6046 lines
164 KiB
JSON
6046 lines
164 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 0.29773719730051607,
|
||
|
|
"eval_steps": 3000,
|
||
|
|
"global_step": 3000,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 4.931299161911011,
|
||
|
|
"epoch": 0.0004962286621675268,
|
||
|
|
"grad_norm": 14.6875,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 14.4374,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 11135.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 4.938097429275513,
|
||
|
|
"epoch": 0.0009924573243350536,
|
||
|
|
"grad_norm": 15.375,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 14.4228,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 22299.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 4.951365232467651,
|
||
|
|
"epoch": 0.0014886859865025804,
|
||
|
|
"grad_norm": 16.375,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 14.3239,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 33670.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 4.991879177093506,
|
||
|
|
"epoch": 0.001984914648670107,
|
||
|
|
"grad_norm": 18.625,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 14.1546,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 44240.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.11100959777832,
|
||
|
|
"epoch": 0.002481143310837634,
|
||
|
|
"grad_norm": 22.5,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 13.6792,
|
||
|
|
"mean_token_accuracy": 0.00010111223673447967,
|
||
|
|
"num_tokens": 54168.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.412902069091797,
|
||
|
|
"epoch": 0.0029773719730051607,
|
||
|
|
"grad_norm": 29.0,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 13.1651,
|
||
|
|
"mean_token_accuracy": 8.11688310932368e-05,
|
||
|
|
"num_tokens": 64704.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.036752700805664,
|
||
|
|
"epoch": 0.0034736006351726877,
|
||
|
|
"grad_norm": 22.25,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 11.9985,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 75766.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.185614490509034,
|
||
|
|
"epoch": 0.003969829297340214,
|
||
|
|
"grad_norm": 3.25,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 10.9414,
|
||
|
|
"mean_token_accuracy": 0.0002966745407320559,
|
||
|
|
"num_tokens": 88074.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.717006397247314,
|
||
|
|
"epoch": 0.004466057959507741,
|
||
|
|
"grad_norm": 2.828125,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 10.725,
|
||
|
|
"mean_token_accuracy": 0.00629717658739537,
|
||
|
|
"num_tokens": 99313.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.743248081207275,
|
||
|
|
"epoch": 0.004962286621675268,
|
||
|
|
"grad_norm": 2.59375,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 10.6055,
|
||
|
|
"mean_token_accuracy": 0.01345829488709569,
|
||
|
|
"num_tokens": 110819.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.739305686950683,
|
||
|
|
"epoch": 0.0054585152838427945,
|
||
|
|
"grad_norm": 1.9921875,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 10.3942,
|
||
|
|
"mean_token_accuracy": 0.016125928703695537,
|
||
|
|
"num_tokens": 121156.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.702740478515626,
|
||
|
|
"epoch": 0.0059547439460103215,
|
||
|
|
"grad_norm": 2.046875,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 10.2317,
|
||
|
|
"mean_token_accuracy": 0.016230483166873456,
|
||
|
|
"num_tokens": 131307.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.715532684326172,
|
||
|
|
"epoch": 0.0064509726081778485,
|
||
|
|
"grad_norm": 1.921875,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 10.0947,
|
||
|
|
"mean_token_accuracy": 0.01627691639587283,
|
||
|
|
"num_tokens": 141812.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.737543678283691,
|
||
|
|
"epoch": 0.0069472012703453755,
|
||
|
|
"grad_norm": 1.703125,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 10.0193,
|
||
|
|
"mean_token_accuracy": 0.01881603915244341,
|
||
|
|
"num_tokens": 152425.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.738888168334961,
|
||
|
|
"epoch": 0.007443429932512902,
|
||
|
|
"grad_norm": 1.9140625,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.902,
|
||
|
|
"mean_token_accuracy": 0.029196479916572572,
|
||
|
|
"num_tokens": 162562.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.733177089691162,
|
||
|
|
"epoch": 0.007939658594680429,
|
||
|
|
"grad_norm": 1.9296875,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 9.835,
|
||
|
|
"mean_token_accuracy": 0.038548733852803704,
|
||
|
|
"num_tokens": 173322.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.730626487731934,
|
||
|
|
"epoch": 0.008435887256847956,
|
||
|
|
"grad_norm": 1.765625,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 9.7586,
|
||
|
|
"mean_token_accuracy": 0.04156450685113668,
|
||
|
|
"num_tokens": 183169.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.72908525466919,
|
||
|
|
"epoch": 0.008932115919015483,
|
||
|
|
"grad_norm": 1.6875,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 9.7319,
|
||
|
|
"mean_token_accuracy": 0.040352378785610196,
|
||
|
|
"num_tokens": 194473.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.723829555511475,
|
||
|
|
"epoch": 0.00942834458118301,
|
||
|
|
"grad_norm": 1.6953125,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 9.5914,
|
||
|
|
"mean_token_accuracy": 0.041312170401215556,
|
||
|
|
"num_tokens": 206166.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.710507011413574,
|
||
|
|
"epoch": 0.009924573243350537,
|
||
|
|
"grad_norm": 1.703125,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 9.4691,
|
||
|
|
"mean_token_accuracy": 0.04619110412895679,
|
||
|
|
"num_tokens": 215923.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.687235641479493,
|
||
|
|
"epoch": 0.010420801905518062,
|
||
|
|
"grad_norm": 1.765625,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 9.3768,
|
||
|
|
"mean_token_accuracy": 0.040744516998529434,
|
||
|
|
"num_tokens": 227139.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.66772632598877,
|
||
|
|
"epoch": 0.010917030567685589,
|
||
|
|
"grad_norm": 1.734375,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 9.2519,
|
||
|
|
"mean_token_accuracy": 0.04524887017905712,
|
||
|
|
"num_tokens": 237770.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.642418003082275,
|
||
|
|
"epoch": 0.011413259229853116,
|
||
|
|
"grad_norm": 1.5703125,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 9.1603,
|
||
|
|
"mean_token_accuracy": 0.050716237351298335,
|
||
|
|
"num_tokens": 249241.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.606610870361328,
|
||
|
|
"epoch": 0.011909487892020643,
|
||
|
|
"grad_norm": 1.6484375,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.9869,
|
||
|
|
"mean_token_accuracy": 0.046933449991047385,
|
||
|
|
"num_tokens": 258562.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.56153678894043,
|
||
|
|
"epoch": 0.01240571655418817,
|
||
|
|
"grad_norm": 1.6328125,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 8.956,
|
||
|
|
"mean_token_accuracy": 0.049542845040559766,
|
||
|
|
"num_tokens": 269548.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.512712478637695,
|
||
|
|
"epoch": 0.012901945216355697,
|
||
|
|
"grad_norm": 1.53125,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 8.8768,
|
||
|
|
"mean_token_accuracy": 0.0483577411621809,
|
||
|
|
"num_tokens": 280965.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.447002983093261,
|
||
|
|
"epoch": 0.013398173878523224,
|
||
|
|
"grad_norm": 1.515625,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 8.6644,
|
||
|
|
"mean_token_accuracy": 0.05167540945112705,
|
||
|
|
"num_tokens": 290063.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.371509552001953,
|
||
|
|
"epoch": 0.013894402540690751,
|
||
|
|
"grad_norm": 1.5546875,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 8.6306,
|
||
|
|
"mean_token_accuracy": 0.047542725875973704,
|
||
|
|
"num_tokens": 301013.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.292595195770264,
|
||
|
|
"epoch": 0.014390631202858276,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 8.5113,
|
||
|
|
"mean_token_accuracy": 0.049639220163226125,
|
||
|
|
"num_tokens": 313351.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.18106632232666,
|
||
|
|
"epoch": 0.014886859865025803,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 8.4824,
|
||
|
|
"mean_token_accuracy": 0.047823553532361986,
|
||
|
|
"num_tokens": 324871.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.063039779663086,
|
||
|
|
"epoch": 0.01538308852719333,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 8.2836,
|
||
|
|
"mean_token_accuracy": 0.048729633539915086,
|
||
|
|
"num_tokens": 335856.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.891231155395507,
|
||
|
|
"epoch": 0.015879317189360857,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 8.2022,
|
||
|
|
"mean_token_accuracy": 0.05146194100379944,
|
||
|
|
"num_tokens": 345410.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.697038269042968,
|
||
|
|
"epoch": 0.016375545851528384,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 8.1555,
|
||
|
|
"mean_token_accuracy": 0.048843025043606755,
|
||
|
|
"num_tokens": 356370.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.49948616027832,
|
||
|
|
"epoch": 0.01687177451369591,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 8.0734,
|
||
|
|
"mean_token_accuracy": 0.04591990895569324,
|
||
|
|
"num_tokens": 368085.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.283473300933839,
|
||
|
|
"epoch": 0.01736800317586344,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.925,
|
||
|
|
"mean_token_accuracy": 0.04852883592247963,
|
||
|
|
"num_tokens": 378995.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.047716808319091,
|
||
|
|
"epoch": 0.017864231838030965,
|
||
|
|
"grad_norm": 0.69921875,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.9793,
|
||
|
|
"mean_token_accuracy": 0.0445900060236454,
|
||
|
|
"num_tokens": 390727.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.858506870269775,
|
||
|
|
"epoch": 0.018360460500198492,
|
||
|
|
"grad_norm": 0.71875,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.8485,
|
||
|
|
"mean_token_accuracy": 0.04807438552379608,
|
||
|
|
"num_tokens": 401875.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.66808204650879,
|
||
|
|
"epoch": 0.01885668916236602,
|
||
|
|
"grad_norm": 0.671875,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.8301,
|
||
|
|
"mean_token_accuracy": 0.05265191309154034,
|
||
|
|
"num_tokens": 414959.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.465768527984618,
|
||
|
|
"epoch": 0.019352917824533546,
|
||
|
|
"grad_norm": 0.69140625,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.7787,
|
||
|
|
"mean_token_accuracy": 0.05121605955064297,
|
||
|
|
"num_tokens": 425745.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.350896739959717,
|
||
|
|
"epoch": 0.019849146486701073,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.7229,
|
||
|
|
"mean_token_accuracy": 0.04516980387270451,
|
||
|
|
"num_tokens": 435149.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.277827644348145,
|
||
|
|
"epoch": 0.0203453751488686,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 7.7528,
|
||
|
|
"mean_token_accuracy": 0.04675165638327598,
|
||
|
|
"num_tokens": 445706.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.202262878417969,
|
||
|
|
"epoch": 0.020841603811036124,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.7464,
|
||
|
|
"mean_token_accuracy": 0.051094313710927965,
|
||
|
|
"num_tokens": 455982.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.231989574432372,
|
||
|
|
"epoch": 0.02133783247320365,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 7.7547,
|
||
|
|
"mean_token_accuracy": 0.04971891045570374,
|
||
|
|
"num_tokens": 465462.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.276477718353272,
|
||
|
|
"epoch": 0.021834061135371178,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 7.7201,
|
||
|
|
"mean_token_accuracy": 0.049120894819498065,
|
||
|
|
"num_tokens": 475770.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.2308780670166,
|
||
|
|
"epoch": 0.022330289797538705,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 7.6536,
|
||
|
|
"mean_token_accuracy": 0.05627523325383663,
|
||
|
|
"num_tokens": 486345.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.243096160888673,
|
||
|
|
"epoch": 0.022826518459706232,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 7.6637,
|
||
|
|
"mean_token_accuracy": 0.057797220349311826,
|
||
|
|
"num_tokens": 496588.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.189409923553466,
|
||
|
|
"epoch": 0.02332274712187376,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 7.6064,
|
||
|
|
"mean_token_accuracy": 0.0653748583048582,
|
||
|
|
"num_tokens": 506676.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.106929397583007,
|
||
|
|
"epoch": 0.023818975784041286,
|
||
|
|
"grad_norm": 0.703125,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 7.6016,
|
||
|
|
"mean_token_accuracy": 0.06197558268904686,
|
||
|
|
"num_tokens": 516866.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.121264171600341,
|
||
|
|
"epoch": 0.024315204446208813,
|
||
|
|
"grad_norm": 0.76953125,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 7.6847,
|
||
|
|
"mean_token_accuracy": 0.0619472224265337,
|
||
|
|
"num_tokens": 529349.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.116961669921874,
|
||
|
|
"epoch": 0.02481143310837634,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 7.6282,
|
||
|
|
"mean_token_accuracy": 0.05949817337095738,
|
||
|
|
"num_tokens": 541310.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.116946792602539,
|
||
|
|
"epoch": 0.025307661770543867,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 7.6313,
|
||
|
|
"mean_token_accuracy": 0.06268465593457222,
|
||
|
|
"num_tokens": 551897.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.077956581115723,
|
||
|
|
"epoch": 0.025803890432711394,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 7.6347,
|
||
|
|
"mean_token_accuracy": 0.06445351354777813,
|
||
|
|
"num_tokens": 564667.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.109729480743407,
|
||
|
|
"epoch": 0.02630011909487892,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 7.51,
|
||
|
|
"mean_token_accuracy": 0.07109251022338867,
|
||
|
|
"num_tokens": 575338.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.040228891372681,
|
||
|
|
"epoch": 0.026796347757046448,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 7.6347,
|
||
|
|
"mean_token_accuracy": 0.06142906881868839,
|
||
|
|
"num_tokens": 586169.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.13642110824585,
|
||
|
|
"epoch": 0.027292576419213975,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 7.5917,
|
||
|
|
"mean_token_accuracy": 0.06226538605988026,
|
||
|
|
"num_tokens": 596864.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.001047468185424,
|
||
|
|
"epoch": 0.027788805081381502,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 7.545,
|
||
|
|
"mean_token_accuracy": 0.06418961510062218,
|
||
|
|
"num_tokens": 608894.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.050166368484497,
|
||
|
|
"epoch": 0.02828503374354903,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 7.5519,
|
||
|
|
"mean_token_accuracy": 0.06657364331185818,
|
||
|
|
"num_tokens": 619863.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.061230039596557,
|
||
|
|
"epoch": 0.028781262405716553,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 7.5501,
|
||
|
|
"mean_token_accuracy": 0.06628488451242447,
|
||
|
|
"num_tokens": 632691.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.056870412826537,
|
||
|
|
"epoch": 0.02927749106788408,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 7.4641,
|
||
|
|
"mean_token_accuracy": 0.06920699514448643,
|
||
|
|
"num_tokens": 643993.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.001115942001343,
|
||
|
|
"epoch": 0.029773719730051607,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 7.4315,
|
||
|
|
"mean_token_accuracy": 0.06977621465921402,
|
||
|
|
"num_tokens": 654275.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.829830694198608,
|
||
|
|
"epoch": 0.030269948392219134,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 7.4137,
|
||
|
|
"mean_token_accuracy": 0.0679971806704998,
|
||
|
|
"num_tokens": 664694.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.01261920928955,
|
||
|
|
"epoch": 0.03076617705438666,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 7.4346,
|
||
|
|
"mean_token_accuracy": 0.06760629676282406,
|
||
|
|
"num_tokens": 674736.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.828978490829468,
|
||
|
|
"epoch": 0.03126240571655419,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 7.3673,
|
||
|
|
"mean_token_accuracy": 0.06551955416798591,
|
||
|
|
"num_tokens": 687261.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.922390127182007,
|
||
|
|
"epoch": 0.031758634378721715,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 7.3618,
|
||
|
|
"mean_token_accuracy": 0.07412862330675125,
|
||
|
|
"num_tokens": 698904.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.855106163024902,
|
||
|
|
"epoch": 0.032254863040889245,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 7.3364,
|
||
|
|
"mean_token_accuracy": 0.07321774028241634,
|
||
|
|
"num_tokens": 709035.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.789221477508545,
|
||
|
|
"epoch": 0.03275109170305677,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 7.3969,
|
||
|
|
"mean_token_accuracy": 0.07102149352431297,
|
||
|
|
"num_tokens": 719565.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.915437698364258,
|
||
|
|
"epoch": 0.03324732036522429,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 7.4084,
|
||
|
|
"mean_token_accuracy": 0.07039739079773426,
|
||
|
|
"num_tokens": 730329.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.888462257385254,
|
||
|
|
"epoch": 0.03374354902739182,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 7.4161,
|
||
|
|
"mean_token_accuracy": 0.06667844317853451,
|
||
|
|
"num_tokens": 741258.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.846066999435425,
|
||
|
|
"epoch": 0.034239777689559346,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 7.3014,
|
||
|
|
"mean_token_accuracy": 0.06842922903597355,
|
||
|
|
"num_tokens": 752636.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.859539461135864,
|
||
|
|
"epoch": 0.03473600635172688,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 7.3813,
|
||
|
|
"mean_token_accuracy": 0.06898528710007668,
|
||
|
|
"num_tokens": 764113.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.697615098953247,
|
||
|
|
"epoch": 0.0352322350138944,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 7.2791,
|
||
|
|
"mean_token_accuracy": 0.07269814386963844,
|
||
|
|
"num_tokens": 772872.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.79153094291687,
|
||
|
|
"epoch": 0.03572846367606193,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 7.2548,
|
||
|
|
"mean_token_accuracy": 0.07947108298540115,
|
||
|
|
"num_tokens": 782788.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.759897947311401,
|
||
|
|
"epoch": 0.036224692338229454,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 7.3299,
|
||
|
|
"mean_token_accuracy": 0.07359667010605335,
|
||
|
|
"num_tokens": 793859.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.739173507690429,
|
||
|
|
"epoch": 0.036720921000396985,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 7.3104,
|
||
|
|
"mean_token_accuracy": 0.07008818164467812,
|
||
|
|
"num_tokens": 804906.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.807758951187134,
|
||
|
|
"epoch": 0.03721714966256451,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 7.3094,
|
||
|
|
"mean_token_accuracy": 0.07675720825791359,
|
||
|
|
"num_tokens": 815520.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.60875358581543,
|
||
|
|
"epoch": 0.03771337832473204,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 7.3141,
|
||
|
|
"mean_token_accuracy": 0.07395646013319493,
|
||
|
|
"num_tokens": 826395.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.747971534729004,
|
||
|
|
"epoch": 0.03820960698689956,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 7.2688,
|
||
|
|
"mean_token_accuracy": 0.07527201510965824,
|
||
|
|
"num_tokens": 836627.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.64195990562439,
|
||
|
|
"epoch": 0.03870583564906709,
|
||
|
|
"grad_norm": 0.7734375,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 7.3072,
|
||
|
|
"mean_token_accuracy": 0.06740010790526867,
|
||
|
|
"num_tokens": 848250.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.7738360404968265,
|
||
|
|
"epoch": 0.039202064311234616,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 7.2937,
|
||
|
|
"mean_token_accuracy": 0.07260859198868275,
|
||
|
|
"num_tokens": 859195.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.725459146499634,
|
||
|
|
"epoch": 0.03969829297340215,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 7.2597,
|
||
|
|
"mean_token_accuracy": 0.078775167837739,
|
||
|
|
"num_tokens": 871955.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.691169404983521,
|
||
|
|
"epoch": 0.04019452163556967,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 7.2548,
|
||
|
|
"mean_token_accuracy": 0.0749235574156046,
|
||
|
|
"num_tokens": 882729.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6321714401245115,
|
||
|
|
"epoch": 0.0406907502977372,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 7.1675,
|
||
|
|
"mean_token_accuracy": 0.07198959216475487,
|
||
|
|
"num_tokens": 893183.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.637913227081299,
|
||
|
|
"epoch": 0.041186978959904724,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 7.2852,
|
||
|
|
"mean_token_accuracy": 0.07573982179164887,
|
||
|
|
"num_tokens": 904988.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.715639543533325,
|
||
|
|
"epoch": 0.04168320762207225,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 7.1686,
|
||
|
|
"mean_token_accuracy": 0.07994935102760792,
|
||
|
|
"num_tokens": 915192.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.647213315963745,
|
||
|
|
"epoch": 0.04217943628423978,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 7.2004,
|
||
|
|
"mean_token_accuracy": 0.07983001545071602,
|
||
|
|
"num_tokens": 926494.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.671146392822266,
|
||
|
|
"epoch": 0.0426756649464073,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 7.1945,
|
||
|
|
"mean_token_accuracy": 0.07794273421168327,
|
||
|
|
"num_tokens": 938376.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.543527317047119,
|
||
|
|
"epoch": 0.04317189360857483,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 7.1208,
|
||
|
|
"mean_token_accuracy": 0.0846080757677555,
|
||
|
|
"num_tokens": 948640.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.636675453186035,
|
||
|
|
"epoch": 0.043668122270742356,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 7.1961,
|
||
|
|
"mean_token_accuracy": 0.07409511283040046,
|
||
|
|
"num_tokens": 959759.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.534220218658447,
|
||
|
|
"epoch": 0.044164350932909886,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 7.1323,
|
||
|
|
"mean_token_accuracy": 0.08176640719175339,
|
||
|
|
"num_tokens": 970137.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.612626314163208,
|
||
|
|
"epoch": 0.04466057959507741,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 7.1693,
|
||
|
|
"mean_token_accuracy": 0.076291673630476,
|
||
|
|
"num_tokens": 979875.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.50954155921936,
|
||
|
|
"epoch": 0.04515680825724494,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 7.1317,
|
||
|
|
"mean_token_accuracy": 0.08605509772896766,
|
||
|
|
"num_tokens": 990324.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.6120024681091305,
|
||
|
|
"epoch": 0.045653036919412464,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 7.1461,
|
||
|
|
"mean_token_accuracy": 0.08133600316941739,
|
||
|
|
"num_tokens": 1000259.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.572062015533447,
|
||
|
|
"epoch": 0.046149265581579994,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 7.1323,
|
||
|
|
"mean_token_accuracy": 0.08284945711493492,
|
||
|
|
"num_tokens": 1012220.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.614422273635864,
|
||
|
|
"epoch": 0.04664549424374752,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 7.1318,
|
||
|
|
"mean_token_accuracy": 0.078894879296422,
|
||
|
|
"num_tokens": 1022968.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.54720253944397,
|
||
|
|
"epoch": 0.04714172290591505,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 7.139,
|
||
|
|
"mean_token_accuracy": 0.07864338010549546,
|
||
|
|
"num_tokens": 1033415.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.455529022216797,
|
||
|
|
"epoch": 0.04763795156808257,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 7.0479,
|
||
|
|
"mean_token_accuracy": 0.08645785674452781,
|
||
|
|
"num_tokens": 1045384.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.553596878051758,
|
||
|
|
"epoch": 0.0481341802302501,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 7.1197,
|
||
|
|
"mean_token_accuracy": 0.08306692317128181,
|
||
|
|
"num_tokens": 1054982.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.476700925827027,
|
||
|
|
"epoch": 0.048630408892417626,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 7.0713,
|
||
|
|
"mean_token_accuracy": 0.08579476028680802,
|
||
|
|
"num_tokens": 1065244.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.534849357604981,
|
||
|
|
"epoch": 0.04912663755458515,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 7.0722,
|
||
|
|
"mean_token_accuracy": 0.08112104386091232,
|
||
|
|
"num_tokens": 1075236.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.512158679962158,
|
||
|
|
"epoch": 0.04962286621675268,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 7.0981,
|
||
|
|
"mean_token_accuracy": 0.07874655723571777,
|
||
|
|
"num_tokens": 1085397.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.460465049743652,
|
||
|
|
"epoch": 0.0501190948789202,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 7.097,
|
||
|
|
"mean_token_accuracy": 0.08893987089395523,
|
||
|
|
"num_tokens": 1095207.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.566689109802246,
|
||
|
|
"epoch": 0.050615323541087734,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 7.0936,
|
||
|
|
"mean_token_accuracy": 0.07820081040263176,
|
||
|
|
"num_tokens": 1105834.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.45391845703125,
|
||
|
|
"epoch": 0.05111155220325526,
|
||
|
|
"grad_norm": 1.5859375,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 7.1052,
|
||
|
|
"mean_token_accuracy": 0.07973617538809777,
|
||
|
|
"num_tokens": 1116105.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.5173252582550045,
|
||
|
|
"epoch": 0.05160778086542279,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 7.0979,
|
||
|
|
"mean_token_accuracy": 0.0877754531800747,
|
||
|
|
"num_tokens": 1125298.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.461072683334351,
|
||
|
|
"epoch": 0.05210400952759031,
|
||
|
|
"grad_norm": 0.7421875,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 7.0785,
|
||
|
|
"mean_token_accuracy": 0.0839509479701519,
|
||
|
|
"num_tokens": 1136797.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.396866083145142,
|
||
|
|
"epoch": 0.05260023818975784,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 7.0534,
|
||
|
|
"mean_token_accuracy": 0.08347654044628143,
|
||
|
|
"num_tokens": 1148674.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.563003301620483,
|
||
|
|
"epoch": 0.053096466851925365,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 7.1343,
|
||
|
|
"mean_token_accuracy": 0.07938608936965466,
|
||
|
|
"num_tokens": 1160329.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.424808549880981,
|
||
|
|
"epoch": 0.053592695514092896,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 7.0971,
|
||
|
|
"mean_token_accuracy": 0.08222321793437004,
|
||
|
|
"num_tokens": 1170318.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.452347183227539,
|
||
|
|
"epoch": 0.05408892417626042,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.9431,
|
||
|
|
"mean_token_accuracy": 0.09257944747805595,
|
||
|
|
"num_tokens": 1181634.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.393966245651245,
|
||
|
|
"epoch": 0.05458515283842795,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 7.0082,
|
||
|
|
"mean_token_accuracy": 0.09105771631002427,
|
||
|
|
"num_tokens": 1191829.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.436964321136474,
|
||
|
|
"epoch": 0.055081381500595473,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 7.0071,
|
||
|
|
"mean_token_accuracy": 0.08593062907457352,
|
||
|
|
"num_tokens": 1202265.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.300072574615479,
|
||
|
|
"epoch": 0.055577610162763004,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 7.0075,
|
||
|
|
"mean_token_accuracy": 0.08627107739448547,
|
||
|
|
"num_tokens": 1214173.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.399516344070435,
|
||
|
|
"epoch": 0.05607383882493053,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.921,
|
||
|
|
"mean_token_accuracy": 0.08665959686040878,
|
||
|
|
"num_tokens": 1224582.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.463116979598999,
|
||
|
|
"epoch": 0.05657006748709806,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 7.1136,
|
||
|
|
"mean_token_accuracy": 0.0828106202185154,
|
||
|
|
"num_tokens": 1235865.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.282903718948364,
|
||
|
|
"epoch": 0.05706629614926558,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.9459,
|
||
|
|
"mean_token_accuracy": 0.08898672014474869,
|
||
|
|
"num_tokens": 1247194.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.277571678161621,
|
||
|
|
"epoch": 0.057562524811433105,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.949,
|
||
|
|
"mean_token_accuracy": 0.08503150045871735,
|
||
|
|
"num_tokens": 1257981.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.39735426902771,
|
||
|
|
"epoch": 0.058058753473600636,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.9111,
|
||
|
|
"mean_token_accuracy": 0.09066925644874572,
|
||
|
|
"num_tokens": 1268443.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.440923500061035,
|
||
|
|
"epoch": 0.05855498213576816,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 7.0199,
|
||
|
|
"mean_token_accuracy": 0.08563335537910462,
|
||
|
|
"num_tokens": 1279134.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3426929950714115,
|
||
|
|
"epoch": 0.05905121079793569,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.9811,
|
||
|
|
"mean_token_accuracy": 0.07985961809754372,
|
||
|
|
"num_tokens": 1289965.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.358950996398926,
|
||
|
|
"epoch": 0.05954743946010321,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.9003,
|
||
|
|
"mean_token_accuracy": 0.08630152940750122,
|
||
|
|
"num_tokens": 1300003.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.291685724258423,
|
||
|
|
"epoch": 0.060043668122270744,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.9428,
|
||
|
|
"mean_token_accuracy": 0.08731391057372093,
|
||
|
|
"num_tokens": 1311990.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.223467254638672,
|
||
|
|
"epoch": 0.06053989678443827,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.981,
|
||
|
|
"mean_token_accuracy": 0.08844437226653099,
|
||
|
|
"num_tokens": 1322963.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.410216188430786,
|
||
|
|
"epoch": 0.0610361254466058,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.9781,
|
||
|
|
"mean_token_accuracy": 0.08575883433222771,
|
||
|
|
"num_tokens": 1334580.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.334858226776123,
|
||
|
|
"epoch": 0.06153235410877332,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.9336,
|
||
|
|
"mean_token_accuracy": 0.08547274991869927,
|
||
|
|
"num_tokens": 1346545.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3943980693817135,
|
||
|
|
"epoch": 0.06202858277094085,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.919,
|
||
|
|
"mean_token_accuracy": 0.08397532440721989,
|
||
|
|
"num_tokens": 1358375.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2383945941925045,
|
||
|
|
"epoch": 0.06252481143310838,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.9856,
|
||
|
|
"mean_token_accuracy": 0.08264455795288086,
|
||
|
|
"num_tokens": 1368376.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.319325971603393,
|
||
|
|
"epoch": 0.0630210400952759,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.864,
|
||
|
|
"mean_token_accuracy": 0.08814716339111328,
|
||
|
|
"num_tokens": 1377749.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.229701232910156,
|
||
|
|
"epoch": 0.06351726875744343,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.914,
|
||
|
|
"mean_token_accuracy": 0.08655236959457398,
|
||
|
|
"num_tokens": 1389581.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.250205373764038,
|
||
|
|
"epoch": 0.06401349741961096,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.8497,
|
||
|
|
"mean_token_accuracy": 0.08738525807857514,
|
||
|
|
"num_tokens": 1399772.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.267027425765991,
|
||
|
|
"epoch": 0.06450972608177849,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.9473,
|
||
|
|
"mean_token_accuracy": 0.08941742517054081,
|
||
|
|
"num_tokens": 1411158.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.267431354522705,
|
||
|
|
"epoch": 0.065005954743946,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.8452,
|
||
|
|
"mean_token_accuracy": 0.08903275355696678,
|
||
|
|
"num_tokens": 1420651.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.18158540725708,
|
||
|
|
"epoch": 0.06550218340611354,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.7959,
|
||
|
|
"mean_token_accuracy": 0.08788748160004616,
|
||
|
|
"num_tokens": 1431628.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.198916244506836,
|
||
|
|
"epoch": 0.06599841206828107,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.8263,
|
||
|
|
"mean_token_accuracy": 0.09162173792719841,
|
||
|
|
"num_tokens": 1441850.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.2991822242736815,
|
||
|
|
"epoch": 0.06649464073044858,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.903,
|
||
|
|
"mean_token_accuracy": 0.09288545921444893,
|
||
|
|
"num_tokens": 1452393.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.235831642150879,
|
||
|
|
"epoch": 0.06699086939261611,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.8342,
|
||
|
|
"mean_token_accuracy": 0.09165843799710274,
|
||
|
|
"num_tokens": 1463109.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1810173988342285,
|
||
|
|
"epoch": 0.06748709805478365,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.9279,
|
||
|
|
"mean_token_accuracy": 0.0936855673789978,
|
||
|
|
"num_tokens": 1475082.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.174162340164185,
|
||
|
|
"epoch": 0.06798332671695118,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.7829,
|
||
|
|
"mean_token_accuracy": 0.09301829412579536,
|
||
|
|
"num_tokens": 1485477.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1776305675506595,
|
||
|
|
"epoch": 0.06847955537911869,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.7743,
|
||
|
|
"mean_token_accuracy": 0.09528700262308121,
|
||
|
|
"num_tokens": 1495422.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.233342695236206,
|
||
|
|
"epoch": 0.06897578404128622,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.799,
|
||
|
|
"mean_token_accuracy": 0.08826558515429497,
|
||
|
|
"num_tokens": 1506368.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.151353263854981,
|
||
|
|
"epoch": 0.06947201270345375,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.801,
|
||
|
|
"mean_token_accuracy": 0.09386853724718094,
|
||
|
|
"num_tokens": 1517437.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.06351146697998,
|
||
|
|
"epoch": 0.06996824136562128,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.7397,
|
||
|
|
"mean_token_accuracy": 0.09502186775207519,
|
||
|
|
"num_tokens": 1527801.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.185938215255737,
|
||
|
|
"epoch": 0.0704644700277888,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.8284,
|
||
|
|
"mean_token_accuracy": 0.0896036982536316,
|
||
|
|
"num_tokens": 1537621.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.186826467514038,
|
||
|
|
"epoch": 0.07096069868995633,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.8201,
|
||
|
|
"mean_token_accuracy": 0.08602025657892227,
|
||
|
|
"num_tokens": 1549123.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1724272727966305,
|
||
|
|
"epoch": 0.07145692735212386,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.8183,
|
||
|
|
"mean_token_accuracy": 0.09465417116880417,
|
||
|
|
"num_tokens": 1561167.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.086180877685547,
|
||
|
|
"epoch": 0.07195315601429139,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.73,
|
||
|
|
"mean_token_accuracy": 0.09641935527324677,
|
||
|
|
"num_tokens": 1571552.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.058502244949341,
|
||
|
|
"epoch": 0.07244938467645891,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.6992,
|
||
|
|
"mean_token_accuracy": 0.09181095212697983,
|
||
|
|
"num_tokens": 1582558.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.986404323577881,
|
||
|
|
"epoch": 0.07294561333862644,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.6883,
|
||
|
|
"mean_token_accuracy": 0.09569443389773369,
|
||
|
|
"num_tokens": 1595259.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.101809167861939,
|
||
|
|
"epoch": 0.07344184200079397,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.715,
|
||
|
|
"mean_token_accuracy": 0.09670865535736084,
|
||
|
|
"num_tokens": 1605585.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.043530368804932,
|
||
|
|
"epoch": 0.07393807066296149,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.6582,
|
||
|
|
"mean_token_accuracy": 0.09511561095714569,
|
||
|
|
"num_tokens": 1616529.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.013380241394043,
|
||
|
|
"epoch": 0.07443429932512902,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.6465,
|
||
|
|
"mean_token_accuracy": 0.09446082040667533,
|
||
|
|
"num_tokens": 1626223.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.02883677482605,
|
||
|
|
"epoch": 0.07493052798729655,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.7589,
|
||
|
|
"mean_token_accuracy": 0.09522427693009376,
|
||
|
|
"num_tokens": 1638173.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.903225469589233,
|
||
|
|
"epoch": 0.07542675664946408,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.5802,
|
||
|
|
"mean_token_accuracy": 0.0996096670627594,
|
||
|
|
"num_tokens": 1648919.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.012854671478271,
|
||
|
|
"epoch": 0.0759229853116316,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.821,
|
||
|
|
"mean_token_accuracy": 0.08750703632831573,
|
||
|
|
"num_tokens": 1660704.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.085955572128296,
|
||
|
|
"epoch": 0.07641921397379912,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.7273,
|
||
|
|
"mean_token_accuracy": 0.08895046189427376,
|
||
|
|
"num_tokens": 1672080.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.075372934341431,
|
||
|
|
"epoch": 0.07691544263596665,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.7014,
|
||
|
|
"mean_token_accuracy": 0.09691619500517845,
|
||
|
|
"num_tokens": 1681930.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.990365028381348,
|
||
|
|
"epoch": 0.07741167129813419,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.7129,
|
||
|
|
"mean_token_accuracy": 0.095877256244421,
|
||
|
|
"num_tokens": 1693075.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.033229637145996,
|
||
|
|
"epoch": 0.0779078999603017,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.6975,
|
||
|
|
"mean_token_accuracy": 0.09433050006628037,
|
||
|
|
"num_tokens": 1704163.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.068866348266601,
|
||
|
|
"epoch": 0.07840412862246923,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.8117,
|
||
|
|
"mean_token_accuracy": 0.09380641803145409,
|
||
|
|
"num_tokens": 1714879.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.057501363754272,
|
||
|
|
"epoch": 0.07890035728463676,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.8275,
|
||
|
|
"mean_token_accuracy": 0.09104160815477372,
|
||
|
|
"num_tokens": 1725464.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.169777536392212,
|
||
|
|
"epoch": 0.0793965859468043,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.7748,
|
||
|
|
"mean_token_accuracy": 0.09609344974160194,
|
||
|
|
"num_tokens": 1736947.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.911767673492432,
|
||
|
|
"epoch": 0.07989281460897181,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.5898,
|
||
|
|
"mean_token_accuracy": 0.10534465983510018,
|
||
|
|
"num_tokens": 1746827.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.104987621307373,
|
||
|
|
"epoch": 0.08038904327113934,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.7954,
|
||
|
|
"mean_token_accuracy": 0.09412779062986373,
|
||
|
|
"num_tokens": 1757079.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.993435382843018,
|
||
|
|
"epoch": 0.08088527193330687,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.7236,
|
||
|
|
"mean_token_accuracy": 0.09052609503269196,
|
||
|
|
"num_tokens": 1767684.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.004999494552612,
|
||
|
|
"epoch": 0.0813815005954744,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.7172,
|
||
|
|
"mean_token_accuracy": 0.0948351763188839,
|
||
|
|
"num_tokens": 1778187.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.968943452835083,
|
||
|
|
"epoch": 0.08187772925764192,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.6845,
|
||
|
|
"mean_token_accuracy": 0.09864413291215897,
|
||
|
|
"num_tokens": 1789139.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.927632141113281,
|
||
|
|
"epoch": 0.08237395791980945,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.5456,
|
||
|
|
"mean_token_accuracy": 0.10136523321270943,
|
||
|
|
"num_tokens": 1799328.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.912218379974365,
|
||
|
|
"epoch": 0.08287018658197698,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.7194,
|
||
|
|
"mean_token_accuracy": 0.09523818269371986,
|
||
|
|
"num_tokens": 1811487.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.958463907241821,
|
||
|
|
"epoch": 0.0833664152441445,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.6047,
|
||
|
|
"mean_token_accuracy": 0.10164962559938431,
|
||
|
|
"num_tokens": 1821923.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.836940288543701,
|
||
|
|
"epoch": 0.08386264390631203,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.6066,
|
||
|
|
"mean_token_accuracy": 0.10125545933842658,
|
||
|
|
"num_tokens": 1833001.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.989613962173462,
|
||
|
|
"epoch": 0.08435887256847956,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.6295,
|
||
|
|
"mean_token_accuracy": 0.10127801448106766,
|
||
|
|
"num_tokens": 1844473.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.892078447341919,
|
||
|
|
"epoch": 0.08485510123064709,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.5524,
|
||
|
|
"mean_token_accuracy": 0.10098758861422538,
|
||
|
|
"num_tokens": 1855851.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.790992307662964,
|
||
|
|
"epoch": 0.0853513298928146,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.5297,
|
||
|
|
"mean_token_accuracy": 0.09879347607493401,
|
||
|
|
"num_tokens": 1866712.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.051131010055542,
|
||
|
|
"epoch": 0.08584755855498213,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.5771,
|
||
|
|
"mean_token_accuracy": 0.09874777272343635,
|
||
|
|
"num_tokens": 1876443.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.778781223297119,
|
||
|
|
"epoch": 0.08634378721714966,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.6377,
|
||
|
|
"mean_token_accuracy": 0.10053054243326187,
|
||
|
|
"num_tokens": 1886239.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9395850658416744,
|
||
|
|
"epoch": 0.0868400158793172,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.5617,
|
||
|
|
"mean_token_accuracy": 0.10510002821683884,
|
||
|
|
"num_tokens": 1896457.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.825030755996704,
|
||
|
|
"epoch": 0.08733624454148471,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.563,
|
||
|
|
"mean_token_accuracy": 0.09209038838744163,
|
||
|
|
"num_tokens": 1908068.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.925831365585327,
|
||
|
|
"epoch": 0.08783247320365224,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.7105,
|
||
|
|
"mean_token_accuracy": 0.09559524208307266,
|
||
|
|
"num_tokens": 1920093.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.803714609146118,
|
||
|
|
"epoch": 0.08832870186581977,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.5027,
|
||
|
|
"mean_token_accuracy": 0.10239366963505744,
|
||
|
|
"num_tokens": 1930401.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.858418369293213,
|
||
|
|
"epoch": 0.0888249305279873,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.6809,
|
||
|
|
"mean_token_accuracy": 0.09742549583315849,
|
||
|
|
"num_tokens": 1940163.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.918571805953979,
|
||
|
|
"epoch": 0.08932115919015482,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.5271,
|
||
|
|
"mean_token_accuracy": 0.09928687438368797,
|
||
|
|
"num_tokens": 1952455.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.713730764389038,
|
||
|
|
"epoch": 0.08981738785232235,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.6428,
|
||
|
|
"mean_token_accuracy": 0.09646887555718422,
|
||
|
|
"num_tokens": 1965079.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.794367742538452,
|
||
|
|
"epoch": 0.09031361651448988,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.5174,
|
||
|
|
"mean_token_accuracy": 0.10413466691970825,
|
||
|
|
"num_tokens": 1976620.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.848107433319091,
|
||
|
|
"epoch": 0.0908098451766574,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.5142,
|
||
|
|
"mean_token_accuracy": 0.0995387688279152,
|
||
|
|
"num_tokens": 1987626.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.743514633178711,
|
||
|
|
"epoch": 0.09130607383882493,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.533,
|
||
|
|
"mean_token_accuracy": 0.10342048928141594,
|
||
|
|
"num_tokens": 1998250.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.878083229064941,
|
||
|
|
"epoch": 0.09180230250099246,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.5135,
|
||
|
|
"mean_token_accuracy": 0.10976848751306534,
|
||
|
|
"num_tokens": 2008098.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.675069999694824,
|
||
|
|
"epoch": 0.09229853116315999,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.4805,
|
||
|
|
"mean_token_accuracy": 0.09911079183220864,
|
||
|
|
"num_tokens": 2020125.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.776659440994263,
|
||
|
|
"epoch": 0.0927947598253275,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.6197,
|
||
|
|
"mean_token_accuracy": 0.10722684860229492,
|
||
|
|
"num_tokens": 2030791.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.848675394058228,
|
||
|
|
"epoch": 0.09329098848749504,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.5898,
|
||
|
|
"mean_token_accuracy": 0.10096785873174667,
|
||
|
|
"num_tokens": 2042358.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.729436016082763,
|
||
|
|
"epoch": 0.09378721714966257,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.5408,
|
||
|
|
"mean_token_accuracy": 0.10336418151855468,
|
||
|
|
"num_tokens": 2054549.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.836209058761597,
|
||
|
|
"epoch": 0.0942834458118301,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.5251,
|
||
|
|
"mean_token_accuracy": 0.10392895936965943,
|
||
|
|
"num_tokens": 2064903.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.76303129196167,
|
||
|
|
"epoch": 0.09477967447399761,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.4917,
|
||
|
|
"mean_token_accuracy": 0.10068923830986024,
|
||
|
|
"num_tokens": 2075795.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.75622067451477,
|
||
|
|
"epoch": 0.09527590313616514,
|
||
|
|
"grad_norm": 0.77734375,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.5309,
|
||
|
|
"mean_token_accuracy": 0.10283064991235732,
|
||
|
|
"num_tokens": 2087249.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.796994209289551,
|
||
|
|
"epoch": 0.09577213179833267,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.4935,
|
||
|
|
"mean_token_accuracy": 0.10899099111557006,
|
||
|
|
"num_tokens": 2097527.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.761102533340454,
|
||
|
|
"epoch": 0.0962683604605002,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.5146,
|
||
|
|
"mean_token_accuracy": 0.10290635898709297,
|
||
|
|
"num_tokens": 2108174.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.649438142776489,
|
||
|
|
"epoch": 0.09676458912266772,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 6.5184,
|
||
|
|
"mean_token_accuracy": 0.100522430986166,
|
||
|
|
"num_tokens": 2120355.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7309898853302,
|
||
|
|
"epoch": 0.09726081778483525,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 6.3974,
|
||
|
|
"mean_token_accuracy": 0.10792523175477982,
|
||
|
|
"num_tokens": 2130861.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.701409101486206,
|
||
|
|
"epoch": 0.09775704644700278,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.561,
|
||
|
|
"mean_token_accuracy": 0.10112565234303475,
|
||
|
|
"num_tokens": 2142162.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.733495473861694,
|
||
|
|
"epoch": 0.0982532751091703,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.4792,
|
||
|
|
"mean_token_accuracy": 0.10216469764709472,
|
||
|
|
"num_tokens": 2153374.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.732190895080566,
|
||
|
|
"epoch": 0.09874950377133783,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.4011,
|
||
|
|
"mean_token_accuracy": 0.10262768343091011,
|
||
|
|
"num_tokens": 2162941.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.757260656356811,
|
||
|
|
"epoch": 0.09924573243350536,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.5,
|
||
|
|
"mean_token_accuracy": 0.09760607853531837,
|
||
|
|
"num_tokens": 2172864.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.697972249984741,
|
||
|
|
"epoch": 0.09974196109567289,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004999999982145551,
|
||
|
|
"loss": 6.5121,
|
||
|
|
"mean_token_accuracy": 0.10802309364080429,
|
||
|
|
"num_tokens": 2184219.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.768112850189209,
|
||
|
|
"epoch": 0.1002381897578404,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999999909611855,
|
||
|
|
"loss": 6.4823,
|
||
|
|
"mean_token_accuracy": 0.09585310667753219,
|
||
|
|
"num_tokens": 2194788.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.702127504348755,
|
||
|
|
"epoch": 0.10073441842000794,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999999781283008,
|
||
|
|
"loss": 6.4988,
|
||
|
|
"mean_token_accuracy": 0.09752344265580178,
|
||
|
|
"num_tokens": 2205493.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.653623962402344,
|
||
|
|
"epoch": 0.10123064708217547,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004999999597159017,
|
||
|
|
"loss": 6.4934,
|
||
|
|
"mean_token_accuracy": 0.10524687170982361,
|
||
|
|
"num_tokens": 2215354.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.642564010620117,
|
||
|
|
"epoch": 0.101726875744343,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004999999357239882,
|
||
|
|
"loss": 6.4358,
|
||
|
|
"mean_token_accuracy": 0.1029872551560402,
|
||
|
|
"num_tokens": 2225781.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.660511827468872,
|
||
|
|
"epoch": 0.10222310440651051,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004999999061525612,
|
||
|
|
"loss": 6.5018,
|
||
|
|
"mean_token_accuracy": 0.10526410788297653,
|
||
|
|
"num_tokens": 2236008.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.666350555419922,
|
||
|
|
"epoch": 0.10271933306867805,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999998710016214,
|
||
|
|
"loss": 6.4144,
|
||
|
|
"mean_token_accuracy": 0.10993591621518135,
|
||
|
|
"num_tokens": 2246998.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.685410451889038,
|
||
|
|
"epoch": 0.10321556173084558,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999998302711696,
|
||
|
|
"loss": 6.537,
|
||
|
|
"mean_token_accuracy": 0.09969183057546616,
|
||
|
|
"num_tokens": 2257451.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.716910266876221,
|
||
|
|
"epoch": 0.1037117903930131,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999997839612069,
|
||
|
|
"loss": 6.515,
|
||
|
|
"mean_token_accuracy": 0.10016707330942154,
|
||
|
|
"num_tokens": 2268151.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.784289979934693,
|
||
|
|
"epoch": 0.10420801905518062,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004999997320717342,
|
||
|
|
"loss": 6.5271,
|
||
|
|
"mean_token_accuracy": 0.09749956205487251,
|
||
|
|
"num_tokens": 2278924.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.590696668624878,
|
||
|
|
"epoch": 0.10470424771734815,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999996746027531,
|
||
|
|
"loss": 6.4375,
|
||
|
|
"mean_token_accuracy": 0.10931600704789161,
|
||
|
|
"num_tokens": 2289229.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.65490140914917,
|
||
|
|
"epoch": 0.10520047637951568,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000499999611554265,
|
||
|
|
"loss": 6.4772,
|
||
|
|
"mean_token_accuracy": 0.0997220940887928,
|
||
|
|
"num_tokens": 2300203.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.689665460586548,
|
||
|
|
"epoch": 0.10569670504168321,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999995429262712,
|
||
|
|
"loss": 6.4325,
|
||
|
|
"mean_token_accuracy": 0.10597841739654541,
|
||
|
|
"num_tokens": 2311991.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5814300060272215,
|
||
|
|
"epoch": 0.10619293370385073,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999994687187737,
|
||
|
|
"loss": 6.4177,
|
||
|
|
"mean_token_accuracy": 0.10108351483941078,
|
||
|
|
"num_tokens": 2322110.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7269233703613285,
|
||
|
|
"epoch": 0.10668916236601826,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999993889317742,
|
||
|
|
"loss": 6.4664,
|
||
|
|
"mean_token_accuracy": 0.10983085185289383,
|
||
|
|
"num_tokens": 2332439.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.517318058013916,
|
||
|
|
"epoch": 0.10718539102818579,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999993035652746,
|
||
|
|
"loss": 6.3221,
|
||
|
|
"mean_token_accuracy": 0.11178816556930542,
|
||
|
|
"num_tokens": 2342339.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.633081340789795,
|
||
|
|
"epoch": 0.10768161969035331,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999992126192771,
|
||
|
|
"loss": 6.4596,
|
||
|
|
"mean_token_accuracy": 0.10636994913220406,
|
||
|
|
"num_tokens": 2353211.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.709958791732788,
|
||
|
|
"epoch": 0.10817784835252084,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.000499999116093784,
|
||
|
|
"loss": 6.4886,
|
||
|
|
"mean_token_accuracy": 0.10582839027047157,
|
||
|
|
"num_tokens": 2364709.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.638761806488037,
|
||
|
|
"epoch": 0.10867407701468837,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999990139887976,
|
||
|
|
"loss": 6.4311,
|
||
|
|
"mean_token_accuracy": 0.10091341882944108,
|
||
|
|
"num_tokens": 2375095.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.641486692428589,
|
||
|
|
"epoch": 0.1091703056768559,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004999989063043206,
|
||
|
|
"loss": 6.4043,
|
||
|
|
"mean_token_accuracy": 0.10428427532315254,
|
||
|
|
"num_tokens": 2384206.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.592662334442139,
|
||
|
|
"epoch": 0.10966653433902342,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999987930403555,
|
||
|
|
"loss": 6.3251,
|
||
|
|
"mean_token_accuracy": 0.11068035364151001,
|
||
|
|
"num_tokens": 2395139.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.577283239364624,
|
||
|
|
"epoch": 0.11016276300119095,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999986741969051,
|
||
|
|
"loss": 6.4501,
|
||
|
|
"mean_token_accuracy": 0.09892478436231614,
|
||
|
|
"num_tokens": 2405652.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.707149410247803,
|
||
|
|
"epoch": 0.11065899166335848,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999985497739724,
|
||
|
|
"loss": 6.4528,
|
||
|
|
"mean_token_accuracy": 0.10405765473842621,
|
||
|
|
"num_tokens": 2416386.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.549600219726562,
|
||
|
|
"epoch": 0.11115522032552601,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999984197715606,
|
||
|
|
"loss": 6.471,
|
||
|
|
"mean_token_accuracy": 0.10263076052069664,
|
||
|
|
"num_tokens": 2427807.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.584462308883667,
|
||
|
|
"epoch": 0.11165144898769352,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999982841896728,
|
||
|
|
"loss": 6.3742,
|
||
|
|
"mean_token_accuracy": 0.1078455038368702,
|
||
|
|
"num_tokens": 2439481.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.644891214370728,
|
||
|
|
"epoch": 0.11214767764986106,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999981430283123,
|
||
|
|
"loss": 6.422,
|
||
|
|
"mean_token_accuracy": 0.10707498490810394,
|
||
|
|
"num_tokens": 2449857.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.55607008934021,
|
||
|
|
"epoch": 0.11264390631202859,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004999979962874827,
|
||
|
|
"loss": 6.3453,
|
||
|
|
"mean_token_accuracy": 0.10785013660788537,
|
||
|
|
"num_tokens": 2461569.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.635892677307129,
|
||
|
|
"epoch": 0.11314013497419612,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004999978439671877,
|
||
|
|
"loss": 6.4311,
|
||
|
|
"mean_token_accuracy": 0.10901110246777534,
|
||
|
|
"num_tokens": 2473255.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.633499383926392,
|
||
|
|
"epoch": 0.11363636363636363,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999976860674309,
|
||
|
|
"loss": 6.3833,
|
||
|
|
"mean_token_accuracy": 0.1040490709245205,
|
||
|
|
"num_tokens": 2484473.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.566697025299073,
|
||
|
|
"epoch": 0.11413259229853116,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004999975225882164,
|
||
|
|
"loss": 6.4046,
|
||
|
|
"mean_token_accuracy": 0.10690351948142052,
|
||
|
|
"num_tokens": 2495652.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.65309100151062,
|
||
|
|
"epoch": 0.1146288209606987,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.000499997353529548,
|
||
|
|
"loss": 6.4341,
|
||
|
|
"mean_token_accuracy": 0.10881170257925987,
|
||
|
|
"num_tokens": 2507137.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.535683012008667,
|
||
|
|
"epoch": 0.11512504962286621,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004999971788914303,
|
||
|
|
"loss": 6.3607,
|
||
|
|
"mean_token_accuracy": 0.10740326344966888,
|
||
|
|
"num_tokens": 2517896.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.523780012130738,
|
||
|
|
"epoch": 0.11562127828503374,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004999969986738672,
|
||
|
|
"loss": 6.3629,
|
||
|
|
"mean_token_accuracy": 0.10846158191561699,
|
||
|
|
"num_tokens": 2529976.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.653525257110596,
|
||
|
|
"epoch": 0.11611750694720127,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999968128768634,
|
||
|
|
"loss": 6.4176,
|
||
|
|
"mean_token_accuracy": 0.10163490399718285,
|
||
|
|
"num_tokens": 2540872.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6223382472991945,
|
||
|
|
"epoch": 0.1166137356093688,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999966215004236,
|
||
|
|
"loss": 6.4314,
|
||
|
|
"mean_token_accuracy": 0.1041704148054123,
|
||
|
|
"num_tokens": 2551178.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.540678930282593,
|
||
|
|
"epoch": 0.11710996427153632,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004999964245445522,
|
||
|
|
"loss": 6.3356,
|
||
|
|
"mean_token_accuracy": 0.10806481763720513,
|
||
|
|
"num_tokens": 2561472.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.559564065933228,
|
||
|
|
"epoch": 0.11760619293370385,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004999962220092545,
|
||
|
|
"loss": 6.3357,
|
||
|
|
"mean_token_accuracy": 0.10722169801592826,
|
||
|
|
"num_tokens": 2572717.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.526041793823242,
|
||
|
|
"epoch": 0.11810242159587138,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999960138945351,
|
||
|
|
"loss": 6.2463,
|
||
|
|
"mean_token_accuracy": 0.11155131533741951,
|
||
|
|
"num_tokens": 2582991.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.437657451629638,
|
||
|
|
"epoch": 0.11859865025803891,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999958002003996,
|
||
|
|
"loss": 6.3384,
|
||
|
|
"mean_token_accuracy": 0.11157690584659577,
|
||
|
|
"num_tokens": 2594872.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.519007015228271,
|
||
|
|
"epoch": 0.11909487892020643,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004999955809268529,
|
||
|
|
"loss": 6.3501,
|
||
|
|
"mean_token_accuracy": 0.11119264140725135,
|
||
|
|
"num_tokens": 2605991.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5526268005371096,
|
||
|
|
"epoch": 0.11959110758237396,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999953560739008,
|
||
|
|
"loss": 6.3742,
|
||
|
|
"mean_token_accuracy": 0.10888314321637153,
|
||
|
|
"num_tokens": 2617613.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.564966106414795,
|
||
|
|
"epoch": 0.12008733624454149,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004999951256415485,
|
||
|
|
"loss": 6.4382,
|
||
|
|
"mean_token_accuracy": 0.10179812833666801,
|
||
|
|
"num_tokens": 2627724.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.583070945739746,
|
||
|
|
"epoch": 0.12058356490670902,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.000499994889629802,
|
||
|
|
"loss": 6.3525,
|
||
|
|
"mean_token_accuracy": 0.10510100647807122,
|
||
|
|
"num_tokens": 2638944.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.452510929107666,
|
||
|
|
"epoch": 0.12107979356887653,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000499994648038667,
|
||
|
|
"loss": 6.2019,
|
||
|
|
"mean_token_accuracy": 0.1171508140861988,
|
||
|
|
"num_tokens": 2649132.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.549446058273316,
|
||
|
|
"epoch": 0.12157602223104406,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004999944008681496,
|
||
|
|
"loss": 6.3345,
|
||
|
|
"mean_token_accuracy": 0.10771893933415413,
|
||
|
|
"num_tokens": 2660482.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.59168848991394,
|
||
|
|
"epoch": 0.1220722508932116,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004999941481182559,
|
||
|
|
"loss": 6.4071,
|
||
|
|
"mean_token_accuracy": 0.10588582754135131,
|
||
|
|
"num_tokens": 2672953.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.458992004394531,
|
||
|
|
"epoch": 0.12256847955537911,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999938897889921,
|
||
|
|
"loss": 6.3076,
|
||
|
|
"mean_token_accuracy": 0.11501472815871239,
|
||
|
|
"num_tokens": 2684958.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5847851753234865,
|
||
|
|
"epoch": 0.12306470821754664,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999936258803647,
|
||
|
|
"loss": 6.3103,
|
||
|
|
"mean_token_accuracy": 0.10793442577123642,
|
||
|
|
"num_tokens": 2695375.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.559399366378784,
|
||
|
|
"epoch": 0.12356093687971417,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999933563923802,
|
||
|
|
"loss": 6.4781,
|
||
|
|
"mean_token_accuracy": 0.10172695145010949,
|
||
|
|
"num_tokens": 2707762.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5289863586425785,
|
||
|
|
"epoch": 0.1240571655418817,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999930813250451,
|
||
|
|
"loss": 6.309,
|
||
|
|
"mean_token_accuracy": 0.10860389918088913,
|
||
|
|
"num_tokens": 2718237.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.479602432250976,
|
||
|
|
"epoch": 0.12455339420404922,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999928006783667,
|
||
|
|
"loss": 6.278,
|
||
|
|
"mean_token_accuracy": 0.11147248297929764,
|
||
|
|
"num_tokens": 2728746.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.495798921585083,
|
||
|
|
"epoch": 0.12504962286621676,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999925144523515,
|
||
|
|
"loss": 6.281,
|
||
|
|
"mean_token_accuracy": 0.10627977550029755,
|
||
|
|
"num_tokens": 2739030.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.411447954177857,
|
||
|
|
"epoch": 0.12554585152838427,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004999922226470066,
|
||
|
|
"loss": 6.2412,
|
||
|
|
"mean_token_accuracy": 0.11322782710194587,
|
||
|
|
"num_tokens": 2750233.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.518495082855225,
|
||
|
|
"epoch": 0.1260420801905518,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004999919252623397,
|
||
|
|
"loss": 6.3145,
|
||
|
|
"mean_token_accuracy": 0.10560797899961472,
|
||
|
|
"num_tokens": 2761298.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.510967969894409,
|
||
|
|
"epoch": 0.12653830885271933,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999916222983577,
|
||
|
|
"loss": 6.3645,
|
||
|
|
"mean_token_accuracy": 0.10636256784200668,
|
||
|
|
"num_tokens": 2771493.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.477094602584839,
|
||
|
|
"epoch": 0.12703453751488686,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.0004999913137550682,
|
||
|
|
"loss": 6.271,
|
||
|
|
"mean_token_accuracy": 0.10662685185670853,
|
||
|
|
"num_tokens": 2782969.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5462244033813475,
|
||
|
|
"epoch": 0.1275307661770544,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004999909996324791,
|
||
|
|
"loss": 6.2984,
|
||
|
|
"mean_token_accuracy": 0.11486872658133507,
|
||
|
|
"num_tokens": 2793355.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.421256589889526,
|
||
|
|
"epoch": 0.12802699483922192,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.000499990679930598,
|
||
|
|
"loss": 6.2118,
|
||
|
|
"mean_token_accuracy": 0.11601667776703835,
|
||
|
|
"num_tokens": 2804473.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.47119288444519,
|
||
|
|
"epoch": 0.12852322350138945,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004999903546494327,
|
||
|
|
"loss": 6.2858,
|
||
|
|
"mean_token_accuracy": 0.10927127152681351,
|
||
|
|
"num_tokens": 2814899.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.552784252166748,
|
||
|
|
"epoch": 0.12901945216355698,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004999900237889916,
|
||
|
|
"loss": 6.3085,
|
||
|
|
"mean_token_accuracy": 0.11181130483746529,
|
||
|
|
"num_tokens": 2825592.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.395250940322876,
|
||
|
|
"epoch": 0.12951568082572448,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999896873492827,
|
||
|
|
"loss": 6.3107,
|
||
|
|
"mean_token_accuracy": 0.11031345725059509,
|
||
|
|
"num_tokens": 2837444.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5371500015258786,
|
||
|
|
"epoch": 0.130011909487892,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.0004999893453303143,
|
||
|
|
"loss": 6.3052,
|
||
|
|
"mean_token_accuracy": 0.10789528265595436,
|
||
|
|
"num_tokens": 2849256.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.516609334945679,
|
||
|
|
"epoch": 0.13050813815005954,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004999889977320949,
|
||
|
|
"loss": 6.3508,
|
||
|
|
"mean_token_accuracy": 0.10912716761231422,
|
||
|
|
"num_tokens": 2860606.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.436788082122803,
|
||
|
|
"epoch": 0.13100436681222707,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.0004999886445546332,
|
||
|
|
"loss": 6.2797,
|
||
|
|
"mean_token_accuracy": 0.11875139251351356,
|
||
|
|
"num_tokens": 2871825.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.539361381530762,
|
||
|
|
"epoch": 0.1315005954743946,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.000499988285797938,
|
||
|
|
"loss": 6.3158,
|
||
|
|
"mean_token_accuracy": 0.11384041458368302,
|
||
|
|
"num_tokens": 2883408.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.459595441818237,
|
||
|
|
"epoch": 0.13199682413656214,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.000499987921462018,
|
||
|
|
"loss": 6.2928,
|
||
|
|
"mean_token_accuracy": 0.11346368417143822,
|
||
|
|
"num_tokens": 2895786.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4756751537323,
|
||
|
|
"epoch": 0.13249305279872967,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999875515468825,
|
||
|
|
"loss": 6.2804,
|
||
|
|
"mean_token_accuracy": 0.11255847290158272,
|
||
|
|
"num_tokens": 2905273.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.56948299407959,
|
||
|
|
"epoch": 0.13298928146089717,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999871760525403,
|
||
|
|
"loss": 6.3865,
|
||
|
|
"mean_token_accuracy": 0.105442725867033,
|
||
|
|
"num_tokens": 2917546.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5599915981292725,
|
||
|
|
"epoch": 0.1334855101230647,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999867949790011,
|
||
|
|
"loss": 6.3222,
|
||
|
|
"mean_token_accuracy": 0.11331170350313187,
|
||
|
|
"num_tokens": 2928715.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.435283613204956,
|
||
|
|
"epoch": 0.13398173878523223,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004999864083262743,
|
||
|
|
"loss": 6.2668,
|
||
|
|
"mean_token_accuracy": 0.1143470786511898,
|
||
|
|
"num_tokens": 2940260.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.487202262878418,
|
||
|
|
"epoch": 0.13447796744739976,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004999860160943691,
|
||
|
|
"loss": 6.2601,
|
||
|
|
"mean_token_accuracy": 0.11385833024978638,
|
||
|
|
"num_tokens": 2951543.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.443022680282593,
|
||
|
|
"epoch": 0.1349741961095673,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004999856182832958,
|
||
|
|
"loss": 6.306,
|
||
|
|
"mean_token_accuracy": 0.11349669769406319,
|
||
|
|
"num_tokens": 2962504.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.441706657409668,
|
||
|
|
"epoch": 0.13547042477173482,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004999852148930637,
|
||
|
|
"loss": 6.2202,
|
||
|
|
"mean_token_accuracy": 0.11742114797234535,
|
||
|
|
"num_tokens": 2973784.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.491312503814697,
|
||
|
|
"epoch": 0.13596665343390235,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999848059236832,
|
||
|
|
"loss": 6.3388,
|
||
|
|
"mean_token_accuracy": 0.10710015147924423,
|
||
|
|
"num_tokens": 2985281.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.395635318756104,
|
||
|
|
"epoch": 0.13646288209606988,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004999843913751643,
|
||
|
|
"loss": 6.1979,
|
||
|
|
"mean_token_accuracy": 0.11877716705203056,
|
||
|
|
"num_tokens": 2996090.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.510016632080078,
|
||
|
|
"epoch": 0.13695911075823738,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999839712475174,
|
||
|
|
"loss": 6.2469,
|
||
|
|
"mean_token_accuracy": 0.11208310946822167,
|
||
|
|
"num_tokens": 3006235.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3472301959991455,
|
||
|
|
"epoch": 0.13745533942040492,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004999835455407526,
|
||
|
|
"loss": 6.1965,
|
||
|
|
"mean_token_accuracy": 0.11313682422041893,
|
||
|
|
"num_tokens": 3016481.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.527986335754394,
|
||
|
|
"epoch": 0.13795156808257245,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999831142548808,
|
||
|
|
"loss": 6.2562,
|
||
|
|
"mean_token_accuracy": 0.11551145687699318,
|
||
|
|
"num_tokens": 3026382.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.418882274627686,
|
||
|
|
"epoch": 0.13844779674473998,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999826773899124,
|
||
|
|
"loss": 6.2683,
|
||
|
|
"mean_token_accuracy": 0.10792074427008629,
|
||
|
|
"num_tokens": 3036637.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.469444751739502,
|
||
|
|
"epoch": 0.1389440254069075,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004999822349458586,
|
||
|
|
"loss": 6.3248,
|
||
|
|
"mean_token_accuracy": 0.10550551563501358,
|
||
|
|
"num_tokens": 3047115.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.574054908752442,
|
||
|
|
"epoch": 0.13944025406907504,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999817869227301,
|
||
|
|
"loss": 6.3377,
|
||
|
|
"mean_token_accuracy": 0.11256245598196983,
|
||
|
|
"num_tokens": 3057499.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4168126583099365,
|
||
|
|
"epoch": 0.13993648273124257,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004999813333205381,
|
||
|
|
"loss": 6.2538,
|
||
|
|
"mean_token_accuracy": 0.11392025426030158,
|
||
|
|
"num_tokens": 3068503.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.42028923034668,
|
||
|
|
"epoch": 0.14043271139341007,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004999808741392937,
|
||
|
|
"loss": 6.2314,
|
||
|
|
"mean_token_accuracy": 0.11181280761957169,
|
||
|
|
"num_tokens": 3079220.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.359934759140015,
|
||
|
|
"epoch": 0.1409289400555776,
|
||
|
|
"grad_norm": 0.765625,
|
||
|
|
"learning_rate": 0.0004999804093790086,
|
||
|
|
"loss": 6.2197,
|
||
|
|
"mean_token_accuracy": 0.11571786925196648,
|
||
|
|
"num_tokens": 3091621.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.446488618850708,
|
||
|
|
"epoch": 0.14142516871774513,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.000499979939039694,
|
||
|
|
"loss": 6.2005,
|
||
|
|
"mean_token_accuracy": 0.11424326300621032,
|
||
|
|
"num_tokens": 3101378.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.348664093017578,
|
||
|
|
"epoch": 0.14192139737991266,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004999794631213618,
|
||
|
|
"loss": 6.2166,
|
||
|
|
"mean_token_accuracy": 0.11557507440447808,
|
||
|
|
"num_tokens": 3112996.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.414705753326416,
|
||
|
|
"epoch": 0.1424176260420802,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999789816240236,
|
||
|
|
"loss": 6.2043,
|
||
|
|
"mean_token_accuracy": 0.10700563341379166,
|
||
|
|
"num_tokens": 3124262.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.345302104949951,
|
||
|
|
"epoch": 0.14291385470424772,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004999784945476915,
|
||
|
|
"loss": 6.2497,
|
||
|
|
"mean_token_accuracy": 0.10843175053596496,
|
||
|
|
"num_tokens": 3135785.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.416088008880616,
|
||
|
|
"epoch": 0.14341008336641525,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004999780018923775,
|
||
|
|
"loss": 6.0994,
|
||
|
|
"mean_token_accuracy": 0.12602320015430452,
|
||
|
|
"num_tokens": 3146841.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.290076351165771,
|
||
|
|
"epoch": 0.14390631202858278,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999775036580939,
|
||
|
|
"loss": 6.2572,
|
||
|
|
"mean_token_accuracy": 0.10866076126694679,
|
||
|
|
"num_tokens": 3158931.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.446962547302246,
|
||
|
|
"epoch": 0.1444025406907503,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004999769998448529,
|
||
|
|
"loss": 6.1983,
|
||
|
|
"mean_token_accuracy": 0.11449775323271752,
|
||
|
|
"num_tokens": 3169320.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4680766582489015,
|
||
|
|
"epoch": 0.14489876935291782,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999764904526672,
|
||
|
|
"loss": 6.2332,
|
||
|
|
"mean_token_accuracy": 0.11214599311351776,
|
||
|
|
"num_tokens": 3179163.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.34765396118164,
|
||
|
|
"epoch": 0.14539499801508535,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004999759754815492,
|
||
|
|
"loss": 6.1782,
|
||
|
|
"mean_token_accuracy": 0.11042089611291886,
|
||
|
|
"num_tokens": 3187987.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.372549295425415,
|
||
|
|
"epoch": 0.14589122667725288,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004999754549315118,
|
||
|
|
"loss": 6.1683,
|
||
|
|
"mean_token_accuracy": 0.11804649159312249,
|
||
|
|
"num_tokens": 3198052.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2816180229187015,
|
||
|
|
"epoch": 0.1463874553394204,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.000499974928802568,
|
||
|
|
"loss": 6.1512,
|
||
|
|
"mean_token_accuracy": 0.11864635944366456,
|
||
|
|
"num_tokens": 3209019.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.298905229568481,
|
||
|
|
"epoch": 0.14688368400158794,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999743970947306,
|
||
|
|
"loss": 6.1034,
|
||
|
|
"mean_token_accuracy": 0.12014764696359634,
|
||
|
|
"num_tokens": 3219130.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.288952350616455,
|
||
|
|
"epoch": 0.14737991266375547,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.000499973859808013,
|
||
|
|
"loss": 6.1357,
|
||
|
|
"mean_token_accuracy": 0.11747602671384812,
|
||
|
|
"num_tokens": 3230882.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3970338821411135,
|
||
|
|
"epoch": 0.14787614132592297,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0004999733169424284,
|
||
|
|
"loss": 6.2601,
|
||
|
|
"mean_token_accuracy": 0.11354640573263168,
|
||
|
|
"num_tokens": 3241752.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.496769285202026,
|
||
|
|
"epoch": 0.1483723699880905,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004999727684979904,
|
||
|
|
"loss": 6.2828,
|
||
|
|
"mean_token_accuracy": 0.1073771022260189,
|
||
|
|
"num_tokens": 3252291.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.41784029006958,
|
||
|
|
"epoch": 0.14886859865025803,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.0004999722144747125,
|
||
|
|
"loss": 6.1967,
|
||
|
|
"mean_token_accuracy": 0.12008021101355552,
|
||
|
|
"num_tokens": 3263525.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.366907787322998,
|
||
|
|
"epoch": 0.14936482731242556,
|
||
|
|
"grad_norm": 0.7734375,
|
||
|
|
"learning_rate": 0.0004999716548726085,
|
||
|
|
"loss": 6.1538,
|
||
|
|
"mean_token_accuracy": 0.11907590329647064,
|
||
|
|
"num_tokens": 3274164.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2786328315734865,
|
||
|
|
"epoch": 0.1498610559745931,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004999710896916921,
|
||
|
|
"loss": 6.1281,
|
||
|
|
"mean_token_accuracy": 0.120063366740942,
|
||
|
|
"num_tokens": 3286244.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.408924198150634,
|
||
|
|
"epoch": 0.15035728463676062,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004999705189319774,
|
||
|
|
"loss": 6.2339,
|
||
|
|
"mean_token_accuracy": 0.10920965149998665,
|
||
|
|
"num_tokens": 3296569.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.31035418510437,
|
||
|
|
"epoch": 0.15085351329892815,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0004999699425934788,
|
||
|
|
"loss": 6.2497,
|
||
|
|
"mean_token_accuracy": 0.11545195132493973,
|
||
|
|
"num_tokens": 3307259.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3992188453674315,
|
||
|
|
"epoch": 0.15134974196109569,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004999693606762103,
|
||
|
|
"loss": 6.0531,
|
||
|
|
"mean_token_accuracy": 0.12170021310448646,
|
||
|
|
"num_tokens": 3317473.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.274422454833984,
|
||
|
|
"epoch": 0.1518459706232632,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004999687731801865,
|
||
|
|
"loss": 6.1779,
|
||
|
|
"mean_token_accuracy": 0.11477752849459648,
|
||
|
|
"num_tokens": 3328783.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.309112119674682,
|
||
|
|
"epoch": 0.15234219928543072,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004999681801054217,
|
||
|
|
"loss": 6.2142,
|
||
|
|
"mean_token_accuracy": 0.11577230393886566,
|
||
|
|
"num_tokens": 3338308.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.423832416534424,
|
||
|
|
"epoch": 0.15283842794759825,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.000499967581451931,
|
||
|
|
"loss": 6.1213,
|
||
|
|
"mean_token_accuracy": 0.11633878573775291,
|
||
|
|
"num_tokens": 3348802.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.263744926452636,
|
||
|
|
"epoch": 0.15333465660976578,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.000499966977219729,
|
||
|
|
"loss": 6.1365,
|
||
|
|
"mean_token_accuracy": 0.11869108527898789,
|
||
|
|
"num_tokens": 3358781.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3492378234863285,
|
||
|
|
"epoch": 0.1538308852719333,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999663674088306,
|
||
|
|
"loss": 6.0753,
|
||
|
|
"mean_token_accuracy": 0.12006449326872826,
|
||
|
|
"num_tokens": 3369360.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.379684591293335,
|
||
|
|
"epoch": 0.15432711393410084,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004999657520192511,
|
||
|
|
"loss": 6.1884,
|
||
|
|
"mean_token_accuracy": 0.11728774011135101,
|
||
|
|
"num_tokens": 3380111.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.255392026901245,
|
||
|
|
"epoch": 0.15482334259626837,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004999651310510058,
|
||
|
|
"loss": 6.1373,
|
||
|
|
"mean_token_accuracy": 0.11838044002652168,
|
||
|
|
"num_tokens": 3391932.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3688195705413815,
|
||
|
|
"epoch": 0.15531957125843587,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.0004999645045041099,
|
||
|
|
"loss": 6.1855,
|
||
|
|
"mean_token_accuracy": 0.11579569801688194,
|
||
|
|
"num_tokens": 3402192.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.375439691543579,
|
||
|
|
"epoch": 0.1558157999206034,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004999638723785791,
|
||
|
|
"loss": 6.0869,
|
||
|
|
"mean_token_accuracy": 0.1146264374256134,
|
||
|
|
"num_tokens": 3412382.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.255414152145386,
|
||
|
|
"epoch": 0.15631202858277093,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000499963234674429,
|
||
|
|
"loss": 6.1256,
|
||
|
|
"mean_token_accuracy": 0.11626426354050637,
|
||
|
|
"num_tokens": 3422471.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.325457906723022,
|
||
|
|
"epoch": 0.15680825724493846,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004999625913916754,
|
||
|
|
"loss": 6.1156,
|
||
|
|
"mean_token_accuracy": 0.12189654409885406,
|
||
|
|
"num_tokens": 3432348.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.290401220321655,
|
||
|
|
"epoch": 0.157304485907106,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999619425303343,
|
||
|
|
"loss": 6.1179,
|
||
|
|
"mean_token_accuracy": 0.1161232702434063,
|
||
|
|
"num_tokens": 3442549.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2806614398956295,
|
||
|
|
"epoch": 0.15780071456927353,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999612880904219,
|
||
|
|
"loss": 6.1954,
|
||
|
|
"mean_token_accuracy": 0.11219574809074402,
|
||
|
|
"num_tokens": 3452317.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3340983390808105,
|
||
|
|
"epoch": 0.15829694323144106,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0004999606280719542,
|
||
|
|
"loss": 6.1293,
|
||
|
|
"mean_token_accuracy": 0.1172614224255085,
|
||
|
|
"num_tokens": 3463432.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.395657205581665,
|
||
|
|
"epoch": 0.1587931718936086,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004999599624749475,
|
||
|
|
"loss": 6.1889,
|
||
|
|
"mean_token_accuracy": 0.11410781070590019,
|
||
|
|
"num_tokens": 3473800.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.311441802978516,
|
||
|
|
"epoch": 0.1592894005557761,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004999592912994187,
|
||
|
|
"loss": 6.171,
|
||
|
|
"mean_token_accuracy": 0.1144875705242157,
|
||
|
|
"num_tokens": 3484803.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3286027908325195,
|
||
|
|
"epoch": 0.15978562921794362,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999586145453842,
|
||
|
|
"loss": 6.1047,
|
||
|
|
"mean_token_accuracy": 0.1186643548309803,
|
||
|
|
"num_tokens": 3494687.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.32429256439209,
|
||
|
|
"epoch": 0.16028185788011115,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999579322128608,
|
||
|
|
"loss": 6.1522,
|
||
|
|
"mean_token_accuracy": 0.11586391776800156,
|
||
|
|
"num_tokens": 3505586.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.186865186691284,
|
||
|
|
"epoch": 0.16077808654227868,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004999572443018654,
|
||
|
|
"loss": 5.9894,
|
||
|
|
"mean_token_accuracy": 0.13321231454610824,
|
||
|
|
"num_tokens": 3516702.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.295269012451172,
|
||
|
|
"epoch": 0.1612743152044462,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999565508124151,
|
||
|
|
"loss": 6.1263,
|
||
|
|
"mean_token_accuracy": 0.11919939890503883,
|
||
|
|
"num_tokens": 3527240.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.314893007278442,
|
||
|
|
"epoch": 0.16177054386661374,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.000499955851744527,
|
||
|
|
"loss": 6.2405,
|
||
|
|
"mean_token_accuracy": 0.11684711053967475,
|
||
|
|
"num_tokens": 3539368.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3168638229370115,
|
||
|
|
"epoch": 0.16226677252878127,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004999551470982185,
|
||
|
|
"loss": 6.1061,
|
||
|
|
"mean_token_accuracy": 0.11994773149490356,
|
||
|
|
"num_tokens": 3551128.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.26086835861206,
|
||
|
|
"epoch": 0.1627630011909488,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999544368735073,
|
||
|
|
"loss": 6.1133,
|
||
|
|
"mean_token_accuracy": 0.11799252703785897,
|
||
|
|
"num_tokens": 3562385.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.35860800743103,
|
||
|
|
"epoch": 0.1632592298531163,
|
||
|
|
"grad_norm": 0.78515625,
|
||
|
|
"learning_rate": 0.0004999537210704106,
|
||
|
|
"loss": 6.107,
|
||
|
|
"mean_token_accuracy": 0.11943186968564987,
|
||
|
|
"num_tokens": 3572737.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.24028697013855,
|
||
|
|
"epoch": 0.16375545851528384,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004999529996889463,
|
||
|
|
"loss": 6.1151,
|
||
|
|
"mean_token_accuracy": 0.11283019334077835,
|
||
|
|
"num_tokens": 3583872.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.313495445251465,
|
||
|
|
"epoch": 0.16425168717745137,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004999522727291325,
|
||
|
|
"loss": 6.1013,
|
||
|
|
"mean_token_accuracy": 0.11968362778425216,
|
||
|
|
"num_tokens": 3595012.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.366147470474243,
|
||
|
|
"epoch": 0.1647479158396189,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.000499951540190987,
|
||
|
|
"loss": 6.209,
|
||
|
|
"mean_token_accuracy": 0.11140498891472816,
|
||
|
|
"num_tokens": 3605733.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.24420485496521,
|
||
|
|
"epoch": 0.16524414450178643,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004999508020745281,
|
||
|
|
"loss": 6.1366,
|
||
|
|
"mean_token_accuracy": 0.1271058052778244,
|
||
|
|
"num_tokens": 3615997.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.272862815856934,
|
||
|
|
"epoch": 0.16574037316395396,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004999500583797739,
|
||
|
|
"loss": 6.1016,
|
||
|
|
"mean_token_accuracy": 0.12369741126894951,
|
||
|
|
"num_tokens": 3628742.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.227112102508545,
|
||
|
|
"epoch": 0.1662366018261215,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999493091067431,
|
||
|
|
"loss": 6.1043,
|
||
|
|
"mean_token_accuracy": 0.12184740528464318,
|
||
|
|
"num_tokens": 3639702.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.369050741195679,
|
||
|
|
"epoch": 0.166732830488289,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004999485542554541,
|
||
|
|
"loss": 6.0985,
|
||
|
|
"mean_token_accuracy": 0.11733277067542076,
|
||
|
|
"num_tokens": 3650414.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.190679216384888,
|
||
|
|
"epoch": 0.16722905915045652,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0004999477938259256,
|
||
|
|
"loss": 6.0631,
|
||
|
|
"mean_token_accuracy": 0.11306010484695435,
|
||
|
|
"num_tokens": 3660739.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.306669664382935,
|
||
|
|
"epoch": 0.16772528781262405,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0004999470278181766,
|
||
|
|
"loss": 6.1382,
|
||
|
|
"mean_token_accuracy": 0.12038198262453079,
|
||
|
|
"num_tokens": 3673109.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.293005657196045,
|
||
|
|
"epoch": 0.16822151647479158,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999462562322261,
|
||
|
|
"loss": 6.1175,
|
||
|
|
"mean_token_accuracy": 0.1181846633553505,
|
||
|
|
"num_tokens": 3683168.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.264427709579468,
|
||
|
|
"epoch": 0.1687177451369591,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.000499945479068093,
|
||
|
|
"loss": 6.1092,
|
||
|
|
"mean_token_accuracy": 0.11897704154253005,
|
||
|
|
"num_tokens": 3694309.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.261802101135254,
|
||
|
|
"epoch": 0.16921397379912664,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004999446963257969,
|
||
|
|
"loss": 6.1845,
|
||
|
|
"mean_token_accuracy": 0.11810654923319816,
|
||
|
|
"num_tokens": 3706165.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.351796007156372,
|
||
|
|
"epoch": 0.16971020246129417,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0004999439080053571,
|
||
|
|
"loss": 6.1929,
|
||
|
|
"mean_token_accuracy": 0.11733902394771575,
|
||
|
|
"num_tokens": 3717818.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.290229082107544,
|
||
|
|
"epoch": 0.1702064311234617,
|
||
|
|
"grad_norm": 0.98046875,
|
||
|
|
"learning_rate": 0.0004999431141067928,
|
||
|
|
"loss": 6.0696,
|
||
|
|
"mean_token_accuracy": 0.11890798285603524,
|
||
|
|
"num_tokens": 3727837.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.205497550964355,
|
||
|
|
"epoch": 0.1707026597856292,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004999423146301242,
|
||
|
|
"loss": 6.0576,
|
||
|
|
"mean_token_accuracy": 0.11845887154340744,
|
||
|
|
"num_tokens": 3738827.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.330425024032593,
|
||
|
|
"epoch": 0.17119888844779674,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004999415095753709,
|
||
|
|
"loss": 6.0668,
|
||
|
|
"mean_token_accuracy": 0.11846604123711586,
|
||
|
|
"num_tokens": 3749859.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.18771653175354,
|
||
|
|
"epoch": 0.17169511710996427,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999406989425527,
|
||
|
|
"loss": 6.0777,
|
||
|
|
"mean_token_accuracy": 0.11917969733476638,
|
||
|
|
"num_tokens": 3760999.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.328619718551636,
|
||
|
|
"epoch": 0.1721913457721318,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004999398827316901,
|
||
|
|
"loss": 6.1057,
|
||
|
|
"mean_token_accuracy": 0.11780516654253007,
|
||
|
|
"num_tokens": 3771541.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.212802362442017,
|
||
|
|
"epoch": 0.17268757443429933,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.000499939060942803,
|
||
|
|
"loss": 6.0552,
|
||
|
|
"mean_token_accuracy": 0.12180277779698372,
|
||
|
|
"num_tokens": 3781503.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.240700149536133,
|
||
|
|
"epoch": 0.17318380309646686,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999382335759119,
|
||
|
|
"loss": 6.127,
|
||
|
|
"mean_token_accuracy": 0.11963073760271073,
|
||
|
|
"num_tokens": 3791278.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.374361801147461,
|
||
|
|
"epoch": 0.1736800317586344,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004999374006310372,
|
||
|
|
"loss": 6.1482,
|
||
|
|
"mean_token_accuracy": 0.12124232724308967,
|
||
|
|
"num_tokens": 3802995.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.22139801979065,
|
||
|
|
"epoch": 0.1741762604208019,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004999365621081999,
|
||
|
|
"loss": 6.1014,
|
||
|
|
"mean_token_accuracy": 0.12158005386590957,
|
||
|
|
"num_tokens": 3813912.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.329367971420288,
|
||
|
|
"epoch": 0.17467248908296942,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004999357180074204,
|
||
|
|
"loss": 6.0405,
|
||
|
|
"mean_token_accuracy": 0.11887364089488983,
|
||
|
|
"num_tokens": 3823513.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.203952169418335,
|
||
|
|
"epoch": 0.17516871774513695,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.0004999348683287199,
|
||
|
|
"loss": 6.0567,
|
||
|
|
"mean_token_accuracy": 0.12055648267269134,
|
||
|
|
"num_tokens": 3835602.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.282654809951782,
|
||
|
|
"epoch": 0.17566494640730448,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0004999340130721192,
|
||
|
|
"loss": 6.1153,
|
||
|
|
"mean_token_accuracy": 0.11746885254979134,
|
||
|
|
"num_tokens": 3847031.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1639931201934814,
|
||
|
|
"epoch": 0.17616117506947201,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999331522376396,
|
||
|
|
"loss": 5.9808,
|
||
|
|
"mean_token_accuracy": 0.11802588552236556,
|
||
|
|
"num_tokens": 3857714.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.25999174118042,
|
||
|
|
"epoch": 0.17665740373163955,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.0004999322858253027,
|
||
|
|
"loss": 6.0745,
|
||
|
|
"mean_token_accuracy": 0.12271984964609146,
|
||
|
|
"num_tokens": 3868818.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.28449068069458,
|
||
|
|
"epoch": 0.17715363239380708,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004999314138351297,
|
||
|
|
"loss": 6.1107,
|
||
|
|
"mean_token_accuracy": 0.12038928046822547,
|
||
|
|
"num_tokens": 3878802.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.277543830871582,
|
||
|
|
"epoch": 0.1776498610559746,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004999305362671424,
|
||
|
|
"loss": 6.1207,
|
||
|
|
"mean_token_accuracy": 0.11644105166196823,
|
||
|
|
"num_tokens": 3890045.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.266772079467773,
|
||
|
|
"epoch": 0.1781460897181421,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004999296531213624,
|
||
|
|
"loss": 6.0013,
|
||
|
|
"mean_token_accuracy": 0.12227872386574745,
|
||
|
|
"num_tokens": 3901429.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.185096502304077,
|
||
|
|
"epoch": 0.17864231838030964,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004999287643978117,
|
||
|
|
"loss": 5.9674,
|
||
|
|
"mean_token_accuracy": 0.12167818248271942,
|
||
|
|
"num_tokens": 3912201.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.186278486251831,
|
||
|
|
"epoch": 0.17913854704247717,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004999278700965124,
|
||
|
|
"loss": 6.0153,
|
||
|
|
"mean_token_accuracy": 0.12317613437771797,
|
||
|
|
"num_tokens": 3922338.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.213421297073364,
|
||
|
|
"epoch": 0.1796347757046447,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004999269702174866,
|
||
|
|
"loss": 6.0516,
|
||
|
|
"mean_token_accuracy": 0.12139523699879647,
|
||
|
|
"num_tokens": 3934469.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.172092056274414,
|
||
|
|
"epoch": 0.18013100436681223,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004999260647607565,
|
||
|
|
"loss": 6.0251,
|
||
|
|
"mean_token_accuracy": 0.1218095563352108,
|
||
|
|
"num_tokens": 3946136.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.243712377548218,
|
||
|
|
"epoch": 0.18062723302897976,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004999251537263448,
|
||
|
|
"loss": 6.0815,
|
||
|
|
"mean_token_accuracy": 0.12056513875722885,
|
||
|
|
"num_tokens": 3956976.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.264207172393799,
|
||
|
|
"epoch": 0.1811234616911473,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0004999242371142739,
|
||
|
|
"loss": 6.0832,
|
||
|
|
"mean_token_accuracy": 0.12240420579910279,
|
||
|
|
"num_tokens": 3967929.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.104647302627564,
|
||
|
|
"epoch": 0.1816196903533148,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0004999233149245665,
|
||
|
|
"loss": 6.03,
|
||
|
|
"mean_token_accuracy": 0.127287620306015,
|
||
|
|
"num_tokens": 3979585.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.303787088394165,
|
||
|
|
"epoch": 0.18211591901548232,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004999223871572456,
|
||
|
|
"loss": 6.0066,
|
||
|
|
"mean_token_accuracy": 0.12537923753261565,
|
||
|
|
"num_tokens": 3990097.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.271418666839599,
|
||
|
|
"epoch": 0.18261214767764986,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004999214538123342,
|
||
|
|
"loss": 6.0754,
|
||
|
|
"mean_token_accuracy": 0.1204076036810875,
|
||
|
|
"num_tokens": 3999864.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.181163644790649,
|
||
|
|
"epoch": 0.18310837633981739,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004999205148898554,
|
||
|
|
"loss": 6.0935,
|
||
|
|
"mean_token_accuracy": 0.11834281980991364,
|
||
|
|
"num_tokens": 4012986.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.230453109741211,
|
||
|
|
"epoch": 0.18360460500198492,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004999195703898325,
|
||
|
|
"loss": 6.0812,
|
||
|
|
"mean_token_accuracy": 0.12549262940883638,
|
||
|
|
"num_tokens": 4024231.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.205415105819702,
|
||
|
|
"epoch": 0.18410083366415245,
|
||
|
|
"grad_norm": 0.7734375,
|
||
|
|
"learning_rate": 0.0004999186203122889,
|
||
|
|
"loss": 6.0739,
|
||
|
|
"mean_token_accuracy": 0.11859336569905281,
|
||
|
|
"num_tokens": 4035709.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.167673015594483,
|
||
|
|
"epoch": 0.18459706232631998,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004999176646572482,
|
||
|
|
"loss": 5.9531,
|
||
|
|
"mean_token_accuracy": 0.12172793224453926,
|
||
|
|
"num_tokens": 4046504.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.215722465515137,
|
||
|
|
"epoch": 0.1850932909884875,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000499916703424734,
|
||
|
|
"loss": 6.0105,
|
||
|
|
"mean_token_accuracy": 0.11848408207297326,
|
||
|
|
"num_tokens": 4056864.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.213238525390625,
|
||
|
|
"epoch": 0.185589519650655,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0004999157366147702,
|
||
|
|
"loss": 6.0176,
|
||
|
|
"mean_token_accuracy": 0.12398831099271775,
|
||
|
|
"num_tokens": 4067682.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.203938627243042,
|
||
|
|
"epoch": 0.18608574831282254,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004999147642273809,
|
||
|
|
"loss": 6.026,
|
||
|
|
"mean_token_accuracy": 0.12088289335370064,
|
||
|
|
"num_tokens": 4078623.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.248812532424926,
|
||
|
|
"epoch": 0.18658197697499007,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.00049991378626259,
|
||
|
|
"loss": 6.1217,
|
||
|
|
"mean_token_accuracy": 0.1188036285340786,
|
||
|
|
"num_tokens": 4090479.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2731225967407225,
|
||
|
|
"epoch": 0.1870782056371576,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004999128027204219,
|
||
|
|
"loss": 6.0342,
|
||
|
|
"mean_token_accuracy": 0.12075977995991707,
|
||
|
|
"num_tokens": 4100379.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.173857021331787,
|
||
|
|
"epoch": 0.18757443429932513,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000499911813600901,
|
||
|
|
"loss": 6.1629,
|
||
|
|
"mean_token_accuracy": 0.11313794627785682,
|
||
|
|
"num_tokens": 4111738.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.290290641784668,
|
||
|
|
"epoch": 0.18807066296149266,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999108189040516,
|
||
|
|
"loss": 6.1278,
|
||
|
|
"mean_token_accuracy": 0.11461761593818665,
|
||
|
|
"num_tokens": 4123602.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.206590223312378,
|
||
|
|
"epoch": 0.1885668916236602,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004999098186298986,
|
||
|
|
"loss": 6.0744,
|
||
|
|
"mean_token_accuracy": 0.12139438912272453,
|
||
|
|
"num_tokens": 4133558.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.151382112503052,
|
||
|
|
"epoch": 0.1890631202858277,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004999088127784667,
|
||
|
|
"loss": 5.9884,
|
||
|
|
"mean_token_accuracy": 0.12704532966017723,
|
||
|
|
"num_tokens": 4143901.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.201519012451172,
|
||
|
|
"epoch": 0.18955934894799523,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.000499907801349781,
|
||
|
|
"loss": 6.034,
|
||
|
|
"mean_token_accuracy": 0.11795807406306266,
|
||
|
|
"num_tokens": 4154180.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.204054355621338,
|
||
|
|
"epoch": 0.19005557761016276,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004999067843438664,
|
||
|
|
"loss": 5.9706,
|
||
|
|
"mean_token_accuracy": 0.12664248719811438,
|
||
|
|
"num_tokens": 4163540.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.17950029373169,
|
||
|
|
"epoch": 0.1905518062723303,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004999057617607482,
|
||
|
|
"loss": 6.0436,
|
||
|
|
"mean_token_accuracy": 0.12264975383877755,
|
||
|
|
"num_tokens": 4173723.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.263732385635376,
|
||
|
|
"epoch": 0.19104803493449782,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004999047336004517,
|
||
|
|
"loss": 6.0341,
|
||
|
|
"mean_token_accuracy": 0.12559134289622306,
|
||
|
|
"num_tokens": 4184771.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.172854852676392,
|
||
|
|
"epoch": 0.19154426359666535,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004999036998630024,
|
||
|
|
"loss": 6.0439,
|
||
|
|
"mean_token_accuracy": 0.11994816809892654,
|
||
|
|
"num_tokens": 4195791.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.213911008834839,
|
||
|
|
"epoch": 0.19204049225883288,
|
||
|
|
"grad_norm": 0.7421875,
|
||
|
|
"learning_rate": 0.000499902660548426,
|
||
|
|
"loss": 6.0617,
|
||
|
|
"mean_token_accuracy": 0.11922118812799454,
|
||
|
|
"num_tokens": 4207393.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.174426698684693,
|
||
|
|
"epoch": 0.1925367209210004,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.0004999016156567482,
|
||
|
|
"loss": 5.9961,
|
||
|
|
"mean_token_accuracy": 0.12561587989330292,
|
||
|
|
"num_tokens": 4218278.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.258877611160278,
|
||
|
|
"epoch": 0.1930329495831679,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000499900565187995,
|
||
|
|
"loss": 6.1393,
|
||
|
|
"mean_token_accuracy": 0.11696879714727401,
|
||
|
|
"num_tokens": 4229448.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.302958202362061,
|
||
|
|
"epoch": 0.19352917824533544,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004998995091421924,
|
||
|
|
"loss": 6.0653,
|
||
|
|
"mean_token_accuracy": 0.11950641125440598,
|
||
|
|
"num_tokens": 4240750.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1788359642028805,
|
||
|
|
"epoch": 0.19402540690750297,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004998984475193665,
|
||
|
|
"loss": 6.0601,
|
||
|
|
"mean_token_accuracy": 0.12437045946717262,
|
||
|
|
"num_tokens": 4252086.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.237712335586548,
|
||
|
|
"epoch": 0.1945216355696705,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004998973803195439,
|
||
|
|
"loss": 6.0034,
|
||
|
|
"mean_token_accuracy": 0.12056957632303238,
|
||
|
|
"num_tokens": 4262756.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.126477241516113,
|
||
|
|
"epoch": 0.19501786423183803,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998963075427508,
|
||
|
|
"loss": 6.061,
|
||
|
|
"mean_token_accuracy": 0.12428061813116073,
|
||
|
|
"num_tokens": 4272965.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.328072643280029,
|
||
|
|
"epoch": 0.19551409289400556,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004998952291890138,
|
||
|
|
"loss": 6.1214,
|
||
|
|
"mean_token_accuracy": 0.11712106689810753,
|
||
|
|
"num_tokens": 4284465.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1758839130401615,
|
||
|
|
"epoch": 0.1960103215561731,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004998941452583599,
|
||
|
|
"loss": 6.0375,
|
||
|
|
"mean_token_accuracy": 0.12105096429586411,
|
||
|
|
"num_tokens": 4295266.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3052088737487795,
|
||
|
|
"epoch": 0.1965065502183406,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004998930557508156,
|
||
|
|
"loss": 6.0844,
|
||
|
|
"mean_token_accuracy": 0.11636104881763458,
|
||
|
|
"num_tokens": 4306477.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.259469699859619,
|
||
|
|
"epoch": 0.19700277888050813,
|
||
|
|
"grad_norm": 0.71875,
|
||
|
|
"learning_rate": 0.0004998919606664082,
|
||
|
|
"loss": 6.113,
|
||
|
|
"mean_token_accuracy": 0.11556319296360015,
|
||
|
|
"num_tokens": 4319150.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.230728054046631,
|
||
|
|
"epoch": 0.19749900754267566,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004998908600051648,
|
||
|
|
"loss": 6.0739,
|
||
|
|
"mean_token_accuracy": 0.12062246054410934,
|
||
|
|
"num_tokens": 4330679.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.29167947769165,
|
||
|
|
"epoch": 0.1979952362048432,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004998897537671126,
|
||
|
|
"loss": 6.0125,
|
||
|
|
"mean_token_accuracy": 0.12165434509515763,
|
||
|
|
"num_tokens": 4340597.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.019966983795166,
|
||
|
|
"epoch": 0.19849146486701072,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004998886419522792,
|
||
|
|
"loss": 6.0044,
|
||
|
|
"mean_token_accuracy": 0.12512857243418693,
|
||
|
|
"num_tokens": 4351814.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3719175338745115,
|
||
|
|
"epoch": 0.19898769352917825,
|
||
|
|
"grad_norm": 1.59375,
|
||
|
|
"learning_rate": 0.0004998875245606919,
|
||
|
|
"loss": 6.1068,
|
||
|
|
"mean_token_accuracy": 0.12338865548372269,
|
||
|
|
"num_tokens": 4363930.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.162980699539185,
|
||
|
|
"epoch": 0.19948392219134578,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004998864015923788,
|
||
|
|
"loss": 6.0042,
|
||
|
|
"mean_token_accuracy": 0.12410440891981125,
|
||
|
|
"num_tokens": 4376127.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.127772045135498,
|
||
|
|
"epoch": 0.1999801508535133,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004998852730473674,
|
||
|
|
"loss": 5.9963,
|
||
|
|
"mean_token_accuracy": 0.12394299507141113,
|
||
|
|
"num_tokens": 4386095.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.152992010116577,
|
||
|
|
"epoch": 0.2004763795156808,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004998841389256859,
|
||
|
|
"loss": 5.9298,
|
||
|
|
"mean_token_accuracy": 0.12322643324732781,
|
||
|
|
"num_tokens": 4397441.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.104267597198486,
|
||
|
|
"epoch": 0.20097260817784834,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0004998829992273622,
|
||
|
|
"loss": 6.029,
|
||
|
|
"mean_token_accuracy": 0.1249389573931694,
|
||
|
|
"num_tokens": 4408295.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.137422323226929,
|
||
|
|
"epoch": 0.20146883684001587,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004998818539524248,
|
||
|
|
"loss": 6.0172,
|
||
|
|
"mean_token_accuracy": 0.12392294108867645,
|
||
|
|
"num_tokens": 4419307.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.212697267532349,
|
||
|
|
"epoch": 0.2019650655021834,
|
||
|
|
"grad_norm": 0.75390625,
|
||
|
|
"learning_rate": 0.000499880703100902,
|
||
|
|
"loss": 6.0055,
|
||
|
|
"mean_token_accuracy": 0.1231863833963871,
|
||
|
|
"num_tokens": 4431908.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.264675903320312,
|
||
|
|
"epoch": 0.20246129416435094,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0004998795466728223,
|
||
|
|
"loss": 6.0427,
|
||
|
|
"mean_token_accuracy": 0.12163790315389633,
|
||
|
|
"num_tokens": 4443417.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.152185726165771,
|
||
|
|
"epoch": 0.20295752282651847,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004998783846682144,
|
||
|
|
"loss": 6.0887,
|
||
|
|
"mean_token_accuracy": 0.11930633261799813,
|
||
|
|
"num_tokens": 4453224.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.206977796554566,
|
||
|
|
"epoch": 0.203453751488686,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0004998772170871072,
|
||
|
|
"loss": 5.9259,
|
||
|
|
"mean_token_accuracy": 0.128037216514349,
|
||
|
|
"num_tokens": 4463231.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.146184635162354,
|
||
|
|
"epoch": 0.20394998015085353,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004998760439295295,
|
||
|
|
"loss": 5.9802,
|
||
|
|
"mean_token_accuracy": 0.11942070052027702,
|
||
|
|
"num_tokens": 4474397.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1672406673431395,
|
||
|
|
"epoch": 0.20444620881302103,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004998748651955105,
|
||
|
|
"loss": 5.991,
|
||
|
|
"mean_token_accuracy": 0.12958767488598824,
|
||
|
|
"num_tokens": 4485623.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.16445894241333,
|
||
|
|
"epoch": 0.20494243747518856,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004998736808850795,
|
||
|
|
"loss": 5.9764,
|
||
|
|
"mean_token_accuracy": 0.12821295857429504,
|
||
|
|
"num_tokens": 4495247.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.162666988372803,
|
||
|
|
"epoch": 0.2054386661373561,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.0004998724909982656,
|
||
|
|
"loss": 6.0394,
|
||
|
|
"mean_token_accuracy": 0.11950158551335335,
|
||
|
|
"num_tokens": 4506490.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.283525276184082,
|
||
|
|
"epoch": 0.20593489479952362,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004998712955350986,
|
||
|
|
"loss": 6.054,
|
||
|
|
"mean_token_accuracy": 0.12060755118727684,
|
||
|
|
"num_tokens": 4517511.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1165454387664795,
|
||
|
|
"epoch": 0.20643112346169115,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004998700944956081,
|
||
|
|
"loss": 6.0188,
|
||
|
|
"mean_token_accuracy": 0.12796789407730103,
|
||
|
|
"num_tokens": 4528655.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.175433397293091,
|
||
|
|
"epoch": 0.20692735212385868,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004998688878798237,
|
||
|
|
"loss": 6.0368,
|
||
|
|
"mean_token_accuracy": 0.12539120018482208,
|
||
|
|
"num_tokens": 4539369.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.179052114486694,
|
||
|
|
"epoch": 0.2074235807860262,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004998676756877753,
|
||
|
|
"loss": 5.9377,
|
||
|
|
"mean_token_accuracy": 0.12160812318325043,
|
||
|
|
"num_tokens": 4548747.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.033137226104737,
|
||
|
|
"epoch": 0.20791980944819372,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004998664579194934,
|
||
|
|
"loss": 5.9297,
|
||
|
|
"mean_token_accuracy": 0.12320928424596786,
|
||
|
|
"num_tokens": 4561283.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.199184131622315,
|
||
|
|
"epoch": 0.20841603811036125,
|
||
|
|
"grad_norm": 0.7578125,
|
||
|
|
"learning_rate": 0.0004998652345750077,
|
||
|
|
"loss": 6.0623,
|
||
|
|
"mean_token_accuracy": 0.12004454135894775,
|
||
|
|
"num_tokens": 4571929.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.221105670928955,
|
||
|
|
"epoch": 0.20891226677252878,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004998640056543487,
|
||
|
|
"loss": 6.0467,
|
||
|
|
"mean_token_accuracy": 0.1145884521305561,
|
||
|
|
"num_tokens": 4583105.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.202408409118652,
|
||
|
|
"epoch": 0.2094084954346963,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.0004998627711575469,
|
||
|
|
"loss": 6.1025,
|
||
|
|
"mean_token_accuracy": 0.12161830887198448,
|
||
|
|
"num_tokens": 4595360.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.137826633453369,
|
||
|
|
"epoch": 0.20990472409686384,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.000499861531084633,
|
||
|
|
"loss": 6.0667,
|
||
|
|
"mean_token_accuracy": 0.1217377468943596,
|
||
|
|
"num_tokens": 4607621.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.210973501205444,
|
||
|
|
"epoch": 0.21040095275903137,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004998602854356376,
|
||
|
|
"loss": 5.9206,
|
||
|
|
"mean_token_accuracy": 0.1290735885500908,
|
||
|
|
"num_tokens": 4618286.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.100604152679443,
|
||
|
|
"epoch": 0.2108971814211989,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004998590342105917,
|
||
|
|
"loss": 5.9972,
|
||
|
|
"mean_token_accuracy": 0.12515969797968865,
|
||
|
|
"num_tokens": 4628345.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.3336169719696045,
|
||
|
|
"epoch": 0.21139341008336643,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004998577774095262,
|
||
|
|
"loss": 6.0492,
|
||
|
|
"mean_token_accuracy": 0.1257066994905472,
|
||
|
|
"num_tokens": 4639074.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.104618978500366,
|
||
|
|
"epoch": 0.21188963874553393,
|
||
|
|
"grad_norm": 0.76171875,
|
||
|
|
"learning_rate": 0.0004998565150324724,
|
||
|
|
"loss": 6.0812,
|
||
|
|
"mean_token_accuracy": 0.12450103238224983,
|
||
|
|
"num_tokens": 4652698.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.192484760284424,
|
||
|
|
"epoch": 0.21238586740770146,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004998552470794616,
|
||
|
|
"loss": 5.9189,
|
||
|
|
"mean_token_accuracy": 0.130835435539484,
|
||
|
|
"num_tokens": 4663924.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1426764011383055,
|
||
|
|
"epoch": 0.212882096069869,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004998539735505251,
|
||
|
|
"loss": 6.0329,
|
||
|
|
"mean_token_accuracy": 0.12281454429030418,
|
||
|
|
"num_tokens": 4673821.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.187332391738892,
|
||
|
|
"epoch": 0.21337832473203652,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004998526944456946,
|
||
|
|
"loss": 5.9649,
|
||
|
|
"mean_token_accuracy": 0.12759994044899942,
|
||
|
|
"num_tokens": 4686646.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.159171628952026,
|
||
|
|
"epoch": 0.21387455339420405,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004998514097650018,
|
||
|
|
"loss": 5.9464,
|
||
|
|
"mean_token_accuracy": 0.1264292851090431,
|
||
|
|
"num_tokens": 4698118.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.125618743896484,
|
||
|
|
"epoch": 0.21437078205637158,
|
||
|
|
"grad_norm": 0.78515625,
|
||
|
|
"learning_rate": 0.0004998501195084786,
|
||
|
|
"loss": 5.975,
|
||
|
|
"mean_token_accuracy": 0.1183625340461731,
|
||
|
|
"num_tokens": 4708869.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.130851745605469,
|
||
|
|
"epoch": 0.21486701071853911,
|
||
|
|
"grad_norm": 0.796875,
|
||
|
|
"learning_rate": 0.0004998488236761569,
|
||
|
|
"loss": 5.9915,
|
||
|
|
"mean_token_accuracy": 0.1173173077404499,
|
||
|
|
"num_tokens": 4720172.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.137715911865234,
|
||
|
|
"epoch": 0.21536323938070662,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004998475222680688,
|
||
|
|
"loss": 6.0444,
|
||
|
|
"mean_token_accuracy": 0.1223752222955227,
|
||
|
|
"num_tokens": 4731886.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.143771076202393,
|
||
|
|
"epoch": 0.21585946804287415,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0004998462152842468,
|
||
|
|
"loss": 5.9246,
|
||
|
|
"mean_token_accuracy": 0.1209682933986187,
|
||
|
|
"num_tokens": 4742381.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.140761852264404,
|
||
|
|
"epoch": 0.21635569670504168,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.000499844902724723,
|
||
|
|
"loss": 5.8892,
|
||
|
|
"mean_token_accuracy": 0.1302737794816494,
|
||
|
|
"num_tokens": 4752851.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.099326419830322,
|
||
|
|
"epoch": 0.2168519253672092,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004998435845895302,
|
||
|
|
"loss": 5.9608,
|
||
|
|
"mean_token_accuracy": 0.12656577080488204,
|
||
|
|
"num_tokens": 4764271.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.10595817565918,
|
||
|
|
"epoch": 0.21734815402937674,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.000499842260878701,
|
||
|
|
"loss": 6.0187,
|
||
|
|
"mean_token_accuracy": 0.12466859817504883,
|
||
|
|
"num_tokens": 4776216.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.157292985916138,
|
||
|
|
"epoch": 0.21784438269154427,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.0004998409315922683,
|
||
|
|
"loss": 5.9608,
|
||
|
|
"mean_token_accuracy": 0.12152473330497741,
|
||
|
|
"num_tokens": 4786666.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1741681575775145,
|
||
|
|
"epoch": 0.2183406113537118,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004998395967302649,
|
||
|
|
"loss": 6.0336,
|
||
|
|
"mean_token_accuracy": 0.12166730538010598,
|
||
|
|
"num_tokens": 4798062.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1284833431243895,
|
||
|
|
"epoch": 0.21883684001587933,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.000499838256292724,
|
||
|
|
"loss": 6.0083,
|
||
|
|
"mean_token_accuracy": 0.12412882819771767,
|
||
|
|
"num_tokens": 4808837.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.108082437515259,
|
||
|
|
"epoch": 0.21933306867804683,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004998369102796787,
|
||
|
|
"loss": 5.9248,
|
||
|
|
"mean_token_accuracy": 0.12848058566451073,
|
||
|
|
"num_tokens": 4819894.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1002240657806395,
|
||
|
|
"epoch": 0.21982929734021436,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004998355586911627,
|
||
|
|
"loss": 5.9195,
|
||
|
|
"mean_token_accuracy": 0.12593771144747734,
|
||
|
|
"num_tokens": 4830976.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.242991495132446,
|
||
|
|
"epoch": 0.2203255260023819,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004998342015272093,
|
||
|
|
"loss": 6.0939,
|
||
|
|
"mean_token_accuracy": 0.12325356379151345,
|
||
|
|
"num_tokens": 4844292.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.131158256530762,
|
||
|
|
"epoch": 0.22082175466454942,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.0004998328387878521,
|
||
|
|
"loss": 5.8928,
|
||
|
|
"mean_token_accuracy": 0.13142480850219726,
|
||
|
|
"num_tokens": 4855284.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.130004787445069,
|
||
|
|
"epoch": 0.22131798332671695,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004998314704731249,
|
||
|
|
"loss": 6.0136,
|
||
|
|
"mean_token_accuracy": 0.1262281470000744,
|
||
|
|
"num_tokens": 4867801.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.122326231002807,
|
||
|
|
"epoch": 0.22181421198888449,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004998300965830618,
|
||
|
|
"loss": 5.8111,
|
||
|
|
"mean_token_accuracy": 0.131843601167202,
|
||
|
|
"num_tokens": 4877392.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.032444047927856,
|
||
|
|
"epoch": 0.22231044065105202,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004998287171176968,
|
||
|
|
"loss": 5.9276,
|
||
|
|
"mean_token_accuracy": 0.12481720820069313,
|
||
|
|
"num_tokens": 4888772.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.186656522750854,
|
||
|
|
"epoch": 0.22280666931321952,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004998273320770641,
|
||
|
|
"loss": 5.974,
|
||
|
|
"mean_token_accuracy": 0.12461790218949317,
|
||
|
|
"num_tokens": 4899739.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.121433925628662,
|
||
|
|
"epoch": 0.22330289797538705,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.000499825941461198,
|
||
|
|
"loss": 5.9563,
|
||
|
|
"mean_token_accuracy": 0.12550890147686006,
|
||
|
|
"num_tokens": 4910455.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1388201236724855,
|
||
|
|
"epoch": 0.22379912663755458,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004998245452701329,
|
||
|
|
"loss": 5.8957,
|
||
|
|
"mean_token_accuracy": 0.12686022520065307,
|
||
|
|
"num_tokens": 4921156.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.107001113891601,
|
||
|
|
"epoch": 0.2242953552997221,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004998231435039036,
|
||
|
|
"loss": 5.915,
|
||
|
|
"mean_token_accuracy": 0.12454593926668167,
|
||
|
|
"num_tokens": 4931771.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.079628324508667,
|
||
|
|
"epoch": 0.22479158396188964,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004998217361625449,
|
||
|
|
"loss": 5.9101,
|
||
|
|
"mean_token_accuracy": 0.12066908702254295,
|
||
|
|
"num_tokens": 4942790.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.068901777267456,
|
||
|
|
"epoch": 0.22528781262405717,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004998203232460915,
|
||
|
|
"loss": 5.9191,
|
||
|
|
"mean_token_accuracy": 0.12233595103025437,
|
||
|
|
"num_tokens": 4952752.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.073587369918823,
|
||
|
|
"epoch": 0.2257840412862247,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004998189047545785,
|
||
|
|
"loss": 5.9571,
|
||
|
|
"mean_token_accuracy": 0.12296144515275956,
|
||
|
|
"num_tokens": 4963659.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.169452142715454,
|
||
|
|
"epoch": 0.22628026994839223,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004998174806880411,
|
||
|
|
"loss": 5.9291,
|
||
|
|
"mean_token_accuracy": 0.1246725894510746,
|
||
|
|
"num_tokens": 4976121.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.072994184494019,
|
||
|
|
"epoch": 0.22677649861055973,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.0004998160510465146,
|
||
|
|
"loss": 5.9597,
|
||
|
|
"mean_token_accuracy": 0.12557747438549996,
|
||
|
|
"num_tokens": 4986515.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.053368473052979,
|
||
|
|
"epoch": 0.22727272727272727,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004998146158300345,
|
||
|
|
"loss": 5.8354,
|
||
|
|
"mean_token_accuracy": 0.12849313914775848,
|
||
|
|
"num_tokens": 4998231.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0678062915802,
|
||
|
|
"epoch": 0.2277689559348948,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004998131750386364,
|
||
|
|
"loss": 5.8649,
|
||
|
|
"mean_token_accuracy": 0.12834521606564522,
|
||
|
|
"num_tokens": 5010309.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.064406776428223,
|
||
|
|
"epoch": 0.22826518459706233,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004998117286723559,
|
||
|
|
"loss": 5.9625,
|
||
|
|
"mean_token_accuracy": 0.13037839084863662,
|
||
|
|
"num_tokens": 5020864.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.049251317977905,
|
||
|
|
"epoch": 0.22876141325922986,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.000499810276731229,
|
||
|
|
"loss": 5.9612,
|
||
|
|
"mean_token_accuracy": 0.1286421723663807,
|
||
|
|
"num_tokens": 5032224.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.169411468505859,
|
||
|
|
"epoch": 0.2292576419213974,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004998088192152918,
|
||
|
|
"loss": 5.9116,
|
||
|
|
"mean_token_accuracy": 0.13263707458972931,
|
||
|
|
"num_tokens": 5044318.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.110779809951782,
|
||
|
|
"epoch": 0.22975387058356492,
|
||
|
|
"grad_norm": 0.9921875,
|
||
|
|
"learning_rate": 0.0004998073561245801,
|
||
|
|
"loss": 6.0024,
|
||
|
|
"mean_token_accuracy": 0.12361429855227471,
|
||
|
|
"num_tokens": 5055270.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.167765951156616,
|
||
|
|
"epoch": 0.23025009924573242,
|
||
|
|
"grad_norm": 0.94921875,
|
||
|
|
"learning_rate": 0.0004998058874591305,
|
||
|
|
"loss": 5.9674,
|
||
|
|
"mean_token_accuracy": 0.12938261702656745,
|
||
|
|
"num_tokens": 5064771.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.092255401611328,
|
||
|
|
"epoch": 0.23074632790789995,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004998044132189793,
|
||
|
|
"loss": 5.9604,
|
||
|
|
"mean_token_accuracy": 0.12339024245738983,
|
||
|
|
"num_tokens": 5075509.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.085866403579712,
|
||
|
|
"epoch": 0.23124255657006748,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.000499802933404163,
|
||
|
|
"loss": 5.9046,
|
||
|
|
"mean_token_accuracy": 0.12324860319495201,
|
||
|
|
"num_tokens": 5086270.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.066864776611328,
|
||
|
|
"epoch": 0.231738785232235,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004998014480147183,
|
||
|
|
"loss": 5.856,
|
||
|
|
"mean_token_accuracy": 0.13291038572788239,
|
||
|
|
"num_tokens": 5096695.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0964189052581785,
|
||
|
|
"epoch": 0.23223501389440254,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004997999570506823,
|
||
|
|
"loss": 5.9362,
|
||
|
|
"mean_token_accuracy": 0.12667595222592354,
|
||
|
|
"num_tokens": 5107775.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1279243469238285,
|
||
|
|
"epoch": 0.23273124255657007,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997984605120917,
|
||
|
|
"loss": 5.9071,
|
||
|
|
"mean_token_accuracy": 0.12755124419927596,
|
||
|
|
"num_tokens": 5118215.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1014261722564695,
|
||
|
|
"epoch": 0.2332274712187376,
|
||
|
|
"grad_norm": 0.82421875,
|
||
|
|
"learning_rate": 0.0004997969583989835,
|
||
|
|
"loss": 5.9279,
|
||
|
|
"mean_token_accuracy": 0.1297263316810131,
|
||
|
|
"num_tokens": 5129509.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.018870449066162,
|
||
|
|
"epoch": 0.23372369988090513,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004997954507113952,
|
||
|
|
"loss": 5.8869,
|
||
|
|
"mean_token_accuracy": 0.12231870293617249,
|
||
|
|
"num_tokens": 5140689.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0995978832244875,
|
||
|
|
"epoch": 0.23421992854307264,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004997939374493642,
|
||
|
|
"loss": 5.8627,
|
||
|
|
"mean_token_accuracy": 0.12557717710733413,
|
||
|
|
"num_tokens": 5151060.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.008219385147095,
|
||
|
|
"epoch": 0.23471615720524017,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.000499792418612928,
|
||
|
|
"loss": 5.8457,
|
||
|
|
"mean_token_accuracy": 0.12821394056081772,
|
||
|
|
"num_tokens": 5161481.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.113403987884522,
|
||
|
|
"epoch": 0.2352123858674077,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004997908942021241,
|
||
|
|
"loss": 5.9664,
|
||
|
|
"mean_token_accuracy": 0.12153320610523224,
|
||
|
|
"num_tokens": 5171961.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.208441591262817,
|
||
|
|
"epoch": 0.23570861452957523,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0004997893642169904,
|
||
|
|
"loss": 6.0081,
|
||
|
|
"mean_token_accuracy": 0.11836620941758155,
|
||
|
|
"num_tokens": 5184158.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.094049882888794,
|
||
|
|
"epoch": 0.23620484319174276,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004997878286575648,
|
||
|
|
"loss": 6.0239,
|
||
|
|
"mean_token_accuracy": 0.1250876732170582,
|
||
|
|
"num_tokens": 5195942.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.102467155456543,
|
||
|
|
"epoch": 0.2367010718539103,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004997862875238855,
|
||
|
|
"loss": 5.8999,
|
||
|
|
"mean_token_accuracy": 0.12667744383215904,
|
||
|
|
"num_tokens": 5208063.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.109834671020508,
|
||
|
|
"epoch": 0.23719730051607782,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004997847408159907,
|
||
|
|
"loss": 5.9515,
|
||
|
|
"mean_token_accuracy": 0.1283447615802288,
|
||
|
|
"num_tokens": 5219424.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.169302701950073,
|
||
|
|
"epoch": 0.23769352917824532,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004997831885339186,
|
||
|
|
"loss": 5.95,
|
||
|
|
"mean_token_accuracy": 0.12057619765400887,
|
||
|
|
"num_tokens": 5230351.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.002688694000244,
|
||
|
|
"epoch": 0.23818975784041285,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004997816306777077,
|
||
|
|
"loss": 5.8321,
|
||
|
|
"mean_token_accuracy": 0.1295178197324276,
|
||
|
|
"num_tokens": 5242906.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.046356296539306,
|
||
|
|
"epoch": 0.23868598650258038,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004997800672473969,
|
||
|
|
"loss": 5.8767,
|
||
|
|
"mean_token_accuracy": 0.13203179612755775,
|
||
|
|
"num_tokens": 5253689.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.11405086517334,
|
||
|
|
"epoch": 0.2391822151647479,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004997784982430247,
|
||
|
|
"loss": 5.9668,
|
||
|
|
"mean_token_accuracy": 0.127695781737566,
|
||
|
|
"num_tokens": 5265896.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.092328882217407,
|
||
|
|
"epoch": 0.23967844382691544,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004997769236646301,
|
||
|
|
"loss": 5.891,
|
||
|
|
"mean_token_accuracy": 0.1248737022280693,
|
||
|
|
"num_tokens": 5276800.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.026219177246094,
|
||
|
|
"epoch": 0.24017467248908297,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004997753435122522,
|
||
|
|
"loss": 5.8682,
|
||
|
|
"mean_token_accuracy": 0.13026652336120606,
|
||
|
|
"num_tokens": 5289113.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.040958499908447,
|
||
|
|
"epoch": 0.2406709011512505,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.00049977375778593,
|
||
|
|
"loss": 5.8421,
|
||
|
|
"mean_token_accuracy": 0.12867625132203103,
|
||
|
|
"num_tokens": 5298825.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.986614465713501,
|
||
|
|
"epoch": 0.24116712981341804,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997721664857032,
|
||
|
|
"loss": 5.8609,
|
||
|
|
"mean_token_accuracy": 0.13291131407022477,
|
||
|
|
"num_tokens": 5310376.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01220850944519,
|
||
|
|
"epoch": 0.24166335847558554,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004997705696116108,
|
||
|
|
"loss": 5.869,
|
||
|
|
"mean_token_accuracy": 0.1286493256688118,
|
||
|
|
"num_tokens": 5320483.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.052859735488892,
|
||
|
|
"epoch": 0.24215958713775307,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004997689671636926,
|
||
|
|
"loss": 5.7784,
|
||
|
|
"mean_token_accuracy": 0.13417652249336243,
|
||
|
|
"num_tokens": 5330995.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.047038984298706,
|
||
|
|
"epoch": 0.2426558157999206,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004997673591419884,
|
||
|
|
"loss": 5.906,
|
||
|
|
"mean_token_accuracy": 0.13337108343839646,
|
||
|
|
"num_tokens": 5341208.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.080028533935547,
|
||
|
|
"epoch": 0.24315204446208813,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.0004997657455465381,
|
||
|
|
"loss": 5.9776,
|
||
|
|
"mean_token_accuracy": 0.1305466502904892,
|
||
|
|
"num_tokens": 5351769.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.106999635696411,
|
||
|
|
"epoch": 0.24364827312425566,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004997641263773815,
|
||
|
|
"loss": 5.7579,
|
||
|
|
"mean_token_accuracy": 0.13589820861816407,
|
||
|
|
"num_tokens": 5361033.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.878340005874634,
|
||
|
|
"epoch": 0.2441445017864232,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.000499762501634559,
|
||
|
|
"loss": 5.8218,
|
||
|
|
"mean_token_accuracy": 0.12982406690716744,
|
||
|
|
"num_tokens": 5372381.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.031815814971924,
|
||
|
|
"epoch": 0.24464073044859072,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004997608713181108,
|
||
|
|
"loss": 5.887,
|
||
|
|
"mean_token_accuracy": 0.1292889140546322,
|
||
|
|
"num_tokens": 5383101.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.09915075302124,
|
||
|
|
"epoch": 0.24513695911075822,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004997592354280772,
|
||
|
|
"loss": 5.9121,
|
||
|
|
"mean_token_accuracy": 0.12618087828159333,
|
||
|
|
"num_tokens": 5393661.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.133698320388794,
|
||
|
|
"epoch": 0.24563318777292575,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.000499757593964499,
|
||
|
|
"loss": 5.9332,
|
||
|
|
"mean_token_accuracy": 0.13135130926966668,
|
||
|
|
"num_tokens": 5405377.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.966562271118164,
|
||
|
|
"epoch": 0.24612941643509328,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004997559469274166,
|
||
|
|
"loss": 5.8388,
|
||
|
|
"mean_token_accuracy": 0.12627245411276816,
|
||
|
|
"num_tokens": 5417172.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.075893211364746,
|
||
|
|
"epoch": 0.24662564509726081,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004997542943168712,
|
||
|
|
"loss": 5.9689,
|
||
|
|
"mean_token_accuracy": 0.1163121998310089,
|
||
|
|
"num_tokens": 5428053.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.147674179077148,
|
||
|
|
"epoch": 0.24712187375942835,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004997526361329035,
|
||
|
|
"loss": 5.8906,
|
||
|
|
"mean_token_accuracy": 0.12604017555713654,
|
||
|
|
"num_tokens": 5438282.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.98391547203064,
|
||
|
|
"epoch": 0.24761810242159588,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004997509723755547,
|
||
|
|
"loss": 5.8671,
|
||
|
|
"mean_token_accuracy": 0.12558303028345108,
|
||
|
|
"num_tokens": 5448940.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965530967712402,
|
||
|
|
"epoch": 0.2481143310837634,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004997493030448662,
|
||
|
|
"loss": 5.7294,
|
||
|
|
"mean_token_accuracy": 0.1320234015583992,
|
||
|
|
"num_tokens": 5458471.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.013654708862305,
|
||
|
|
"epoch": 0.24861055974593094,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004997476281408793,
|
||
|
|
"loss": 5.8341,
|
||
|
|
"mean_token_accuracy": 0.13364496156573297,
|
||
|
|
"num_tokens": 5467979.0,
|
||
|
|
"step": 2505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.064499998092652,
|
||
|
|
"epoch": 0.24910678840809844,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004997459476636354,
|
||
|
|
"loss": 5.9608,
|
||
|
|
"mean_token_accuracy": 0.12101689428091049,
|
||
|
|
"num_tokens": 5479852.0,
|
||
|
|
"step": 2510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.007748031616211,
|
||
|
|
"epoch": 0.24960301707026597,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004997442616131763,
|
||
|
|
"loss": 5.8138,
|
||
|
|
"mean_token_accuracy": 0.12828044667840005,
|
||
|
|
"num_tokens": 5491827.0,
|
||
|
|
"step": 2515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006802654266357,
|
||
|
|
"epoch": 0.25009924573243353,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004997425699895438,
|
||
|
|
"loss": 5.8029,
|
||
|
|
"mean_token_accuracy": 0.1329714372754097,
|
||
|
|
"num_tokens": 5502206.0,
|
||
|
|
"step": 2520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.989188814163208,
|
||
|
|
"epoch": 0.25059547439460106,
|
||
|
|
"grad_norm": 0.83984375,
|
||
|
|
"learning_rate": 0.0004997408727927798,
|
||
|
|
"loss": 5.8227,
|
||
|
|
"mean_token_accuracy": 0.12857313305139542,
|
||
|
|
"num_tokens": 5514352.0,
|
||
|
|
"step": 2525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.100388622283935,
|
||
|
|
"epoch": 0.25109170305676853,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004997391700229264,
|
||
|
|
"loss": 5.8341,
|
||
|
|
"mean_token_accuracy": 0.1370926581323147,
|
||
|
|
"num_tokens": 5524413.0,
|
||
|
|
"step": 2530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976933336257934,
|
||
|
|
"epoch": 0.25158793171893606,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.000499737461680026,
|
||
|
|
"loss": 5.8412,
|
||
|
|
"mean_token_accuracy": 0.12043567895889282,
|
||
|
|
"num_tokens": 5533692.0,
|
||
|
|
"step": 2535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.050266551971435,
|
||
|
|
"epoch": 0.2520841603811036,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.0004997357477641207,
|
||
|
|
"loss": 5.9739,
|
||
|
|
"mean_token_accuracy": 0.12689899504184723,
|
||
|
|
"num_tokens": 5545955.0,
|
||
|
|
"step": 2540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0521016120910645,
|
||
|
|
"epoch": 0.2525803890432711,
|
||
|
|
"grad_norm": 0.84375,
|
||
|
|
"learning_rate": 0.0004997340282752532,
|
||
|
|
"loss": 5.8999,
|
||
|
|
"mean_token_accuracy": 0.1276570178568363,
|
||
|
|
"num_tokens": 5557667.0,
|
||
|
|
"step": 2545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9338500022888185,
|
||
|
|
"epoch": 0.25307661770543866,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.000499732303213466,
|
||
|
|
"loss": 5.8107,
|
||
|
|
"mean_token_accuracy": 0.1274030514061451,
|
||
|
|
"num_tokens": 5567635.0,
|
||
|
|
"step": 2550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.971767520904541,
|
||
|
|
"epoch": 0.2535728463676062,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004997305725788019,
|
||
|
|
"loss": 5.8188,
|
||
|
|
"mean_token_accuracy": 0.13125893771648406,
|
||
|
|
"num_tokens": 5578584.0,
|
||
|
|
"step": 2555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.077448606491089,
|
||
|
|
"epoch": 0.2540690750297737,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.000499728836371304,
|
||
|
|
"loss": 5.924,
|
||
|
|
"mean_token_accuracy": 0.13032637014985085,
|
||
|
|
"num_tokens": 5589679.0,
|
||
|
|
"step": 2560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.066747713088989,
|
||
|
|
"epoch": 0.25456530369194125,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004997270945910151,
|
||
|
|
"loss": 5.8927,
|
||
|
|
"mean_token_accuracy": 0.131753259152174,
|
||
|
|
"num_tokens": 5601550.0,
|
||
|
|
"step": 2565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0625098705291744,
|
||
|
|
"epoch": 0.2550615323541088,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004997253472379785,
|
||
|
|
"loss": 5.9181,
|
||
|
|
"mean_token_accuracy": 0.12465985491871834,
|
||
|
|
"num_tokens": 5611777.0,
|
||
|
|
"step": 2570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093583059310913,
|
||
|
|
"epoch": 0.2555577610162763,
|
||
|
|
"grad_norm": 0.7890625,
|
||
|
|
"learning_rate": 0.0004997235943122375,
|
||
|
|
"loss": 5.9347,
|
||
|
|
"mean_token_accuracy": 0.1278335139155388,
|
||
|
|
"num_tokens": 5623792.0,
|
||
|
|
"step": 2575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.975198221206665,
|
||
|
|
"epoch": 0.25605398967844384,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004997218358138356,
|
||
|
|
"loss": 5.7337,
|
||
|
|
"mean_token_accuracy": 0.13377925157546997,
|
||
|
|
"num_tokens": 5634072.0,
|
||
|
|
"step": 2580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.06852536201477,
|
||
|
|
"epoch": 0.25655021834061137,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004997200717428165,
|
||
|
|
"loss": 5.9925,
|
||
|
|
"mean_token_accuracy": 0.12501400709152222,
|
||
|
|
"num_tokens": 5645046.0,
|
||
|
|
"step": 2585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.986842298507691,
|
||
|
|
"epoch": 0.2570464470027789,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004997183020992237,
|
||
|
|
"loss": 5.8603,
|
||
|
|
"mean_token_accuracy": 0.1285901851952076,
|
||
|
|
"num_tokens": 5655156.0,
|
||
|
|
"step": 2590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.025115919113159,
|
||
|
|
"epoch": 0.25754267566494643,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004997165268831014,
|
||
|
|
"loss": 5.8286,
|
||
|
|
"mean_token_accuracy": 0.12798064202070236,
|
||
|
|
"num_tokens": 5665621.0,
|
||
|
|
"step": 2595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.023578310012818,
|
||
|
|
"epoch": 0.25803890432711396,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004997147460944933,
|
||
|
|
"loss": 5.8843,
|
||
|
|
"mean_token_accuracy": 0.12540870010852814,
|
||
|
|
"num_tokens": 5677072.0,
|
||
|
|
"step": 2600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093571472167969,
|
||
|
|
"epoch": 0.25853513298928144,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.0004997129597334438,
|
||
|
|
"loss": 5.834,
|
||
|
|
"mean_token_accuracy": 0.13478555008769036,
|
||
|
|
"num_tokens": 5687926.0,
|
||
|
|
"step": 2605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.910076093673706,
|
||
|
|
"epoch": 0.25903136165144897,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004997111677999971,
|
||
|
|
"loss": 5.8391,
|
||
|
|
"mean_token_accuracy": 0.1295539267361164,
|
||
|
|
"num_tokens": 5698923.0,
|
||
|
|
"step": 2610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.104871034622192,
|
||
|
|
"epoch": 0.2595275903136165,
|
||
|
|
"grad_norm": 0.80078125,
|
||
|
|
"learning_rate": 0.0004997093702941976,
|
||
|
|
"loss": 5.9432,
|
||
|
|
"mean_token_accuracy": 0.12401391565799713,
|
||
|
|
"num_tokens": 5709879.0,
|
||
|
|
"step": 2615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0787454605102536,
|
||
|
|
"epoch": 0.260023818975784,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.00049970756721609,
|
||
|
|
"loss": 5.8857,
|
||
|
|
"mean_token_accuracy": 0.12929130122065544,
|
||
|
|
"num_tokens": 5720698.0,
|
||
|
|
"step": 2620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.974215459823609,
|
||
|
|
"epoch": 0.26052004763795156,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.000499705758565719,
|
||
|
|
"loss": 5.8317,
|
||
|
|
"mean_token_accuracy": 0.1328559137880802,
|
||
|
|
"num_tokens": 5732890.0,
|
||
|
|
"step": 2625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.003826332092285,
|
||
|
|
"epoch": 0.2610162763001191,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004997039443431292,
|
||
|
|
"loss": 5.8339,
|
||
|
|
"mean_token_accuracy": 0.1282294899225235,
|
||
|
|
"num_tokens": 5743741.0,
|
||
|
|
"step": 2630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.945276737213135,
|
||
|
|
"epoch": 0.2615125049622866,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004997021245483659,
|
||
|
|
"loss": 5.745,
|
||
|
|
"mean_token_accuracy": 0.1344357542693615,
|
||
|
|
"num_tokens": 5754730.0,
|
||
|
|
"step": 2635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.975873947143555,
|
||
|
|
"epoch": 0.26200873362445415,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.000499700299181474,
|
||
|
|
"loss": 5.7816,
|
||
|
|
"mean_token_accuracy": 0.13547359257936478,
|
||
|
|
"num_tokens": 5764705.0,
|
||
|
|
"step": 2640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.053955745697022,
|
||
|
|
"epoch": 0.2625049622866217,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004996984682424989,
|
||
|
|
"loss": 5.9062,
|
||
|
|
"mean_token_accuracy": 0.12410091534256935,
|
||
|
|
"num_tokens": 5776803.0,
|
||
|
|
"step": 2645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.090683031082153,
|
||
|
|
"epoch": 0.2630011909487892,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.000499696631731486,
|
||
|
|
"loss": 5.9541,
|
||
|
|
"mean_token_accuracy": 0.12392831742763519,
|
||
|
|
"num_tokens": 5788203.0,
|
||
|
|
"step": 2650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.06274151802063,
|
||
|
|
"epoch": 0.26349741961095674,
|
||
|
|
"grad_norm": 0.78125,
|
||
|
|
"learning_rate": 0.0004996947896484809,
|
||
|
|
"loss": 5.8677,
|
||
|
|
"mean_token_accuracy": 0.12673098966479301,
|
||
|
|
"num_tokens": 5800476.0,
|
||
|
|
"step": 2655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.944343852996826,
|
||
|
|
"epoch": 0.26399364827312427,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.000499692941993529,
|
||
|
|
"loss": 5.922,
|
||
|
|
"mean_token_accuracy": 0.12605136781930923,
|
||
|
|
"num_tokens": 5811652.0,
|
||
|
|
"step": 2660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.055945110321045,
|
||
|
|
"epoch": 0.2644898769352918,
|
||
|
|
"grad_norm": 0.76171875,
|
||
|
|
"learning_rate": 0.0004996910887666765,
|
||
|
|
"loss": 5.8237,
|
||
|
|
"mean_token_accuracy": 0.1357803925871849,
|
||
|
|
"num_tokens": 5823036.0,
|
||
|
|
"step": 2665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.979827785491944,
|
||
|
|
"epoch": 0.26498610559745933,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.000499689229967969,
|
||
|
|
"loss": 5.7742,
|
||
|
|
"mean_token_accuracy": 0.13261008635163307,
|
||
|
|
"num_tokens": 5833220.0,
|
||
|
|
"step": 2670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.952842378616333,
|
||
|
|
"epoch": 0.26548233425962686,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.0004996873655974529,
|
||
|
|
"loss": 5.8511,
|
||
|
|
"mean_token_accuracy": 0.12471630349755287,
|
||
|
|
"num_tokens": 5843777.0,
|
||
|
|
"step": 2675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.013588809967041,
|
||
|
|
"epoch": 0.26597856292179434,
|
||
|
|
"grad_norm": 0.77734375,
|
||
|
|
"learning_rate": 0.0004996854956551743,
|
||
|
|
"loss": 5.8734,
|
||
|
|
"mean_token_accuracy": 0.12791570276021957,
|
||
|
|
"num_tokens": 5854942.0,
|
||
|
|
"step": 2680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.092654275894165,
|
||
|
|
"epoch": 0.26647479158396187,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004996836201411794,
|
||
|
|
"loss": 5.8779,
|
||
|
|
"mean_token_accuracy": 0.1297077603638172,
|
||
|
|
"num_tokens": 5866536.0,
|
||
|
|
"step": 2685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.936705446243286,
|
||
|
|
"epoch": 0.2669710202461294,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.000499681739055515,
|
||
|
|
"loss": 5.7586,
|
||
|
|
"mean_token_accuracy": 0.13553930893540383,
|
||
|
|
"num_tokens": 5876653.0,
|
||
|
|
"step": 2690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.047937488555908,
|
||
|
|
"epoch": 0.26746724890829693,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004996798523982276,
|
||
|
|
"loss": 5.8022,
|
||
|
|
"mean_token_accuracy": 0.13020532354712486,
|
||
|
|
"num_tokens": 5887092.0,
|
||
|
|
"step": 2695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006089544296264,
|
||
|
|
"epoch": 0.26796347757046446,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.000499677960169364,
|
||
|
|
"loss": 5.9163,
|
||
|
|
"mean_token_accuracy": 0.12631798684597015,
|
||
|
|
"num_tokens": 5898224.0,
|
||
|
|
"step": 2700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0130256652832035,
|
||
|
|
"epoch": 0.268459706232632,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004996760623689711,
|
||
|
|
"loss": 5.7482,
|
||
|
|
"mean_token_accuracy": 0.13969457894563675,
|
||
|
|
"num_tokens": 5909235.0,
|
||
|
|
"step": 2705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.01822190284729,
|
||
|
|
"epoch": 0.2689559348947995,
|
||
|
|
"grad_norm": 0.890625,
|
||
|
|
"learning_rate": 0.000499674158997096,
|
||
|
|
"loss": 5.9196,
|
||
|
|
"mean_token_accuracy": 0.13010889217257499,
|
||
|
|
"num_tokens": 5921299.0,
|
||
|
|
"step": 2710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.007842779159546,
|
||
|
|
"epoch": 0.26945216355696705,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004996722500537859,
|
||
|
|
"loss": 5.8747,
|
||
|
|
"mean_token_accuracy": 0.12728465348482132,
|
||
|
|
"num_tokens": 5933249.0,
|
||
|
|
"step": 2715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0062947273254395,
|
||
|
|
"epoch": 0.2699483922191346,
|
||
|
|
"grad_norm": 0.80859375,
|
||
|
|
"learning_rate": 0.0004996703355390881,
|
||
|
|
"loss": 5.9094,
|
||
|
|
"mean_token_accuracy": 0.1252631276845932,
|
||
|
|
"num_tokens": 5945942.0,
|
||
|
|
"step": 2720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.968673038482666,
|
||
|
|
"epoch": 0.2704446208813021,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.00049966841545305,
|
||
|
|
"loss": 5.8196,
|
||
|
|
"mean_token_accuracy": 0.13000037670135497,
|
||
|
|
"num_tokens": 5956315.0,
|
||
|
|
"step": 2725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0654479503631595,
|
||
|
|
"epoch": 0.27094084954346964,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004996664897957195,
|
||
|
|
"loss": 5.8891,
|
||
|
|
"mean_token_accuracy": 0.12286564558744431,
|
||
|
|
"num_tokens": 5966566.0,
|
||
|
|
"step": 2730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.943171072006225,
|
||
|
|
"epoch": 0.2714370782056372,
|
||
|
|
"grad_norm": 0.83203125,
|
||
|
|
"learning_rate": 0.0004996645585671441,
|
||
|
|
"loss": 5.7425,
|
||
|
|
"mean_token_accuracy": 0.13684265613555907,
|
||
|
|
"num_tokens": 5977137.0,
|
||
|
|
"step": 2735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021245813369751,
|
||
|
|
"epoch": 0.2719333068678047,
|
||
|
|
"grad_norm": 0.9375,
|
||
|
|
"learning_rate": 0.0004996626217673717,
|
||
|
|
"loss": 5.8674,
|
||
|
|
"mean_token_accuracy": 0.1314192496240139,
|
||
|
|
"num_tokens": 5987653.0,
|
||
|
|
"step": 2740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0384129047393795,
|
||
|
|
"epoch": 0.27242953552997223,
|
||
|
|
"grad_norm": 0.8984375,
|
||
|
|
"learning_rate": 0.0004996606793964504,
|
||
|
|
"loss": 5.9187,
|
||
|
|
"mean_token_accuracy": 0.12729719430208206,
|
||
|
|
"num_tokens": 5998530.0,
|
||
|
|
"step": 2745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.968395137786866,
|
||
|
|
"epoch": 0.27292576419213976,
|
||
|
|
"grad_norm": 0.921875,
|
||
|
|
"learning_rate": 0.0004996587314544284,
|
||
|
|
"loss": 5.7641,
|
||
|
|
"mean_token_accuracy": 0.13758938238024712,
|
||
|
|
"num_tokens": 6009550.0,
|
||
|
|
"step": 2750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.017692184448242,
|
||
|
|
"epoch": 0.27342199285430724,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004996567779413539,
|
||
|
|
"loss": 5.9465,
|
||
|
|
"mean_token_accuracy": 0.12807289212942125,
|
||
|
|
"num_tokens": 6021522.0,
|
||
|
|
"step": 2755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.015359878540039,
|
||
|
|
"epoch": 0.27391822151647477,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.0004996548188572755,
|
||
|
|
"loss": 5.8181,
|
||
|
|
"mean_token_accuracy": 0.12846075966954232,
|
||
|
|
"num_tokens": 6033993.0,
|
||
|
|
"step": 2760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.101863288879395,
|
||
|
|
"epoch": 0.2744144501786423,
|
||
|
|
"grad_norm": 0.8203125,
|
||
|
|
"learning_rate": 0.0004996528542022416,
|
||
|
|
"loss": 5.9794,
|
||
|
|
"mean_token_accuracy": 0.1278089925646782,
|
||
|
|
"num_tokens": 6044804.0,
|
||
|
|
"step": 2765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9826210021972654,
|
||
|
|
"epoch": 0.27491067884080983,
|
||
|
|
"grad_norm": 0.85546875,
|
||
|
|
"learning_rate": 0.000499650883976301,
|
||
|
|
"loss": 5.8315,
|
||
|
|
"mean_token_accuracy": 0.12525355890393258,
|
||
|
|
"num_tokens": 6054878.0,
|
||
|
|
"step": 2770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0613480567932125,
|
||
|
|
"epoch": 0.27540690750297736,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004996489081795026,
|
||
|
|
"loss": 5.83,
|
||
|
|
"mean_token_accuracy": 0.12792847976088523,
|
||
|
|
"num_tokens": 6065492.0,
|
||
|
|
"step": 2775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.012570095062256,
|
||
|
|
"epoch": 0.2759031361651449,
|
||
|
|
"grad_norm": 0.94140625,
|
||
|
|
"learning_rate": 0.0004996469268118953,
|
||
|
|
"loss": 5.8623,
|
||
|
|
"mean_token_accuracy": 0.12609369233250617,
|
||
|
|
"num_tokens": 6077360.0,
|
||
|
|
"step": 2780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.981580781936645,
|
||
|
|
"epoch": 0.2763993648273124,
|
||
|
|
"grad_norm": 0.9140625,
|
||
|
|
"learning_rate": 0.0004996449398735283,
|
||
|
|
"loss": 5.8343,
|
||
|
|
"mean_token_accuracy": 0.12407092973589898,
|
||
|
|
"num_tokens": 6087530.0,
|
||
|
|
"step": 2785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0558830261230465,
|
||
|
|
"epoch": 0.27689559348947995,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004996429473644509,
|
||
|
|
"loss": 5.8194,
|
||
|
|
"mean_token_accuracy": 0.13177746906876564,
|
||
|
|
"num_tokens": 6098064.0,
|
||
|
|
"step": 2790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.905488109588623,
|
||
|
|
"epoch": 0.2773918221516475,
|
||
|
|
"grad_norm": 0.90625,
|
||
|
|
"learning_rate": 0.0004996409492847124,
|
||
|
|
"loss": 5.7419,
|
||
|
|
"mean_token_accuracy": 0.1355844110250473,
|
||
|
|
"num_tokens": 6108446.0,
|
||
|
|
"step": 2795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.991134786605835,
|
||
|
|
"epoch": 0.277888050813815,
|
||
|
|
"grad_norm": 0.93359375,
|
||
|
|
"learning_rate": 0.0004996389456343624,
|
||
|
|
"loss": 5.7935,
|
||
|
|
"mean_token_accuracy": 0.12804083600640298,
|
||
|
|
"num_tokens": 6118923.0,
|
||
|
|
"step": 2800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9639771461486815,
|
||
|
|
"epoch": 0.27838427947598254,
|
||
|
|
"grad_norm": 0.8046875,
|
||
|
|
"learning_rate": 0.0004996369364134507,
|
||
|
|
"loss": 5.6892,
|
||
|
|
"mean_token_accuracy": 0.13721818029880523,
|
||
|
|
"num_tokens": 6130583.0,
|
||
|
|
"step": 2805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.992746829986572,
|
||
|
|
"epoch": 0.2788805081381501,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.000499634921622027,
|
||
|
|
"loss": 5.9108,
|
||
|
|
"mean_token_accuracy": 0.1296452686190605,
|
||
|
|
"num_tokens": 6142351.0,
|
||
|
|
"step": 2810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.940733814239502,
|
||
|
|
"epoch": 0.2793767368003176,
|
||
|
|
"grad_norm": 0.7734375,
|
||
|
|
"learning_rate": 0.0004996329012601413,
|
||
|
|
"loss": 5.7348,
|
||
|
|
"mean_token_accuracy": 0.1339046314358711,
|
||
|
|
"num_tokens": 6152964.0,
|
||
|
|
"step": 2815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.968123912811279,
|
||
|
|
"epoch": 0.27987296546248513,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004996308753278437,
|
||
|
|
"loss": 5.8149,
|
||
|
|
"mean_token_accuracy": 0.13025947213172911,
|
||
|
|
"num_tokens": 6163522.0,
|
||
|
|
"step": 2820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.044860601425171,
|
||
|
|
"epoch": 0.28036919412465267,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004996288438251843,
|
||
|
|
"loss": 5.8309,
|
||
|
|
"mean_token_accuracy": 0.12943392023444175,
|
||
|
|
"num_tokens": 6174060.0,
|
||
|
|
"step": 2825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.940817499160767,
|
||
|
|
"epoch": 0.28086542278682014,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004996268067522137,
|
||
|
|
"loss": 5.7561,
|
||
|
|
"mean_token_accuracy": 0.13433966636657715,
|
||
|
|
"num_tokens": 6183850.0,
|
||
|
|
"step": 2830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.010298871994019,
|
||
|
|
"epoch": 0.28136165144898767,
|
||
|
|
"grad_norm": 0.89453125,
|
||
|
|
"learning_rate": 0.0004996247641089823,
|
||
|
|
"loss": 5.822,
|
||
|
|
"mean_token_accuracy": 0.12921777442097665,
|
||
|
|
"num_tokens": 6195073.0,
|
||
|
|
"step": 2835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.014202022552491,
|
||
|
|
"epoch": 0.2818578801111552,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004996227158955409,
|
||
|
|
"loss": 5.8334,
|
||
|
|
"mean_token_accuracy": 0.13027386069297792,
|
||
|
|
"num_tokens": 6206658.0,
|
||
|
|
"step": 2840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.891300058364868,
|
||
|
|
"epoch": 0.28235410877332273,
|
||
|
|
"grad_norm": 0.81640625,
|
||
|
|
"learning_rate": 0.00049962066211194,
|
||
|
|
"loss": 5.7269,
|
||
|
|
"mean_token_accuracy": 0.1362061731517315,
|
||
|
|
"num_tokens": 6217183.0,
|
||
|
|
"step": 2845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.912215232849121,
|
||
|
|
"epoch": 0.28285033743549026,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004996186027582308,
|
||
|
|
"loss": 5.7702,
|
||
|
|
"mean_token_accuracy": 0.1330777660012245,
|
||
|
|
"num_tokens": 6227575.0,
|
||
|
|
"step": 2850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9731401920318605,
|
||
|
|
"epoch": 0.2833465660976578,
|
||
|
|
"grad_norm": 0.8671875,
|
||
|
|
"learning_rate": 0.0004996165378344642,
|
||
|
|
"loss": 5.7632,
|
||
|
|
"mean_token_accuracy": 0.13205480054020882,
|
||
|
|
"num_tokens": 6239698.0,
|
||
|
|
"step": 2855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.963889408111572,
|
||
|
|
"epoch": 0.2838427947598253,
|
||
|
|
"grad_norm": 0.91796875,
|
||
|
|
"learning_rate": 0.0004996144673406914,
|
||
|
|
"loss": 5.7796,
|
||
|
|
"mean_token_accuracy": 0.13623137325048446,
|
||
|
|
"num_tokens": 6249730.0,
|
||
|
|
"step": 2860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.922169256210327,
|
||
|
|
"epoch": 0.28433902342199285,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004996123912769639,
|
||
|
|
"loss": 5.7807,
|
||
|
|
"mean_token_accuracy": 0.1335216723382473,
|
||
|
|
"num_tokens": 6259493.0,
|
||
|
|
"step": 2865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.947891187667847,
|
||
|
|
"epoch": 0.2848352520841604,
|
||
|
|
"grad_norm": 0.92578125,
|
||
|
|
"learning_rate": 0.0004996103096433332,
|
||
|
|
"loss": 5.7801,
|
||
|
|
"mean_token_accuracy": 0.13493156805634499,
|
||
|
|
"num_tokens": 6269568.0,
|
||
|
|
"step": 2870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.986701917648316,
|
||
|
|
"epoch": 0.2853314807463279,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004996082224398506,
|
||
|
|
"loss": 5.8276,
|
||
|
|
"mean_token_accuracy": 0.13422205969691275,
|
||
|
|
"num_tokens": 6280028.0,
|
||
|
|
"step": 2875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.926356792449951,
|
||
|
|
"epoch": 0.28582770940849545,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004996061296665682,
|
||
|
|
"loss": 5.7768,
|
||
|
|
"mean_token_accuracy": 0.13312428295612336,
|
||
|
|
"num_tokens": 6290321.0,
|
||
|
|
"step": 2880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.971750688552857,
|
||
|
|
"epoch": 0.286323938070663,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004996040313235377,
|
||
|
|
"loss": 5.7778,
|
||
|
|
"mean_token_accuracy": 0.13141178712248802,
|
||
|
|
"num_tokens": 6300729.0,
|
||
|
|
"step": 2885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.991149187088013,
|
||
|
|
"epoch": 0.2868201667328305,
|
||
|
|
"grad_norm": 0.88671875,
|
||
|
|
"learning_rate": 0.0004996019274108112,
|
||
|
|
"loss": 5.8172,
|
||
|
|
"mean_token_accuracy": 0.12256841883063316,
|
||
|
|
"num_tokens": 6311051.0,
|
||
|
|
"step": 2890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.88832540512085,
|
||
|
|
"epoch": 0.28731639539499804,
|
||
|
|
"grad_norm": 0.79296875,
|
||
|
|
"learning_rate": 0.000499599817928441,
|
||
|
|
"loss": 5.7324,
|
||
|
|
"mean_token_accuracy": 0.14212445318698883,
|
||
|
|
"num_tokens": 6322201.0,
|
||
|
|
"step": 2895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9889750480651855,
|
||
|
|
"epoch": 0.28781262405716557,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004995977028764792,
|
||
|
|
"loss": 5.8283,
|
||
|
|
"mean_token_accuracy": 0.13292579874396324,
|
||
|
|
"num_tokens": 6332372.0,
|
||
|
|
"step": 2900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.032767820358276,
|
||
|
|
"epoch": 0.28830885271933304,
|
||
|
|
"grad_norm": 0.87890625,
|
||
|
|
"learning_rate": 0.0004995955822549783,
|
||
|
|
"loss": 5.9456,
|
||
|
|
"mean_token_accuracy": 0.1312311202287674,
|
||
|
|
"num_tokens": 6344070.0,
|
||
|
|
"step": 2905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.872374725341797,
|
||
|
|
"epoch": 0.2888050813815006,
|
||
|
|
"grad_norm": 0.87109375,
|
||
|
|
"learning_rate": 0.0004995934560639909,
|
||
|
|
"loss": 5.7614,
|
||
|
|
"mean_token_accuracy": 0.13059834465384484,
|
||
|
|
"num_tokens": 6355118.0,
|
||
|
|
"step": 2910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.010786342620849,
|
||
|
|
"epoch": 0.2893013100436681,
|
||
|
|
"grad_norm": 0.9296875,
|
||
|
|
"learning_rate": 0.0004995913243035699,
|
||
|
|
"loss": 5.8164,
|
||
|
|
"mean_token_accuracy": 0.13058557361364365,
|
||
|
|
"num_tokens": 6366722.0,
|
||
|
|
"step": 2915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9085742950439455,
|
||
|
|
"epoch": 0.28979753870583563,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004995891869737678,
|
||
|
|
"loss": 5.763,
|
||
|
|
"mean_token_accuracy": 0.13042425736784935,
|
||
|
|
"num_tokens": 6376190.0,
|
||
|
|
"step": 2920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.031855201721191,
|
||
|
|
"epoch": 0.29029376736800316,
|
||
|
|
"grad_norm": 0.90234375,
|
||
|
|
"learning_rate": 0.0004995870440746379,
|
||
|
|
"loss": 5.8846,
|
||
|
|
"mean_token_accuracy": 0.12776149213314056,
|
||
|
|
"num_tokens": 6385883.0,
|
||
|
|
"step": 2925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9083640575408936,
|
||
|
|
"epoch": 0.2907899960301707,
|
||
|
|
"grad_norm": 0.8359375,
|
||
|
|
"learning_rate": 0.0004995848956062333,
|
||
|
|
"loss": 5.7467,
|
||
|
|
"mean_token_accuracy": 0.13742488473653794,
|
||
|
|
"num_tokens": 6397762.0,
|
||
|
|
"step": 2930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.953339385986328,
|
||
|
|
"epoch": 0.2912862246923382,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004995827415686071,
|
||
|
|
"loss": 5.8544,
|
||
|
|
"mean_token_accuracy": 0.1268588684499264,
|
||
|
|
"num_tokens": 6408972.0,
|
||
|
|
"step": 2935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9890693664550785,
|
||
|
|
"epoch": 0.29178245335450576,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.000499580581961813,
|
||
|
|
"loss": 5.7297,
|
||
|
|
"mean_token_accuracy": 0.12740637883543968,
|
||
|
|
"num_tokens": 6418998.0,
|
||
|
|
"step": 2940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9924187660217285,
|
||
|
|
"epoch": 0.2922786820166733,
|
||
|
|
"grad_norm": 0.9453125,
|
||
|
|
"learning_rate": 0.0004995784167859043,
|
||
|
|
"loss": 5.8176,
|
||
|
|
"mean_token_accuracy": 0.133935584127903,
|
||
|
|
"num_tokens": 6430046.0,
|
||
|
|
"step": 2945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.004527235031128,
|
||
|
|
"epoch": 0.2927749106788408,
|
||
|
|
"grad_norm": 0.91015625,
|
||
|
|
"learning_rate": 0.0004995762460409349,
|
||
|
|
"loss": 5.7752,
|
||
|
|
"mean_token_accuracy": 0.13516283929347991,
|
||
|
|
"num_tokens": 6441351.0,
|
||
|
|
"step": 2950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.874765920639038,
|
||
|
|
"epoch": 0.29327113934100835,
|
||
|
|
"grad_norm": 0.8828125,
|
||
|
|
"learning_rate": 0.0004995740697269584,
|
||
|
|
"loss": 5.8047,
|
||
|
|
"mean_token_accuracy": 0.13173421323299409,
|
||
|
|
"num_tokens": 6453259.0,
|
||
|
|
"step": 2955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.952497243881226,
|
||
|
|
"epoch": 0.2937673680031759,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004995718878440289,
|
||
|
|
"loss": 5.7901,
|
||
|
|
"mean_token_accuracy": 0.1302712343633175,
|
||
|
|
"num_tokens": 6464819.0,
|
||
|
|
"step": 2960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.05925498008728,
|
||
|
|
"epoch": 0.2942635966653434,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004995697003922006,
|
||
|
|
"loss": 5.8809,
|
||
|
|
"mean_token_accuracy": 0.13085756078362465,
|
||
|
|
"num_tokens": 6477315.0,
|
||
|
|
"step": 2965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.986642456054687,
|
||
|
|
"epoch": 0.29475982532751094,
|
||
|
|
"grad_norm": 0.859375,
|
||
|
|
"learning_rate": 0.0004995675073715274,
|
||
|
|
"loss": 5.7895,
|
||
|
|
"mean_token_accuracy": 0.1315566822886467,
|
||
|
|
"num_tokens": 6488461.0,
|
||
|
|
"step": 2970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9029899597167965,
|
||
|
|
"epoch": 0.29525605398967847,
|
||
|
|
"grad_norm": 0.86328125,
|
||
|
|
"learning_rate": 0.0004995653087820641,
|
||
|
|
"loss": 5.7658,
|
||
|
|
"mean_token_accuracy": 0.13758422061800957,
|
||
|
|
"num_tokens": 6499486.0,
|
||
|
|
"step": 2975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.06349925994873,
|
||
|
|
"epoch": 0.29575228265184594,
|
||
|
|
"grad_norm": 0.8125,
|
||
|
|
"learning_rate": 0.000499563104623865,
|
||
|
|
"loss": 5.8495,
|
||
|
|
"mean_token_accuracy": 0.13247794285416603,
|
||
|
|
"num_tokens": 6511337.0,
|
||
|
|
"step": 2980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.87068018913269,
|
||
|
|
"epoch": 0.2962485113140135,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004995608948969849,
|
||
|
|
"loss": 5.7496,
|
||
|
|
"mean_token_accuracy": 0.13712706938385963,
|
||
|
|
"num_tokens": 6521066.0,
|
||
|
|
"step": 2985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.923775768280029,
|
||
|
|
"epoch": 0.296744739976181,
|
||
|
|
"grad_norm": 0.8515625,
|
||
|
|
"learning_rate": 0.0004995586796014784,
|
||
|
|
"loss": 5.7578,
|
||
|
|
"mean_token_accuracy": 0.13636653870344162,
|
||
|
|
"num_tokens": 6531267.0,
|
||
|
|
"step": 2990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9300535202026365,
|
||
|
|
"epoch": 0.29724096863834853,
|
||
|
|
"grad_norm": 0.84765625,
|
||
|
|
"learning_rate": 0.0004995564587374005,
|
||
|
|
"loss": 5.7948,
|
||
|
|
"mean_token_accuracy": 0.12985561564564704,
|
||
|
|
"num_tokens": 6541891.0,
|
||
|
|
"step": 2995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.960822010040284,
|
||
|
|
"epoch": 0.29773719730051607,
|
||
|
|
"grad_norm": 0.828125,
|
||
|
|
"learning_rate": 0.0004995542323048063,
|
||
|
|
"loss": 5.7554,
|
||
|
|
"mean_token_accuracy": 0.1335455968976021,
|
||
|
|
"num_tokens": 6551974.0,
|
||
|
|
"step": 3000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.29773719730051607,
|
||
|
|
"eval_entropy": 5.791192339332746,
|
||
|
|
"eval_loss": 5.854363441467285,
|
||
|
|
"eval_mean_token_accuracy": 0.13373962398746797,
|
||
|
|
"eval_num_tokens": 6551974.0,
|
||
|
|
"eval_runtime": 20.5635,
|
||
|
|
"eval_samples_per_second": 1637.315,
|
||
|
|
"eval_steps_per_second": 204.683,
|
||
|
|
"step": 3000
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 100750,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 10,
|
||
|
|
"save_steps": 3000,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 1631120449536000.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|