,
|
||
|
|
"mean_token_accuracy": 0.21451370120048524,
|
||
|
|
"num_tokens": 2637455.0,
|
||
|
|
"step": 3110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.70268816947937,
|
||
|
|
"epoch": 0.06960349469873865,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00014009394459972964,
|
||
|
|
"loss": 5.5515,
|
||
|
|
"mean_token_accuracy": 0.20195948630571364,
|
||
|
|
"num_tokens": 2642205.0,
|
||
|
|
"step": 3115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.719800329208374,
|
||
|
|
"epoch": 0.06971521780419408,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.00013915295165149513,
|
||
|
|
"loss": 5.4788,
|
||
|
|
"mean_token_accuracy": 0.20116885006427765,
|
||
|
|
"num_tokens": 2646534.0,
|
||
|
|
"step": 3120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.64207239151001,
|
||
|
|
"epoch": 0.06982694090964953,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00013821568301871384,
|
||
|
|
"loss": 5.449,
|
||
|
|
"mean_token_accuracy": 0.19510029256343842,
|
||
|
|
"num_tokens": 2651164.0,
|
||
|
|
"step": 3125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.598998975753784,
|
||
|
|
"epoch": 0.06993866401510497,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00013728216439707862,
|
||
|
|
"loss": 5.2194,
|
||
|
|
"mean_token_accuracy": 0.22186099737882614,
|
||
|
|
"num_tokens": 2654874.0,
|
||
|
|
"step": 3130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.641804456710815,
|
||
|
|
"epoch": 0.0700503871205604,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00013635242137947419,
|
||
|
|
"loss": 5.4562,
|
||
|
|
"mean_token_accuracy": 0.20273958146572113,
|
||
|
|
"num_tokens": 2659125.0,
|
||
|
|
"step": 3135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.648518085479736,
|
||
|
|
"epoch": 0.07016211022601584,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00013542647945527498,
|
||
|
|
"loss": 5.3014,
|
||
|
|
"mean_token_accuracy": 0.2190367430448532,
|
||
|
|
"num_tokens": 2663161.0,
|
||
|
|
"step": 3140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.617127418518066,
|
||
|
|
"epoch": 0.07027383333147127,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0001345043640096465,
|
||
|
|
"loss": 5.2522,
|
||
|
|
"mean_token_accuracy": 0.2186114564538002,
|
||
|
|
"num_tokens": 2667561.0,
|
||
|
|
"step": 3145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.575188446044922,
|
||
|
|
"epoch": 0.07038555643692672,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00013358610032284957,
|
||
|
|
"loss": 5.2346,
|
||
|
|
"mean_token_accuracy": 0.22437924295663833,
|
||
|
|
"num_tokens": 2671854.0,
|
||
|
|
"step": 3150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.619395685195923,
|
||
|
|
"epoch": 0.07049727954238216,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.000132671713569547,
|
||
|
|
"loss": 5.4031,
|
||
|
|
"mean_token_accuracy": 0.20520273745059966,
|
||
|
|
"num_tokens": 2676350.0,
|
||
|
|
"step": 3155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.623759126663208,
|
||
|
|
"epoch": 0.0706090026478376,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0001317612288181136,
|
||
|
|
"loss": 5.335,
|
||
|
|
"mean_token_accuracy": 0.20776157081127167,
|
||
|
|
"num_tokens": 2680290.0,
|
||
|
|
"step": 3160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.513316249847412,
|
||
|
|
"epoch": 0.07072072575329304,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00013085467102994864,
|
||
|
|
"loss": 5.2621,
|
||
|
|
"mean_token_accuracy": 0.21627698540687562,
|
||
|
|
"num_tokens": 2684856.0,
|
||
|
|
"step": 3165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.519444227218628,
|
||
|
|
"epoch": 0.07083244885874848,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00012995206505879198,
|
||
|
|
"loss": 5.2567,
|
||
|
|
"mean_token_accuracy": 0.22906775772571564,
|
||
|
|
"num_tokens": 2689344.0,
|
||
|
|
"step": 3170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.652344274520874,
|
||
|
|
"epoch": 0.07094417196420391,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0001290534356500421,
|
||
|
|
"loss": 5.4571,
|
||
|
|
"mean_token_accuracy": 0.19304423332214354,
|
||
|
|
"num_tokens": 2693646.0,
|
||
|
|
"step": 3175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.671027946472168,
|
||
|
|
"epoch": 0.07105589506965936,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00012815880744007827,
|
||
|
|
"loss": 5.3689,
|
||
|
|
"mean_token_accuracy": 0.20677870661020278,
|
||
|
|
"num_tokens": 2697624.0,
|
||
|
|
"step": 3180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.518811798095703,
|
||
|
|
"epoch": 0.0711676181751148,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00012726820495558483,
|
||
|
|
"loss": 5.1631,
|
||
|
|
"mean_token_accuracy": 0.2378458559513092,
|
||
|
|
"num_tokens": 2701715.0,
|
||
|
|
"step": 3185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.649792337417603,
|
||
|
|
"epoch": 0.07127934128057023,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00012638165261287868,
|
||
|
|
"loss": 5.3514,
|
||
|
|
"mean_token_accuracy": 0.21666739583015443,
|
||
|
|
"num_tokens": 2705944.0,
|
||
|
|
"step": 3190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6121738910675045,
|
||
|
|
"epoch": 0.07139106438602567,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 0.0001254991747172402,
|
||
|
|
"loss": 5.3352,
|
||
|
|
"mean_token_accuracy": 0.2155696466565132,
|
||
|
|
"num_tokens": 2710131.0,
|
||
|
|
"step": 3195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.653721332550049,
|
||
|
|
"epoch": 0.07150278749148112,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00012462079546224662,
|
||
|
|
"loss": 5.5097,
|
||
|
|
"mean_token_accuracy": 0.20381901562213897,
|
||
|
|
"num_tokens": 2714667.0,
|
||
|
|
"step": 3200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.615315675735474,
|
||
|
|
"epoch": 0.07161451059693655,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.00012374653892910896,
|
||
|
|
"loss": 5.2634,
|
||
|
|
"mean_token_accuracy": 0.21610590815544128,
|
||
|
|
"num_tokens": 2719067.0,
|
||
|
|
"step": 3205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5931305408477785,
|
||
|
|
"epoch": 0.07172623370239199,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.00012287642908601166,
|
||
|
|
"loss": 5.2798,
|
||
|
|
"mean_token_accuracy": 0.21317292153835296,
|
||
|
|
"num_tokens": 2723283.0,
|
||
|
|
"step": 3210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.70312271118164,
|
||
|
|
"epoch": 0.07183795680784744,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00012201048978745569,
|
||
|
|
"loss": 5.4082,
|
||
|
|
"mean_token_accuracy": 0.20306612849235534,
|
||
|
|
"num_tokens": 2727838.0,
|
||
|
|
"step": 3215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.688286066055298,
|
||
|
|
"epoch": 0.07194967991330287,
|
||
|
|
"grad_norm": 2.515625,
|
||
|
|
"learning_rate": 0.00012114874477360427,
|
||
|
|
"loss": 5.2829,
|
||
|
|
"mean_token_accuracy": 0.2075771778821945,
|
||
|
|
"num_tokens": 2732225.0,
|
||
|
|
"step": 3220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.630373954772949,
|
||
|
|
"epoch": 0.07206140301875831,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.00012029121766963236,
|
||
|
|
"loss": 5.367,
|
||
|
|
"mean_token_accuracy": 0.21760180741548538,
|
||
|
|
"num_tokens": 2736392.0,
|
||
|
|
"step": 3225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.611014318466187,
|
||
|
|
"epoch": 0.07217312612421375,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.00011943793198507858,
|
||
|
|
"loss": 5.3061,
|
||
|
|
"mean_token_accuracy": 0.21080368161201476,
|
||
|
|
"num_tokens": 2740807.0,
|
||
|
|
"step": 3230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.633539915084839,
|
||
|
|
"epoch": 0.07228484922966918,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.00011858891111320104,
|
||
|
|
"loss": 5.2852,
|
||
|
|
"mean_token_accuracy": 0.2113287329673767,
|
||
|
|
"num_tokens": 2744882.0,
|
||
|
|
"step": 3235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.652337455749512,
|
||
|
|
"epoch": 0.07239657233512463,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.0001177441783303359,
|
||
|
|
"loss": 5.3465,
|
||
|
|
"mean_token_accuracy": 0.19676152616739273,
|
||
|
|
"num_tokens": 2749005.0,
|
||
|
|
"step": 3240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.596548557281494,
|
||
|
|
"epoch": 0.07250829544058007,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.00011690375679525896,
|
||
|
|
"loss": 5.3138,
|
||
|
|
"mean_token_accuracy": 0.21947170794010162,
|
||
|
|
"num_tokens": 2753144.0,
|
||
|
|
"step": 3245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.594069957733154,
|
||
|
|
"epoch": 0.0726200185460355,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00011606766954855124,
|
||
|
|
"loss": 5.375,
|
||
|
|
"mean_token_accuracy": 0.20199813395738603,
|
||
|
|
"num_tokens": 2757166.0,
|
||
|
|
"step": 3250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.686679220199585,
|
||
|
|
"epoch": 0.07273174165149095,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00011523593951196702,
|
||
|
|
"loss": 5.4953,
|
||
|
|
"mean_token_accuracy": 0.20583337396383286,
|
||
|
|
"num_tokens": 2761694.0,
|
||
|
|
"step": 3255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.639123249053955,
|
||
|
|
"epoch": 0.07284346475694638,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00011440858948780523,
|
||
|
|
"loss": 5.3497,
|
||
|
|
"mean_token_accuracy": 0.20156496912240982,
|
||
|
|
"num_tokens": 2765805.0,
|
||
|
|
"step": 3260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.677051067352295,
|
||
|
|
"epoch": 0.07295518786240182,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00011358564215828484,
|
||
|
|
"loss": 5.4183,
|
||
|
|
"mean_token_accuracy": 0.20630619972944259,
|
||
|
|
"num_tokens": 2769943.0,
|
||
|
|
"step": 3265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.627818298339844,
|
||
|
|
"epoch": 0.07306691096785727,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.00011276712008492254,
|
||
|
|
"loss": 5.4099,
|
||
|
|
"mean_token_accuracy": 0.20188342779874802,
|
||
|
|
"num_tokens": 2773942.0,
|
||
|
|
"step": 3270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.66841311454773,
|
||
|
|
"epoch": 0.0731786340733127,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00011195304570791451,
|
||
|
|
"loss": 5.3857,
|
||
|
|
"mean_token_accuracy": 0.19944757223129272,
|
||
|
|
"num_tokens": 2778400.0,
|
||
|
|
"step": 3275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.587056684494018,
|
||
|
|
"epoch": 0.07329035717876814,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.00011114344134552094,
|
||
|
|
"loss": 5.3839,
|
||
|
|
"mean_token_accuracy": 0.21059890538454057,
|
||
|
|
"num_tokens": 2782508.0,
|
||
|
|
"step": 3280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7147684574127195,
|
||
|
|
"epoch": 0.07340208028422358,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.0001103383291934545,
|
||
|
|
"loss": 5.4363,
|
||
|
|
"mean_token_accuracy": 0.1962822750210762,
|
||
|
|
"num_tokens": 2786691.0,
|
||
|
|
"step": 3285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.712974691390992,
|
||
|
|
"epoch": 0.07351380338967901,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.00010953773132427141,
|
||
|
|
"loss": 5.4821,
|
||
|
|
"mean_token_accuracy": 0.19333103895187378,
|
||
|
|
"num_tokens": 2791548.0,
|
||
|
|
"step": 3290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6734947681427,
|
||
|
|
"epoch": 0.07362552649513446,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00010874166968676677,
|
||
|
|
"loss": 5.2523,
|
||
|
|
"mean_token_accuracy": 0.21183599829673766,
|
||
|
|
"num_tokens": 2795852.0,
|
||
|
|
"step": 3295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.733351469039917,
|
||
|
|
"epoch": 0.0737372496005899,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00010795016610537251,
|
||
|
|
"loss": 5.3301,
|
||
|
|
"mean_token_accuracy": 0.20432137697935104,
|
||
|
|
"num_tokens": 2800385.0,
|
||
|
|
"step": 3300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.611080169677734,
|
||
|
|
"epoch": 0.07384897270604533,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.00010716324227955904,
|
||
|
|
"loss": 5.2166,
|
||
|
|
"mean_token_accuracy": 0.2197134181857109,
|
||
|
|
"num_tokens": 2804295.0,
|
||
|
|
"step": 3305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.539245700836181,
|
||
|
|
"epoch": 0.07396069581150078,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0001063809197832406,
|
||
|
|
"loss": 5.2014,
|
||
|
|
"mean_token_accuracy": 0.21054498553276063,
|
||
|
|
"num_tokens": 2808305.0,
|
||
|
|
"step": 3310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.469600009918213,
|
||
|
|
"epoch": 0.07407241891695622,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00010560322006418368,
|
||
|
|
"loss": 5.2348,
|
||
|
|
"mean_token_accuracy": 0.22622232586145402,
|
||
|
|
"num_tokens": 2813215.0,
|
||
|
|
"step": 3315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5544756889343265,
|
||
|
|
"epoch": 0.07418414202241165,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.00010483016444341887,
|
||
|
|
"loss": 5.3035,
|
||
|
|
"mean_token_accuracy": 0.21456746906042098,
|
||
|
|
"num_tokens": 2817352.0,
|
||
|
|
"step": 3320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5173357963562015,
|
||
|
|
"epoch": 0.0742958651278671,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.00010406177411465654,
|
||
|
|
"loss": 5.1518,
|
||
|
|
"mean_token_accuracy": 0.22930039912462236,
|
||
|
|
"num_tokens": 2821486.0,
|
||
|
|
"step": 3325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.63260703086853,
|
||
|
|
"epoch": 0.07440758823332254,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.00010329807014370562,
|
||
|
|
"loss": 5.3578,
|
||
|
|
"mean_token_accuracy": 0.20518976747989653,
|
||
|
|
"num_tokens": 2825772.0,
|
||
|
|
"step": 3330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.613286876678467,
|
||
|
|
"epoch": 0.07451931133877797,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.00010253907346789632,
|
||
|
|
"loss": 5.2301,
|
||
|
|
"mean_token_accuracy": 0.2215651661157608,
|
||
|
|
"num_tokens": 2829751.0,
|
||
|
|
"step": 3335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.589096975326538,
|
||
|
|
"epoch": 0.07463103444423341,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00010178480489550596,
|
||
|
|
"loss": 5.2576,
|
||
|
|
"mean_token_accuracy": 0.21702108085155486,
|
||
|
|
"num_tokens": 2833887.0,
|
||
|
|
"step": 3340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.63301568031311,
|
||
|
|
"epoch": 0.07474275754968886,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.00010103528510518836,
|
||
|
|
"loss": 5.3826,
|
||
|
|
"mean_token_accuracy": 0.20653112530708312,
|
||
|
|
"num_tokens": 2838255.0,
|
||
|
|
"step": 3345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.67524151802063,
|
||
|
|
"epoch": 0.07485448065514429,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0001002905346454073,
|
||
|
|
"loss": 5.4079,
|
||
|
|
"mean_token_accuracy": 0.20599524229764937,
|
||
|
|
"num_tokens": 2842432.0,
|
||
|
|
"step": 3350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.547143030166626,
|
||
|
|
"epoch": 0.07496620376059973,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 9.955057393387285e-05,
|
||
|
|
"loss": 5.2149,
|
||
|
|
"mean_token_accuracy": 0.22138799726963043,
|
||
|
|
"num_tokens": 2846793.0,
|
||
|
|
"step": 3355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.594313383102417,
|
||
|
|
"epoch": 0.07507792686605518,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 9.88154232569816e-05,
|
||
|
|
"loss": 5.2984,
|
||
|
|
"mean_token_accuracy": 0.21841018348932267,
|
||
|
|
"num_tokens": 2850640.0,
|
||
|
|
"step": 3360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.552529430389404,
|
||
|
|
"epoch": 0.0751896499715106,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 9.808510276926075e-05,
|
||
|
|
"loss": 5.2852,
|
||
|
|
"mean_token_accuracy": 0.22227568924427032,
|
||
|
|
"num_tokens": 2854935.0,
|
||
|
|
"step": 3365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.525260782241821,
|
||
|
|
"epoch": 0.07530137307696605,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 9.735963249281549e-05,
|
||
|
|
"loss": 5.1534,
|
||
|
|
"mean_token_accuracy": 0.23119736164808274,
|
||
|
|
"num_tokens": 2858777.0,
|
||
|
|
"step": 3370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.597141599655151,
|
||
|
|
"epoch": 0.0754130961824215,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 9.663903231677974e-05,
|
||
|
|
"loss": 5.3521,
|
||
|
|
"mean_token_accuracy": 0.20306329131126405,
|
||
|
|
"num_tokens": 2863048.0,
|
||
|
|
"step": 3375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6410009384155275,
|
||
|
|
"epoch": 0.07552481928787692,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 9.592332199677145e-05,
|
||
|
|
"loss": 5.4613,
|
||
|
|
"mean_token_accuracy": 0.2133955880999565,
|
||
|
|
"num_tokens": 2867614.0,
|
||
|
|
"step": 3380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.609254264831543,
|
||
|
|
"epoch": 0.07563654239333237,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 9.521252115435061e-05,
|
||
|
|
"loss": 5.3742,
|
||
|
|
"mean_token_accuracy": 0.21081015318632126,
|
||
|
|
"num_tokens": 2871872.0,
|
||
|
|
"step": 3385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.691639852523804,
|
||
|
|
"epoch": 0.0757482654987878,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 9.450664927648126e-05,
|
||
|
|
"loss": 5.4202,
|
||
|
|
"mean_token_accuracy": 0.20292532742023467,
|
||
|
|
"num_tokens": 2876240.0,
|
||
|
|
"step": 3390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.636670351028442,
|
||
|
|
"epoch": 0.07585998860424324,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 9.380572571499758e-05,
|
||
|
|
"loss": 5.2689,
|
||
|
|
"mean_token_accuracy": 0.21996590942144395,
|
||
|
|
"num_tokens": 2880301.0,
|
||
|
|
"step": 3395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.675829076766968,
|
||
|
|
"epoch": 0.07597171170969869,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 9.310976968607307e-05,
|
||
|
|
"loss": 5.3086,
|
||
|
|
"mean_token_accuracy": 0.22123734802007675,
|
||
|
|
"num_tokens": 2884552.0,
|
||
|
|
"step": 3400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.634104871749878,
|
||
|
|
"epoch": 0.07608343481515412,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 9.241880026969381e-05,
|
||
|
|
"loss": 5.3006,
|
||
|
|
"mean_token_accuracy": 0.20040488690137864,
|
||
|
|
"num_tokens": 2888851.0,
|
||
|
|
"step": 3405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5746925354003904,
|
||
|
|
"epoch": 0.07619515792060956,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 9.173283640913537e-05,
|
||
|
|
"loss": 5.2415,
|
||
|
|
"mean_token_accuracy": 0.22433702349662782,
|
||
|
|
"num_tokens": 2892712.0,
|
||
|
|
"step": 3410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.620074892044068,
|
||
|
|
"epoch": 0.076306881026065,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 9.10518969104436e-05,
|
||
|
|
"loss": 5.3529,
|
||
|
|
"mean_token_accuracy": 0.20692348778247832,
|
||
|
|
"num_tokens": 2897018.0,
|
||
|
|
"step": 3415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.516711568832397,
|
||
|
|
"epoch": 0.07641860413152043,
|
||
|
|
"grad_norm": 1.90625,
|
||
|
|
"learning_rate": 9.037600044191868e-05,
|
||
|
|
"loss": 5.4452,
|
||
|
|
"mean_token_accuracy": 0.21995796114206315,
|
||
|
|
"num_tokens": 2901689.0,
|
||
|
|
"step": 3420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.528185558319092,
|
||
|
|
"epoch": 0.07653032723697588,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 8.970516553360383e-05,
|
||
|
|
"loss": 5.2348,
|
||
|
|
"mean_token_accuracy": 0.2222063884139061,
|
||
|
|
"num_tokens": 2905625.0,
|
||
|
|
"step": 3425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.593515157699585,
|
||
|
|
"epoch": 0.07664205034243132,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 8.903941057677692e-05,
|
||
|
|
"loss": 5.3418,
|
||
|
|
"mean_token_accuracy": 0.21491294354200363,
|
||
|
|
"num_tokens": 2909913.0,
|
||
|
|
"step": 3430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.633850717544556,
|
||
|
|
"epoch": 0.07675377344788675,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 8.837875382344635e-05,
|
||
|
|
"loss": 5.3329,
|
||
|
|
"mean_token_accuracy": 0.21063277274370193,
|
||
|
|
"num_tokens": 2914583.0,
|
||
|
|
"step": 3435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.605971717834473,
|
||
|
|
"epoch": 0.0768654965533422,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 8.772321338585076e-05,
|
||
|
|
"loss": 5.2942,
|
||
|
|
"mean_token_accuracy": 0.21364900469779968,
|
||
|
|
"num_tokens": 2918753.0,
|
||
|
|
"step": 3440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.581877565383911,
|
||
|
|
"epoch": 0.07697721965879764,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 8.707280723596242e-05,
|
||
|
|
"loss": 5.3525,
|
||
|
|
"mean_token_accuracy": 0.212966750562191,
|
||
|
|
"num_tokens": 2922982.0,
|
||
|
|
"step": 3445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.540095424652099,
|
||
|
|
"epoch": 0.07708894276425307,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 8.64275532049944e-05,
|
||
|
|
"loss": 5.2323,
|
||
|
|
"mean_token_accuracy": 0.2168658971786499,
|
||
|
|
"num_tokens": 2927603.0,
|
||
|
|
"step": 3450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.559815359115601,
|
||
|
|
"epoch": 0.07720066586970852,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 8.578746898291198e-05,
|
||
|
|
"loss": 5.1838,
|
||
|
|
"mean_token_accuracy": 0.22491378486156463,
|
||
|
|
"num_tokens": 2932040.0,
|
||
|
|
"step": 3455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.619689416885376,
|
||
|
|
"epoch": 0.07731238897516396,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 8.515257211794742e-05,
|
||
|
|
"loss": 5.2521,
|
||
|
|
"mean_token_accuracy": 0.21349863857030868,
|
||
|
|
"num_tokens": 2935857.0,
|
||
|
|
"step": 3460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5853088855743405,
|
||
|
|
"epoch": 0.07742411208061939,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 8.452288001611896e-05,
|
||
|
|
"loss": 5.3033,
|
||
|
|
"mean_token_accuracy": 0.21696949154138565,
|
||
|
|
"num_tokens": 2940103.0,
|
||
|
|
"step": 3465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.624681711196899,
|
||
|
|
"epoch": 0.07753583518607483,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 8.389840994075379e-05,
|
||
|
|
"loss": 5.3664,
|
||
|
|
"mean_token_accuracy": 0.2176609754562378,
|
||
|
|
"num_tokens": 2944437.0,
|
||
|
|
"step": 3470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.614411687850952,
|
||
|
|
"epoch": 0.07764755829153028,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 8.327917901201435e-05,
|
||
|
|
"loss": 5.3038,
|
||
|
|
"mean_token_accuracy": 0.2120346873998642,
|
||
|
|
"num_tokens": 2948550.0,
|
||
|
|
"step": 3475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.609672546386719,
|
||
|
|
"epoch": 0.07775928139698571,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 8.266520420642931e-05,
|
||
|
|
"loss": 5.2985,
|
||
|
|
"mean_token_accuracy": 0.21615774631500245,
|
||
|
|
"num_tokens": 2952466.0,
|
||
|
|
"step": 3480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.695987367630005,
|
||
|
|
"epoch": 0.07787100450244115,
|
||
|
|
"grad_norm": 1.625,
|
||
|
|
"learning_rate": 8.205650235642828e-05,
|
||
|
|
"loss": 5.4194,
|
||
|
|
"mean_token_accuracy": 0.19847894757986068,
|
||
|
|
"num_tokens": 2956504.0,
|
||
|
|
"step": 3485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.666062545776367,
|
||
|
|
"epoch": 0.0779827276078966,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 8.145309014987978e-05,
|
||
|
|
"loss": 5.3827,
|
||
|
|
"mean_token_accuracy": 0.20386045277118683,
|
||
|
|
"num_tokens": 2961034.0,
|
||
|
|
"step": 3490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.606233358383179,
|
||
|
|
"epoch": 0.07809445071335203,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 8.085498412963437e-05,
|
||
|
|
"loss": 5.4119,
|
||
|
|
"mean_token_accuracy": 0.20896730124950408,
|
||
|
|
"num_tokens": 2965522.0,
|
||
|
|
"step": 3495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.582093715667725,
|
||
|
|
"epoch": 0.07820617381880747,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 8.026220069307078e-05,
|
||
|
|
"loss": 5.175,
|
||
|
|
"mean_token_accuracy": 0.22600839287042618,
|
||
|
|
"num_tokens": 2969523.0,
|
||
|
|
"step": 3500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.648726129531861,
|
||
|
|
"epoch": 0.0783178969242629,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 7.967475609164621e-05,
|
||
|
|
"loss": 5.2617,
|
||
|
|
"mean_token_accuracy": 0.2210591584444046,
|
||
|
|
"num_tokens": 2973482.0,
|
||
|
|
"step": 3505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.64477858543396,
|
||
|
|
"epoch": 0.07842962002971834,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 7.909266643045124e-05,
|
||
|
|
"loss": 5.3993,
|
||
|
|
"mean_token_accuracy": 0.20203785747289657,
|
||
|
|
"num_tokens": 2977696.0,
|
||
|
|
"step": 3510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.661210346221924,
|
||
|
|
"epoch": 0.07854134313517379,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 7.851594766776802e-05,
|
||
|
|
"loss": 5.307,
|
||
|
|
"mean_token_accuracy": 0.21592496931552888,
|
||
|
|
"num_tokens": 2981683.0,
|
||
|
|
"step": 3515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.591487312316895,
|
||
|
|
"epoch": 0.07865306624062922,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 7.794461561463265e-05,
|
||
|
|
"loss": 5.2825,
|
||
|
|
"mean_token_accuracy": 0.21814689189195632,
|
||
|
|
"num_tokens": 2986040.0,
|
||
|
|
"step": 3520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.520713806152344,
|
||
|
|
"epoch": 0.07876478934608466,
|
||
|
|
"grad_norm": 2.328125,
|
||
|
|
"learning_rate": 7.7378685934402e-05,
|
||
|
|
"loss": 5.1859,
|
||
|
|
"mean_token_accuracy": 0.22736109644174576,
|
||
|
|
"num_tokens": 2990453.0,
|
||
|
|
"step": 3525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.57408881187439,
|
||
|
|
"epoch": 0.0788765124515401,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 7.68181741423242e-05,
|
||
|
|
"loss": 5.3577,
|
||
|
|
"mean_token_accuracy": 0.20576396882534026,
|
||
|
|
"num_tokens": 2994870.0,
|
||
|
|
"step": 3530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.566109895706177,
|
||
|
|
"epoch": 0.07898823555699554,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 7.626309560511313e-05,
|
||
|
|
"loss": 5.2321,
|
||
|
|
"mean_token_accuracy": 0.22257633805274962,
|
||
|
|
"num_tokens": 2998692.0,
|
||
|
|
"step": 3535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.651077699661255,
|
||
|
|
"epoch": 0.07909995866245098,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 7.571346554052724e-05,
|
||
|
|
"loss": 5.4113,
|
||
|
|
"mean_token_accuracy": 0.20006688684225082,
|
||
|
|
"num_tokens": 3002830.0,
|
||
|
|
"step": 3540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.665845584869385,
|
||
|
|
"epoch": 0.07921168176790643,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 7.516929901695249e-05,
|
||
|
|
"loss": 5.3137,
|
||
|
|
"mean_token_accuracy": 0.20740436911582946,
|
||
|
|
"num_tokens": 3007302.0,
|
||
|
|
"step": 3545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.618817615509033,
|
||
|
|
"epoch": 0.07932340487336186,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 7.463061095298893e-05,
|
||
|
|
"loss": 5.2635,
|
||
|
|
"mean_token_accuracy": 0.2198699712753296,
|
||
|
|
"num_tokens": 3011156.0,
|
||
|
|
"step": 3550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.666779851913452,
|
||
|
|
"epoch": 0.0794351279788173,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 7.409741611704198e-05,
|
||
|
|
"loss": 5.3482,
|
||
|
|
"mean_token_accuracy": 0.20920169055461885,
|
||
|
|
"num_tokens": 3015577.0,
|
||
|
|
"step": 3555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.505196571350098,
|
||
|
|
"epoch": 0.07954685108427274,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 7.35697291269174e-05,
|
||
|
|
"loss": 5.1681,
|
||
|
|
"mean_token_accuracy": 0.22661744505167009,
|
||
|
|
"num_tokens": 3019801.0,
|
||
|
|
"step": 3560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.628220748901367,
|
||
|
|
"epoch": 0.07965857418972817,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 7.304756444942056e-05,
|
||
|
|
"loss": 5.3181,
|
||
|
|
"mean_token_accuracy": 0.2193499967455864,
|
||
|
|
"num_tokens": 3023916.0,
|
||
|
|
"step": 3565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.612834501266479,
|
||
|
|
"epoch": 0.07977029729518362,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 7.253093639995994e-05,
|
||
|
|
"loss": 5.3256,
|
||
|
|
"mean_token_accuracy": 0.20452884137630462,
|
||
|
|
"num_tokens": 3028161.0,
|
||
|
|
"step": 3570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.682301568984985,
|
||
|
|
"epoch": 0.07988202040063906,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 7.20198591421544e-05,
|
||
|
|
"loss": 5.3278,
|
||
|
|
"mean_token_accuracy": 0.21033651977777482,
|
||
|
|
"num_tokens": 3032080.0,
|
||
|
|
"step": 3575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.686801958084106,
|
||
|
|
"epoch": 0.07999374350609449,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 7.151434668744517e-05,
|
||
|
|
"loss": 5.4331,
|
||
|
|
"mean_token_accuracy": 0.20019310861825942,
|
||
|
|
"num_tokens": 3036535.0,
|
||
|
|
"step": 3580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.584930467605591,
|
||
|
|
"epoch": 0.08010546661154994,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 7.101441289471153e-05,
|
||
|
|
"loss": 5.3741,
|
||
|
|
"mean_token_accuracy": 0.20859978944063187,
|
||
|
|
"num_tokens": 3040649.0,
|
||
|
|
"step": 3585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.607728004455566,
|
||
|
|
"epoch": 0.08021718971700538,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 7.052007146989098e-05,
|
||
|
|
"loss": 5.3176,
|
||
|
|
"mean_token_accuracy": 0.2208326652646065,
|
||
|
|
"num_tokens": 3044883.0,
|
||
|
|
"step": 3590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.606212949752807,
|
||
|
|
"epoch": 0.08032891282246081,
|
||
|
|
"grad_norm": 1.578125,
|
||
|
|
"learning_rate": 7.003133596560341e-05,
|
||
|
|
"loss": 5.2064,
|
||
|
|
"mean_token_accuracy": 0.22535468339920045,
|
||
|
|
"num_tokens": 3048802.0,
|
||
|
|
"step": 3595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.628868532180786,
|
||
|
|
"epoch": 0.08044063592791625,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 6.954821978077952e-05,
|
||
|
|
"loss": 5.3854,
|
||
|
|
"mean_token_accuracy": 0.21277399063110353,
|
||
|
|
"num_tokens": 3053078.0,
|
||
|
|
"step": 3600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.65153751373291,
|
||
|
|
"epoch": 0.0805523590333717,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 6.907073616029356e-05,
|
||
|
|
"loss": 5.3074,
|
||
|
|
"mean_token_accuracy": 0.20606451183557511,
|
||
|
|
"num_tokens": 3057691.0,
|
||
|
|
"step": 3605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.760905456542969,
|
||
|
|
"epoch": 0.08066408213882713,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 6.85988981946002e-05,
|
||
|
|
"loss": 5.5137,
|
||
|
|
"mean_token_accuracy": 0.19400741457939147,
|
||
|
|
"num_tokens": 3062459.0,
|
||
|
|
"step": 3610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.711138677597046,
|
||
|
|
"epoch": 0.08077580524428257,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 6.813271881937564e-05,
|
||
|
|
"loss": 5.3843,
|
||
|
|
"mean_token_accuracy": 0.20873532444238663,
|
||
|
|
"num_tokens": 3066453.0,
|
||
|
|
"step": 3615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.532869958877564,
|
||
|
|
"epoch": 0.080887528349738,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 6.767221081516286e-05,
|
||
|
|
"loss": 5.2696,
|
||
|
|
"mean_token_accuracy": 0.22122857272624968,
|
||
|
|
"num_tokens": 3070726.0,
|
||
|
|
"step": 3620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7132974624633786,
|
||
|
|
"epoch": 0.08099925145519345,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 6.72173868070215e-05,
|
||
|
|
"loss": 5.3751,
|
||
|
|
"mean_token_accuracy": 0.21080582290887834,
|
||
|
|
"num_tokens": 3074907.0,
|
||
|
|
"step": 3625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.64652190208435,
|
||
|
|
"epoch": 0.08111097456064889,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 6.676825926418149e-05,
|
||
|
|
"loss": 5.343,
|
||
|
|
"mean_token_accuracy": 0.2070286214351654,
|
||
|
|
"num_tokens": 3078851.0,
|
||
|
|
"step": 3630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.631018114089966,
|
||
|
|
"epoch": 0.08122269766610432,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 6.632484049970122e-05,
|
||
|
|
"loss": 5.2338,
|
||
|
|
"mean_token_accuracy": 0.21441571563482284,
|
||
|
|
"num_tokens": 3082871.0,
|
||
|
|
"step": 3635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.665914630889892,
|
||
|
|
"epoch": 0.08133442077155977,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 6.588714267013019e-05,
|
||
|
|
"loss": 5.3675,
|
||
|
|
"mean_token_accuracy": 0.21185107082128524,
|
||
|
|
"num_tokens": 3087385.0,
|
||
|
|
"step": 3640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.570506286621094,
|
||
|
|
"epoch": 0.08144614387701521,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 6.545517777517544e-05,
|
||
|
|
"loss": 5.3111,
|
||
|
|
"mean_token_accuracy": 0.20417589098215103,
|
||
|
|
"num_tokens": 3091818.0,
|
||
|
|
"step": 3645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.659856939315796,
|
||
|
|
"epoch": 0.08155786698247064,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 6.502895765737281e-05,
|
||
|
|
"loss": 5.3422,
|
||
|
|
"mean_token_accuracy": 0.2085869640111923,
|
||
|
|
"num_tokens": 3096045.0,
|
||
|
|
"step": 3650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6597761631011965,
|
||
|
|
"epoch": 0.08166959008792608,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 6.460849400176212e-05,
|
||
|
|
"loss": 5.379,
|
||
|
|
"mean_token_accuracy": 0.2018310993909836,
|
||
|
|
"num_tokens": 3100313.0,
|
||
|
|
"step": 3655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.610556793212891,
|
||
|
|
"epoch": 0.08178131319338153,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 6.419379833556694e-05,
|
||
|
|
"loss": 5.3534,
|
||
|
|
"mean_token_accuracy": 0.22189855575561523,
|
||
|
|
"num_tokens": 3104434.0,
|
||
|
|
"step": 3660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.654457426071167,
|
||
|
|
"epoch": 0.08189303629883696,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 6.378488202787835e-05,
|
||
|
|
"loss": 5.2827,
|
||
|
|
"mean_token_accuracy": 0.22774875164031982,
|
||
|
|
"num_tokens": 3108801.0,
|
||
|
|
"step": 3665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.638199090957642,
|
||
|
|
"epoch": 0.0820047594042924,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 6.33817562893435e-05,
|
||
|
|
"loss": 5.3595,
|
||
|
|
"mean_token_accuracy": 0.20279042720794677,
|
||
|
|
"num_tokens": 3113250.0,
|
||
|
|
"step": 3670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.627264547348022,
|
||
|
|
"epoch": 0.08211648250974785,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 6.29844321718582e-05,
|
||
|
|
"loss": 5.268,
|
||
|
|
"mean_token_accuracy": 0.21937764436006546,
|
||
|
|
"num_tokens": 3117524.0,
|
||
|
|
"step": 3675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6254109859466555,
|
||
|
|
"epoch": 0.08222820561520328,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 6.259292056826383e-05,
|
||
|
|
"loss": 5.3917,
|
||
|
|
"mean_token_accuracy": 0.20597360134124756,
|
||
|
|
"num_tokens": 3122416.0,
|
||
|
|
"step": 3680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.67297739982605,
|
||
|
|
"epoch": 0.08233992872065872,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 6.220723221204873e-05,
|
||
|
|
"loss": 5.3425,
|
||
|
|
"mean_token_accuracy": 0.21909067630767823,
|
||
|
|
"num_tokens": 3126556.0,
|
||
|
|
"step": 3685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.5861554622650145,
|
||
|
|
"epoch": 0.08245165182611416,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 6.182737767705406e-05,
|
||
|
|
"loss": 5.2812,
|
||
|
|
"mean_token_accuracy": 0.21893683075904846,
|
||
|
|
"num_tokens": 3130802.0,
|
||
|
|
"step": 3690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.676740026473999,
|
||
|
|
"epoch": 0.0825633749315696,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 6.145336737718375e-05,
|
||
|
|
"loss": 5.3257,
|
||
|
|
"mean_token_accuracy": 0.20887255668640137,
|
||
|
|
"num_tokens": 3135123.0,
|
||
|
|
"step": 3695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.573624897003174,
|
||
|
|
"epoch": 0.08267509803702504,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 6.10852115661191e-05,
|
||
|
|
"loss": 5.2818,
|
||
|
|
"mean_token_accuracy": 0.20997430831193925,
|
||
|
|
"num_tokens": 3139154.0,
|
||
|
|
"step": 3700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.61875286102295,
|
||
|
|
"epoch": 0.08278682114248048,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 6.072292033703766e-05,
|
||
|
|
"loss": 5.3097,
|
||
|
|
"mean_token_accuracy": 0.21799131631851196,
|
||
|
|
"num_tokens": 3143563.0,
|
||
|
|
"step": 3705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.612141466140747,
|
||
|
|
"epoch": 0.08289854424793591,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 6.036650362233648e-05,
|
||
|
|
"loss": 5.2624,
|
||
|
|
"mean_token_accuracy": 0.21610828042030333,
|
||
|
|
"num_tokens": 3147426.0,
|
||
|
|
"step": 3710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.630769205093384,
|
||
|
|
"epoch": 0.08301026735339136,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 6.0015971193359824e-05,
|
||
|
|
"loss": 5.3198,
|
||
|
|
"mean_token_accuracy": 0.22308328300714492,
|
||
|
|
"num_tokens": 3151602.0,
|
||
|
|
"step": 3715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.662342548370361,
|
||
|
|
"epoch": 0.0831219904588468,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 5.9671332660131306e-05,
|
||
|
|
"loss": 5.3128,
|
||
|
|
"mean_token_accuracy": 0.20877344012260438,
|
||
|
|
"num_tokens": 3155494.0,
|
||
|
|
"step": 3720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.616480445861816,
|
||
|
|
"epoch": 0.08323371356430223,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 5.933259747109042e-05,
|
||
|
|
"loss": 5.249,
|
||
|
|
"mean_token_accuracy": 0.2296250879764557,
|
||
|
|
"num_tokens": 3159548.0,
|
||
|
|
"step": 3725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.616093254089355,
|
||
|
|
"epoch": 0.08334543666975767,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 5.899977491283351e-05,
|
||
|
|
"loss": 5.2948,
|
||
|
|
"mean_token_accuracy": 0.21538150012493135,
|
||
|
|
"num_tokens": 3163531.0,
|
||
|
|
"step": 3730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.640008640289307,
|
||
|
|
"epoch": 0.0834571597752131,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 5.867287410985908e-05,
|
||
|
|
"loss": 5.2828,
|
||
|
|
"mean_token_accuracy": 0.22129616886377335,
|
||
|
|
"num_tokens": 3167833.0,
|
||
|
|
"step": 3735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.693461656570435,
|
||
|
|
"epoch": 0.08356888288066855,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 5.835190402431779e-05,
|
||
|
|
"loss": 5.3702,
|
||
|
|
"mean_token_accuracy": 0.21054567247629166,
|
||
|
|
"num_tokens": 3172022.0,
|
||
|
|
"step": 3740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.677970314025879,
|
||
|
|
"epoch": 0.083680605986124,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 5.803687345576673e-05,
|
||
|
|
"loss": 5.4136,
|
||
|
|
"mean_token_accuracy": 0.2075629785656929,
|
||
|
|
"num_tokens": 3176354.0,
|
||
|
|
"step": 3745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.578473663330078,
|
||
|
|
"epoch": 0.08379232909157942,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 5.7727791040927977e-05,
|
||
|
|
"loss": 5.2941,
|
||
|
|
"mean_token_accuracy": 0.2221289023756981,
|
||
|
|
"num_tokens": 3180828.0,
|
||
|
|
"step": 3750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.672476530075073,
|
||
|
|
"epoch": 0.08390405219703487,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 5.742466525345213e-05,
|
||
|
|
"loss": 5.3437,
|
||
|
|
"mean_token_accuracy": 0.20644573420286177,
|
||
|
|
"num_tokens": 3185032.0,
|
||
|
|
"step": 3755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.604012823104858,
|
||
|
|
"epoch": 0.08401577530249031,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 5.7127504403685775e-05,
|
||
|
|
"loss": 5.2496,
|
||
|
|
"mean_token_accuracy": 0.2142631232738495,
|
||
|
|
"num_tokens": 3189160.0,
|
||
|
|
"step": 3760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.663827133178711,
|
||
|
|
"epoch": 0.08412749840794574,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 5.6836316638443664e-05,
|
||
|
|
"loss": 5.3955,
|
||
|
|
"mean_token_accuracy": 0.20509500205516815,
|
||
|
|
"num_tokens": 3193489.0,
|
||
|
|
"step": 3765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.597621488571167,
|
||
|
|
"epoch": 0.08423922151340119,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 5.655110994078553e-05,
|
||
|
|
"loss": 5.3143,
|
||
|
|
"mean_token_accuracy": 0.2035353362560272,
|
||
|
|
"num_tokens": 3197847.0,
|
||
|
|
"step": 3770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.65077919960022,
|
||
|
|
"epoch": 0.08435094461885663,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 5.6271892129797056e-05,
|
||
|
|
"loss": 5.3806,
|
||
|
|
"mean_token_accuracy": 0.20232707709074021,
|
||
|
|
"num_tokens": 3202248.0,
|
||
|
|
"step": 3775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.553995800018311,
|
||
|
|
"epoch": 0.08446266772431206,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 5.599867086037556e-05,
|
||
|
|
"loss": 5.235,
|
||
|
|
"mean_token_accuracy": 0.2232307404279709,
|
||
|
|
"num_tokens": 3206458.0,
|
||
|
|
"step": 3780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.678331470489502,
|
||
|
|
"epoch": 0.0845743908297675,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 5.573145362302012e-05,
|
||
|
|
"loss": 5.3889,
|
||
|
|
"mean_token_accuracy": 0.19883892238140105,
|
||
|
|
"num_tokens": 3210283.0,
|
||
|
|
"step": 3785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.762803459167481,
|
||
|
|
"epoch": 0.08468611393522295,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 5.5470247743626404e-05,
|
||
|
|
"loss": 5.4709,
|
||
|
|
"mean_token_accuracy": 0.2024947628378868,
|
||
|
|
"num_tokens": 3214630.0,
|
||
|
|
"step": 3790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.675040864944458,
|
||
|
|
"epoch": 0.08479783704067838,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 5.5215060383285414e-05,
|
||
|
|
"loss": 5.3822,
|
||
|
|
"mean_token_accuracy": 0.19620390236377716,
|
||
|
|
"num_tokens": 3218614.0,
|
||
|
|
"step": 3795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.663913774490356,
|
||
|
|
"epoch": 0.08490956014613382,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 5.496589853808759e-05,
|
||
|
|
"loss": 5.2087,
|
||
|
|
"mean_token_accuracy": 0.21898047477006913,
|
||
|
|
"num_tokens": 3222629.0,
|
||
|
|
"step": 3800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6438130855560305,
|
||
|
|
"epoch": 0.08502128325158927,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 5.47227690389308e-05,
|
||
|
|
"loss": 5.3723,
|
||
|
|
"mean_token_accuracy": 0.20091044455766677,
|
||
|
|
"num_tokens": 3226610.0,
|
||
|
|
"step": 3805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.621782350540161,
|
||
|
|
"epoch": 0.0851330063570447,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 5.448567855133306e-05,
|
||
|
|
"loss": 5.2408,
|
||
|
|
"mean_token_accuracy": 0.21439284235239028,
|
||
|
|
"num_tokens": 3230733.0,
|
||
|
|
"step": 3810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.639111328125,
|
||
|
|
"epoch": 0.08524472946250014,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 5.425463357524986e-05,
|
||
|
|
"loss": 5.3778,
|
||
|
|
"mean_token_accuracy": 0.2101699247956276,
|
||
|
|
"num_tokens": 3234886.0,
|
||
|
|
"step": 3815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.644361877441407,
|
||
|
|
"epoch": 0.08535645256795558,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 5.402964044489591e-05,
|
||
|
|
"loss": 5.2513,
|
||
|
|
"mean_token_accuracy": 0.20897443294525148,
|
||
|
|
"num_tokens": 3239256.0,
|
||
|
|
"step": 3820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.611676645278931,
|
||
|
|
"epoch": 0.08546817567341101,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 5.381070532857153e-05,
|
||
|
|
"loss": 5.316,
|
||
|
|
"mean_token_accuracy": 0.21087998300790786,
|
||
|
|
"num_tokens": 3243300.0,
|
||
|
|
"step": 3825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.672077608108521,
|
||
|
|
"epoch": 0.08557989877886646,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 5.359783422849357e-05,
|
||
|
|
"loss": 5.4337,
|
||
|
|
"mean_token_accuracy": 0.19756073355674744,
|
||
|
|
"num_tokens": 3248038.0,
|
||
|
|
"step": 3830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.582310199737549,
|
||
|
|
"epoch": 0.0856916218843219,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 5.3391032980630736e-05,
|
||
|
|
"loss": 5.3052,
|
||
|
|
"mean_token_accuracy": 0.21166286915540694,
|
||
|
|
"num_tokens": 3251987.0,
|
||
|
|
"step": 3835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6600724220275875,
|
||
|
|
"epoch": 0.08580334498977733,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 5.31903072545437e-05,
|
||
|
|
"loss": 5.4011,
|
||
|
|
"mean_token_accuracy": 0.203070168197155,
|
||
|
|
"num_tokens": 3256104.0,
|
||
|
|
"step": 3840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.666264581680298,
|
||
|
|
"epoch": 0.08591506809523278,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 5.29956625532297e-05,
|
||
|
|
"loss": 5.2765,
|
||
|
|
"mean_token_accuracy": 0.21566030532121658,
|
||
|
|
"num_tokens": 3260439.0,
|
||
|
|
"step": 3845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.61574649810791,
|
||
|
|
"epoch": 0.08602679120068821,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 5.280710421297146e-05,
|
||
|
|
"loss": 5.3493,
|
||
|
|
"mean_token_accuracy": 0.20139459818601607,
|
||
|
|
"num_tokens": 3264766.0,
|
||
|
|
"step": 3850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.624459362030029,
|
||
|
|
"epoch": 0.08613851430614365,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 5.2624637403191165e-05,
|
||
|
|
"loss": 5.4526,
|
||
|
|
"mean_token_accuracy": 0.19859057813882827,
|
||
|
|
"num_tokens": 3269211.0,
|
||
|
|
"step": 3855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6024806022644045,
|
||
|
|
"epoch": 0.0862502374115991,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 5.2448267126308605e-05,
|
||
|
|
"loss": 5.3306,
|
||
|
|
"mean_token_accuracy": 0.2112487643957138,
|
||
|
|
"num_tokens": 3273116.0,
|
||
|
|
"step": 3860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.597120571136474,
|
||
|
|
"epoch": 0.08636196051705453,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 5.2277998217603954e-05,
|
||
|
|
"loss": 5.3694,
|
||
|
|
"mean_token_accuracy": 0.2089441180229187,
|
||
|
|
"num_tokens": 3277347.0,
|
||
|
|
"step": 3865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.700920629501343,
|
||
|
|
"epoch": 0.08647368362250997,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 5.211383534508541e-05,
|
||
|
|
"loss": 5.3661,
|
||
|
|
"mean_token_accuracy": 0.20611102283000945,
|
||
|
|
"num_tokens": 3281772.0,
|
||
|
|
"step": 3870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.585329294204712,
|
||
|
|
"epoch": 0.08658540672796541,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 5.1955783009361044e-05,
|
||
|
|
"loss": 5.2832,
|
||
|
|
"mean_token_accuracy": 0.21443279832601547,
|
||
|
|
"num_tokens": 3286115.0,
|
||
|
|
"step": 3875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.653279829025268,
|
||
|
|
"epoch": 0.08669712983342084,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 5.180384554351543e-05,
|
||
|
|
"loss": 5.3824,
|
||
|
|
"mean_token_accuracy": 0.2080657109618187,
|
||
|
|
"num_tokens": 3290791.0,
|
||
|
|
"step": 3880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.669637393951416,
|
||
|
|
"epoch": 0.08680885293887629,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 5.1658027112990976e-05,
|
||
|
|
"loss": 5.3465,
|
||
|
|
"mean_token_accuracy": 0.22144186198711396,
|
||
|
|
"num_tokens": 3295327.0,
|
||
|
|
"step": 3885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.711081886291504,
|
||
|
|
"epoch": 0.08692057604433173,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 5.151833171547365e-05,
|
||
|
|
"loss": 5.4463,
|
||
|
|
"mean_token_accuracy": 0.20244335383176804,
|
||
|
|
"num_tokens": 3299267.0,
|
||
|
|
"step": 3890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.636924457550049,
|
||
|
|
"epoch": 0.08703229914978716,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 5.1384763180783274e-05,
|
||
|
|
"loss": 5.4062,
|
||
|
|
"mean_token_accuracy": 0.20746810883283615,
|
||
|
|
"num_tokens": 3304074.0,
|
||
|
|
"step": 3895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.637734651565552,
|
||
|
|
"epoch": 0.0871440222552426,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 5.125732517076876e-05,
|
||
|
|
"loss": 5.3251,
|
||
|
|
"mean_token_accuracy": 0.2097361832857132,
|
||
|
|
"num_tokens": 3308292.0,
|
||
|
|
"step": 3900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.633953189849853,
|
||
|
|
"epoch": 0.08725574536069805,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 5.113602117920747e-05,
|
||
|
|
"loss": 5.3888,
|
||
|
|
"mean_token_accuracy": 0.21099466532468797,
|
||
|
|
"num_tokens": 3312161.0,
|
||
|
|
"step": 3905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.656825065612793,
|
||
|
|
"epoch": 0.08736746846615348,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 5.102085453170966e-05,
|
||
|
|
"loss": 5.3267,
|
||
|
|
"mean_token_accuracy": 0.2001182571053505,
|
||
|
|
"num_tokens": 3316271.0,
|
||
|
|
"step": 3910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.677023983001709,
|
||
|
|
"epoch": 0.08747919157160892,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 5.091182838562709e-05,
|
||
|
|
"loss": 5.4061,
|
||
|
|
"mean_token_accuracy": 0.19816306382417678,
|
||
|
|
"num_tokens": 3320663.0,
|
||
|
|
"step": 3915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.607973432540893,
|
||
|
|
"epoch": 0.08759091467706437,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 5.0808945729966716e-05,
|
||
|
|
"loss": 5.3822,
|
||
|
|
"mean_token_accuracy": 0.20814824402332305,
|
||
|
|
"num_tokens": 3324699.0,
|
||
|
|
"step": 3920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.697803211212158,
|
||
|
|
"epoch": 0.0877026377825198,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 5.071220938530844e-05,
|
||
|
|
"loss": 5.3707,
|
||
|
|
"mean_token_accuracy": 0.19458835422992707,
|
||
|
|
"num_tokens": 3328737.0,
|
||
|
|
"step": 3925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7307751178741455,
|
||
|
|
"epoch": 0.08781436088797524,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 5.0621622003728026e-05,
|
||
|
|
"loss": 5.4589,
|
||
|
|
"mean_token_accuracy": 0.20548731684684754,
|
||
|
|
"num_tokens": 3333238.0,
|
||
|
|
"step": 3930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.672309398651123,
|
||
|
|
"epoch": 0.08792608399343069,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 5.053718606872433e-05,
|
||
|
|
"loss": 5.398,
|
||
|
|
"mean_token_accuracy": 0.20169921666383744,
|
||
|
|
"num_tokens": 3337505.0,
|
||
|
|
"step": 3935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6464564323425295,
|
||
|
|
"epoch": 0.08803780709888612,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 5.0458903895151134e-05,
|
||
|
|
"loss": 5.2632,
|
||
|
|
"mean_token_accuracy": 0.2304834946990013,
|
||
|
|
"num_tokens": 3341870.0,
|
||
|
|
"step": 3940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.685274839401245,
|
||
|
|
"epoch": 0.08814953020434156,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 5.038677762915381e-05,
|
||
|
|
"loss": 5.2985,
|
||
|
|
"mean_token_accuracy": 0.20485025644302368,
|
||
|
|
"num_tokens": 3346200.0,
|
||
|
|
"step": 3945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.628360939025879,
|
||
|
|
"epoch": 0.088261253309797,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 5.032080924811033e-05,
|
||
|
|
"loss": 5.2183,
|
||
|
|
"mean_token_accuracy": 0.2136240467429161,
|
||
|
|
"num_tokens": 3350463.0,
|
||
|
|
"step": 3950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.582505941390991,
|
||
|
|
"epoch": 0.08837297641525244,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 5.026100056057718e-05,
|
||
|
|
"loss": 5.2084,
|
||
|
|
"mean_token_accuracy": 0.23170518428087233,
|
||
|
|
"num_tokens": 3354207.0,
|
||
|
|
"step": 3955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.67683629989624,
|
||
|
|
"epoch": 0.08848469952070788,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 5.0207353206239764e-05,
|
||
|
|
"loss": 5.348,
|
||
|
|
"mean_token_accuracy": 0.21558842658996583,
|
||
|
|
"num_tokens": 3358954.0,
|
||
|
|
"step": 3960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7070441246032715,
|
||
|
|
"epoch": 0.08859642262616332,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 5.0159868655867436e-05,
|
||
|
|
"loss": 5.4158,
|
||
|
|
"mean_token_accuracy": 0.21012357175350188,
|
||
|
|
"num_tokens": 3363031.0,
|
||
|
|
"step": 3965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.63456654548645,
|
||
|
|
"epoch": 0.08870814573161875,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 5.011854821127305e-05,
|
||
|
|
"loss": 5.3845,
|
||
|
|
"mean_token_accuracy": 0.20455027371644974,
|
||
|
|
"num_tokens": 3367512.0,
|
||
|
|
"step": 3970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.658596038818359,
|
||
|
|
"epoch": 0.0888198688370742,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 5.008339300527755e-05,
|
||
|
|
"loss": 5.3662,
|
||
|
|
"mean_token_accuracy": 0.2060423269867897,
|
||
|
|
"num_tokens": 3371509.0,
|
||
|
|
"step": 3975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.630813550949097,
|
||
|
|
"epoch": 0.08893159194252963,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 5.005440400167859e-05,
|
||
|
|
"loss": 5.3012,
|
||
|
|
"mean_token_accuracy": 0.2052410736680031,
|
||
|
|
"num_tokens": 3375476.0,
|
||
|
|
"step": 3980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.597796773910522,
|
||
|
|
"epoch": 0.08904331504798507,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 5.003158199522442e-05,
|
||
|
|
"loss": 5.2462,
|
||
|
|
"mean_token_accuracy": 0.21848327964544295,
|
||
|
|
"num_tokens": 3379687.0,
|
||
|
|
"step": 3985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.62085919380188,
|
||
|
|
"epoch": 0.08915503815344052,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 5.0014927611591806e-05,
|
||
|
|
"loss": 5.3419,
|
||
|
|
"mean_token_accuracy": 0.21537360697984695,
|
||
|
|
"num_tokens": 3383750.0,
|
||
|
|
"step": 3990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.628591918945313,
|
||
|
|
"epoch": 0.08926676125889595,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 5.000444130736916e-05,
|
||
|
|
"loss": 5.3254,
|
||
|
|
"mean_token_accuracy": 0.21683470755815507,
|
||
|
|
"num_tokens": 3387621.0,
|
||
|
|
"step": 3995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.56071720123291,
|
||
|
|
"epoch": 0.08937848436435139,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 5.0000123370043736e-05,
|
||
|
|
"loss": 5.2765,
|
||
|
|
"mean_token_accuracy": 0.215224190056324,
|
||
|
|
"num_tokens": 3392112.0,
|
||
|
|
"step": 4000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 4000,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 728529201561600.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|