5090 lines
137 KiB
JSON
5090 lines
137 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 2.092050209205021,
|
||
|
|
"eval_steps": 500,
|
||
|
|
"global_step": 2500,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 10.692013263702393,
|
||
|
|
"epoch": 0.0041841004184100415,
|
||
|
|
"grad_norm": 14.4375,
|
||
|
|
"learning_rate": 2e-06,
|
||
|
|
"loss": 10.8216,
|
||
|
|
"mean_token_accuracy": 0.0,
|
||
|
|
"num_tokens": 9848.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.69194860458374,
|
||
|
|
"epoch": 0.008368200836820083,
|
||
|
|
"grad_norm": 13.4375,
|
||
|
|
"learning_rate": 4.5e-06,
|
||
|
|
"loss": 10.7246,
|
||
|
|
"mean_token_accuracy": 0.00012674271129071714,
|
||
|
|
"num_tokens": 18196.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.691147422790527,
|
||
|
|
"epoch": 0.012552301255230125,
|
||
|
|
"grad_norm": 9.9375,
|
||
|
|
"learning_rate": 7e-06,
|
||
|
|
"loss": 10.4677,
|
||
|
|
"mean_token_accuracy": 0.0241286511416547,
|
||
|
|
"num_tokens": 26927.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.680734634399414,
|
||
|
|
"epoch": 0.016736401673640166,
|
||
|
|
"grad_norm": 6.6875,
|
||
|
|
"learning_rate": 9.5e-06,
|
||
|
|
"loss": 10.115,
|
||
|
|
"mean_token_accuracy": 0.04429602064192295,
|
||
|
|
"num_tokens": 34987.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.62258882522583,
|
||
|
|
"epoch": 0.02092050209205021,
|
||
|
|
"grad_norm": 4.25,
|
||
|
|
"learning_rate": 1.2e-05,
|
||
|
|
"loss": 9.8294,
|
||
|
|
"mean_token_accuracy": 0.04711197260767221,
|
||
|
|
"num_tokens": 44936.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.580855178833009,
|
||
|
|
"epoch": 0.02510460251046025,
|
||
|
|
"grad_norm": 3.515625,
|
||
|
|
"learning_rate": 1.4500000000000002e-05,
|
||
|
|
"loss": 9.6731,
|
||
|
|
"mean_token_accuracy": 0.046292875334620474,
|
||
|
|
"num_tokens": 54562.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.583562088012695,
|
||
|
|
"epoch": 0.029288702928870293,
|
||
|
|
"grad_norm": 2.890625,
|
||
|
|
"learning_rate": 1.7000000000000003e-05,
|
||
|
|
"loss": 9.6171,
|
||
|
|
"mean_token_accuracy": 0.04133799690753222,
|
||
|
|
"num_tokens": 63844.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.599079990386963,
|
||
|
|
"epoch": 0.03347280334728033,
|
||
|
|
"grad_norm": 2.8125,
|
||
|
|
"learning_rate": 1.95e-05,
|
||
|
|
"loss": 9.6032,
|
||
|
|
"mean_token_accuracy": 0.040498660318553446,
|
||
|
|
"num_tokens": 74331.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.584051704406738,
|
||
|
|
"epoch": 0.03765690376569038,
|
||
|
|
"grad_norm": 2.796875,
|
||
|
|
"learning_rate": 2.2e-05,
|
||
|
|
"loss": 9.5052,
|
||
|
|
"mean_token_accuracy": 0.04810179658234119,
|
||
|
|
"num_tokens": 83028.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.553222179412842,
|
||
|
|
"epoch": 0.04184100418410042,
|
||
|
|
"grad_norm": 2.5625,
|
||
|
|
"learning_rate": 2.4500000000000003e-05,
|
||
|
|
"loss": 9.4503,
|
||
|
|
"mean_token_accuracy": 0.04860256612300873,
|
||
|
|
"num_tokens": 91395.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.53250617980957,
|
||
|
|
"epoch": 0.04602510460251046,
|
||
|
|
"grad_norm": 2.859375,
|
||
|
|
"learning_rate": 2.7e-05,
|
||
|
|
"loss": 9.3929,
|
||
|
|
"mean_token_accuracy": 0.05782372578978538,
|
||
|
|
"num_tokens": 101868.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.429417991638184,
|
||
|
|
"epoch": 0.0502092050209205,
|
||
|
|
"grad_norm": 2.40625,
|
||
|
|
"learning_rate": 2.95e-05,
|
||
|
|
"loss": 9.2812,
|
||
|
|
"mean_token_accuracy": 0.05993606857955456,
|
||
|
|
"num_tokens": 110403.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.376260757446289,
|
||
|
|
"epoch": 0.05439330543933055,
|
||
|
|
"grad_norm": 2.5,
|
||
|
|
"learning_rate": 3.2e-05,
|
||
|
|
"loss": 9.3299,
|
||
|
|
"mean_token_accuracy": 0.05404467172920704,
|
||
|
|
"num_tokens": 119557.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.482521724700927,
|
||
|
|
"epoch": 0.058577405857740586,
|
||
|
|
"grad_norm": 2.515625,
|
||
|
|
"learning_rate": 3.4500000000000005e-05,
|
||
|
|
"loss": 9.1462,
|
||
|
|
"mean_token_accuracy": 0.05712815783917904,
|
||
|
|
"num_tokens": 128903.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.432404041290283,
|
||
|
|
"epoch": 0.06276150627615062,
|
||
|
|
"grad_norm": 2.546875,
|
||
|
|
"learning_rate": 3.7e-05,
|
||
|
|
"loss": 9.1137,
|
||
|
|
"mean_token_accuracy": 0.05686149187386036,
|
||
|
|
"num_tokens": 137630.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.388175106048584,
|
||
|
|
"epoch": 0.06694560669456066,
|
||
|
|
"grad_norm": 2.890625,
|
||
|
|
"learning_rate": 3.95e-05,
|
||
|
|
"loss": 8.8947,
|
||
|
|
"mean_token_accuracy": 0.06613010838627816,
|
||
|
|
"num_tokens": 146335.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.388596439361573,
|
||
|
|
"epoch": 0.07112970711297072,
|
||
|
|
"grad_norm": 2.4375,
|
||
|
|
"learning_rate": 4.2000000000000004e-05,
|
||
|
|
"loss": 8.8136,
|
||
|
|
"mean_token_accuracy": 0.06454679258167743,
|
||
|
|
"num_tokens": 155766.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.335438442230224,
|
||
|
|
"epoch": 0.07531380753138076,
|
||
|
|
"grad_norm": 2.234375,
|
||
|
|
"learning_rate": 4.45e-05,
|
||
|
|
"loss": 8.7316,
|
||
|
|
"mean_token_accuracy": 0.06548036001622677,
|
||
|
|
"num_tokens": 165844.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.317347526550293,
|
||
|
|
"epoch": 0.0794979079497908,
|
||
|
|
"grad_norm": 2.34375,
|
||
|
|
"learning_rate": 4.7000000000000004e-05,
|
||
|
|
"loss": 8.6896,
|
||
|
|
"mean_token_accuracy": 0.06795907951891422,
|
||
|
|
"num_tokens": 174858.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.24217710494995,
|
||
|
|
"epoch": 0.08368200836820083,
|
||
|
|
"grad_norm": 2.21875,
|
||
|
|
"learning_rate": 4.9500000000000004e-05,
|
||
|
|
"loss": 8.5453,
|
||
|
|
"mean_token_accuracy": 0.07007661424577236,
|
||
|
|
"num_tokens": 184020.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.19391098022461,
|
||
|
|
"epoch": 0.08786610878661087,
|
||
|
|
"grad_norm": 2.25,
|
||
|
|
"learning_rate": 5.2e-05,
|
||
|
|
"loss": 8.4004,
|
||
|
|
"mean_token_accuracy": 0.06834917515516281,
|
||
|
|
"num_tokens": 193714.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.143691921234131,
|
||
|
|
"epoch": 0.09205020920502092,
|
||
|
|
"grad_norm": 2.265625,
|
||
|
|
"learning_rate": 5.45e-05,
|
||
|
|
"loss": 8.3625,
|
||
|
|
"mean_token_accuracy": 0.07014007195830345,
|
||
|
|
"num_tokens": 203139.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 10.033193874359132,
|
||
|
|
"epoch": 0.09623430962343096,
|
||
|
|
"grad_norm": 2.75,
|
||
|
|
"learning_rate": 5.7e-05,
|
||
|
|
"loss": 8.2108,
|
||
|
|
"mean_token_accuracy": 0.0716083101928234,
|
||
|
|
"num_tokens": 212446.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.93264389038086,
|
||
|
|
"epoch": 0.100418410041841,
|
||
|
|
"grad_norm": 2.15625,
|
||
|
|
"learning_rate": 5.9499999999999996e-05,
|
||
|
|
"loss": 8.0305,
|
||
|
|
"mean_token_accuracy": 0.08365688249468803,
|
||
|
|
"num_tokens": 220910.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.831494235992432,
|
||
|
|
"epoch": 0.10460251046025104,
|
||
|
|
"grad_norm": 1.9453125,
|
||
|
|
"learning_rate": 6.2e-05,
|
||
|
|
"loss": 7.975,
|
||
|
|
"mean_token_accuracy": 0.07431616149842739,
|
||
|
|
"num_tokens": 230522.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.695558643341064,
|
||
|
|
"epoch": 0.1087866108786611,
|
||
|
|
"grad_norm": 1.8046875,
|
||
|
|
"learning_rate": 6.450000000000001e-05,
|
||
|
|
"loss": 7.8131,
|
||
|
|
"mean_token_accuracy": 0.07820754498243332,
|
||
|
|
"num_tokens": 240092.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.519502639770508,
|
||
|
|
"epoch": 0.11297071129707113,
|
||
|
|
"grad_norm": 1.859375,
|
||
|
|
"learning_rate": 6.7e-05,
|
||
|
|
"loss": 7.7618,
|
||
|
|
"mean_token_accuracy": 0.07841893658041954,
|
||
|
|
"num_tokens": 249478.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.289987373352051,
|
||
|
|
"epoch": 0.11715481171548117,
|
||
|
|
"grad_norm": 2.578125,
|
||
|
|
"learning_rate": 6.950000000000001e-05,
|
||
|
|
"loss": 7.522,
|
||
|
|
"mean_token_accuracy": 0.09086068868637084,
|
||
|
|
"num_tokens": 257714.0,
|
||
|
|
"step": 140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 9.143731307983398,
|
||
|
|
"epoch": 0.12133891213389121,
|
||
|
|
"grad_norm": 1.6484375,
|
||
|
|
"learning_rate": 7.2e-05,
|
||
|
|
"loss": 7.5578,
|
||
|
|
"mean_token_accuracy": 0.08316774666309357,
|
||
|
|
"num_tokens": 266569.0,
|
||
|
|
"step": 145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.99811429977417,
|
||
|
|
"epoch": 0.12552301255230125,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 7.45e-05,
|
||
|
|
"loss": 7.4546,
|
||
|
|
"mean_token_accuracy": 0.08273414000868798,
|
||
|
|
"num_tokens": 276688.0,
|
||
|
|
"step": 150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.839478302001954,
|
||
|
|
"epoch": 0.1297071129707113,
|
||
|
|
"grad_norm": 1.6171875,
|
||
|
|
"learning_rate": 7.7e-05,
|
||
|
|
"loss": 7.3044,
|
||
|
|
"mean_token_accuracy": 0.08153865486383438,
|
||
|
|
"num_tokens": 285430.0,
|
||
|
|
"step": 155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.572208499908447,
|
||
|
|
"epoch": 0.13389121338912133,
|
||
|
|
"grad_norm": 1.8203125,
|
||
|
|
"learning_rate": 7.950000000000001e-05,
|
||
|
|
"loss": 7.2963,
|
||
|
|
"mean_token_accuracy": 0.08305188342928886,
|
||
|
|
"num_tokens": 295727.0,
|
||
|
|
"step": 160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.346776962280273,
|
||
|
|
"epoch": 0.13807531380753138,
|
||
|
|
"grad_norm": 1.6171875,
|
||
|
|
"learning_rate": 8.2e-05,
|
||
|
|
"loss": 7.2537,
|
||
|
|
"mean_token_accuracy": 0.0843418687582016,
|
||
|
|
"num_tokens": 304854.0,
|
||
|
|
"step": 165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.35010871887207,
|
||
|
|
"epoch": 0.14225941422594143,
|
||
|
|
"grad_norm": 1.640625,
|
||
|
|
"learning_rate": 8.450000000000001e-05,
|
||
|
|
"loss": 7.2224,
|
||
|
|
"mean_token_accuracy": 0.08320909515023231,
|
||
|
|
"num_tokens": 313579.0,
|
||
|
|
"step": 170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.109733581542969,
|
||
|
|
"epoch": 0.14644351464435146,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 8.7e-05,
|
||
|
|
"loss": 7.2637,
|
||
|
|
"mean_token_accuracy": 0.08496511876583099,
|
||
|
|
"num_tokens": 323310.0,
|
||
|
|
"step": 175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.118343544006347,
|
||
|
|
"epoch": 0.1506276150627615,
|
||
|
|
"grad_norm": 1.4453125,
|
||
|
|
"learning_rate": 8.95e-05,
|
||
|
|
"loss": 7.1236,
|
||
|
|
"mean_token_accuracy": 0.0888123981654644,
|
||
|
|
"num_tokens": 331720.0,
|
||
|
|
"step": 180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 8.003835868835449,
|
||
|
|
"epoch": 0.15481171548117154,
|
||
|
|
"grad_norm": 1.6640625,
|
||
|
|
"learning_rate": 9.2e-05,
|
||
|
|
"loss": 7.0728,
|
||
|
|
"mean_token_accuracy": 0.0916049025952816,
|
||
|
|
"num_tokens": 340331.0,
|
||
|
|
"step": 185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.846502780914307,
|
||
|
|
"epoch": 0.1589958158995816,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 9.45e-05,
|
||
|
|
"loss": 7.0803,
|
||
|
|
"mean_token_accuracy": 0.09315933063626289,
|
||
|
|
"num_tokens": 349677.0,
|
||
|
|
"step": 190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.870132970809936,
|
||
|
|
"epoch": 0.16317991631799164,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 9.7e-05,
|
||
|
|
"loss": 7.0721,
|
||
|
|
"mean_token_accuracy": 0.08652734383940697,
|
||
|
|
"num_tokens": 358674.0,
|
||
|
|
"step": 195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.712577533721924,
|
||
|
|
"epoch": 0.16736401673640167,
|
||
|
|
"grad_norm": 1.4921875,
|
||
|
|
"learning_rate": 9.95e-05,
|
||
|
|
"loss": 7.0811,
|
||
|
|
"mean_token_accuracy": 0.08503658622503281,
|
||
|
|
"num_tokens": 368258.0,
|
||
|
|
"step": 200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.745207118988037,
|
||
|
|
"epoch": 0.17154811715481172,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.000102,
|
||
|
|
"loss": 6.9726,
|
||
|
|
"mean_token_accuracy": 0.09250840395689011,
|
||
|
|
"num_tokens": 377083.0,
|
||
|
|
"step": 205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.754372835159302,
|
||
|
|
"epoch": 0.17573221757322174,
|
||
|
|
"grad_norm": 1.7109375,
|
||
|
|
"learning_rate": 0.00010449999999999999,
|
||
|
|
"loss": 7.0446,
|
||
|
|
"mean_token_accuracy": 0.0841131079941988,
|
||
|
|
"num_tokens": 385456.0,
|
||
|
|
"step": 210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.639361429214477,
|
||
|
|
"epoch": 0.1799163179916318,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.000107,
|
||
|
|
"loss": 6.9265,
|
||
|
|
"mean_token_accuracy": 0.0942225843667984,
|
||
|
|
"num_tokens": 395295.0,
|
||
|
|
"step": 215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.558081722259521,
|
||
|
|
"epoch": 0.18410041841004185,
|
||
|
|
"grad_norm": 1.796875,
|
||
|
|
"learning_rate": 0.0001095,
|
||
|
|
"loss": 6.9772,
|
||
|
|
"mean_token_accuracy": 0.08982849642634391,
|
||
|
|
"num_tokens": 405023.0,
|
||
|
|
"step": 220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.534724760055542,
|
||
|
|
"epoch": 0.18828451882845187,
|
||
|
|
"grad_norm": 1.6171875,
|
||
|
|
"learning_rate": 0.000112,
|
||
|
|
"loss": 6.9996,
|
||
|
|
"mean_token_accuracy": 0.08760679811239243,
|
||
|
|
"num_tokens": 414224.0,
|
||
|
|
"step": 225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.567825078964233,
|
||
|
|
"epoch": 0.19246861924686193,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0001145,
|
||
|
|
"loss": 6.8948,
|
||
|
|
"mean_token_accuracy": 0.08697729334235191,
|
||
|
|
"num_tokens": 423951.0,
|
||
|
|
"step": 230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.65638952255249,
|
||
|
|
"epoch": 0.19665271966527198,
|
||
|
|
"grad_norm": 1.5546875,
|
||
|
|
"learning_rate": 0.00011700000000000001,
|
||
|
|
"loss": 6.9173,
|
||
|
|
"mean_token_accuracy": 0.08747867494821548,
|
||
|
|
"num_tokens": 432427.0,
|
||
|
|
"step": 235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.392250013351441,
|
||
|
|
"epoch": 0.200836820083682,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.00011949999999999999,
|
||
|
|
"loss": 6.8495,
|
||
|
|
"mean_token_accuracy": 0.09490769654512406,
|
||
|
|
"num_tokens": 441560.0,
|
||
|
|
"step": 240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.542767906188965,
|
||
|
|
"epoch": 0.20502092050209206,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 0.000122,
|
||
|
|
"loss": 6.9423,
|
||
|
|
"mean_token_accuracy": 0.08346537575125694,
|
||
|
|
"num_tokens": 450364.0,
|
||
|
|
"step": 245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.399922561645508,
|
||
|
|
"epoch": 0.20920502092050208,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0001245,
|
||
|
|
"loss": 6.8922,
|
||
|
|
"mean_token_accuracy": 0.08459680303931236,
|
||
|
|
"num_tokens": 460076.0,
|
||
|
|
"step": 250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.435028028488159,
|
||
|
|
"epoch": 0.21338912133891214,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000127,
|
||
|
|
"loss": 6.8343,
|
||
|
|
"mean_token_accuracy": 0.09127931594848633,
|
||
|
|
"num_tokens": 468718.0,
|
||
|
|
"step": 255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.456234979629516,
|
||
|
|
"epoch": 0.2175732217573222,
|
||
|
|
"grad_norm": 1.3359375,
|
||
|
|
"learning_rate": 0.0001295,
|
||
|
|
"loss": 6.9113,
|
||
|
|
"mean_token_accuracy": 0.08921206891536712,
|
||
|
|
"num_tokens": 478436.0,
|
||
|
|
"step": 260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.390152215957642,
|
||
|
|
"epoch": 0.2217573221757322,
|
||
|
|
"grad_norm": 1.6171875,
|
||
|
|
"learning_rate": 0.000132,
|
||
|
|
"loss": 6.9278,
|
||
|
|
"mean_token_accuracy": 0.0872597984969616,
|
||
|
|
"num_tokens": 486833.0,
|
||
|
|
"step": 265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.41746563911438,
|
||
|
|
"epoch": 0.22594142259414227,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.00013450000000000002,
|
||
|
|
"loss": 6.7959,
|
||
|
|
"mean_token_accuracy": 0.09919953644275666,
|
||
|
|
"num_tokens": 495119.0,
|
||
|
|
"step": 270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.363225364685059,
|
||
|
|
"epoch": 0.2301255230125523,
|
||
|
|
"grad_norm": 1.6953125,
|
||
|
|
"learning_rate": 0.00013700000000000002,
|
||
|
|
"loss": 6.9685,
|
||
|
|
"mean_token_accuracy": 0.09823801144957542,
|
||
|
|
"num_tokens": 505396.0,
|
||
|
|
"step": 275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.373254871368408,
|
||
|
|
"epoch": 0.23430962343096234,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 0.0001395,
|
||
|
|
"loss": 6.8264,
|
||
|
|
"mean_token_accuracy": 0.08988286629319191,
|
||
|
|
"num_tokens": 515259.0,
|
||
|
|
"step": 280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.381401538848877,
|
||
|
|
"epoch": 0.2384937238493724,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.00014199999999999998,
|
||
|
|
"loss": 6.8366,
|
||
|
|
"mean_token_accuracy": 0.08750834614038468,
|
||
|
|
"num_tokens": 523608.0,
|
||
|
|
"step": 285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.272293424606323,
|
||
|
|
"epoch": 0.24267782426778242,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0001445,
|
||
|
|
"loss": 6.8138,
|
||
|
|
"mean_token_accuracy": 0.09048807919025421,
|
||
|
|
"num_tokens": 534613.0,
|
||
|
|
"step": 290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.320169878005982,
|
||
|
|
"epoch": 0.24686192468619247,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 0.000147,
|
||
|
|
"loss": 6.8579,
|
||
|
|
"mean_token_accuracy": 0.09750684052705764,
|
||
|
|
"num_tokens": 543347.0,
|
||
|
|
"step": 295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.278151416778565,
|
||
|
|
"epoch": 0.2510460251046025,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0001495,
|
||
|
|
"loss": 6.8097,
|
||
|
|
"mean_token_accuracy": 0.08896707370877266,
|
||
|
|
"num_tokens": 552371.0,
|
||
|
|
"step": 300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.234066581726074,
|
||
|
|
"epoch": 0.25523012552301255,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.000152,
|
||
|
|
"loss": 6.7401,
|
||
|
|
"mean_token_accuracy": 0.09521848261356354,
|
||
|
|
"num_tokens": 560742.0,
|
||
|
|
"step": 305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.309448719024658,
|
||
|
|
"epoch": 0.2594142259414226,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00015450000000000001,
|
||
|
|
"loss": 6.8506,
|
||
|
|
"mean_token_accuracy": 0.09421026632189751,
|
||
|
|
"num_tokens": 569960.0,
|
||
|
|
"step": 310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.26940336227417,
|
||
|
|
"epoch": 0.26359832635983266,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000157,
|
||
|
|
"loss": 6.7952,
|
||
|
|
"mean_token_accuracy": 0.09265207946300506,
|
||
|
|
"num_tokens": 578859.0,
|
||
|
|
"step": 315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1658327102661135,
|
||
|
|
"epoch": 0.26778242677824265,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0001595,
|
||
|
|
"loss": 6.802,
|
||
|
|
"mean_token_accuracy": 0.09623523280024529,
|
||
|
|
"num_tokens": 588146.0,
|
||
|
|
"step": 320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.232771396636963,
|
||
|
|
"epoch": 0.2719665271966527,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.000162,
|
||
|
|
"loss": 6.7437,
|
||
|
|
"mean_token_accuracy": 0.09764528870582581,
|
||
|
|
"num_tokens": 597268.0,
|
||
|
|
"step": 325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.080677461624146,
|
||
|
|
"epoch": 0.27615062761506276,
|
||
|
|
"grad_norm": 1.328125,
|
||
|
|
"learning_rate": 0.00016450000000000001,
|
||
|
|
"loss": 6.676,
|
||
|
|
"mean_token_accuracy": 0.0969509594142437,
|
||
|
|
"num_tokens": 606199.0,
|
||
|
|
"step": 330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.3103187561035154,
|
||
|
|
"epoch": 0.2803347280334728,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.00016700000000000002,
|
||
|
|
"loss": 6.8102,
|
||
|
|
"mean_token_accuracy": 0.08201513588428497,
|
||
|
|
"num_tokens": 615966.0,
|
||
|
|
"step": 335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.242901706695557,
|
||
|
|
"epoch": 0.28451882845188287,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00016950000000000003,
|
||
|
|
"loss": 6.7714,
|
||
|
|
"mean_token_accuracy": 0.0932280994951725,
|
||
|
|
"num_tokens": 625689.0,
|
||
|
|
"step": 340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.17906231880188,
|
||
|
|
"epoch": 0.28870292887029286,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.00017199999999999998,
|
||
|
|
"loss": 6.7957,
|
||
|
|
"mean_token_accuracy": 0.08773538246750831,
|
||
|
|
"num_tokens": 634877.0,
|
||
|
|
"step": 345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.1589775562286375,
|
||
|
|
"epoch": 0.2928870292887029,
|
||
|
|
"grad_norm": 1.5390625,
|
||
|
|
"learning_rate": 0.00017449999999999999,
|
||
|
|
"loss": 6.7211,
|
||
|
|
"mean_token_accuracy": 0.09845930486917495,
|
||
|
|
"num_tokens": 644042.0,
|
||
|
|
"step": 350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.122976160049438,
|
||
|
|
"epoch": 0.29707112970711297,
|
||
|
|
"grad_norm": 1.4296875,
|
||
|
|
"learning_rate": 0.000177,
|
||
|
|
"loss": 6.7157,
|
||
|
|
"mean_token_accuracy": 0.09408211931586266,
|
||
|
|
"num_tokens": 653072.0,
|
||
|
|
"step": 355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.08035979270935,
|
||
|
|
"epoch": 0.301255230125523,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0001795,
|
||
|
|
"loss": 6.7206,
|
||
|
|
"mean_token_accuracy": 0.09660579040646552,
|
||
|
|
"num_tokens": 663686.0,
|
||
|
|
"step": 360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.087335777282715,
|
||
|
|
"epoch": 0.3054393305439331,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.000182,
|
||
|
|
"loss": 6.655,
|
||
|
|
"mean_token_accuracy": 0.09818260595202447,
|
||
|
|
"num_tokens": 672293.0,
|
||
|
|
"step": 365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.929145002365113,
|
||
|
|
"epoch": 0.30962343096234307,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0001845,
|
||
|
|
"loss": 6.617,
|
||
|
|
"mean_token_accuracy": 0.10118300542235374,
|
||
|
|
"num_tokens": 681758.0,
|
||
|
|
"step": 370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.119603776931763,
|
||
|
|
"epoch": 0.3138075313807531,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000187,
|
||
|
|
"loss": 6.6496,
|
||
|
|
"mean_token_accuracy": 0.10070758163928986,
|
||
|
|
"num_tokens": 690727.0,
|
||
|
|
"step": 375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.051980209350586,
|
||
|
|
"epoch": 0.3179916317991632,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0001895,
|
||
|
|
"loss": 6.6052,
|
||
|
|
"mean_token_accuracy": 0.09968686252832412,
|
||
|
|
"num_tokens": 701210.0,
|
||
|
|
"step": 380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.929204320907592,
|
||
|
|
"epoch": 0.32217573221757323,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000192,
|
||
|
|
"loss": 6.5924,
|
||
|
|
"mean_token_accuracy": 0.10255414322018623,
|
||
|
|
"num_tokens": 710869.0,
|
||
|
|
"step": 385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.104875373840332,
|
||
|
|
"epoch": 0.3263598326359833,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0001945,
|
||
|
|
"loss": 6.7186,
|
||
|
|
"mean_token_accuracy": 0.095282444357872,
|
||
|
|
"num_tokens": 721455.0,
|
||
|
|
"step": 390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.909361505508423,
|
||
|
|
"epoch": 0.3305439330543933,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00019700000000000002,
|
||
|
|
"loss": 6.5982,
|
||
|
|
"mean_token_accuracy": 0.10492872297763825,
|
||
|
|
"num_tokens": 730917.0,
|
||
|
|
"step": 395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.0232825756073,
|
||
|
|
"epoch": 0.33472803347280333,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.00019950000000000002,
|
||
|
|
"loss": 6.6235,
|
||
|
|
"mean_token_accuracy": 0.10053492337465286,
|
||
|
|
"num_tokens": 739302.0,
|
||
|
|
"step": 400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.034136819839477,
|
||
|
|
"epoch": 0.3389121338912134,
|
||
|
|
"grad_norm": 1.4609375,
|
||
|
|
"learning_rate": 0.000202,
|
||
|
|
"loss": 6.5922,
|
||
|
|
"mean_token_accuracy": 0.09860573858022689,
|
||
|
|
"num_tokens": 748785.0,
|
||
|
|
"step": 405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.9551417350769045,
|
||
|
|
"epoch": 0.34309623430962344,
|
||
|
|
"grad_norm": 1.25,
|
||
|
|
"learning_rate": 0.00020449999999999998,
|
||
|
|
"loss": 6.5277,
|
||
|
|
"mean_token_accuracy": 0.10383330285549164,
|
||
|
|
"num_tokens": 757215.0,
|
||
|
|
"step": 410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.833004713058472,
|
||
|
|
"epoch": 0.3472803347280335,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.000207,
|
||
|
|
"loss": 6.4628,
|
||
|
|
"mean_token_accuracy": 0.10961654931306838,
|
||
|
|
"num_tokens": 765682.0,
|
||
|
|
"step": 415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 7.001798439025879,
|
||
|
|
"epoch": 0.3514644351464435,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.0002095,
|
||
|
|
"loss": 6.6685,
|
||
|
|
"mean_token_accuracy": 0.09785127714276314,
|
||
|
|
"num_tokens": 774814.0,
|
||
|
|
"step": 420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.951812839508056,
|
||
|
|
"epoch": 0.35564853556485354,
|
||
|
|
"grad_norm": 1.46875,
|
||
|
|
"learning_rate": 0.000212,
|
||
|
|
"loss": 6.5856,
|
||
|
|
"mean_token_accuracy": 0.10029251947999,
|
||
|
|
"num_tokens": 784019.0,
|
||
|
|
"step": 425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.814007663726807,
|
||
|
|
"epoch": 0.3598326359832636,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0002145,
|
||
|
|
"loss": 6.4521,
|
||
|
|
"mean_token_accuracy": 0.10874552577733994,
|
||
|
|
"num_tokens": 793237.0,
|
||
|
|
"step": 430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.967527246475219,
|
||
|
|
"epoch": 0.36401673640167365,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00021700000000000002,
|
||
|
|
"loss": 6.5148,
|
||
|
|
"mean_token_accuracy": 0.1004909910261631,
|
||
|
|
"num_tokens": 801548.0,
|
||
|
|
"step": 435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.829876708984375,
|
||
|
|
"epoch": 0.3682008368200837,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0002195,
|
||
|
|
"loss": 6.5539,
|
||
|
|
"mean_token_accuracy": 0.10507597774267197,
|
||
|
|
"num_tokens": 810974.0,
|
||
|
|
"step": 440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.837385892868042,
|
||
|
|
"epoch": 0.3723849372384937,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.000222,
|
||
|
|
"loss": 6.4384,
|
||
|
|
"mean_token_accuracy": 0.10976337790489196,
|
||
|
|
"num_tokens": 820023.0,
|
||
|
|
"step": 445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.836634254455566,
|
||
|
|
"epoch": 0.37656903765690375,
|
||
|
|
"grad_norm": 1.5234375,
|
||
|
|
"learning_rate": 0.0002245,
|
||
|
|
"loss": 6.5294,
|
||
|
|
"mean_token_accuracy": 0.10367678925395012,
|
||
|
|
"num_tokens": 828297.0,
|
||
|
|
"step": 450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.901482248306275,
|
||
|
|
"epoch": 0.3807531380753138,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00022700000000000002,
|
||
|
|
"loss": 6.5793,
|
||
|
|
"mean_token_accuracy": 0.09453905671834946,
|
||
|
|
"num_tokens": 838268.0,
|
||
|
|
"step": 455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.938200902938843,
|
||
|
|
"epoch": 0.38493723849372385,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.00022950000000000002,
|
||
|
|
"loss": 6.4984,
|
||
|
|
"mean_token_accuracy": 0.10036915764212609,
|
||
|
|
"num_tokens": 846491.0,
|
||
|
|
"step": 460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.742056369781494,
|
||
|
|
"epoch": 0.3891213389121339,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00023200000000000003,
|
||
|
|
"loss": 6.4374,
|
||
|
|
"mean_token_accuracy": 0.10895640999078751,
|
||
|
|
"num_tokens": 856501.0,
|
||
|
|
"step": 465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.806368494033814,
|
||
|
|
"epoch": 0.39330543933054396,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.00023449999999999998,
|
||
|
|
"loss": 6.5002,
|
||
|
|
"mean_token_accuracy": 0.10559085234999657,
|
||
|
|
"num_tokens": 867054.0,
|
||
|
|
"step": 470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.738630914688111,
|
||
|
|
"epoch": 0.39748953974895396,
|
||
|
|
"grad_norm": 1.3203125,
|
||
|
|
"learning_rate": 0.000237,
|
||
|
|
"loss": 6.521,
|
||
|
|
"mean_token_accuracy": 0.10245606228709221,
|
||
|
|
"num_tokens": 875956.0,
|
||
|
|
"step": 475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.697034120559692,
|
||
|
|
"epoch": 0.401673640167364,
|
||
|
|
"grad_norm": 1.6171875,
|
||
|
|
"learning_rate": 0.0002395,
|
||
|
|
"loss": 6.4358,
|
||
|
|
"mean_token_accuracy": 0.10774662867188453,
|
||
|
|
"num_tokens": 884427.0,
|
||
|
|
"step": 480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.911193704605102,
|
||
|
|
"epoch": 0.40585774058577406,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000242,
|
||
|
|
"loss": 6.5239,
|
||
|
|
"mean_token_accuracy": 0.1094229944050312,
|
||
|
|
"num_tokens": 894181.0,
|
||
|
|
"step": 485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.690055084228516,
|
||
|
|
"epoch": 0.4100418410041841,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.0002445,
|
||
|
|
"loss": 6.3689,
|
||
|
|
"mean_token_accuracy": 0.11442587077617646,
|
||
|
|
"num_tokens": 904076.0,
|
||
|
|
"step": 490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.700846529006958,
|
||
|
|
"epoch": 0.41422594142259417,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000247,
|
||
|
|
"loss": 6.5172,
|
||
|
|
"mean_token_accuracy": 0.10785161033272743,
|
||
|
|
"num_tokens": 913915.0,
|
||
|
|
"step": 495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.8667717456817625,
|
||
|
|
"epoch": 0.41841004184100417,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0002495,
|
||
|
|
"loss": 6.5828,
|
||
|
|
"mean_token_accuracy": 0.10332566574215889,
|
||
|
|
"num_tokens": 922876.0,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.41841004184100417,
|
||
|
|
"eval_entropy": 6.700536389536166,
|
||
|
|
"eval_loss": 6.505311965942383,
|
||
|
|
"eval_mean_token_accuracy": 0.10990596924487554,
|
||
|
|
"eval_num_tokens": 922876.0,
|
||
|
|
"eval_runtime": 2.7776,
|
||
|
|
"eval_samples_per_second": 1406.597,
|
||
|
|
"eval_steps_per_second": 176.05,
|
||
|
|
"step": 500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.676968288421631,
|
||
|
|
"epoch": 0.4225941422594142,
|
||
|
|
"grad_norm": 1.3828125,
|
||
|
|
"learning_rate": 0.000252,
|
||
|
|
"loss": 6.3727,
|
||
|
|
"mean_token_accuracy": 0.11308198049664497,
|
||
|
|
"num_tokens": 931998.0,
|
||
|
|
"step": 505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.805904197692871,
|
||
|
|
"epoch": 0.42677824267782427,
|
||
|
|
"grad_norm": 1.4140625,
|
||
|
|
"learning_rate": 0.0002545,
|
||
|
|
"loss": 6.4411,
|
||
|
|
"mean_token_accuracy": 0.10866107791662216,
|
||
|
|
"num_tokens": 941387.0,
|
||
|
|
"step": 510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.625282573699951,
|
||
|
|
"epoch": 0.4309623430962343,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.000257,
|
||
|
|
"loss": 6.4789,
|
||
|
|
"mean_token_accuracy": 0.10362649038434028,
|
||
|
|
"num_tokens": 951866.0,
|
||
|
|
"step": 515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.657781028747559,
|
||
|
|
"epoch": 0.4351464435146444,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0002595,
|
||
|
|
"loss": 6.4117,
|
||
|
|
"mean_token_accuracy": 0.10945287123322486,
|
||
|
|
"num_tokens": 961252.0,
|
||
|
|
"step": 520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.821563005447388,
|
||
|
|
"epoch": 0.4393305439330544,
|
||
|
|
"grad_norm": 1.5,
|
||
|
|
"learning_rate": 0.000262,
|
||
|
|
"loss": 6.4206,
|
||
|
|
"mean_token_accuracy": 0.11085275113582611,
|
||
|
|
"num_tokens": 969857.0,
|
||
|
|
"step": 525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.679222440719604,
|
||
|
|
"epoch": 0.4435146443514644,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00026450000000000003,
|
||
|
|
"loss": 6.4176,
|
||
|
|
"mean_token_accuracy": 0.11243949085474014,
|
||
|
|
"num_tokens": 978754.0,
|
||
|
|
"step": 530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.723608922958374,
|
||
|
|
"epoch": 0.4476987447698745,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.00026700000000000004,
|
||
|
|
"loss": 6.391,
|
||
|
|
"mean_token_accuracy": 0.1103011853992939,
|
||
|
|
"num_tokens": 987935.0,
|
||
|
|
"step": 535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.682740306854248,
|
||
|
|
"epoch": 0.45188284518828453,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00026950000000000005,
|
||
|
|
"loss": 6.3588,
|
||
|
|
"mean_token_accuracy": 0.11257985085248948,
|
||
|
|
"num_tokens": 996873.0,
|
||
|
|
"step": 540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.741128253936767,
|
||
|
|
"epoch": 0.4560669456066946,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00027200000000000005,
|
||
|
|
"loss": 6.4534,
|
||
|
|
"mean_token_accuracy": 0.10576379746198654,
|
||
|
|
"num_tokens": 1006487.0,
|
||
|
|
"step": 545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.482868623733521,
|
||
|
|
"epoch": 0.4602510460251046,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0002745,
|
||
|
|
"loss": 6.2856,
|
||
|
|
"mean_token_accuracy": 0.11558721140027046,
|
||
|
|
"num_tokens": 1015715.0,
|
||
|
|
"step": 550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.656096649169922,
|
||
|
|
"epoch": 0.46443514644351463,
|
||
|
|
"grad_norm": 1.4375,
|
||
|
|
"learning_rate": 0.000277,
|
||
|
|
"loss": 6.4102,
|
||
|
|
"mean_token_accuracy": 0.11223409548401833,
|
||
|
|
"num_tokens": 1025091.0,
|
||
|
|
"step": 555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.6403412342071535,
|
||
|
|
"epoch": 0.4686192468619247,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0002795,
|
||
|
|
"loss": 6.342,
|
||
|
|
"mean_token_accuracy": 0.10930742770433426,
|
||
|
|
"num_tokens": 1034174.0,
|
||
|
|
"step": 560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.697489976882935,
|
||
|
|
"epoch": 0.47280334728033474,
|
||
|
|
"grad_norm": 1.40625,
|
||
|
|
"learning_rate": 0.00028199999999999997,
|
||
|
|
"loss": 6.549,
|
||
|
|
"mean_token_accuracy": 0.09722351431846618,
|
||
|
|
"num_tokens": 1043777.0,
|
||
|
|
"step": 565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.652381849288941,
|
||
|
|
"epoch": 0.4769874476987448,
|
||
|
|
"grad_norm": 1.359375,
|
||
|
|
"learning_rate": 0.0002845,
|
||
|
|
"loss": 6.3832,
|
||
|
|
"mean_token_accuracy": 0.11293103024363518,
|
||
|
|
"num_tokens": 1052749.0,
|
||
|
|
"step": 570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7199958801269535,
|
||
|
|
"epoch": 0.4811715481171548,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.000287,
|
||
|
|
"loss": 6.4071,
|
||
|
|
"mean_token_accuracy": 0.11299470067024231,
|
||
|
|
"num_tokens": 1061564.0,
|
||
|
|
"step": 575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.540546655654907,
|
||
|
|
"epoch": 0.48535564853556484,
|
||
|
|
"grad_norm": 1.5078125,
|
||
|
|
"learning_rate": 0.0002895,
|
||
|
|
"loss": 6.3267,
|
||
|
|
"mean_token_accuracy": 0.11745149567723275,
|
||
|
|
"num_tokens": 1070006.0,
|
||
|
|
"step": 580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.592943572998047,
|
||
|
|
"epoch": 0.4895397489539749,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000292,
|
||
|
|
"loss": 6.3903,
|
||
|
|
"mean_token_accuracy": 0.1095091424882412,
|
||
|
|
"num_tokens": 1079799.0,
|
||
|
|
"step": 585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.655527019500733,
|
||
|
|
"epoch": 0.49372384937238495,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.0002945,
|
||
|
|
"loss": 6.2219,
|
||
|
|
"mean_token_accuracy": 0.120665642619133,
|
||
|
|
"num_tokens": 1088842.0,
|
||
|
|
"step": 590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.531441926956177,
|
||
|
|
"epoch": 0.497907949790795,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000297,
|
||
|
|
"loss": 6.3064,
|
||
|
|
"mean_token_accuracy": 0.12399455532431602,
|
||
|
|
"num_tokens": 1097960.0,
|
||
|
|
"step": 595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.42484769821167,
|
||
|
|
"epoch": 0.502092050209205,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.0002995,
|
||
|
|
"loss": 6.2793,
|
||
|
|
"mean_token_accuracy": 0.11625320315361024,
|
||
|
|
"num_tokens": 1106797.0,
|
||
|
|
"step": 600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.580197429656982,
|
||
|
|
"epoch": 0.5062761506276151,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000302,
|
||
|
|
"loss": 6.4432,
|
||
|
|
"mean_token_accuracy": 0.11806596219539642,
|
||
|
|
"num_tokens": 1116384.0,
|
||
|
|
"step": 605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.462054252624512,
|
||
|
|
"epoch": 0.5104602510460251,
|
||
|
|
"grad_norm": 1.296875,
|
||
|
|
"learning_rate": 0.0003045,
|
||
|
|
"loss": 6.2024,
|
||
|
|
"mean_token_accuracy": 0.12296005710959435,
|
||
|
|
"num_tokens": 1125206.0,
|
||
|
|
"step": 610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.673148584365845,
|
||
|
|
"epoch": 0.5146443514644351,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.000307,
|
||
|
|
"loss": 6.4218,
|
||
|
|
"mean_token_accuracy": 0.11573300361633301,
|
||
|
|
"num_tokens": 1134110.0,
|
||
|
|
"step": 615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.7004382610321045,
|
||
|
|
"epoch": 0.5188284518828452,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.0003095,
|
||
|
|
"loss": 6.417,
|
||
|
|
"mean_token_accuracy": 0.11261885166168213,
|
||
|
|
"num_tokens": 1142833.0,
|
||
|
|
"step": 620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.535337591171265,
|
||
|
|
"epoch": 0.5230125523012552,
|
||
|
|
"grad_norm": 1.375,
|
||
|
|
"learning_rate": 0.000312,
|
||
|
|
"loss": 6.3455,
|
||
|
|
"mean_token_accuracy": 0.11737915500998497,
|
||
|
|
"num_tokens": 1152006.0,
|
||
|
|
"step": 625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4866430282592775,
|
||
|
|
"epoch": 0.5271966527196653,
|
||
|
|
"grad_norm": 1.421875,
|
||
|
|
"learning_rate": 0.0003145,
|
||
|
|
"loss": 6.2844,
|
||
|
|
"mean_token_accuracy": 0.11385276094079018,
|
||
|
|
"num_tokens": 1161061.0,
|
||
|
|
"step": 630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.597733354568481,
|
||
|
|
"epoch": 0.5313807531380753,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000317,
|
||
|
|
"loss": 6.3047,
|
||
|
|
"mean_token_accuracy": 0.11783810779452324,
|
||
|
|
"num_tokens": 1170754.0,
|
||
|
|
"step": 635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.399986743927002,
|
||
|
|
"epoch": 0.5355648535564853,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0003195,
|
||
|
|
"loss": 6.2454,
|
||
|
|
"mean_token_accuracy": 0.11883974969387054,
|
||
|
|
"num_tokens": 1180854.0,
|
||
|
|
"step": 640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.562164402008056,
|
||
|
|
"epoch": 0.5397489539748954,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000322,
|
||
|
|
"loss": 6.3273,
|
||
|
|
"mean_token_accuracy": 0.11495971083641052,
|
||
|
|
"num_tokens": 1190567.0,
|
||
|
|
"step": 645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4136192321777346,
|
||
|
|
"epoch": 0.5439330543933054,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.00032450000000000003,
|
||
|
|
"loss": 6.1772,
|
||
|
|
"mean_token_accuracy": 0.12412636205554009,
|
||
|
|
"num_tokens": 1200247.0,
|
||
|
|
"step": 650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.411277961730957,
|
||
|
|
"epoch": 0.5481171548117155,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00032700000000000003,
|
||
|
|
"loss": 6.29,
|
||
|
|
"mean_token_accuracy": 0.11657113656401634,
|
||
|
|
"num_tokens": 1209358.0,
|
||
|
|
"step": 655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.452598428726196,
|
||
|
|
"epoch": 0.5523012552301255,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.00032950000000000004,
|
||
|
|
"loss": 6.3091,
|
||
|
|
"mean_token_accuracy": 0.12059221267700196,
|
||
|
|
"num_tokens": 1217746.0,
|
||
|
|
"step": 660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.468178224563599,
|
||
|
|
"epoch": 0.5564853556485355,
|
||
|
|
"grad_norm": 1.3984375,
|
||
|
|
"learning_rate": 0.00033200000000000005,
|
||
|
|
"loss": 6.273,
|
||
|
|
"mean_token_accuracy": 0.12242133840918541,
|
||
|
|
"num_tokens": 1226829.0,
|
||
|
|
"step": 665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.409869623184204,
|
||
|
|
"epoch": 0.5606694560669456,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.00033450000000000005,
|
||
|
|
"loss": 6.1811,
|
||
|
|
"mean_token_accuracy": 0.1252070352435112,
|
||
|
|
"num_tokens": 1236642.0,
|
||
|
|
"step": 670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.611316394805908,
|
||
|
|
"epoch": 0.5648535564853556,
|
||
|
|
"grad_norm": 1.3671875,
|
||
|
|
"learning_rate": 0.000337,
|
||
|
|
"loss": 6.3054,
|
||
|
|
"mean_token_accuracy": 0.12332511767745018,
|
||
|
|
"num_tokens": 1244934.0,
|
||
|
|
"step": 675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.345842742919922,
|
||
|
|
"epoch": 0.5690376569037657,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0003395,
|
||
|
|
"loss": 6.1933,
|
||
|
|
"mean_token_accuracy": 0.11780603304505348,
|
||
|
|
"num_tokens": 1254786.0,
|
||
|
|
"step": 680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.343827581405639,
|
||
|
|
"epoch": 0.5732217573221757,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000342,
|
||
|
|
"loss": 6.1659,
|
||
|
|
"mean_token_accuracy": 0.12387140616774558,
|
||
|
|
"num_tokens": 1263745.0,
|
||
|
|
"step": 685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.4398839473724365,
|
||
|
|
"epoch": 0.5774058577405857,
|
||
|
|
"grad_norm": 1.28125,
|
||
|
|
"learning_rate": 0.00034449999999999997,
|
||
|
|
"loss": 6.3144,
|
||
|
|
"mean_token_accuracy": 0.12714288905262947,
|
||
|
|
"num_tokens": 1273101.0,
|
||
|
|
"step": 690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.485600519180298,
|
||
|
|
"epoch": 0.5815899581589958,
|
||
|
|
"grad_norm": 1.453125,
|
||
|
|
"learning_rate": 0.000347,
|
||
|
|
"loss": 6.2931,
|
||
|
|
"mean_token_accuracy": 0.11583595350384712,
|
||
|
|
"num_tokens": 1282547.0,
|
||
|
|
"step": 695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.455876684188842,
|
||
|
|
"epoch": 0.5857740585774058,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0003495,
|
||
|
|
"loss": 6.3152,
|
||
|
|
"mean_token_accuracy": 0.11679297238588333,
|
||
|
|
"num_tokens": 1291594.0,
|
||
|
|
"step": 700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.429898071289062,
|
||
|
|
"epoch": 0.5899581589958159,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000352,
|
||
|
|
"loss": 6.2199,
|
||
|
|
"mean_token_accuracy": 0.12549455389380454,
|
||
|
|
"num_tokens": 1300282.0,
|
||
|
|
"step": 705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.407459688186646,
|
||
|
|
"epoch": 0.5941422594142259,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.0003545,
|
||
|
|
"loss": 6.3096,
|
||
|
|
"mean_token_accuracy": 0.12226130589842796,
|
||
|
|
"num_tokens": 1309304.0,
|
||
|
|
"step": 710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.392927360534668,
|
||
|
|
"epoch": 0.5983263598326359,
|
||
|
|
"grad_norm": 1.34375,
|
||
|
|
"learning_rate": 0.000357,
|
||
|
|
"loss": 6.1472,
|
||
|
|
"mean_token_accuracy": 0.12595504522323608,
|
||
|
|
"num_tokens": 1317638.0,
|
||
|
|
"step": 715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.5016227722167965,
|
||
|
|
"epoch": 0.602510460251046,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0003595,
|
||
|
|
"loss": 6.353,
|
||
|
|
"mean_token_accuracy": 0.11902206242084504,
|
||
|
|
"num_tokens": 1327242.0,
|
||
|
|
"step": 720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.401812124252319,
|
||
|
|
"epoch": 0.606694560669456,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000362,
|
||
|
|
"loss": 6.1596,
|
||
|
|
"mean_token_accuracy": 0.12535706236958505,
|
||
|
|
"num_tokens": 1335880.0,
|
||
|
|
"step": 725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.383457088470459,
|
||
|
|
"epoch": 0.6108786610878661,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.0003645,
|
||
|
|
"loss": 6.2361,
|
||
|
|
"mean_token_accuracy": 0.12056306451559066,
|
||
|
|
"num_tokens": 1344909.0,
|
||
|
|
"step": 730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.346205854415894,
|
||
|
|
"epoch": 0.6150627615062761,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000367,
|
||
|
|
"loss": 6.1104,
|
||
|
|
"mean_token_accuracy": 0.12955476492643356,
|
||
|
|
"num_tokens": 1353997.0,
|
||
|
|
"step": 735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.379322576522827,
|
||
|
|
"epoch": 0.6192468619246861,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0003695,
|
||
|
|
"loss": 6.2733,
|
||
|
|
"mean_token_accuracy": 0.12443547993898392,
|
||
|
|
"num_tokens": 1363293.0,
|
||
|
|
"step": 740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.49610013961792,
|
||
|
|
"epoch": 0.6234309623430963,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000372,
|
||
|
|
"loss": 6.2785,
|
||
|
|
"mean_token_accuracy": 0.11846815049648285,
|
||
|
|
"num_tokens": 1372174.0,
|
||
|
|
"step": 745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.406333255767822,
|
||
|
|
"epoch": 0.6276150627615062,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0003745,
|
||
|
|
"loss": 6.1697,
|
||
|
|
"mean_token_accuracy": 0.12304460108280182,
|
||
|
|
"num_tokens": 1381067.0,
|
||
|
|
"step": 750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.325730276107788,
|
||
|
|
"epoch": 0.6317991631799164,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000377,
|
||
|
|
"loss": 6.1643,
|
||
|
|
"mean_token_accuracy": 0.12812735885381699,
|
||
|
|
"num_tokens": 1390072.0,
|
||
|
|
"step": 755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.292504358291626,
|
||
|
|
"epoch": 0.6359832635983264,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0003795,
|
||
|
|
"loss": 6.156,
|
||
|
|
"mean_token_accuracy": 0.12865231558680534,
|
||
|
|
"num_tokens": 1399391.0,
|
||
|
|
"step": 760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.304660320281982,
|
||
|
|
"epoch": 0.6401673640167364,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.000382,
|
||
|
|
"loss": 6.1631,
|
||
|
|
"mean_token_accuracy": 0.12419576495885849,
|
||
|
|
"num_tokens": 1408054.0,
|
||
|
|
"step": 765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.39186725616455,
|
||
|
|
"epoch": 0.6443514644351465,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0003845,
|
||
|
|
"loss": 6.1785,
|
||
|
|
"mean_token_accuracy": 0.11784627810120582,
|
||
|
|
"num_tokens": 1417406.0,
|
||
|
|
"step": 770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.323220872879029,
|
||
|
|
"epoch": 0.6485355648535565,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00038700000000000003,
|
||
|
|
"loss": 6.237,
|
||
|
|
"mean_token_accuracy": 0.11933397874236107,
|
||
|
|
"num_tokens": 1426907.0,
|
||
|
|
"step": 775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.324512672424317,
|
||
|
|
"epoch": 0.6527196652719666,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00038950000000000003,
|
||
|
|
"loss": 6.3007,
|
||
|
|
"mean_token_accuracy": 0.11848932132124901,
|
||
|
|
"num_tokens": 1436085.0,
|
||
|
|
"step": 780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.432321214675904,
|
||
|
|
"epoch": 0.6569037656903766,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00039200000000000004,
|
||
|
|
"loss": 6.208,
|
||
|
|
"mean_token_accuracy": 0.12037489041686059,
|
||
|
|
"num_tokens": 1444823.0,
|
||
|
|
"step": 785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.354400157928467,
|
||
|
|
"epoch": 0.6610878661087866,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00039450000000000005,
|
||
|
|
"loss": 6.2424,
|
||
|
|
"mean_token_accuracy": 0.1207665555179119,
|
||
|
|
"num_tokens": 1454621.0,
|
||
|
|
"step": 790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.24983959197998,
|
||
|
|
"epoch": 0.6652719665271967,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00039700000000000005,
|
||
|
|
"loss": 6.1116,
|
||
|
|
"mean_token_accuracy": 0.12615672051906585,
|
||
|
|
"num_tokens": 1463784.0,
|
||
|
|
"step": 795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.329709482192993,
|
||
|
|
"epoch": 0.6694560669456067,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0003995,
|
||
|
|
"loss": 6.2278,
|
||
|
|
"mean_token_accuracy": 0.12423735633492469,
|
||
|
|
"num_tokens": 1473257.0,
|
||
|
|
"step": 800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.327875566482544,
|
||
|
|
"epoch": 0.6736401673640168,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.000402,
|
||
|
|
"loss": 6.1715,
|
||
|
|
"mean_token_accuracy": 0.13215391784906388,
|
||
|
|
"num_tokens": 1482195.0,
|
||
|
|
"step": 805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.267716884613037,
|
||
|
|
"epoch": 0.6778242677824268,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004045,
|
||
|
|
"loss": 6.2104,
|
||
|
|
"mean_token_accuracy": 0.12745170965790747,
|
||
|
|
"num_tokens": 1491590.0,
|
||
|
|
"step": 810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.32491455078125,
|
||
|
|
"epoch": 0.6820083682008368,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.00040699999999999997,
|
||
|
|
"loss": 6.0945,
|
||
|
|
"mean_token_accuracy": 0.1320909932255745,
|
||
|
|
"num_tokens": 1500208.0,
|
||
|
|
"step": 815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.329631280899048,
|
||
|
|
"epoch": 0.6861924686192469,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004095,
|
||
|
|
"loss": 6.2269,
|
||
|
|
"mean_token_accuracy": 0.12872799932956697,
|
||
|
|
"num_tokens": 1509412.0,
|
||
|
|
"step": 820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2926709175109865,
|
||
|
|
"epoch": 0.6903765690376569,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.000412,
|
||
|
|
"loss": 6.2233,
|
||
|
|
"mean_token_accuracy": 0.12587290704250337,
|
||
|
|
"num_tokens": 1518426.0,
|
||
|
|
"step": 825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.372130298614502,
|
||
|
|
"epoch": 0.694560669456067,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004145,
|
||
|
|
"loss": 6.173,
|
||
|
|
"mean_token_accuracy": 0.12464739456772804,
|
||
|
|
"num_tokens": 1528605.0,
|
||
|
|
"step": 830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.198592662811279,
|
||
|
|
"epoch": 0.698744769874477,
|
||
|
|
"grad_norm": 1.3125,
|
||
|
|
"learning_rate": 0.000417,
|
||
|
|
"loss": 6.1198,
|
||
|
|
"mean_token_accuracy": 0.12950538620352745,
|
||
|
|
"num_tokens": 1537449.0,
|
||
|
|
"step": 835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2445250988006595,
|
||
|
|
"epoch": 0.702928870292887,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004195,
|
||
|
|
"loss": 6.1531,
|
||
|
|
"mean_token_accuracy": 0.12678662985563277,
|
||
|
|
"num_tokens": 1546743.0,
|
||
|
|
"step": 840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.198931741714477,
|
||
|
|
"epoch": 0.7071129707112971,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.000422,
|
||
|
|
"loss": 6.1512,
|
||
|
|
"mean_token_accuracy": 0.12723555639386178,
|
||
|
|
"num_tokens": 1555691.0,
|
||
|
|
"step": 845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.251468992233276,
|
||
|
|
"epoch": 0.7112970711297071,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004245,
|
||
|
|
"loss": 6.1,
|
||
|
|
"mean_token_accuracy": 0.13119761049747466,
|
||
|
|
"num_tokens": 1564957.0,
|
||
|
|
"step": 850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.330463075637818,
|
||
|
|
"epoch": 0.7154811715481172,
|
||
|
|
"grad_norm": 1.3515625,
|
||
|
|
"learning_rate": 0.000427,
|
||
|
|
"loss": 6.1739,
|
||
|
|
"mean_token_accuracy": 0.12831180393695832,
|
||
|
|
"num_tokens": 1573901.0,
|
||
|
|
"step": 855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1841747760772705,
|
||
|
|
"epoch": 0.7196652719665272,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004295,
|
||
|
|
"loss": 6.1514,
|
||
|
|
"mean_token_accuracy": 0.13142475932836534,
|
||
|
|
"num_tokens": 1582644.0,
|
||
|
|
"step": 860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.314925765991211,
|
||
|
|
"epoch": 0.7238493723849372,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000432,
|
||
|
|
"loss": 6.2846,
|
||
|
|
"mean_token_accuracy": 0.12040768340229988,
|
||
|
|
"num_tokens": 1592363.0,
|
||
|
|
"step": 865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.307796049118042,
|
||
|
|
"epoch": 0.7280334728033473,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004345,
|
||
|
|
"loss": 6.2164,
|
||
|
|
"mean_token_accuracy": 0.12550526708364487,
|
||
|
|
"num_tokens": 1602012.0,
|
||
|
|
"step": 870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.193496656417847,
|
||
|
|
"epoch": 0.7322175732217573,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.000437,
|
||
|
|
"loss": 6.1262,
|
||
|
|
"mean_token_accuracy": 0.12875815853476524,
|
||
|
|
"num_tokens": 1611625.0,
|
||
|
|
"step": 875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.1236217498779295,
|
||
|
|
"epoch": 0.7364016736401674,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004395,
|
||
|
|
"loss": 6.0812,
|
||
|
|
"mean_token_accuracy": 0.12527592107653618,
|
||
|
|
"num_tokens": 1620941.0,
|
||
|
|
"step": 880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.263450574874878,
|
||
|
|
"epoch": 0.7405857740585774,
|
||
|
|
"grad_norm": 1.2890625,
|
||
|
|
"learning_rate": 0.000442,
|
||
|
|
"loss": 6.1654,
|
||
|
|
"mean_token_accuracy": 0.12486932873725891,
|
||
|
|
"num_tokens": 1629225.0,
|
||
|
|
"step": 885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.240986633300781,
|
||
|
|
"epoch": 0.7447698744769874,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004445,
|
||
|
|
"loss": 6.1445,
|
||
|
|
"mean_token_accuracy": 0.12441490367054939,
|
||
|
|
"num_tokens": 1639551.0,
|
||
|
|
"step": 890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.223584127426148,
|
||
|
|
"epoch": 0.7489539748953975,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000447,
|
||
|
|
"loss": 6.1279,
|
||
|
|
"mean_token_accuracy": 0.12395419999957084,
|
||
|
|
"num_tokens": 1648963.0,
|
||
|
|
"step": 895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.18436336517334,
|
||
|
|
"epoch": 0.7531380753138075,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00044950000000000003,
|
||
|
|
"loss": 6.0355,
|
||
|
|
"mean_token_accuracy": 0.13170942068099975,
|
||
|
|
"num_tokens": 1657735.0,
|
||
|
|
"step": 900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.318353271484375,
|
||
|
|
"epoch": 0.7573221757322176,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00045200000000000004,
|
||
|
|
"loss": 6.0891,
|
||
|
|
"mean_token_accuracy": 0.1331306591629982,
|
||
|
|
"num_tokens": 1666349.0,
|
||
|
|
"step": 905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.016112899780273,
|
||
|
|
"epoch": 0.7615062761506276,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00045450000000000004,
|
||
|
|
"loss": 6.0271,
|
||
|
|
"mean_token_accuracy": 0.1322978489100933,
|
||
|
|
"num_tokens": 1675920.0,
|
||
|
|
"step": 910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.141036748886108,
|
||
|
|
"epoch": 0.7656903765690377,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.00045700000000000005,
|
||
|
|
"loss": 6.0628,
|
||
|
|
"mean_token_accuracy": 0.13066673129796982,
|
||
|
|
"num_tokens": 1685626.0,
|
||
|
|
"step": 915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.278197765350342,
|
||
|
|
"epoch": 0.7698744769874477,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.00045950000000000006,
|
||
|
|
"loss": 6.1888,
|
||
|
|
"mean_token_accuracy": 0.1338045746088028,
|
||
|
|
"num_tokens": 1694972.0,
|
||
|
|
"step": 920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.141257333755493,
|
||
|
|
"epoch": 0.7740585774058577,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000462,
|
||
|
|
"loss": 6.0668,
|
||
|
|
"mean_token_accuracy": 0.13685579001903533,
|
||
|
|
"num_tokens": 1703806.0,
|
||
|
|
"step": 925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.192854118347168,
|
||
|
|
"epoch": 0.7782426778242678,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004645,
|
||
|
|
"loss": 6.1659,
|
||
|
|
"mean_token_accuracy": 0.13321068361401558,
|
||
|
|
"num_tokens": 1712949.0,
|
||
|
|
"step": 930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.347252273559571,
|
||
|
|
"epoch": 0.7824267782426778,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000467,
|
||
|
|
"loss": 6.287,
|
||
|
|
"mean_token_accuracy": 0.12331678792834282,
|
||
|
|
"num_tokens": 1722328.0,
|
||
|
|
"step": 935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.2889646053314205,
|
||
|
|
"epoch": 0.7866108786610879,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004695,
|
||
|
|
"loss": 6.253,
|
||
|
|
"mean_token_accuracy": 0.13125553727149963,
|
||
|
|
"num_tokens": 1731880.0,
|
||
|
|
"step": 940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.093116664886475,
|
||
|
|
"epoch": 0.7907949790794979,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.000472,
|
||
|
|
"loss": 6.0693,
|
||
|
|
"mean_token_accuracy": 0.13057696744799613,
|
||
|
|
"num_tokens": 1740719.0,
|
||
|
|
"step": 945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.186368799209594,
|
||
|
|
"epoch": 0.7949790794979079,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004745,
|
||
|
|
"loss": 6.1042,
|
||
|
|
"mean_token_accuracy": 0.12656014263629914,
|
||
|
|
"num_tokens": 1749753.0,
|
||
|
|
"step": 950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.255837249755859,
|
||
|
|
"epoch": 0.799163179916318,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.000477,
|
||
|
|
"loss": 6.1211,
|
||
|
|
"mean_token_accuracy": 0.1266303114593029,
|
||
|
|
"num_tokens": 1758913.0,
|
||
|
|
"step": 955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.229157781600952,
|
||
|
|
"epoch": 0.803347280334728,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004795,
|
||
|
|
"loss": 6.1442,
|
||
|
|
"mean_token_accuracy": 0.12871945798397064,
|
||
|
|
"num_tokens": 1768536.0,
|
||
|
|
"step": 960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.113988447189331,
|
||
|
|
"epoch": 0.8075313807531381,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000482,
|
||
|
|
"loss": 6.0653,
|
||
|
|
"mean_token_accuracy": 0.12936384379863738,
|
||
|
|
"num_tokens": 1777291.0,
|
||
|
|
"step": 965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.186689996719361,
|
||
|
|
"epoch": 0.8117154811715481,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004845,
|
||
|
|
"loss": 6.1634,
|
||
|
|
"mean_token_accuracy": 0.12880500480532647,
|
||
|
|
"num_tokens": 1787186.0,
|
||
|
|
"step": 970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.11544098854065,
|
||
|
|
"epoch": 0.8158995815899581,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.000487,
|
||
|
|
"loss": 5.9697,
|
||
|
|
"mean_token_accuracy": 0.13747073709964752,
|
||
|
|
"num_tokens": 1795581.0,
|
||
|
|
"step": 975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.999046802520752,
|
||
|
|
"epoch": 0.8200836820083682,
|
||
|
|
"grad_norm": 1.265625,
|
||
|
|
"learning_rate": 0.0004895,
|
||
|
|
"loss": 5.9825,
|
||
|
|
"mean_token_accuracy": 0.1357624500989914,
|
||
|
|
"num_tokens": 1804627.0,
|
||
|
|
"step": 980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.198841238021851,
|
||
|
|
"epoch": 0.8242677824267782,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000492,
|
||
|
|
"loss": 6.1134,
|
||
|
|
"mean_token_accuracy": 0.13310517519712448,
|
||
|
|
"num_tokens": 1813808.0,
|
||
|
|
"step": 985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.064494943618774,
|
||
|
|
"epoch": 0.8284518828451883,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004945,
|
||
|
|
"loss": 6.1108,
|
||
|
|
"mean_token_accuracy": 0.1350795842707157,
|
||
|
|
"num_tokens": 1823422.0,
|
||
|
|
"step": 990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.163973569869995,
|
||
|
|
"epoch": 0.8326359832635983,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.000497,
|
||
|
|
"loss": 6.1526,
|
||
|
|
"mean_token_accuracy": 0.13110492676496505,
|
||
|
|
"num_tokens": 1832437.0,
|
||
|
|
"step": 995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.180834436416626,
|
||
|
|
"epoch": 0.8368200836820083,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004995,
|
||
|
|
"loss": 6.0707,
|
||
|
|
"mean_token_accuracy": 0.12942072749137878,
|
||
|
|
"num_tokens": 1842063.0,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8368200836820083,
|
||
|
|
"eval_entropy": 5.93860879558727,
|
||
|
|
"eval_loss": 6.10989236831665,
|
||
|
|
"eval_mean_token_accuracy": 0.14120837797721228,
|
||
|
|
"eval_num_tokens": 1842063.0,
|
||
|
|
"eval_runtime": 2.7411,
|
||
|
|
"eval_samples_per_second": 1425.332,
|
||
|
|
"eval_steps_per_second": 178.395,
|
||
|
|
"step": 1000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.116349458694458,
|
||
|
|
"epoch": 0.8410041841004184,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004999998518355666,
|
||
|
|
"loss": 6.2017,
|
||
|
|
"mean_token_accuracy": 0.13061145469546317,
|
||
|
|
"num_tokens": 1851043.0,
|
||
|
|
"step": 1005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.059402561187744,
|
||
|
|
"epoch": 0.8451882845188284,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004999992499178905,
|
||
|
|
"loss": 6.0564,
|
||
|
|
"mean_token_accuracy": 0.13553041368722915,
|
||
|
|
"num_tokens": 1860268.0,
|
||
|
|
"step": 1010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.27886700630188,
|
||
|
|
"epoch": 0.8493723849372385,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004999981849879322,
|
||
|
|
"loss": 6.1793,
|
||
|
|
"mean_token_accuracy": 0.133279487490654,
|
||
|
|
"num_tokens": 1870096.0,
|
||
|
|
"step": 1015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.025306558609008,
|
||
|
|
"epoch": 0.8535564853556485,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004999966570478833,
|
||
|
|
"loss": 6.031,
|
||
|
|
"mean_token_accuracy": 0.13792885467410088,
|
||
|
|
"num_tokens": 1879164.0,
|
||
|
|
"step": 1020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.075544977188111,
|
||
|
|
"epoch": 0.8577405857740585,
|
||
|
|
"grad_norm": 1.3046875,
|
||
|
|
"learning_rate": 0.0004999946661008878,
|
||
|
|
"loss": 6.0018,
|
||
|
|
"mean_token_accuracy": 0.14045969545841216,
|
||
|
|
"num_tokens": 1888135.0,
|
||
|
|
"step": 1025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.10041766166687,
|
||
|
|
"epoch": 0.8619246861924686,
|
||
|
|
"grad_norm": 1.1796875,
|
||
|
|
"learning_rate": 0.000499992212151043,
|
||
|
|
"loss": 6.0593,
|
||
|
|
"mean_token_accuracy": 0.13504695892333984,
|
||
|
|
"num_tokens": 1898302.0,
|
||
|
|
"step": 1030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.017566347122193,
|
||
|
|
"epoch": 0.8661087866108786,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004999892952033987,
|
||
|
|
"loss": 6.0455,
|
||
|
|
"mean_token_accuracy": 0.13498899713158607,
|
||
|
|
"num_tokens": 1907753.0,
|
||
|
|
"step": 1035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.111660099029541,
|
||
|
|
"epoch": 0.8702928870292888,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004999859152639573,
|
||
|
|
"loss": 6.0849,
|
||
|
|
"mean_token_accuracy": 0.12984225451946257,
|
||
|
|
"num_tokens": 1917543.0,
|
||
|
|
"step": 1040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.189549350738526,
|
||
|
|
"epoch": 0.8744769874476988,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999820723396745,
|
||
|
|
"loss": 6.1305,
|
||
|
|
"mean_token_accuracy": 0.1277165487408638,
|
||
|
|
"num_tokens": 1927335.0,
|
||
|
|
"step": 1045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.131802034378052,
|
||
|
|
"epoch": 0.8786610878661087,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004999777664384581,
|
||
|
|
"loss": 6.0468,
|
||
|
|
"mean_token_accuracy": 0.13682940900325774,
|
||
|
|
"num_tokens": 1936381.0,
|
||
|
|
"step": 1050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.053474760055542,
|
||
|
|
"epoch": 0.8828451882845189,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004999729975691692,
|
||
|
|
"loss": 6.0878,
|
||
|
|
"mean_token_accuracy": 0.13545934334397317,
|
||
|
|
"num_tokens": 1945559.0,
|
||
|
|
"step": 1055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001845169067383,
|
||
|
|
"epoch": 0.8870292887029289,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004999677657416212,
|
||
|
|
"loss": 5.9453,
|
||
|
|
"mean_token_accuracy": 0.13565901443362235,
|
||
|
|
"num_tokens": 1954709.0,
|
||
|
|
"step": 1060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0640534400939945,
|
||
|
|
"epoch": 0.891213389121339,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004999620709665804,
|
||
|
|
"loss": 6.0854,
|
||
|
|
"mean_token_accuracy": 0.13231634050607682,
|
||
|
|
"num_tokens": 1963664.0,
|
||
|
|
"step": 1065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.13521728515625,
|
||
|
|
"epoch": 0.895397489539749,
|
||
|
|
"grad_norm": 0.953125,
|
||
|
|
"learning_rate": 0.0004999559132557659,
|
||
|
|
"loss": 6.1175,
|
||
|
|
"mean_token_accuracy": 0.13134895339608194,
|
||
|
|
"num_tokens": 1974103.0,
|
||
|
|
"step": 1070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.173500108718872,
|
||
|
|
"epoch": 0.899581589958159,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004999492926218489,
|
||
|
|
"loss": 6.0113,
|
||
|
|
"mean_token_accuracy": 0.1355544939637184,
|
||
|
|
"num_tokens": 1982924.0,
|
||
|
|
"step": 1075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.965735149383545,
|
||
|
|
"epoch": 0.9037656903765691,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000499942209078454,
|
||
|
|
"loss": 5.9378,
|
||
|
|
"mean_token_accuracy": 0.1465287446975708,
|
||
|
|
"num_tokens": 1992033.0,
|
||
|
|
"step": 1080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.998280811309814,
|
||
|
|
"epoch": 0.9079497907949791,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004999346626401578,
|
||
|
|
"loss": 5.9444,
|
||
|
|
"mean_token_accuracy": 0.14567727744579315,
|
||
|
|
"num_tokens": 2001218.0,
|
||
|
|
"step": 1085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.986832046508789,
|
||
|
|
"epoch": 0.9121338912133892,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004999266533224897,
|
||
|
|
"loss": 6.1065,
|
||
|
|
"mean_token_accuracy": 0.1391438327729702,
|
||
|
|
"num_tokens": 2010463.0,
|
||
|
|
"step": 1090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.14104437828064,
|
||
|
|
"epoch": 0.9163179916317992,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004999181811419314,
|
||
|
|
"loss": 5.9562,
|
||
|
|
"mean_token_accuracy": 0.13891242519021035,
|
||
|
|
"num_tokens": 2019246.0,
|
||
|
|
"step": 1095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.079975891113281,
|
||
|
|
"epoch": 0.9205020920502092,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004999092461159177,
|
||
|
|
"loss": 6.0431,
|
||
|
|
"mean_token_accuracy": 0.13607420697808265,
|
||
|
|
"num_tokens": 2028083.0,
|
||
|
|
"step": 1100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9877180576324465,
|
||
|
|
"epoch": 0.9246861924686193,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004998998482628351,
|
||
|
|
"loss": 5.8649,
|
||
|
|
"mean_token_accuracy": 0.14478956088423728,
|
||
|
|
"num_tokens": 2036631.0,
|
||
|
|
"step": 1105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.946710157394409,
|
||
|
|
"epoch": 0.9288702928870293,
|
||
|
|
"grad_norm": 1.2578125,
|
||
|
|
"learning_rate": 0.0004998899876020229,
|
||
|
|
"loss": 5.9929,
|
||
|
|
"mean_token_accuracy": 0.13790326938033104,
|
||
|
|
"num_tokens": 2045910.0,
|
||
|
|
"step": 1110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.976225805282593,
|
||
|
|
"epoch": 0.9330543933054394,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000499879664153773,
|
||
|
|
"loss": 6.0313,
|
||
|
|
"mean_token_accuracy": 0.1479876421391964,
|
||
|
|
"num_tokens": 2055959.0,
|
||
|
|
"step": 1115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.234367895126343,
|
||
|
|
"epoch": 0.9372384937238494,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998688779393291,
|
||
|
|
"loss": 6.1265,
|
||
|
|
"mean_token_accuracy": 0.13584480583667755,
|
||
|
|
"num_tokens": 2065475.0,
|
||
|
|
"step": 1120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7713428974151615,
|
||
|
|
"epoch": 0.9414225941422594,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004998576289808877,
|
||
|
|
"loss": 5.8793,
|
||
|
|
"mean_token_accuracy": 0.14183773547410966,
|
||
|
|
"num_tokens": 2074469.0,
|
||
|
|
"step": 1125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.010820722579956,
|
||
|
|
"epoch": 0.9456066945606695,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004998459173015972,
|
||
|
|
"loss": 6.0604,
|
||
|
|
"mean_token_accuracy": 0.13986758440732955,
|
||
|
|
"num_tokens": 2084604.0,
|
||
|
|
"step": 1130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.090184593200684,
|
||
|
|
"epoch": 0.9497907949790795,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004998337429255584,
|
||
|
|
"loss": 6.0115,
|
||
|
|
"mean_token_accuracy": 0.1413180112838745,
|
||
|
|
"num_tokens": 2093377.0,
|
||
|
|
"step": 1135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.078766250610352,
|
||
|
|
"epoch": 0.9539748953974896,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004998211058778243,
|
||
|
|
"loss": 6.045,
|
||
|
|
"mean_token_accuracy": 0.13628122508525847,
|
||
|
|
"num_tokens": 2102798.0,
|
||
|
|
"step": 1140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.039411830902099,
|
||
|
|
"epoch": 0.9581589958158996,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004998080061843999,
|
||
|
|
"loss": 6.0185,
|
||
|
|
"mean_token_accuracy": 0.1370515465736389,
|
||
|
|
"num_tokens": 2112516.0,
|
||
|
|
"step": 1145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.11058464050293,
|
||
|
|
"epoch": 0.9623430962343096,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000499794443872242,
|
||
|
|
"loss": 6.1106,
|
||
|
|
"mean_token_accuracy": 0.13264601677656174,
|
||
|
|
"num_tokens": 2121677.0,
|
||
|
|
"step": 1150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.006878089904785,
|
||
|
|
"epoch": 0.9665271966527197,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004997804189692601,
|
||
|
|
"loss": 5.9499,
|
||
|
|
"mean_token_accuracy": 0.14087534546852112,
|
||
|
|
"num_tokens": 2131220.0,
|
||
|
|
"step": 1155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.021556997299195,
|
||
|
|
"epoch": 0.9707112970711297,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004997659315043149,
|
||
|
|
"loss": 6.0939,
|
||
|
|
"mean_token_accuracy": 0.13201906755566598,
|
||
|
|
"num_tokens": 2142104.0,
|
||
|
|
"step": 1160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.0106141567230225,
|
||
|
|
"epoch": 0.9748953974895398,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004997509815072191,
|
||
|
|
"loss": 6.0054,
|
||
|
|
"mean_token_accuracy": 0.13905177861452103,
|
||
|
|
"num_tokens": 2151970.0,
|
||
|
|
"step": 1165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.97538275718689,
|
||
|
|
"epoch": 0.9790794979079498,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004997355690087379,
|
||
|
|
"loss": 5.9543,
|
||
|
|
"mean_token_accuracy": 0.14026949256658555,
|
||
|
|
"num_tokens": 2161371.0,
|
||
|
|
"step": 1170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.91616268157959,
|
||
|
|
"epoch": 0.9832635983263598,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004997196940405874,
|
||
|
|
"loss": 5.9131,
|
||
|
|
"mean_token_accuracy": 0.1355208821594715,
|
||
|
|
"num_tokens": 2170650.0,
|
||
|
|
"step": 1175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.999844169616699,
|
||
|
|
"epoch": 0.9874476987447699,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004997033566354358,
|
||
|
|
"loss": 5.993,
|
||
|
|
"mean_token_accuracy": 0.14383321404457092,
|
||
|
|
"num_tokens": 2180934.0,
|
||
|
|
"step": 1180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.03171181678772,
|
||
|
|
"epoch": 0.9916317991631799,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004996865568269028,
|
||
|
|
"loss": 5.9362,
|
||
|
|
"mean_token_accuracy": 0.14685204923152922,
|
||
|
|
"num_tokens": 2189894.0,
|
||
|
|
"step": 1185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.93413290977478,
|
||
|
|
"epoch": 0.99581589958159,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004996692946495597,
|
||
|
|
"loss": 5.8959,
|
||
|
|
"mean_token_accuracy": 0.1524686649441719,
|
||
|
|
"num_tokens": 2200208.0,
|
||
|
|
"step": 1190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.956554412841797,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"grad_norm": 1.2734375,
|
||
|
|
"learning_rate": 0.0004996515701389295,
|
||
|
|
"loss": 5.9548,
|
||
|
|
"mean_token_accuracy": 0.1403520457446575,
|
||
|
|
"num_tokens": 2209322.0,
|
||
|
|
"step": 1195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.894754028320312,
|
||
|
|
"epoch": 1.00418410041841,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004996333833314862,
|
||
|
|
"loss": 5.7446,
|
||
|
|
"mean_token_accuracy": 0.15427049696445466,
|
||
|
|
"num_tokens": 2217663.0,
|
||
|
|
"step": 1200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.828617906570434,
|
||
|
|
"epoch": 1.00836820083682,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004996147342646554,
|
||
|
|
"loss": 5.7845,
|
||
|
|
"mean_token_accuracy": 0.14702118411660195,
|
||
|
|
"num_tokens": 2226559.0,
|
||
|
|
"step": 1205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.070319509506225,
|
||
|
|
"epoch": 1.0125523012552302,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004995956229768137,
|
||
|
|
"loss": 5.819,
|
||
|
|
"mean_token_accuracy": 0.1527664080262184,
|
||
|
|
"num_tokens": 2235468.0,
|
||
|
|
"step": 1210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.813411045074463,
|
||
|
|
"epoch": 1.0167364016736402,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004995760495072893,
|
||
|
|
"loss": 5.6136,
|
||
|
|
"mean_token_accuracy": 0.1567228153347969,
|
||
|
|
"num_tokens": 2245176.0,
|
||
|
|
"step": 1215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.895093011856079,
|
||
|
|
"epoch": 1.0209205020920502,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004995560138963611,
|
||
|
|
"loss": 5.7825,
|
||
|
|
"mean_token_accuracy": 0.14997974932193756,
|
||
|
|
"num_tokens": 2255123.0,
|
||
|
|
"step": 1220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8670361042022705,
|
||
|
|
"epoch": 1.0251046025104602,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004995355161852593,
|
||
|
|
"loss": 5.702,
|
||
|
|
"mean_token_accuracy": 0.15056501626968383,
|
||
|
|
"num_tokens": 2263596.0,
|
||
|
|
"step": 1225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.887784576416015,
|
||
|
|
"epoch": 1.0292887029288702,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004995145564161648,
|
||
|
|
"loss": 5.7436,
|
||
|
|
"mean_token_accuracy": 0.14897513389587402,
|
||
|
|
"num_tokens": 2272228.0,
|
||
|
|
"step": 1230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.846974182128906,
|
||
|
|
"epoch": 1.0334728033472804,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004994931346322094,
|
||
|
|
"loss": 5.7995,
|
||
|
|
"mean_token_accuracy": 0.1486528918147087,
|
||
|
|
"num_tokens": 2281248.0,
|
||
|
|
"step": 1235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.952018976211548,
|
||
|
|
"epoch": 1.0376569037656904,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004994712508774757,
|
||
|
|
"loss": 5.76,
|
||
|
|
"mean_token_accuracy": 0.14765810891985892,
|
||
|
|
"num_tokens": 2290958.0,
|
||
|
|
"step": 1240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.779097032546997,
|
||
|
|
"epoch": 1.0418410041841004,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.000499448905196997,
|
||
|
|
"loss": 5.714,
|
||
|
|
"mean_token_accuracy": 0.15628314018249512,
|
||
|
|
"num_tokens": 2299763.0,
|
||
|
|
"step": 1245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.858342695236206,
|
||
|
|
"epoch": 1.0460251046025104,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004994260976367573,
|
||
|
|
"loss": 5.7272,
|
||
|
|
"mean_token_accuracy": 0.15564334839582444,
|
||
|
|
"num_tokens": 2309847.0,
|
||
|
|
"step": 1250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.9082927227020265,
|
||
|
|
"epoch": 1.0502092050209204,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004994028282436905,
|
||
|
|
"loss": 5.7491,
|
||
|
|
"mean_token_accuracy": 0.14895465224981308,
|
||
|
|
"num_tokens": 2317556.0,
|
||
|
|
"step": 1255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7722269058227536,
|
||
|
|
"epoch": 1.0543933054393306,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004993790970656814,
|
||
|
|
"loss": 5.6812,
|
||
|
|
"mean_token_accuracy": 0.15420028567314148,
|
||
|
|
"num_tokens": 2327151.0,
|
||
|
|
"step": 1260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7930036067962645,
|
||
|
|
"epoch": 1.0585774058577406,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004993549041515652,
|
||
|
|
"loss": 5.6802,
|
||
|
|
"mean_token_accuracy": 0.15717751085758208,
|
||
|
|
"num_tokens": 2336119.0,
|
||
|
|
"step": 1265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.781204509735107,
|
||
|
|
"epoch": 1.0627615062761506,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004993302495511268,
|
||
|
|
"loss": 5.7134,
|
||
|
|
"mean_token_accuracy": 0.15141206830739976,
|
||
|
|
"num_tokens": 2345262.0,
|
||
|
|
"step": 1270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 6.001182174682617,
|
||
|
|
"epoch": 1.0669456066945606,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004993051333151014,
|
||
|
|
"loss": 5.847,
|
||
|
|
"mean_token_accuracy": 0.1470116265118122,
|
||
|
|
"num_tokens": 2355210.0,
|
||
|
|
"step": 1275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.718861150741577,
|
||
|
|
"epoch": 1.0711297071129706,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004992795554951742,
|
||
|
|
"loss": 5.5887,
|
||
|
|
"mean_token_accuracy": 0.15690547823905945,
|
||
|
|
"num_tokens": 2364599.0,
|
||
|
|
"step": 1280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.716666555404663,
|
||
|
|
"epoch": 1.0753138075313808,
|
||
|
|
"grad_norm": 1.390625,
|
||
|
|
"learning_rate": 0.0004992535161439803,
|
||
|
|
"loss": 5.781,
|
||
|
|
"mean_token_accuracy": 0.1451686941087246,
|
||
|
|
"num_tokens": 2374143.0,
|
||
|
|
"step": 1285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.969261169433594,
|
||
|
|
"epoch": 1.0794979079497908,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004992270153151045,
|
||
|
|
"loss": 5.7635,
|
||
|
|
"mean_token_accuracy": 0.15289389342069626,
|
||
|
|
"num_tokens": 2383155.0,
|
||
|
|
"step": 1290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.92108302116394,
|
||
|
|
"epoch": 1.0836820083682008,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004992000530630812,
|
||
|
|
"loss": 5.8095,
|
||
|
|
"mean_token_accuracy": 0.1509893462061882,
|
||
|
|
"num_tokens": 2392542.0,
|
||
|
|
"step": 1295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.737433242797851,
|
||
|
|
"epoch": 1.0878661087866108,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004991726294433943,
|
||
|
|
"loss": 5.7792,
|
||
|
|
"mean_token_accuracy": 0.14687865376472473,
|
||
|
|
"num_tokens": 2401851.0,
|
||
|
|
"step": 1300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.892284393310547,
|
||
|
|
"epoch": 1.0920502092050208,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004991447445124774,
|
||
|
|
"loss": 5.7048,
|
||
|
|
"mean_token_accuracy": 0.1529296711087227,
|
||
|
|
"num_tokens": 2410726.0,
|
||
|
|
"step": 1305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.729634380340576,
|
||
|
|
"epoch": 1.096234309623431,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000499116398327713,
|
||
|
|
"loss": 5.7891,
|
||
|
|
"mean_token_accuracy": 0.14780578166246414,
|
||
|
|
"num_tokens": 2420702.0,
|
||
|
|
"step": 1310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.774093294143677,
|
||
|
|
"epoch": 1.100418410041841,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004990875909474331,
|
||
|
|
"loss": 5.7044,
|
||
|
|
"mean_token_accuracy": 0.1555623084306717,
|
||
|
|
"num_tokens": 2431335.0,
|
||
|
|
"step": 1315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8864298343658445,
|
||
|
|
"epoch": 1.104602510460251,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004990583224309187,
|
||
|
|
"loss": 5.6981,
|
||
|
|
"mean_token_accuracy": 0.15561241209506987,
|
||
|
|
"num_tokens": 2440722.0,
|
||
|
|
"step": 1320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.802323818206787,
|
||
|
|
"epoch": 1.108786610878661,
|
||
|
|
"grad_norm": 0.9609375,
|
||
|
|
"learning_rate": 0.0004990285928383997,
|
||
|
|
"loss": 5.7621,
|
||
|
|
"mean_token_accuracy": 0.1484719768166542,
|
||
|
|
"num_tokens": 2451230.0,
|
||
|
|
"step": 1325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.884494256973267,
|
||
|
|
"epoch": 1.112970711297071,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004989984022310545,
|
||
|
|
"loss": 5.7884,
|
||
|
|
"mean_token_accuracy": 0.14925398379564286,
|
||
|
|
"num_tokens": 2461442.0,
|
||
|
|
"step": 1330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.787790966033936,
|
||
|
|
"epoch": 1.1171548117154813,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004989677506710109,
|
||
|
|
"loss": 5.6094,
|
||
|
|
"mean_token_accuracy": 0.16102316826581956,
|
||
|
|
"num_tokens": 2471381.0,
|
||
|
|
"step": 1335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.780320405960083,
|
||
|
|
"epoch": 1.1213389121338913,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004989366382213449,
|
||
|
|
"loss": 5.6627,
|
||
|
|
"mean_token_accuracy": 0.15939401984214782,
|
||
|
|
"num_tokens": 2479937.0,
|
||
|
|
"step": 1340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.739678001403808,
|
||
|
|
"epoch": 1.1255230125523012,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004989050649460806,
|
||
|
|
"loss": 5.6362,
|
||
|
|
"mean_token_accuracy": 0.15941027402877808,
|
||
|
|
"num_tokens": 2488974.0,
|
||
|
|
"step": 1345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.791116237640381,
|
||
|
|
"epoch": 1.1297071129707112,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.000498873030910191,
|
||
|
|
"loss": 5.781,
|
||
|
|
"mean_token_accuracy": 0.150092051923275,
|
||
|
|
"num_tokens": 2498800.0,
|
||
|
|
"step": 1350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.717321586608887,
|
||
|
|
"epoch": 1.1338912133891212,
|
||
|
|
"grad_norm": 1.1875,
|
||
|
|
"learning_rate": 0.0004988405361795969,
|
||
|
|
"loss": 5.6848,
|
||
|
|
"mean_token_accuracy": 0.14925537556409835,
|
||
|
|
"num_tokens": 2506580.0,
|
||
|
|
"step": 1355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.770847225189209,
|
||
|
|
"epoch": 1.1380753138075315,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004988075808211672,
|
||
|
|
"loss": 5.739,
|
||
|
|
"mean_token_accuracy": 0.1563566356897354,
|
||
|
|
"num_tokens": 2516342.0,
|
||
|
|
"step": 1360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.770087480545044,
|
||
|
|
"epoch": 1.1422594142259415,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004987741649027189,
|
||
|
|
"loss": 5.7688,
|
||
|
|
"mean_token_accuracy": 0.15330522656440734,
|
||
|
|
"num_tokens": 2526054.0,
|
||
|
|
"step": 1365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.847585964202881,
|
||
|
|
"epoch": 1.1464435146443515,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004987402884930163,
|
||
|
|
"loss": 5.7187,
|
||
|
|
"mean_token_accuracy": 0.15662140548229217,
|
||
|
|
"num_tokens": 2535556.0,
|
||
|
|
"step": 1370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.832192087173462,
|
||
|
|
"epoch": 1.1506276150627615,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004987059516617717,
|
||
|
|
"loss": 5.6932,
|
||
|
|
"mean_token_accuracy": 0.15749878734350203,
|
||
|
|
"num_tokens": 2544930.0,
|
||
|
|
"step": 1375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.700648450851441,
|
||
|
|
"epoch": 1.1548117154811715,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004986711544796449,
|
||
|
|
"loss": 5.6074,
|
||
|
|
"mean_token_accuracy": 0.16140320003032685,
|
||
|
|
"num_tokens": 2554362.0,
|
||
|
|
"step": 1380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.79828109741211,
|
||
|
|
"epoch": 1.1589958158995817,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000498635897018243,
|
||
|
|
"loss": 5.7171,
|
||
|
|
"mean_token_accuracy": 0.15348803699016572,
|
||
|
|
"num_tokens": 2563499.0,
|
||
|
|
"step": 1385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.725475692749024,
|
||
|
|
"epoch": 1.1631799163179917,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004986001793501198,
|
||
|
|
"loss": 5.741,
|
||
|
|
"mean_token_accuracy": 0.15232713371515275,
|
||
|
|
"num_tokens": 2573346.0,
|
||
|
|
"step": 1390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.78861083984375,
|
||
|
|
"epoch": 1.1673640167364017,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004985640015487768,
|
||
|
|
"loss": 5.6204,
|
||
|
|
"mean_token_accuracy": 0.16266809701919555,
|
||
|
|
"num_tokens": 2582541.0,
|
||
|
|
"step": 1395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.745808744430542,
|
||
|
|
"epoch": 1.1715481171548117,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004985273636886621,
|
||
|
|
"loss": 5.6995,
|
||
|
|
"mean_token_accuracy": 0.1560098946094513,
|
||
|
|
"num_tokens": 2592015.0,
|
||
|
|
"step": 1400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.726541948318482,
|
||
|
|
"epoch": 1.1757322175732217,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004984902658451704,
|
||
|
|
"loss": 5.7151,
|
||
|
|
"mean_token_accuracy": 0.15896441042423248,
|
||
|
|
"num_tokens": 2601998.0,
|
||
|
|
"step": 1405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.72317328453064,
|
||
|
|
"epoch": 1.1799163179916319,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004984527080946432,
|
||
|
|
"loss": 5.6508,
|
||
|
|
"mean_token_accuracy": 0.15956526398658752,
|
||
|
|
"num_tokens": 2611435.0,
|
||
|
|
"step": 1410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.779344701766968,
|
||
|
|
"epoch": 1.1841004184100419,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004984146905143683,
|
||
|
|
"loss": 5.7451,
|
||
|
|
"mean_token_accuracy": 0.15034509003162383,
|
||
|
|
"num_tokens": 2621639.0,
|
||
|
|
"step": 1415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.777336454391479,
|
||
|
|
"epoch": 1.1882845188284519,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004983762131825797,
|
||
|
|
"loss": 5.7047,
|
||
|
|
"mean_token_accuracy": 0.1531509578227997,
|
||
|
|
"num_tokens": 2631390.0,
|
||
|
|
"step": 1420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.752439022064209,
|
||
|
|
"epoch": 1.1924686192468619,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004983372761784576,
|
||
|
|
"loss": 5.7487,
|
||
|
|
"mean_token_accuracy": 0.14954135715961456,
|
||
|
|
"num_tokens": 2640769.0,
|
||
|
|
"step": 1425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.865439939498901,
|
||
|
|
"epoch": 1.196652719665272,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004982978795821281,
|
||
|
|
"loss": 5.7567,
|
||
|
|
"mean_token_accuracy": 0.1547407925128937,
|
||
|
|
"num_tokens": 2651137.0,
|
||
|
|
"step": 1430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.814016962051392,
|
||
|
|
"epoch": 1.200836820083682,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004982580234746632,
|
||
|
|
"loss": 5.6655,
|
||
|
|
"mean_token_accuracy": 0.15743645280599594,
|
||
|
|
"num_tokens": 2660530.0,
|
||
|
|
"step": 1435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.694674301147461,
|
||
|
|
"epoch": 1.205020920502092,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00049821770793808,
|
||
|
|
"loss": 5.7379,
|
||
|
|
"mean_token_accuracy": 0.15339982360601426,
|
||
|
|
"num_tokens": 2669541.0,
|
||
|
|
"step": 1440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.861599159240723,
|
||
|
|
"epoch": 1.209205020920502,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004981769330553418,
|
||
|
|
"loss": 5.737,
|
||
|
|
"mean_token_accuracy": 0.15259334444999695,
|
||
|
|
"num_tokens": 2678542.0,
|
||
|
|
"step": 1445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.763570022583008,
|
||
|
|
"epoch": 1.213389121338912,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004981356989103566,
|
||
|
|
"loss": 5.7951,
|
||
|
|
"mean_token_accuracy": 0.15657299458980561,
|
||
|
|
"num_tokens": 2687720.0,
|
||
|
|
"step": 1450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.803497743606568,
|
||
|
|
"epoch": 1.217573221757322,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004980940055879774,
|
||
|
|
"loss": 5.6471,
|
||
|
|
"mean_token_accuracy": 0.15510508120059968,
|
||
|
|
"num_tokens": 2697641.0,
|
||
|
|
"step": 1455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.740324783325195,
|
||
|
|
"epoch": 1.2217573221757323,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004980518531740027,
|
||
|
|
"loss": 5.7073,
|
||
|
|
"mean_token_accuracy": 0.1536521553993225,
|
||
|
|
"num_tokens": 2706600.0,
|
||
|
|
"step": 1460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.839646625518799,
|
||
|
|
"epoch": 1.2259414225941423,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004980092417551752,
|
||
|
|
"loss": 5.818,
|
||
|
|
"mean_token_accuracy": 0.15001391619443893,
|
||
|
|
"num_tokens": 2716633.0,
|
||
|
|
"step": 1465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.8136616230010985,
|
||
|
|
"epoch": 1.2301255230125523,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004979661714191825,
|
||
|
|
"loss": 5.5849,
|
||
|
|
"mean_token_accuracy": 0.16975591331720352,
|
||
|
|
"num_tokens": 2724829.0,
|
||
|
|
"step": 1470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.69421501159668,
|
||
|
|
"epoch": 1.2343096234309623,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004979226422546563,
|
||
|
|
"loss": 5.7013,
|
||
|
|
"mean_token_accuracy": 0.1594356283545494,
|
||
|
|
"num_tokens": 2734276.0,
|
||
|
|
"step": 1475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.816491365432739,
|
||
|
|
"epoch": 1.2384937238493725,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004978786543511726,
|
||
|
|
"loss": 5.8119,
|
||
|
|
"mean_token_accuracy": 0.15787640661001207,
|
||
|
|
"num_tokens": 2744413.0,
|
||
|
|
"step": 1480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.775937271118164,
|
||
|
|
"epoch": 1.2426778242677825,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004978342077992515,
|
||
|
|
"loss": 5.6762,
|
||
|
|
"mean_token_accuracy": 0.15499028116464614,
|
||
|
|
"num_tokens": 2753242.0,
|
||
|
|
"step": 1485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.606312656402588,
|
||
|
|
"epoch": 1.2468619246861925,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004977893026903568,
|
||
|
|
"loss": 5.6161,
|
||
|
|
"mean_token_accuracy": 0.166127747297287,
|
||
|
|
"num_tokens": 2761811.0,
|
||
|
|
"step": 1490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.812732315063476,
|
||
|
|
"epoch": 1.2510460251046025,
|
||
|
|
"grad_norm": 0.9765625,
|
||
|
|
"learning_rate": 0.0004977439391168963,
|
||
|
|
"loss": 5.7151,
|
||
|
|
"mean_token_accuracy": 0.16037967205047607,
|
||
|
|
"num_tokens": 2770560.0,
|
||
|
|
"step": 1495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.781078672409057,
|
||
|
|
"epoch": 1.2552301255230125,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004976981171722205,
|
||
|
|
"loss": 5.7108,
|
||
|
|
"mean_token_accuracy": 0.15685239136219026,
|
||
|
|
"num_tokens": 2780131.0,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.2552301255230125,
|
||
|
|
"eval_entropy": 5.562492416436443,
|
||
|
|
"eval_loss": 5.858166217803955,
|
||
|
|
"eval_mean_token_accuracy": 0.15818902674932908,
|
||
|
|
"eval_num_tokens": 2780131.0,
|
||
|
|
"eval_runtime": 2.9229,
|
||
|
|
"eval_samples_per_second": 1336.691,
|
||
|
|
"eval_steps_per_second": 167.3,
|
||
|
|
"step": 1500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.832910346984863,
|
||
|
|
"epoch": 1.2594142259414225,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004976518369506237,
|
||
|
|
"loss": 5.8164,
|
||
|
|
"mean_token_accuracy": 0.14845228791236878,
|
||
|
|
"num_tokens": 2789319.0,
|
||
|
|
"step": 1505
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.669151735305786,
|
||
|
|
"epoch": 1.2635983263598327,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004976050985473433,
|
||
|
|
"loss": 5.6901,
|
||
|
|
"mean_token_accuracy": 0.1474151998758316,
|
||
|
|
"num_tokens": 2799253.0,
|
||
|
|
"step": 1510
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.815981101989746,
|
||
|
|
"epoch": 1.2677824267782427,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004975579020585593,
|
||
|
|
"loss": 5.7889,
|
||
|
|
"mean_token_accuracy": 0.1519041746854782,
|
||
|
|
"num_tokens": 2808968.0,
|
||
|
|
"step": 1515
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.869286918640137,
|
||
|
|
"epoch": 1.2719665271966527,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004975102475813947,
|
||
|
|
"loss": 5.6701,
|
||
|
|
"mean_token_accuracy": 0.15941894352436065,
|
||
|
|
"num_tokens": 2817282.0,
|
||
|
|
"step": 1520
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.687379598617554,
|
||
|
|
"epoch": 1.2761506276150627,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004974621352139144,
|
||
|
|
"loss": 5.7378,
|
||
|
|
"mean_token_accuracy": 0.1533280447125435,
|
||
|
|
"num_tokens": 2826395.0,
|
||
|
|
"step": 1525
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.823107051849365,
|
||
|
|
"epoch": 1.280334728033473,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004974135650551262,
|
||
|
|
"loss": 5.8028,
|
||
|
|
"mean_token_accuracy": 0.15243592411279677,
|
||
|
|
"num_tokens": 2836195.0,
|
||
|
|
"step": 1530
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.762291669845581,
|
||
|
|
"epoch": 1.284518828451883,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004973645372049796,
|
||
|
|
"loss": 5.6422,
|
||
|
|
"mean_token_accuracy": 0.15816431641578674,
|
||
|
|
"num_tokens": 2846020.0,
|
||
|
|
"step": 1535
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.687832546234131,
|
||
|
|
"epoch": 1.288702928870293,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004973150517643659,
|
||
|
|
"loss": 5.5872,
|
||
|
|
"mean_token_accuracy": 0.16854178458452224,
|
||
|
|
"num_tokens": 2854895.0,
|
||
|
|
"step": 1540
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.724603605270386,
|
||
|
|
"epoch": 1.292887029288703,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004972651088351185,
|
||
|
|
"loss": 5.6319,
|
||
|
|
"mean_token_accuracy": 0.15647992193698884,
|
||
|
|
"num_tokens": 2864491.0,
|
||
|
|
"step": 1545
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.78979229927063,
|
||
|
|
"epoch": 1.297071129707113,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004972147085200116,
|
||
|
|
"loss": 5.6483,
|
||
|
|
"mean_token_accuracy": 0.1545269563794136,
|
||
|
|
"num_tokens": 2873962.0,
|
||
|
|
"step": 1550
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.721522378921509,
|
||
|
|
"epoch": 1.301255230125523,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004971638509227611,
|
||
|
|
"loss": 5.6967,
|
||
|
|
"mean_token_accuracy": 0.16045853793621062,
|
||
|
|
"num_tokens": 2883530.0,
|
||
|
|
"step": 1555
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.705851316452026,
|
||
|
|
"epoch": 1.3054393305439331,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004971125361480236,
|
||
|
|
"loss": 5.6853,
|
||
|
|
"mean_token_accuracy": 0.15562771111726761,
|
||
|
|
"num_tokens": 2892867.0,
|
||
|
|
"step": 1560
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.719560289382935,
|
||
|
|
"epoch": 1.3096234309623431,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004970607643013969,
|
||
|
|
"loss": 5.643,
|
||
|
|
"mean_token_accuracy": 0.16159158051013947,
|
||
|
|
"num_tokens": 2902320.0,
|
||
|
|
"step": 1565
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.679278230667114,
|
||
|
|
"epoch": 1.3138075313807531,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000497008535489419,
|
||
|
|
"loss": 5.5838,
|
||
|
|
"mean_token_accuracy": 0.16410900056362152,
|
||
|
|
"num_tokens": 2911390.0,
|
||
|
|
"step": 1570
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.678142166137695,
|
||
|
|
"epoch": 1.3179916317991631,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004969558498195684,
|
||
|
|
"loss": 5.6136,
|
||
|
|
"mean_token_accuracy": 0.16564353704452514,
|
||
|
|
"num_tokens": 2921295.0,
|
||
|
|
"step": 1575
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.726165390014648,
|
||
|
|
"epoch": 1.3221757322175733,
|
||
|
|
"grad_norm": 0.96875,
|
||
|
|
"learning_rate": 0.0004969027074002638,
|
||
|
|
"loss": 5.6419,
|
||
|
|
"mean_token_accuracy": 0.16103103309869765,
|
||
|
|
"num_tokens": 2931328.0,
|
||
|
|
"step": 1580
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.626484727859497,
|
||
|
|
"epoch": 1.3263598326359833,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004968491083408636,
|
||
|
|
"loss": 5.5921,
|
||
|
|
"mean_token_accuracy": 0.1605369418859482,
|
||
|
|
"num_tokens": 2940193.0,
|
||
|
|
"step": 1585
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.644883728027343,
|
||
|
|
"epoch": 1.3305439330543933,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004967950527516663,
|
||
|
|
"loss": 5.6319,
|
||
|
|
"mean_token_accuracy": 0.16434539556503297,
|
||
|
|
"num_tokens": 2949759.0,
|
||
|
|
"step": 1590
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6134930610656735,
|
||
|
|
"epoch": 1.3347280334728033,
|
||
|
|
"grad_norm": 0.96484375,
|
||
|
|
"learning_rate": 0.0004967405407439092,
|
||
|
|
"loss": 5.556,
|
||
|
|
"mean_token_accuracy": 0.15818172544240952,
|
||
|
|
"num_tokens": 2959185.0,
|
||
|
|
"step": 1595
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.77109956741333,
|
||
|
|
"epoch": 1.3389121338912133,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004966855724297698,
|
||
|
|
"loss": 5.7123,
|
||
|
|
"mean_token_accuracy": 0.15126804038882255,
|
||
|
|
"num_tokens": 2968945.0,
|
||
|
|
"step": 1600
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.717288303375244,
|
||
|
|
"epoch": 1.3430962343096233,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004966301479223637,
|
||
|
|
"loss": 5.6578,
|
||
|
|
"mean_token_accuracy": 0.15509079843759538,
|
||
|
|
"num_tokens": 2978395.0,
|
||
|
|
"step": 1605
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.650655460357666,
|
||
|
|
"epoch": 1.3472803347280335,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004965742673357456,
|
||
|
|
"loss": 5.5628,
|
||
|
|
"mean_token_accuracy": 0.1712281510233879,
|
||
|
|
"num_tokens": 2987030.0,
|
||
|
|
"step": 1610
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.700111675262451,
|
||
|
|
"epoch": 1.3514644351464435,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004965179307849088,
|
||
|
|
"loss": 5.6241,
|
||
|
|
"mean_token_accuracy": 0.16350831985473632,
|
||
|
|
"num_tokens": 2995736.0,
|
||
|
|
"step": 1615
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.741107034683227,
|
||
|
|
"epoch": 1.3556485355648535,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.000496461138385785,
|
||
|
|
"loss": 5.722,
|
||
|
|
"mean_token_accuracy": 0.1551881417632103,
|
||
|
|
"num_tokens": 3005105.0,
|
||
|
|
"step": 1620
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6597717761993405,
|
||
|
|
"epoch": 1.3598326359832635,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004964038902552438,
|
||
|
|
"loss": 5.6405,
|
||
|
|
"mean_token_accuracy": 0.15983598679304123,
|
||
|
|
"num_tokens": 3013857.0,
|
||
|
|
"step": 1625
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.71797742843628,
|
||
|
|
"epoch": 1.3640167364016738,
|
||
|
|
"grad_norm": 0.984375,
|
||
|
|
"learning_rate": 0.0004963461865110926,
|
||
|
|
"loss": 5.6753,
|
||
|
|
"mean_token_accuracy": 0.16151416003704072,
|
||
|
|
"num_tokens": 3023972.0,
|
||
|
|
"step": 1630
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.615366840362549,
|
||
|
|
"epoch": 1.3682008368200838,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004962880272720764,
|
||
|
|
"loss": 5.6281,
|
||
|
|
"mean_token_accuracy": 0.16673413515090943,
|
||
|
|
"num_tokens": 3032705.0,
|
||
|
|
"step": 1635
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.748799800872803,
|
||
|
|
"epoch": 1.3723849372384938,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004962294126578775,
|
||
|
|
"loss": 5.5674,
|
||
|
|
"mean_token_accuracy": 0.16736229360103608,
|
||
|
|
"num_tokens": 3040900.0,
|
||
|
|
"step": 1640
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.635876178741455,
|
||
|
|
"epoch": 1.3765690376569037,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004961703427891154,
|
||
|
|
"loss": 5.6241,
|
||
|
|
"mean_token_accuracy": 0.1661652982234955,
|
||
|
|
"num_tokens": 3050477.0,
|
||
|
|
"step": 1645
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.716712760925293,
|
||
|
|
"epoch": 1.3807531380753137,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004961108177873466,
|
||
|
|
"loss": 5.6781,
|
||
|
|
"mean_token_accuracy": 0.1577182188630104,
|
||
|
|
"num_tokens": 3059743.0,
|
||
|
|
"step": 1650
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.63826847076416,
|
||
|
|
"epoch": 1.3849372384937237,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004960508377750638,
|
||
|
|
"loss": 5.4816,
|
||
|
|
"mean_token_accuracy": 0.1699427306652069,
|
||
|
|
"num_tokens": 3067801.0,
|
||
|
|
"step": 1655
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.599407529830932,
|
||
|
|
"epoch": 1.389121338912134,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004959904028756961,
|
||
|
|
"loss": 5.6768,
|
||
|
|
"mean_token_accuracy": 0.15741273611783982,
|
||
|
|
"num_tokens": 3077404.0,
|
||
|
|
"step": 1660
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.752321434020996,
|
||
|
|
"epoch": 1.393305439330544,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004959295132136091,
|
||
|
|
"loss": 5.7073,
|
||
|
|
"mean_token_accuracy": 0.1570734903216362,
|
||
|
|
"num_tokens": 3087130.0,
|
||
|
|
"step": 1665
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7756424903869625,
|
||
|
|
"epoch": 1.397489539748954,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004958681689141036,
|
||
|
|
"loss": 5.7149,
|
||
|
|
"mean_token_accuracy": 0.15712554901838302,
|
||
|
|
"num_tokens": 3096038.0,
|
||
|
|
"step": 1670
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.627508974075317,
|
||
|
|
"epoch": 1.401673640167364,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004958063701034167,
|
||
|
|
"loss": 5.569,
|
||
|
|
"mean_token_accuracy": 0.1632245361804962,
|
||
|
|
"num_tokens": 3105668.0,
|
||
|
|
"step": 1675
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.595325088500976,
|
||
|
|
"epoch": 1.4058577405857742,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.00049574411690872,
|
||
|
|
"loss": 5.5417,
|
||
|
|
"mean_token_accuracy": 0.15734163001179696,
|
||
|
|
"num_tokens": 3114020.0,
|
||
|
|
"step": 1680
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.577217531204224,
|
||
|
|
"epoch": 1.4100418410041842,
|
||
|
|
"grad_norm": 0.99609375,
|
||
|
|
"learning_rate": 0.0004956814094581208,
|
||
|
|
"loss": 5.5852,
|
||
|
|
"mean_token_accuracy": 0.1656106784939766,
|
||
|
|
"num_tokens": 3124096.0,
|
||
|
|
"step": 1685
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7230309009552,
|
||
|
|
"epoch": 1.4142259414225942,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.000495618247880661,
|
||
|
|
"loss": 5.6452,
|
||
|
|
"mean_token_accuracy": 0.15970809012651443,
|
||
|
|
"num_tokens": 3132806.0,
|
||
|
|
"step": 1690
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.648838520050049,
|
||
|
|
"epoch": 1.4184100418410042,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004955546323063168,
|
||
|
|
"loss": 5.574,
|
||
|
|
"mean_token_accuracy": 0.17397267371416092,
|
||
|
|
"num_tokens": 3142001.0,
|
||
|
|
"step": 1695
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.563747406005859,
|
||
|
|
"epoch": 1.4225941422594142,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.0004954905628659989,
|
||
|
|
"loss": 5.5495,
|
||
|
|
"mean_token_accuracy": 0.1571080982685089,
|
||
|
|
"num_tokens": 3151658.0,
|
||
|
|
"step": 1700
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.665132617950439,
|
||
|
|
"epoch": 1.4267782426778242,
|
||
|
|
"grad_norm": 1.2421875,
|
||
|
|
"learning_rate": 0.0004954260396915521,
|
||
|
|
"loss": 5.5774,
|
||
|
|
"mean_token_accuracy": 0.16344356238842012,
|
||
|
|
"num_tokens": 3159573.0,
|
||
|
|
"step": 1705
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.464680528640747,
|
||
|
|
"epoch": 1.4309623430962344,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004953610629157544,
|
||
|
|
"loss": 5.4537,
|
||
|
|
"mean_token_accuracy": 0.1730719119310379,
|
||
|
|
"num_tokens": 3168312.0,
|
||
|
|
"step": 1710
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.727207994461059,
|
||
|
|
"epoch": 1.4351464435146444,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004952956326723177,
|
||
|
|
"loss": 5.5523,
|
||
|
|
"mean_token_accuracy": 0.1717923477292061,
|
||
|
|
"num_tokens": 3176811.0,
|
||
|
|
"step": 1715
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.65036792755127,
|
||
|
|
"epoch": 1.4393305439330544,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.000495229749095887,
|
||
|
|
"loss": 5.6479,
|
||
|
|
"mean_token_accuracy": 0.15595420598983764,
|
||
|
|
"num_tokens": 3186599.0,
|
||
|
|
"step": 1720
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.775017213821411,
|
||
|
|
"epoch": 1.4435146443514644,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.00049516341232204,
|
||
|
|
"loss": 5.7534,
|
||
|
|
"mean_token_accuracy": 0.15901043713092805,
|
||
|
|
"num_tokens": 3195905.0,
|
||
|
|
"step": 1725
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.671367931365967,
|
||
|
|
"epoch": 1.4476987447698746,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.000495096622487287,
|
||
|
|
"loss": 5.7076,
|
||
|
|
"mean_token_accuracy": 0.15824892222881318,
|
||
|
|
"num_tokens": 3205132.0,
|
||
|
|
"step": 1730
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.791279268264771,
|
||
|
|
"epoch": 1.4518828451882846,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.000495029379729071,
|
||
|
|
"loss": 5.704,
|
||
|
|
"mean_token_accuracy": 0.1495993286371231,
|
||
|
|
"num_tokens": 3214362.0,
|
||
|
|
"step": 1735
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.713367319107055,
|
||
|
|
"epoch": 1.4560669456066946,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004949616841857666,
|
||
|
|
"loss": 5.7001,
|
||
|
|
"mean_token_accuracy": 0.15628902167081832,
|
||
|
|
"num_tokens": 3224248.0,
|
||
|
|
"step": 1740
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.627431154251099,
|
||
|
|
"epoch": 1.4602510460251046,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004948935359966806,
|
||
|
|
"loss": 5.57,
|
||
|
|
"mean_token_accuracy": 0.1658832088112831,
|
||
|
|
"num_tokens": 3233416.0,
|
||
|
|
"step": 1745
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.533376026153564,
|
||
|
|
"epoch": 1.4644351464435146,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.0004948249353020506,
|
||
|
|
"loss": 5.5031,
|
||
|
|
"mean_token_accuracy": 0.1715339496731758,
|
||
|
|
"num_tokens": 3242354.0,
|
||
|
|
"step": 1750
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.683704471588134,
|
||
|
|
"epoch": 1.4686192468619246,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004947558822430461,
|
||
|
|
"loss": 5.5964,
|
||
|
|
"mean_token_accuracy": 0.1610857516527176,
|
||
|
|
"num_tokens": 3251026.0,
|
||
|
|
"step": 1755
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.659394121170044,
|
||
|
|
"epoch": 1.4728033472803348,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004946863769617672,
|
||
|
|
"loss": 5.5468,
|
||
|
|
"mean_token_accuracy": 0.16529789119958876,
|
||
|
|
"num_tokens": 3259429.0,
|
||
|
|
"step": 1760
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.613833808898926,
|
||
|
|
"epoch": 1.4769874476987448,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004946164196012445,
|
||
|
|
"loss": 5.5968,
|
||
|
|
"mean_token_accuracy": 0.16423317044973373,
|
||
|
|
"num_tokens": 3269305.0,
|
||
|
|
"step": 1765
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.672654628753662,
|
||
|
|
"epoch": 1.4811715481171548,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004945460103054389,
|
||
|
|
"loss": 5.6816,
|
||
|
|
"mean_token_accuracy": 0.15662355720996857,
|
||
|
|
"num_tokens": 3278846.0,
|
||
|
|
"step": 1770
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.669299554824829,
|
||
|
|
"epoch": 1.4853556485355648,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004944751492192416,
|
||
|
|
"loss": 5.5884,
|
||
|
|
"mean_token_accuracy": 0.16536742597818374,
|
||
|
|
"num_tokens": 3287200.0,
|
||
|
|
"step": 1775
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.683395767211914,
|
||
|
|
"epoch": 1.489539748953975,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004944038364884734,
|
||
|
|
"loss": 5.6288,
|
||
|
|
"mean_token_accuracy": 0.16207243353128434,
|
||
|
|
"num_tokens": 3296651.0,
|
||
|
|
"step": 1780
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.641139030456543,
|
||
|
|
"epoch": 1.493723849372385,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.0004943320722598842,
|
||
|
|
"loss": 5.4855,
|
||
|
|
"mean_token_accuracy": 0.16841897070407869,
|
||
|
|
"num_tokens": 3304887.0,
|
||
|
|
"step": 1785
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.611622476577759,
|
||
|
|
"epoch": 1.497907949790795,
|
||
|
|
"grad_norm": 1.203125,
|
||
|
|
"learning_rate": 0.0004942598566811532,
|
||
|
|
"loss": 5.5241,
|
||
|
|
"mean_token_accuracy": 0.16441086083650588,
|
||
|
|
"num_tokens": 3313925.0,
|
||
|
|
"step": 1790
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.564924716949463,
|
||
|
|
"epoch": 1.502092050209205,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004941871899008887,
|
||
|
|
"loss": 5.523,
|
||
|
|
"mean_token_accuracy": 0.1679730162024498,
|
||
|
|
"num_tokens": 3322943.0,
|
||
|
|
"step": 1795
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.561237525939942,
|
||
|
|
"epoch": 1.506276150627615,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.000494114072068627,
|
||
|
|
"loss": 5.5396,
|
||
|
|
"mean_token_accuracy": 0.15930552929639816,
|
||
|
|
"num_tokens": 3332742.0,
|
||
|
|
"step": 1800
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.60180697441101,
|
||
|
|
"epoch": 1.510460251046025,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004940405033348332,
|
||
|
|
"loss": 5.6209,
|
||
|
|
"mean_token_accuracy": 0.16569100469350814,
|
||
|
|
"num_tokens": 3342228.0,
|
||
|
|
"step": 1805
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.643794870376587,
|
||
|
|
"epoch": 1.514644351464435,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004939664838508996,
|
||
|
|
"loss": 5.5844,
|
||
|
|
"mean_token_accuracy": 0.16332708448171615,
|
||
|
|
"num_tokens": 3351854.0,
|
||
|
|
"step": 1810
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.556795120239258,
|
||
|
|
"epoch": 1.5188284518828452,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004938920137691465,
|
||
|
|
"loss": 5.5729,
|
||
|
|
"mean_token_accuracy": 0.16669173836708068,
|
||
|
|
"num_tokens": 3360809.0,
|
||
|
|
"step": 1815
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.631477355957031,
|
||
|
|
"epoch": 1.5230125523012552,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004938170932428214,
|
||
|
|
"loss": 5.611,
|
||
|
|
"mean_token_accuracy": 0.1575515404343605,
|
||
|
|
"num_tokens": 3371033.0,
|
||
|
|
"step": 1820
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.687102317810059,
|
||
|
|
"epoch": 1.5271966527196654,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004937417224260984,
|
||
|
|
"loss": 5.4723,
|
||
|
|
"mean_token_accuracy": 0.16213055700063705,
|
||
|
|
"num_tokens": 3379943.0,
|
||
|
|
"step": 1825
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.527942228317261,
|
||
|
|
"epoch": 1.5313807531380754,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004936659014740791,
|
||
|
|
"loss": 5.6114,
|
||
|
|
"mean_token_accuracy": 0.16545302420854568,
|
||
|
|
"num_tokens": 3389316.0,
|
||
|
|
"step": 1830
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.69856481552124,
|
||
|
|
"epoch": 1.5355648535564854,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004935896305427904,
|
||
|
|
"loss": 5.6451,
|
||
|
|
"mean_token_accuracy": 0.1602216750383377,
|
||
|
|
"num_tokens": 3398914.0,
|
||
|
|
"step": 1835
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.756103801727295,
|
||
|
|
"epoch": 1.5397489539748954,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004935129097891857,
|
||
|
|
"loss": 5.6111,
|
||
|
|
"mean_token_accuracy": 0.16129681766033171,
|
||
|
|
"num_tokens": 3407967.0,
|
||
|
|
"step": 1840
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.65551176071167,
|
||
|
|
"epoch": 1.5439330543933054,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000493435739371144,
|
||
|
|
"loss": 5.6406,
|
||
|
|
"mean_token_accuracy": 0.1634376108646393,
|
||
|
|
"num_tokens": 3416530.0,
|
||
|
|
"step": 1845
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.584914255142212,
|
||
|
|
"epoch": 1.5481171548117154,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004933581194474695,
|
||
|
|
"loss": 5.5043,
|
||
|
|
"mean_token_accuracy": 0.16534085869789122,
|
||
|
|
"num_tokens": 3425762.0,
|
||
|
|
"step": 1850
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.579939603805542,
|
||
|
|
"epoch": 1.5523012552301254,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004932800501778918,
|
||
|
|
"loss": 5.5956,
|
||
|
|
"mean_token_accuracy": 0.16289042830467224,
|
||
|
|
"num_tokens": 3434799.0,
|
||
|
|
"step": 1855
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.686808443069458,
|
||
|
|
"epoch": 1.5564853556485354,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004932015317230646,
|
||
|
|
"loss": 5.5969,
|
||
|
|
"mean_token_accuracy": 0.1612599492073059,
|
||
|
|
"num_tokens": 3442986.0,
|
||
|
|
"step": 1860
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.627131843566895,
|
||
|
|
"epoch": 1.5606694560669456,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004931225642445665,
|
||
|
|
"loss": 5.6385,
|
||
|
|
"mean_token_accuracy": 0.16176490783691405,
|
||
|
|
"num_tokens": 3452914.0,
|
||
|
|
"step": 1865
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.601911830902099,
|
||
|
|
"epoch": 1.5648535564853556,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004930431479048998,
|
||
|
|
"loss": 5.4773,
|
||
|
|
"mean_token_accuracy": 0.1727757453918457,
|
||
|
|
"num_tokens": 3462093.0,
|
||
|
|
"step": 1870
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.599895477294922,
|
||
|
|
"epoch": 1.5690376569037658,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004929632828674904,
|
||
|
|
"loss": 5.6701,
|
||
|
|
"mean_token_accuracy": 0.15993697494268416,
|
||
|
|
"num_tokens": 3471259.0,
|
||
|
|
"step": 1875
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.64299430847168,
|
||
|
|
"epoch": 1.5732217573221758,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004928829692966879,
|
||
|
|
"loss": 5.5967,
|
||
|
|
"mean_token_accuracy": 0.17002829760313035,
|
||
|
|
"num_tokens": 3480071.0,
|
||
|
|
"step": 1880
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.7399860382080075,
|
||
|
|
"epoch": 1.5774058577405858,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004928022073577646,
|
||
|
|
"loss": 5.6332,
|
||
|
|
"mean_token_accuracy": 0.16624970436096193,
|
||
|
|
"num_tokens": 3489075.0,
|
||
|
|
"step": 1885
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.606470966339112,
|
||
|
|
"epoch": 1.5815899581589958,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004927209972169157,
|
||
|
|
"loss": 5.4697,
|
||
|
|
"mean_token_accuracy": 0.1706315368413925,
|
||
|
|
"num_tokens": 3498495.0,
|
||
|
|
"step": 1890
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.556340599060059,
|
||
|
|
"epoch": 1.5857740585774058,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004926393390412586,
|
||
|
|
"loss": 5.6112,
|
||
|
|
"mean_token_accuracy": 0.16138895153999328,
|
||
|
|
"num_tokens": 3508590.0,
|
||
|
|
"step": 1895
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.680856943130493,
|
||
|
|
"epoch": 1.5899581589958158,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004925572329988325,
|
||
|
|
"loss": 5.6171,
|
||
|
|
"mean_token_accuracy": 0.15914507061243058,
|
||
|
|
"num_tokens": 3518397.0,
|
||
|
|
"step": 1900
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.604571723937989,
|
||
|
|
"epoch": 1.5941422594142258,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004924746792585987,
|
||
|
|
"loss": 5.6019,
|
||
|
|
"mean_token_accuracy": 0.1657917842268944,
|
||
|
|
"num_tokens": 3526620.0,
|
||
|
|
"step": 1905
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.760931587219238,
|
||
|
|
"epoch": 1.5983263598326358,
|
||
|
|
"grad_norm": 1.15625,
|
||
|
|
"learning_rate": 0.0004923916779904394,
|
||
|
|
"loss": 5.6215,
|
||
|
|
"mean_token_accuracy": 0.16468919068574905,
|
||
|
|
"num_tokens": 3535534.0,
|
||
|
|
"step": 1910
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.53223729133606,
|
||
|
|
"epoch": 1.602510460251046,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004923082293651578,
|
||
|
|
"loss": 5.568,
|
||
|
|
"mean_token_accuracy": 0.16554071754217148,
|
||
|
|
"num_tokens": 3544771.0,
|
||
|
|
"step": 1915
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.640694427490234,
|
||
|
|
"epoch": 1.606694560669456,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.000492224333554478,
|
||
|
|
"loss": 5.5337,
|
||
|
|
"mean_token_accuracy": 0.15835429430007936,
|
||
|
|
"num_tokens": 3553970.0,
|
||
|
|
"step": 1920
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.546091079711914,
|
||
|
|
"epoch": 1.6108786610878663,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004921399907310437,
|
||
|
|
"loss": 5.4523,
|
||
|
|
"mean_token_accuracy": 0.1624826580286026,
|
||
|
|
"num_tokens": 3563116.0,
|
||
|
|
"step": 1925
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.54065899848938,
|
||
|
|
"epoch": 1.6150627615062763,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004920552010684191,
|
||
|
|
"loss": 5.5843,
|
||
|
|
"mean_token_accuracy": 0.1632082238793373,
|
||
|
|
"num_tokens": 3571605.0,
|
||
|
|
"step": 1930
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.579107475280762,
|
||
|
|
"epoch": 1.6192468619246863,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004919699647410878,
|
||
|
|
"loss": 5.6733,
|
||
|
|
"mean_token_accuracy": 0.15940951108932494,
|
||
|
|
"num_tokens": 3581837.0,
|
||
|
|
"step": 1935
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.651897621154785,
|
||
|
|
"epoch": 1.6234309623430963,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004918842819244523,
|
||
|
|
"loss": 5.6108,
|
||
|
|
"mean_token_accuracy": 0.15646165311336518,
|
||
|
|
"num_tokens": 3590853.0,
|
||
|
|
"step": 1940
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.609458684921265,
|
||
|
|
"epoch": 1.6276150627615062,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004917981527948342,
|
||
|
|
"loss": 5.5049,
|
||
|
|
"mean_token_accuracy": 0.16811413764953614,
|
||
|
|
"num_tokens": 3599708.0,
|
||
|
|
"step": 1945
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.549583625793457,
|
||
|
|
"epoch": 1.6317991631799162,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004917115775294731,
|
||
|
|
"loss": 5.5331,
|
||
|
|
"mean_token_accuracy": 0.1643170267343521,
|
||
|
|
"num_tokens": 3608634.0,
|
||
|
|
"step": 1950
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.594006633758545,
|
||
|
|
"epoch": 1.6359832635983262,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004916245563065273,
|
||
|
|
"loss": 5.5907,
|
||
|
|
"mean_token_accuracy": 0.1617286831140518,
|
||
|
|
"num_tokens": 3618776.0,
|
||
|
|
"step": 1955
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.669147920608521,
|
||
|
|
"epoch": 1.6401673640167362,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004915370893050722,
|
||
|
|
"loss": 5.6027,
|
||
|
|
"mean_token_accuracy": 0.1599277600646019,
|
||
|
|
"num_tokens": 3628595.0,
|
||
|
|
"step": 1960
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.733761310577393,
|
||
|
|
"epoch": 1.6443514644351465,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004914491767051012,
|
||
|
|
"loss": 5.7264,
|
||
|
|
"mean_token_accuracy": 0.15489014610648155,
|
||
|
|
"num_tokens": 3638133.0,
|
||
|
|
"step": 1965
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.570251989364624,
|
||
|
|
"epoch": 1.6485355648535565,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004913608186875241,
|
||
|
|
"loss": 5.5056,
|
||
|
|
"mean_token_accuracy": 0.1667278602719307,
|
||
|
|
"num_tokens": 3646679.0,
|
||
|
|
"step": 1970
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.62856240272522,
|
||
|
|
"epoch": 1.6527196652719667,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004912720154341674,
|
||
|
|
"loss": 5.6283,
|
||
|
|
"mean_token_accuracy": 0.15991436094045638,
|
||
|
|
"num_tokens": 3656131.0,
|
||
|
|
"step": 1975
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.649011325836182,
|
||
|
|
"epoch": 1.6569037656903767,
|
||
|
|
"grad_norm": 1.0546875,
|
||
|
|
"learning_rate": 0.0004911827671277739,
|
||
|
|
"loss": 5.531,
|
||
|
|
"mean_token_accuracy": 0.16518089473247527,
|
||
|
|
"num_tokens": 3665187.0,
|
||
|
|
"step": 1980
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.646500158309936,
|
||
|
|
"epoch": 1.6610878661087867,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004910930739520025,
|
||
|
|
"loss": 5.5849,
|
||
|
|
"mean_token_accuracy": 0.1645905703306198,
|
||
|
|
"num_tokens": 3674649.0,
|
||
|
|
"step": 1985
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.67808575630188,
|
||
|
|
"epoch": 1.6652719665271967,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.0004910029360914271,
|
||
|
|
"loss": 5.6256,
|
||
|
|
"mean_token_accuracy": 0.15767135918140412,
|
||
|
|
"num_tokens": 3684680.0,
|
||
|
|
"step": 1990
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.539081144332886,
|
||
|
|
"epoch": 1.6694560669456067,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.000490912353731537,
|
||
|
|
"loss": 5.5464,
|
||
|
|
"mean_token_accuracy": 0.1714841827750206,
|
||
|
|
"num_tokens": 3693560.0,
|
||
|
|
"step": 1995
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.563750696182251,
|
||
|
|
"epoch": 1.6736401673640167,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004908213270587363,
|
||
|
|
"loss": 5.5372,
|
||
|
|
"mean_token_accuracy": 0.16540804207324983,
|
||
|
|
"num_tokens": 3702632.0,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.6736401673640167,
|
||
|
|
"eval_entropy": 5.491124003942759,
|
||
|
|
"eval_loss": 5.678599834442139,
|
||
|
|
"eval_mean_token_accuracy": 0.16818918819503062,
|
||
|
|
"eval_num_tokens": 3702632.0,
|
||
|
|
"eval_runtime": 2.7304,
|
||
|
|
"eval_samples_per_second": 1430.95,
|
||
|
|
"eval_steps_per_second": 179.098,
|
||
|
|
"step": 2000
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.572523546218872,
|
||
|
|
"epoch": 1.6778242677824267,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004907298562603431,
|
||
|
|
"loss": 5.4302,
|
||
|
|
"mean_token_accuracy": 0.1779036343097687,
|
||
|
|
"num_tokens": 3711022.0,
|
||
|
|
"step": 2005
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.51769700050354,
|
||
|
|
"epoch": 1.6820083682008367,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004906379415245896,
|
||
|
|
"loss": 5.5388,
|
||
|
|
"mean_token_accuracy": 0.16877284198999404,
|
||
|
|
"num_tokens": 3719778.0,
|
||
|
|
"step": 2010
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.562564992904663,
|
||
|
|
"epoch": 1.6861924686192469,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004905455830406215,
|
||
|
|
"loss": 5.5346,
|
||
|
|
"mean_token_accuracy": 0.1705291375517845,
|
||
|
|
"num_tokens": 3728773.0,
|
||
|
|
"step": 2015
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.590969371795654,
|
||
|
|
"epoch": 1.6903765690376569,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004904527809984978,
|
||
|
|
"loss": 5.58,
|
||
|
|
"mean_token_accuracy": 0.1744068220257759,
|
||
|
|
"num_tokens": 3737781.0,
|
||
|
|
"step": 2020
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.690853548049927,
|
||
|
|
"epoch": 1.694560669456067,
|
||
|
|
"grad_norm": 0.98828125,
|
||
|
|
"learning_rate": 0.0004903595355891902,
|
||
|
|
"loss": 5.6152,
|
||
|
|
"mean_token_accuracy": 0.1568044126033783,
|
||
|
|
"num_tokens": 3748010.0,
|
||
|
|
"step": 2025
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.597555637359619,
|
||
|
|
"epoch": 1.698744769874477,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004902658470045826,
|
||
|
|
"loss": 5.6003,
|
||
|
|
"mean_token_accuracy": 0.16391026079654694,
|
||
|
|
"num_tokens": 3757894.0,
|
||
|
|
"step": 2030
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.673963737487793,
|
||
|
|
"epoch": 1.702928870292887,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.0004901717154374713,
|
||
|
|
"loss": 5.6991,
|
||
|
|
"mean_token_accuracy": 0.16143399029970168,
|
||
|
|
"num_tokens": 3768760.0,
|
||
|
|
"step": 2035
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.624513435363769,
|
||
|
|
"epoch": 1.707112970711297,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004900771410815638,
|
||
|
|
"loss": 5.5315,
|
||
|
|
"mean_token_accuracy": 0.16945276856422425,
|
||
|
|
"num_tokens": 3778273.0,
|
||
|
|
"step": 2040
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.517771816253662,
|
||
|
|
"epoch": 1.711297071129707,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004899821241314788,
|
||
|
|
"loss": 5.5358,
|
||
|
|
"mean_token_accuracy": 0.1683587208390236,
|
||
|
|
"num_tokens": 3787012.0,
|
||
|
|
"step": 2045
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.567167663574219,
|
||
|
|
"epoch": 1.715481171548117,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.000489886664782746,
|
||
|
|
"loss": 5.486,
|
||
|
|
"mean_token_accuracy": 0.1716827154159546,
|
||
|
|
"num_tokens": 3795144.0,
|
||
|
|
"step": 2050
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.686856889724732,
|
||
|
|
"epoch": 1.719665271966527,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004897907632318055,
|
||
|
|
"loss": 5.7107,
|
||
|
|
"mean_token_accuracy": 0.15753279775381088,
|
||
|
|
"num_tokens": 3804534.0,
|
||
|
|
"step": 2055
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.55545563697815,
|
||
|
|
"epoch": 1.723849372384937,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004896944196760071,
|
||
|
|
"loss": 5.4828,
|
||
|
|
"mean_token_accuracy": 0.16995557993650437,
|
||
|
|
"num_tokens": 3813757.0,
|
||
|
|
"step": 2060
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.505803346633911,
|
||
|
|
"epoch": 1.7280334728033473,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004895976343136106,
|
||
|
|
"loss": 5.5339,
|
||
|
|
"mean_token_accuracy": 0.17111619263887407,
|
||
|
|
"num_tokens": 3823157.0,
|
||
|
|
"step": 2065
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.46083288192749,
|
||
|
|
"epoch": 1.7322175732217573,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004895004073437844,
|
||
|
|
"loss": 5.4172,
|
||
|
|
"mean_token_accuracy": 0.17137759774923325,
|
||
|
|
"num_tokens": 3831661.0,
|
||
|
|
"step": 2070
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.466241359710693,
|
||
|
|
"epoch": 1.7364016736401675,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004894027389666061,
|
||
|
|
"loss": 5.4048,
|
||
|
|
"mean_token_accuracy": 0.16757647842168807,
|
||
|
|
"num_tokens": 3840591.0,
|
||
|
|
"step": 2075
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.573554372787475,
|
||
|
|
"epoch": 1.7405857740585775,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004893046293830616,
|
||
|
|
"loss": 5.5502,
|
||
|
|
"mean_token_accuracy": 0.16351725161075592,
|
||
|
|
"num_tokens": 3850094.0,
|
||
|
|
"step": 2080
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.571382141113281,
|
||
|
|
"epoch": 1.7447698744769875,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004892060787950447,
|
||
|
|
"loss": 5.5728,
|
||
|
|
"mean_token_accuracy": 0.16660072952508925,
|
||
|
|
"num_tokens": 3858973.0,
|
||
|
|
"step": 2085
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.496927070617676,
|
||
|
|
"epoch": 1.7489539748953975,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004891070874053564,
|
||
|
|
"loss": 5.3678,
|
||
|
|
"mean_token_accuracy": 0.17261970937252044,
|
||
|
|
"num_tokens": 3868315.0,
|
||
|
|
"step": 2090
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.528550434112549,
|
||
|
|
"epoch": 1.7531380753138075,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004890076554177051,
|
||
|
|
"loss": 5.5204,
|
||
|
|
"mean_token_accuracy": 0.16873810589313507,
|
||
|
|
"num_tokens": 3877605.0,
|
||
|
|
"step": 2095
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6158366203308105,
|
||
|
|
"epoch": 1.7573221757322175,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004889077830367061,
|
||
|
|
"loss": 5.5403,
|
||
|
|
"mean_token_accuracy": 0.16531874537467955,
|
||
|
|
"num_tokens": 3886998.0,
|
||
|
|
"step": 2100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.541978931427002,
|
||
|
|
"epoch": 1.7615062761506275,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004888074704678806,
|
||
|
|
"loss": 5.4911,
|
||
|
|
"mean_token_accuracy": 0.1717954158782959,
|
||
|
|
"num_tokens": 3896018.0,
|
||
|
|
"step": 2105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.581347227096558,
|
||
|
|
"epoch": 1.7656903765690377,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004887067179176558,
|
||
|
|
"loss": 5.483,
|
||
|
|
"mean_token_accuracy": 0.16950565576553345,
|
||
|
|
"num_tokens": 3904957.0,
|
||
|
|
"step": 2110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.531962156295776,
|
||
|
|
"epoch": 1.7698744769874477,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.0004886055255933639,
|
||
|
|
"loss": 5.5971,
|
||
|
|
"mean_token_accuracy": 0.16620343998074533,
|
||
|
|
"num_tokens": 3913427.0,
|
||
|
|
"step": 2115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.583233118057251,
|
||
|
|
"epoch": 1.7740585774058577,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004885038937032429,
|
||
|
|
"loss": 5.5093,
|
||
|
|
"mean_token_accuracy": 0.16479990780353546,
|
||
|
|
"num_tokens": 3923134.0,
|
||
|
|
"step": 2120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.555366945266724,
|
||
|
|
"epoch": 1.778242677824268,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.0004884018224564345,
|
||
|
|
"loss": 5.4355,
|
||
|
|
"mean_token_accuracy": 0.16853926777839662,
|
||
|
|
"num_tokens": 3931867.0,
|
||
|
|
"step": 2125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.533804702758789,
|
||
|
|
"epoch": 1.782426778242678,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004882993120629852,
|
||
|
|
"loss": 5.5219,
|
||
|
|
"mean_token_accuracy": 0.1705673635005951,
|
||
|
|
"num_tokens": 3941057.0,
|
||
|
|
"step": 2130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.687018394470215,
|
||
|
|
"epoch": 1.786610878661088,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.0004881963627338449,
|
||
|
|
"loss": 5.6362,
|
||
|
|
"mean_token_accuracy": 0.15854295045137407,
|
||
|
|
"num_tokens": 3950511.0,
|
||
|
|
"step": 2135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.586686897277832,
|
||
|
|
"epoch": 1.790794979079498,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00048809297468086654,
|
||
|
|
"loss": 5.5561,
|
||
|
|
"mean_token_accuracy": 0.17459627687931062,
|
||
|
|
"num_tokens": 3959769.0,
|
||
|
|
"step": 2140
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.593465280532837,
|
||
|
|
"epoch": 1.794979079497908,
|
||
|
|
"grad_norm": 0.97265625,
|
||
|
|
"learning_rate": 0.0004879891481168063,
|
||
|
|
"loss": 5.4756,
|
||
|
|
"mean_token_accuracy": 0.17072359174489976,
|
||
|
|
"num_tokens": 3968462.0,
|
||
|
|
"step": 2145
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.463370895385742,
|
||
|
|
"epoch": 1.799163179916318,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00048788488325532235,
|
||
|
|
"loss": 5.5393,
|
||
|
|
"mean_token_accuracy": 0.1667232632637024,
|
||
|
|
"num_tokens": 3977464.0,
|
||
|
|
"step": 2150
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.515686464309693,
|
||
|
|
"epoch": 1.803347280334728,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.0004877801803109753,
|
||
|
|
"loss": 5.4495,
|
||
|
|
"mean_token_accuracy": 0.17411705553531648,
|
||
|
|
"num_tokens": 3986303.0,
|
||
|
|
"step": 2155
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.621507215499878,
|
||
|
|
"epoch": 1.8075313807531381,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00048767503949922683,
|
||
|
|
"loss": 5.4763,
|
||
|
|
"mean_token_accuracy": 0.17094481438398362,
|
||
|
|
"num_tokens": 3994970.0,
|
||
|
|
"step": 2160
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.613283586502075,
|
||
|
|
"epoch": 1.8117154811715481,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004875694610364398,
|
||
|
|
"loss": 5.5803,
|
||
|
|
"mean_token_accuracy": 0.16584169268608093,
|
||
|
|
"num_tokens": 4004679.0,
|
||
|
|
"step": 2165
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.642657518386841,
|
||
|
|
"epoch": 1.8158995815899581,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00048746344513987775,
|
||
|
|
"loss": 5.5997,
|
||
|
|
"mean_token_accuracy": 0.16097164154052734,
|
||
|
|
"num_tokens": 4013516.0,
|
||
|
|
"step": 2170
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.576339340209961,
|
||
|
|
"epoch": 1.8200836820083683,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004873569920277043,
|
||
|
|
"loss": 5.4456,
|
||
|
|
"mean_token_accuracy": 0.17589643746614456,
|
||
|
|
"num_tokens": 4022335.0,
|
||
|
|
"step": 2175
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.451902580261231,
|
||
|
|
"epoch": 1.8242677824267783,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00048725010191898296,
|
||
|
|
"loss": 5.433,
|
||
|
|
"mean_token_accuracy": 0.17280954718589783,
|
||
|
|
"num_tokens": 4031295.0,
|
||
|
|
"step": 2180
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.596143627166748,
|
||
|
|
"epoch": 1.8284518828451883,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00048714277503367627,
|
||
|
|
"loss": 5.6556,
|
||
|
|
"mean_token_accuracy": 0.16676488071680068,
|
||
|
|
"num_tokens": 4040378.0,
|
||
|
|
"step": 2185
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.647720813751221,
|
||
|
|
"epoch": 1.8326359832635983,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00048703501159264576,
|
||
|
|
"loss": 5.5182,
|
||
|
|
"mean_token_accuracy": 0.15616264939308167,
|
||
|
|
"num_tokens": 4050217.0,
|
||
|
|
"step": 2190
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.399335479736328,
|
||
|
|
"epoch": 1.8368200836820083,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.0004869268118176512,
|
||
|
|
"loss": 5.39,
|
||
|
|
"mean_token_accuracy": 0.16944845616817475,
|
||
|
|
"num_tokens": 4059088.0,
|
||
|
|
"step": 2195
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6183709621429445,
|
||
|
|
"epoch": 1.8410041841004183,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00048681817593135046,
|
||
|
|
"loss": 5.4924,
|
||
|
|
"mean_token_accuracy": 0.18004305362701417,
|
||
|
|
"num_tokens": 4067609.0,
|
||
|
|
"step": 2200
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.551707029342651,
|
||
|
|
"epoch": 1.8451882845188283,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00048670910415729855,
|
||
|
|
"loss": 5.4916,
|
||
|
|
"mean_token_accuracy": 0.1724642962217331,
|
||
|
|
"num_tokens": 4076763.0,
|
||
|
|
"step": 2205
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.59165768623352,
|
||
|
|
"epoch": 1.8493723849372385,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00048659959671994786,
|
||
|
|
"loss": 5.6457,
|
||
|
|
"mean_token_accuracy": 0.16204374581575393,
|
||
|
|
"num_tokens": 4086552.0,
|
||
|
|
"step": 2210
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.455987501144409,
|
||
|
|
"epoch": 1.8535564853556485,
|
||
|
|
"grad_norm": 1.0390625,
|
||
|
|
"learning_rate": 0.00048648965384464693,
|
||
|
|
"loss": 5.406,
|
||
|
|
"mean_token_accuracy": 0.1716286361217499,
|
||
|
|
"num_tokens": 4096200.0,
|
||
|
|
"step": 2215
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.506076335906982,
|
||
|
|
"epoch": 1.8577405857740585,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00048637927575764057,
|
||
|
|
"loss": 5.4556,
|
||
|
|
"mean_token_accuracy": 0.17082349807024003,
|
||
|
|
"num_tokens": 4105080.0,
|
||
|
|
"step": 2220
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.517089176177978,
|
||
|
|
"epoch": 1.8619246861924688,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.00048626846268606913,
|
||
|
|
"loss": 5.4106,
|
||
|
|
"mean_token_accuracy": 0.16985356509685517,
|
||
|
|
"num_tokens": 4113972.0,
|
||
|
|
"step": 2225
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6436656475067135,
|
||
|
|
"epoch": 1.8661087866108788,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.00048615721485796803,
|
||
|
|
"loss": 5.6571,
|
||
|
|
"mean_token_accuracy": 0.16025995314121247,
|
||
|
|
"num_tokens": 4123615.0,
|
||
|
|
"step": 2230
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.553581619262696,
|
||
|
|
"epoch": 1.8702928870292888,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.0004860455325022676,
|
||
|
|
"loss": 5.4155,
|
||
|
|
"mean_token_accuracy": 0.1689600870013237,
|
||
|
|
"num_tokens": 4132128.0,
|
||
|
|
"step": 2235
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.622593832015991,
|
||
|
|
"epoch": 1.8744769874476988,
|
||
|
|
"grad_norm": 1.0703125,
|
||
|
|
"learning_rate": 0.000485933415848792,
|
||
|
|
"loss": 5.6146,
|
||
|
|
"mean_token_accuracy": 0.16623764038085936,
|
||
|
|
"num_tokens": 4141575.0,
|
||
|
|
"step": 2240
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.566574192047119,
|
||
|
|
"epoch": 1.8786610878661087,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004858208651282593,
|
||
|
|
"loss": 5.4563,
|
||
|
|
"mean_token_accuracy": 0.1704362750053406,
|
||
|
|
"num_tokens": 4150372.0,
|
||
|
|
"step": 2245
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.508659744262696,
|
||
|
|
"epoch": 1.8828451882845187,
|
||
|
|
"grad_norm": 1.1640625,
|
||
|
|
"learning_rate": 0.000485707880572281,
|
||
|
|
"loss": 5.5718,
|
||
|
|
"mean_token_accuracy": 0.17235517501831055,
|
||
|
|
"num_tokens": 4159007.0,
|
||
|
|
"step": 2250
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.592802858352661,
|
||
|
|
"epoch": 1.8870292887029287,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004855944624133608,
|
||
|
|
"loss": 5.6236,
|
||
|
|
"mean_token_accuracy": 0.16393871158361434,
|
||
|
|
"num_tokens": 4168646.0,
|
||
|
|
"step": 2255
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.489811658859253,
|
||
|
|
"epoch": 1.891213389121339,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.00048548061088489523,
|
||
|
|
"loss": 5.5131,
|
||
|
|
"mean_token_accuracy": 0.16455192416906356,
|
||
|
|
"num_tokens": 4177979.0,
|
||
|
|
"step": 2260
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.58298807144165,
|
||
|
|
"epoch": 1.895397489539749,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00048536632622117246,
|
||
|
|
"loss": 5.4378,
|
||
|
|
"mean_token_accuracy": 0.17333355098962783,
|
||
|
|
"num_tokens": 4186781.0,
|
||
|
|
"step": 2265
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.503539419174194,
|
||
|
|
"epoch": 1.899581589958159,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.00048525160865737186,
|
||
|
|
"loss": 5.5073,
|
||
|
|
"mean_token_accuracy": 0.16708964258432388,
|
||
|
|
"num_tokens": 4195661.0,
|
||
|
|
"step": 2270
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.515585327148438,
|
||
|
|
"epoch": 1.9037656903765692,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00048513645842956384,
|
||
|
|
"loss": 5.4108,
|
||
|
|
"mean_token_accuracy": 0.17160611748695373,
|
||
|
|
"num_tokens": 4203902.0,
|
||
|
|
"step": 2275
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.459004068374634,
|
||
|
|
"epoch": 1.9079497907949792,
|
||
|
|
"grad_norm": 1.0,
|
||
|
|
"learning_rate": 0.00048502087577470895,
|
||
|
|
"loss": 5.4666,
|
||
|
|
"mean_token_accuracy": 0.16583277732133866,
|
||
|
|
"num_tokens": 4213663.0,
|
||
|
|
"step": 2280
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.629412889480591,
|
||
|
|
"epoch": 1.9121338912133892,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.00048490486093065774,
|
||
|
|
"loss": 5.514,
|
||
|
|
"mean_token_accuracy": 0.1735001504421234,
|
||
|
|
"num_tokens": 4222152.0,
|
||
|
|
"step": 2285
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.527402353286743,
|
||
|
|
"epoch": 1.9163179916317992,
|
||
|
|
"grad_norm": 0.95703125,
|
||
|
|
"learning_rate": 0.00048478841413615017,
|
||
|
|
"loss": 5.529,
|
||
|
|
"mean_token_accuracy": 0.17351837158203126,
|
||
|
|
"num_tokens": 4232347.0,
|
||
|
|
"step": 2290
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.60933895111084,
|
||
|
|
"epoch": 1.9205020920502092,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00048467153563081487,
|
||
|
|
"loss": 5.6077,
|
||
|
|
"mean_token_accuracy": 0.1692125305533409,
|
||
|
|
"num_tokens": 4240607.0,
|
||
|
|
"step": 2295
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.599947690963745,
|
||
|
|
"epoch": 1.9246861924686192,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004845542256551692,
|
||
|
|
"loss": 5.6023,
|
||
|
|
"mean_token_accuracy": 0.16642989665269853,
|
||
|
|
"num_tokens": 4251131.0,
|
||
|
|
"step": 2300
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.583032417297363,
|
||
|
|
"epoch": 1.9288702928870292,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.0004844364844506181,
|
||
|
|
"loss": 5.5281,
|
||
|
|
"mean_token_accuracy": 0.16871487051248552,
|
||
|
|
"num_tokens": 4259955.0,
|
||
|
|
"step": 2305
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.600530576705933,
|
||
|
|
"epoch": 1.9330543933054394,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004843183122594541,
|
||
|
|
"loss": 5.5134,
|
||
|
|
"mean_token_accuracy": 0.16982486397027968,
|
||
|
|
"num_tokens": 4268686.0,
|
||
|
|
"step": 2310
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.535481405258179,
|
||
|
|
"epoch": 1.9372384937238494,
|
||
|
|
"grad_norm": 1.1953125,
|
||
|
|
"learning_rate": 0.0004841997093248566,
|
||
|
|
"loss": 5.4926,
|
||
|
|
"mean_token_accuracy": 0.17420293092727662,
|
||
|
|
"num_tokens": 4277377.0,
|
||
|
|
"step": 2315
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.471238851547241,
|
||
|
|
"epoch": 1.9414225941422594,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004840806758908913,
|
||
|
|
"loss": 5.4791,
|
||
|
|
"mean_token_accuracy": 0.16643480509519576,
|
||
|
|
"num_tokens": 4287037.0,
|
||
|
|
"step": 2320
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.6762055397033695,
|
||
|
|
"epoch": 1.9456066945606696,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00048396121220250983,
|
||
|
|
"loss": 5.6222,
|
||
|
|
"mean_token_accuracy": 0.15888616740703582,
|
||
|
|
"num_tokens": 4296923.0,
|
||
|
|
"step": 2325
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.445138311386108,
|
||
|
|
"epoch": 1.9497907949790796,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004838413185055494,
|
||
|
|
"loss": 5.3837,
|
||
|
|
"mean_token_accuracy": 0.17829248905181885,
|
||
|
|
"num_tokens": 4305873.0,
|
||
|
|
"step": 2330
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.485724210739136,
|
||
|
|
"epoch": 1.9539748953974896,
|
||
|
|
"grad_norm": 1.0078125,
|
||
|
|
"learning_rate": 0.0004837209950467318,
|
||
|
|
"loss": 5.5408,
|
||
|
|
"mean_token_accuracy": 0.16909062415361403,
|
||
|
|
"num_tokens": 4314912.0,
|
||
|
|
"step": 2335
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.572770309448242,
|
||
|
|
"epoch": 1.9581589958158996,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004836002420736635,
|
||
|
|
"loss": 5.5479,
|
||
|
|
"mean_token_accuracy": 0.160999795794487,
|
||
|
|
"num_tokens": 4324606.0,
|
||
|
|
"step": 2340
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.4958367347717285,
|
||
|
|
"epoch": 1.9623430962343096,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.0004834790598348347,
|
||
|
|
"loss": 5.4023,
|
||
|
|
"mean_token_accuracy": 0.17136014699935914,
|
||
|
|
"num_tokens": 4333076.0,
|
||
|
|
"step": 2345
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.666383218765259,
|
||
|
|
"epoch": 1.9665271966527196,
|
||
|
|
"grad_norm": 1.1328125,
|
||
|
|
"learning_rate": 0.0004833574485796188,
|
||
|
|
"loss": 5.5494,
|
||
|
|
"mean_token_accuracy": 0.17031686305999755,
|
||
|
|
"num_tokens": 4341893.0,
|
||
|
|
"step": 2350
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.475465250015259,
|
||
|
|
"epoch": 1.9707112970711296,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.00048323540855827244,
|
||
|
|
"loss": 5.5148,
|
||
|
|
"mean_token_accuracy": 0.16724376380443573,
|
||
|
|
"num_tokens": 4352303.0,
|
||
|
|
"step": 2355
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.614174842834473,
|
||
|
|
"epoch": 1.9748953974895398,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.0004831129400219341,
|
||
|
|
"loss": 5.4649,
|
||
|
|
"mean_token_accuracy": 0.17016783058643342,
|
||
|
|
"num_tokens": 4361166.0,
|
||
|
|
"step": 2360
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.578010511398316,
|
||
|
|
"epoch": 1.9790794979079498,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00048299004322262457,
|
||
|
|
"loss": 5.5273,
|
||
|
|
"mean_token_accuracy": 0.1644423395395279,
|
||
|
|
"num_tokens": 4369999.0,
|
||
|
|
"step": 2365
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.497027206420898,
|
||
|
|
"epoch": 1.9832635983263598,
|
||
|
|
"grad_norm": 1.0859375,
|
||
|
|
"learning_rate": 0.00048286671841324565,
|
||
|
|
"loss": 5.4836,
|
||
|
|
"mean_token_accuracy": 0.17087049186229705,
|
||
|
|
"num_tokens": 4379373.0,
|
||
|
|
"step": 2370
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.576445913314819,
|
||
|
|
"epoch": 1.98744769874477,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004827429658475799,
|
||
|
|
"loss": 5.4755,
|
||
|
|
"mean_token_accuracy": 0.1715611144900322,
|
||
|
|
"num_tokens": 4389035.0,
|
||
|
|
"step": 2375
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.533624887466431,
|
||
|
|
"epoch": 1.99163179916318,
|
||
|
|
"grad_norm": 1.0234375,
|
||
|
|
"learning_rate": 0.00048261878578029026,
|
||
|
|
"loss": 5.6441,
|
||
|
|
"mean_token_accuracy": 0.1629743292927742,
|
||
|
|
"num_tokens": 4399366.0,
|
||
|
|
"step": 2380
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.575339126586914,
|
||
|
|
"epoch": 1.99581589958159,
|
||
|
|
"grad_norm": 1.21875,
|
||
|
|
"learning_rate": 0.0004824941784669193,
|
||
|
|
"loss": 5.4744,
|
||
|
|
"mean_token_accuracy": 0.1669633612036705,
|
||
|
|
"num_tokens": 4408183.0,
|
||
|
|
"step": 2385
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.541588544845581,
|
||
|
|
"epoch": 2.0,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.0004823691441638889,
|
||
|
|
"loss": 5.5844,
|
||
|
|
"mean_token_accuracy": 0.15914448723196983,
|
||
|
|
"num_tokens": 4418644.0,
|
||
|
|
"step": 2390
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.465671730041504,
|
||
|
|
"epoch": 2.00418410041841,
|
||
|
|
"grad_norm": 1.046875,
|
||
|
|
"learning_rate": 0.0004822436831284995,
|
||
|
|
"loss": 5.1718,
|
||
|
|
"mean_token_accuracy": 0.1804201766848564,
|
||
|
|
"num_tokens": 4427828.0,
|
||
|
|
"step": 2395
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.462167692184448,
|
||
|
|
"epoch": 2.00836820083682,
|
||
|
|
"grad_norm": 1.09375,
|
||
|
|
"learning_rate": 0.0004821177956189297,
|
||
|
|
"loss": 5.0932,
|
||
|
|
"mean_token_accuracy": 0.18268589228391646,
|
||
|
|
"num_tokens": 4436194.0,
|
||
|
|
"step": 2400
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.3815234184265135,
|
||
|
|
"epoch": 2.01255230125523,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004819914818942359,
|
||
|
|
"loss": 5.1587,
|
||
|
|
"mean_token_accuracy": 0.18811518847942352,
|
||
|
|
"num_tokens": 4444468.0,
|
||
|
|
"step": 2405
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.480875778198242,
|
||
|
|
"epoch": 2.01673640167364,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00048186474221435127,
|
||
|
|
"loss": 5.0801,
|
||
|
|
"mean_token_accuracy": 0.19296729266643525,
|
||
|
|
"num_tokens": 4452760.0,
|
||
|
|
"step": 2410
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.3785402297973635,
|
||
|
|
"epoch": 2.02092050209205,
|
||
|
|
"grad_norm": 1.078125,
|
||
|
|
"learning_rate": 0.00048173757684008583,
|
||
|
|
"loss": 5.1482,
|
||
|
|
"mean_token_accuracy": 0.1877833530306816,
|
||
|
|
"num_tokens": 4462154.0,
|
||
|
|
"step": 2415
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.477201223373413,
|
||
|
|
"epoch": 2.0251046025104604,
|
||
|
|
"grad_norm": 0.875,
|
||
|
|
"learning_rate": 0.0004816099860331255,
|
||
|
|
"loss": 5.2378,
|
||
|
|
"mean_token_accuracy": 0.18000938147306442,
|
||
|
|
"num_tokens": 4471987.0,
|
||
|
|
"step": 2420
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.446134471893311,
|
||
|
|
"epoch": 2.0292887029288704,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.00048148197005603145,
|
||
|
|
"loss": 5.1628,
|
||
|
|
"mean_token_accuracy": 0.18375986963510513,
|
||
|
|
"num_tokens": 4481645.0,
|
||
|
|
"step": 2425
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.28934006690979,
|
||
|
|
"epoch": 2.0334728033472804,
|
||
|
|
"grad_norm": 1.125,
|
||
|
|
"learning_rate": 0.00048135352917224005,
|
||
|
|
"loss": 5.132,
|
||
|
|
"mean_token_accuracy": 0.19004039466381073,
|
||
|
|
"num_tokens": 4491166.0,
|
||
|
|
"step": 2430
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.52780499458313,
|
||
|
|
"epoch": 2.0376569037656904,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.00048122466364606214,
|
||
|
|
"loss": 5.1386,
|
||
|
|
"mean_token_accuracy": 0.18404159545898438,
|
||
|
|
"num_tokens": 4500159.0,
|
||
|
|
"step": 2435
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.346362209320068,
|
||
|
|
"epoch": 2.0418410041841004,
|
||
|
|
"grad_norm": 1.1171875,
|
||
|
|
"learning_rate": 0.00048109537374268216,
|
||
|
|
"loss": 5.0872,
|
||
|
|
"mean_token_accuracy": 0.19677301347255707,
|
||
|
|
"num_tokens": 4509737.0,
|
||
|
|
"step": 2440
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.292774248123169,
|
||
|
|
"epoch": 2.0460251046025104,
|
||
|
|
"grad_norm": 1.234375,
|
||
|
|
"learning_rate": 0.00048096565972815793,
|
||
|
|
"loss": 5.0221,
|
||
|
|
"mean_token_accuracy": 0.19164910465478896,
|
||
|
|
"num_tokens": 4518379.0,
|
||
|
|
"step": 2445
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.365337228775024,
|
||
|
|
"epoch": 2.0502092050209204,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.0004808355218694199,
|
||
|
|
"loss": 5.1611,
|
||
|
|
"mean_token_accuracy": 0.18420323133468627,
|
||
|
|
"num_tokens": 4527885.0,
|
||
|
|
"step": 2450
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.407716226577759,
|
||
|
|
"epoch": 2.0543933054393304,
|
||
|
|
"grad_norm": 1.1484375,
|
||
|
|
"learning_rate": 0.00048070496043427116,
|
||
|
|
"loss": 5.1975,
|
||
|
|
"mean_token_accuracy": 0.1824670508503914,
|
||
|
|
"num_tokens": 4537894.0,
|
||
|
|
"step": 2455
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.380266380310059,
|
||
|
|
"epoch": 2.0585774058577404,
|
||
|
|
"grad_norm": 1.140625,
|
||
|
|
"learning_rate": 0.00048057397569138596,
|
||
|
|
"loss": 5.0945,
|
||
|
|
"mean_token_accuracy": 0.19576826244592666,
|
||
|
|
"num_tokens": 4546462.0,
|
||
|
|
"step": 2460
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.378341960906982,
|
||
|
|
"epoch": 2.062761506276151,
|
||
|
|
"grad_norm": 1.1015625,
|
||
|
|
"learning_rate": 0.0004804425679103099,
|
||
|
|
"loss": 5.1205,
|
||
|
|
"mean_token_accuracy": 0.18275196850299835,
|
||
|
|
"num_tokens": 4555970.0,
|
||
|
|
"step": 2465
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.402397394180298,
|
||
|
|
"epoch": 2.066945606694561,
|
||
|
|
"grad_norm": 1.0625,
|
||
|
|
"learning_rate": 0.0004803107373614589,
|
||
|
|
"loss": 5.1896,
|
||
|
|
"mean_token_accuracy": 0.17988977134227752,
|
||
|
|
"num_tokens": 4565799.0,
|
||
|
|
"step": 2470
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.4651405811309814,
|
||
|
|
"epoch": 2.071129707112971,
|
||
|
|
"grad_norm": 1.015625,
|
||
|
|
"learning_rate": 0.0004801784843161194,
|
||
|
|
"loss": 5.2097,
|
||
|
|
"mean_token_accuracy": 0.17294996231794357,
|
||
|
|
"num_tokens": 4575571.0,
|
||
|
|
"step": 2475
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.369615983963013,
|
||
|
|
"epoch": 2.075313807531381,
|
||
|
|
"grad_norm": 1.2109375,
|
||
|
|
"learning_rate": 0.0004800458090464465,
|
||
|
|
"loss": 5.1138,
|
||
|
|
"mean_token_accuracy": 0.18762540370225905,
|
||
|
|
"num_tokens": 4584263.0,
|
||
|
|
"step": 2480
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.3507678508758545,
|
||
|
|
"epoch": 2.079497907949791,
|
||
|
|
"grad_norm": 1.2265625,
|
||
|
|
"learning_rate": 0.00047991271182546476,
|
||
|
|
"loss": 5.0984,
|
||
|
|
"mean_token_accuracy": 0.1907823845744133,
|
||
|
|
"num_tokens": 4592979.0,
|
||
|
|
"step": 2485
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.3727912425994875,
|
||
|
|
"epoch": 2.083682008368201,
|
||
|
|
"grad_norm": 1.109375,
|
||
|
|
"learning_rate": 0.00047977919292706696,
|
||
|
|
"loss": 5.1208,
|
||
|
|
"mean_token_accuracy": 0.1879875510931015,
|
||
|
|
"num_tokens": 4602042.0,
|
||
|
|
"step": 2490
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.352688646316528,
|
||
|
|
"epoch": 2.087866108786611,
|
||
|
|
"grad_norm": 1.171875,
|
||
|
|
"learning_rate": 0.0004796452526260134,
|
||
|
|
"loss": 5.1756,
|
||
|
|
"mean_token_accuracy": 0.18628377914428712,
|
||
|
|
"num_tokens": 4611197.0,
|
||
|
|
"step": 2495
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 5.2905971050262455,
|
||
|
|
"epoch": 2.092050209205021,
|
||
|
|
"grad_norm": 1.03125,
|
||
|
|
"learning_rate": 0.00047951089119793164,
|
||
|
|
"loss": 5.1278,
|
||
|
|
"mean_token_accuracy": 0.1851946383714676,
|
||
|
|
"num_tokens": 4621612.0,
|
||
|
|
"step": 2500
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.092050209205021,
|
||
|
|
"eval_entropy": 5.239512876498918,
|
||
|
|
"eval_loss": 5.599039077758789,
|
||
|
|
"eval_mean_token_accuracy": 0.17449360253986407,
|
||
|
|
"eval_num_tokens": 4621612.0,
|
||
|
|
"eval_runtime": 2.7292,
|
||
|
|
"eval_samples_per_second": 1431.545,
|
||
|
|
"eval_steps_per_second": 179.172,
|
||
|
|
"step": 2500
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 11950,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 10,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": false
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 6730711271424000.0,
|
||
|
|
"train_batch_size": 16,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|