| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.175, | |
| "eval_steps": 500, | |
| "global_step": 87000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 2.8962271213531494, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.1292, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 6.777284145355225, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.1979, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.0732028484344482, | |
| "learning_rate": 6e-06, | |
| "loss": 1.1233, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 2.748718023300171, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.1694, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.2017223834991455, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1499, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": 1.1749963760375977, | |
| "eval_runtime": 106.2784, | |
| "eval_samples_per_second": 9.409, | |
| "eval_steps_per_second": 2.352, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 3.5688204765319824, | |
| "learning_rate": 9.98994974874372e-06, | |
| "loss": 1.1033, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 2.247222900390625, | |
| "learning_rate": 9.979899497487437e-06, | |
| "loss": 1.1353, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 5.563870906829834, | |
| "learning_rate": 9.969849246231156e-06, | |
| "loss": 1.1575, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 3.093879461288452, | |
| "learning_rate": 9.959798994974875e-06, | |
| "loss": 1.186, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 3.5246388912200928, | |
| "learning_rate": 9.949748743718594e-06, | |
| "loss": 1.123, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 1.2011113166809082, | |
| "eval_runtime": 106.2391, | |
| "eval_samples_per_second": 9.413, | |
| "eval_steps_per_second": 2.353, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 8.584878921508789, | |
| "learning_rate": 9.939698492462311e-06, | |
| "loss": 1.1876, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 1.8535866737365723, | |
| "learning_rate": 9.929648241206032e-06, | |
| "loss": 1.147, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 4.041557788848877, | |
| "learning_rate": 9.91959798994975e-06, | |
| "loss": 1.1527, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 4.288966655731201, | |
| "learning_rate": 9.909547738693468e-06, | |
| "loss": 1.1, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 3.992133378982544, | |
| "learning_rate": 9.899497487437186e-06, | |
| "loss": 1.1702, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 1.194442629814148, | |
| "eval_runtime": 106.2775, | |
| "eval_samples_per_second": 9.409, | |
| "eval_steps_per_second": 2.352, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 10.900914192199707, | |
| "learning_rate": 9.889447236180906e-06, | |
| "loss": 1.1407, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 2.308995485305786, | |
| "learning_rate": 9.879396984924624e-06, | |
| "loss": 1.1732, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 4.821071147918701, | |
| "learning_rate": 9.869346733668343e-06, | |
| "loss": 1.178, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 2.4869799613952637, | |
| "learning_rate": 9.859296482412062e-06, | |
| "loss": 1.1236, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 3.6243529319763184, | |
| "learning_rate": 9.84924623115578e-06, | |
| "loss": 1.1383, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.197302222251892, | |
| "eval_runtime": 106.476, | |
| "eval_samples_per_second": 9.392, | |
| "eval_steps_per_second": 2.348, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 4.772403717041016, | |
| "learning_rate": 9.839195979899498e-06, | |
| "loss": 1.1792, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 5.6403985023498535, | |
| "learning_rate": 9.829145728643217e-06, | |
| "loss": 1.2086, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 6.52122163772583, | |
| "learning_rate": 9.819095477386936e-06, | |
| "loss": 1.1417, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 5.543770790100098, | |
| "learning_rate": 9.809045226130655e-06, | |
| "loss": 1.18, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 7.871328353881836, | |
| "learning_rate": 9.798994974874372e-06, | |
| "loss": 1.1623, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.2371257543563843, | |
| "eval_runtime": 106.486, | |
| "eval_samples_per_second": 9.391, | |
| "eval_steps_per_second": 2.348, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 9.064556121826172, | |
| "learning_rate": 9.788944723618091e-06, | |
| "loss": 1.2078, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 6.955998420715332, | |
| "learning_rate": 9.77889447236181e-06, | |
| "loss": 1.105, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 2.0823745727539062, | |
| "learning_rate": 9.768844221105529e-06, | |
| "loss": 1.093, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 3.0110859870910645, | |
| "learning_rate": 9.758793969849248e-06, | |
| "loss": 1.1217, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 6.344435691833496, | |
| "learning_rate": 9.748743718592965e-06, | |
| "loss": 1.0912, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 1.1914273500442505, | |
| "eval_runtime": 106.2585, | |
| "eval_samples_per_second": 9.411, | |
| "eval_steps_per_second": 2.353, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 1.916799783706665, | |
| "learning_rate": 9.738693467336684e-06, | |
| "loss": 1.1098, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 6.60597038269043, | |
| "learning_rate": 9.728643216080402e-06, | |
| "loss": 1.1522, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 6.223481178283691, | |
| "learning_rate": 9.718592964824122e-06, | |
| "loss": 1.1633, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 3.995976686477661, | |
| "learning_rate": 9.70854271356784e-06, | |
| "loss": 1.168, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 4.338571071624756, | |
| "learning_rate": 9.698492462311559e-06, | |
| "loss": 1.1514, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": 1.2231833934783936, | |
| "eval_runtime": 106.0603, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 1.8867563009262085, | |
| "learning_rate": 9.688442211055276e-06, | |
| "loss": 1.1255, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 4.41115140914917, | |
| "learning_rate": 9.678391959798997e-06, | |
| "loss": 1.1184, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 4.065484046936035, | |
| "learning_rate": 9.668341708542714e-06, | |
| "loss": 1.1587, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 4.625395774841309, | |
| "learning_rate": 9.658291457286433e-06, | |
| "loss": 1.1494, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 3.19793963432312, | |
| "learning_rate": 9.648241206030152e-06, | |
| "loss": 1.1196, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 1.1993799209594727, | |
| "eval_runtime": 106.0818, | |
| "eval_samples_per_second": 9.427, | |
| "eval_steps_per_second": 2.357, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 8.89126205444336, | |
| "learning_rate": 9.63819095477387e-06, | |
| "loss": 1.1485, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 2.234679698944092, | |
| "learning_rate": 9.628140703517588e-06, | |
| "loss": 1.1758, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 8.758123397827148, | |
| "learning_rate": 9.618090452261307e-06, | |
| "loss": 1.177, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 3.4299983978271484, | |
| "learning_rate": 9.608040201005026e-06, | |
| "loss": 1.1694, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 11.623360633850098, | |
| "learning_rate": 9.597989949748745e-06, | |
| "loss": 1.1724, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.22361421585083, | |
| "eval_runtime": 106.1398, | |
| "eval_samples_per_second": 9.422, | |
| "eval_steps_per_second": 2.355, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 3.621526002883911, | |
| "learning_rate": 9.587939698492464e-06, | |
| "loss": 1.176, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 6.011305809020996, | |
| "learning_rate": 9.577889447236181e-06, | |
| "loss": 1.132, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 4.702287673950195, | |
| "learning_rate": 9.5678391959799e-06, | |
| "loss": 1.2036, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 7.796123027801514, | |
| "learning_rate": 9.55778894472362e-06, | |
| "loss": 1.1573, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 4.329326152801514, | |
| "learning_rate": 9.547738693467338e-06, | |
| "loss": 1.1477, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.1805349588394165, | |
| "eval_runtime": 106.2287, | |
| "eval_samples_per_second": 9.414, | |
| "eval_steps_per_second": 2.353, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 3.5872912406921387, | |
| "learning_rate": 9.537688442211056e-06, | |
| "loss": 1.1774, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 7.94892692565918, | |
| "learning_rate": 9.527638190954775e-06, | |
| "loss": 1.1639, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 2.417180061340332, | |
| "learning_rate": 9.517587939698492e-06, | |
| "loss": 1.1626, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 4.434834003448486, | |
| "learning_rate": 9.507537688442213e-06, | |
| "loss": 1.1846, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 6.536422252655029, | |
| "learning_rate": 9.49748743718593e-06, | |
| "loss": 1.1359, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 1.220381498336792, | |
| "eval_runtime": 106.2553, | |
| "eval_samples_per_second": 9.411, | |
| "eval_steps_per_second": 2.353, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 7.294464111328125, | |
| "learning_rate": 9.487437185929649e-06, | |
| "loss": 1.1081, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 5.32218074798584, | |
| "learning_rate": 9.477386934673368e-06, | |
| "loss": 1.1621, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 3.692546844482422, | |
| "learning_rate": 9.467336683417087e-06, | |
| "loss": 1.1703, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 6.460719585418701, | |
| "learning_rate": 9.457286432160804e-06, | |
| "loss": 1.2071, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 5.178548336029053, | |
| "learning_rate": 9.447236180904523e-06, | |
| "loss": 1.1124, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": 1.1760114431381226, | |
| "eval_runtime": 106.2308, | |
| "eval_samples_per_second": 9.413, | |
| "eval_steps_per_second": 2.353, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 7.670156478881836, | |
| "learning_rate": 9.437185929648242e-06, | |
| "loss": 1.1385, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 4.211444854736328, | |
| "learning_rate": 9.427135678391961e-06, | |
| "loss": 1.1298, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 3.375978469848633, | |
| "learning_rate": 9.41708542713568e-06, | |
| "loss": 1.1745, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 7.415770053863525, | |
| "learning_rate": 9.407035175879397e-06, | |
| "loss": 1.1609, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 5.558354377746582, | |
| "learning_rate": 9.396984924623116e-06, | |
| "loss": 1.1433, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.1909652948379517, | |
| "eval_runtime": 106.1934, | |
| "eval_samples_per_second": 9.417, | |
| "eval_steps_per_second": 2.354, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 4.368566989898682, | |
| "learning_rate": 9.386934673366835e-06, | |
| "loss": 1.2008, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 4.2384209632873535, | |
| "learning_rate": 9.376884422110554e-06, | |
| "loss": 1.2142, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 4.848013877868652, | |
| "learning_rate": 9.366834170854272e-06, | |
| "loss": 1.1843, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 6.339895725250244, | |
| "learning_rate": 9.35678391959799e-06, | |
| "loss": 1.1703, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 7.7875518798828125, | |
| "learning_rate": 9.34673366834171e-06, | |
| "loss": 1.1185, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 1.2201147079467773, | |
| "eval_runtime": 106.1893, | |
| "eval_samples_per_second": 9.417, | |
| "eval_steps_per_second": 2.354, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 4.590594291687012, | |
| "learning_rate": 9.336683417085429e-06, | |
| "loss": 1.1346, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 5.217388153076172, | |
| "learning_rate": 9.326633165829146e-06, | |
| "loss": 1.118, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 2.3999927043914795, | |
| "learning_rate": 9.316582914572865e-06, | |
| "loss": 1.1394, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 2.4164233207702637, | |
| "learning_rate": 9.306532663316584e-06, | |
| "loss": 1.1311, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 1.3500103950500488, | |
| "learning_rate": 9.296482412060303e-06, | |
| "loss": 1.1907, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": 1.2538405656814575, | |
| "eval_runtime": 106.2387, | |
| "eval_samples_per_second": 9.413, | |
| "eval_steps_per_second": 2.353, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 4.407262325286865, | |
| "learning_rate": 9.28643216080402e-06, | |
| "loss": 1.1847, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 2.9364423751831055, | |
| "learning_rate": 9.276381909547739e-06, | |
| "loss": 1.1634, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 4.788465976715088, | |
| "learning_rate": 9.266331658291458e-06, | |
| "loss": 1.1667, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 1.906449317932129, | |
| "learning_rate": 9.256281407035177e-06, | |
| "loss": 1.1199, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 4.966096878051758, | |
| "learning_rate": 9.246231155778896e-06, | |
| "loss": 1.1859, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": 1.1558078527450562, | |
| "eval_runtime": 106.2052, | |
| "eval_samples_per_second": 9.416, | |
| "eval_steps_per_second": 2.354, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 7.45963191986084, | |
| "learning_rate": 9.236180904522613e-06, | |
| "loss": 1.1246, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 7.322927951812744, | |
| "learning_rate": 9.226130653266332e-06, | |
| "loss": 1.1553, | |
| "step": 8200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 5.216075420379639, | |
| "learning_rate": 9.216080402010051e-06, | |
| "loss": 1.1181, | |
| "step": 8300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 4.784651279449463, | |
| "learning_rate": 9.20603015075377e-06, | |
| "loss": 1.0775, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 6.537864685058594, | |
| "learning_rate": 9.195979899497488e-06, | |
| "loss": 1.1112, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 1.1949126720428467, | |
| "eval_runtime": 106.2149, | |
| "eval_samples_per_second": 9.415, | |
| "eval_steps_per_second": 2.354, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 1.4382109642028809, | |
| "learning_rate": 9.185929648241207e-06, | |
| "loss": 1.1235, | |
| "step": 8600 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 7.871183395385742, | |
| "learning_rate": 9.175879396984926e-06, | |
| "loss": 1.2089, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 3.897693395614624, | |
| "learning_rate": 9.165829145728645e-06, | |
| "loss": 1.1792, | |
| "step": 8800 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 3.8129703998565674, | |
| "learning_rate": 9.155778894472362e-06, | |
| "loss": 1.1458, | |
| "step": 8900 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 2.998715877532959, | |
| "learning_rate": 9.14572864321608e-06, | |
| "loss": 1.1321, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 1.165256381034851, | |
| "eval_runtime": 106.0709, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 6.936214923858643, | |
| "learning_rate": 9.1356783919598e-06, | |
| "loss": 1.1338, | |
| "step": 9100 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 6.714348793029785, | |
| "learning_rate": 9.125628140703519e-06, | |
| "loss": 1.1526, | |
| "step": 9200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 6.532776832580566, | |
| "learning_rate": 9.115577889447236e-06, | |
| "loss": 1.1279, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 4.0869245529174805, | |
| "learning_rate": 9.105527638190955e-06, | |
| "loss": 1.152, | |
| "step": 9400 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 5.13925313949585, | |
| "learning_rate": 9.095477386934674e-06, | |
| "loss": 1.1462, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.2190707921981812, | |
| "eval_runtime": 106.0445, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 2.3696067333221436, | |
| "learning_rate": 9.085427135678393e-06, | |
| "loss": 1.1338, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 4.178169250488281, | |
| "learning_rate": 9.075376884422112e-06, | |
| "loss": 1.1047, | |
| "step": 9700 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 8.618546485900879, | |
| "learning_rate": 9.06532663316583e-06, | |
| "loss": 1.2217, | |
| "step": 9800 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 7.047238349914551, | |
| "learning_rate": 9.055276381909548e-06, | |
| "loss": 1.1277, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 3.2608633041381836, | |
| "learning_rate": 9.045226130653267e-06, | |
| "loss": 1.0982, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.2301849126815796, | |
| "eval_runtime": 106.0445, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 7.365833759307861, | |
| "learning_rate": 9.035175879396986e-06, | |
| "loss": 1.1367, | |
| "step": 10100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 5.321079254150391, | |
| "learning_rate": 9.025125628140704e-06, | |
| "loss": 1.1288, | |
| "step": 10200 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 6.2387518882751465, | |
| "learning_rate": 9.015075376884423e-06, | |
| "loss": 1.1415, | |
| "step": 10300 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 4.032764911651611, | |
| "learning_rate": 9.005025125628142e-06, | |
| "loss": 1.1471, | |
| "step": 10400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 7.161890506744385, | |
| "learning_rate": 8.99497487437186e-06, | |
| "loss": 1.1121, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.1580675840377808, | |
| "eval_runtime": 106.0405, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 8.492444038391113, | |
| "learning_rate": 8.984924623115578e-06, | |
| "loss": 1.2182, | |
| "step": 10600 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 3.7185165882110596, | |
| "learning_rate": 8.974874371859297e-06, | |
| "loss": 1.1466, | |
| "step": 10700 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 5.3694963455200195, | |
| "learning_rate": 8.964824120603016e-06, | |
| "loss": 1.1329, | |
| "step": 10800 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 2.5741922855377197, | |
| "learning_rate": 8.954773869346735e-06, | |
| "loss": 1.1466, | |
| "step": 10900 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 4.072163105010986, | |
| "learning_rate": 8.944723618090452e-06, | |
| "loss": 1.127, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": 1.2112760543823242, | |
| "eval_runtime": 106.0385, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 6.539740085601807, | |
| "learning_rate": 8.934673366834171e-06, | |
| "loss": 1.2167, | |
| "step": 11100 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 3.4889700412750244, | |
| "learning_rate": 8.92462311557789e-06, | |
| "loss": 1.1264, | |
| "step": 11200 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 5.519000053405762, | |
| "learning_rate": 8.914572864321609e-06, | |
| "loss": 1.1552, | |
| "step": 11300 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 4.674288272857666, | |
| "learning_rate": 8.904522613065328e-06, | |
| "loss": 1.1393, | |
| "step": 11400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 7.456840991973877, | |
| "learning_rate": 8.894472361809045e-06, | |
| "loss": 1.1376, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 1.2394318580627441, | |
| "eval_runtime": 106.0218, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 4.70370626449585, | |
| "learning_rate": 8.884422110552764e-06, | |
| "loss": 1.139, | |
| "step": 11600 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 7.3822922706604, | |
| "learning_rate": 8.874371859296483e-06, | |
| "loss": 1.1231, | |
| "step": 11700 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 8.374277114868164, | |
| "learning_rate": 8.864321608040202e-06, | |
| "loss": 1.1627, | |
| "step": 11800 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 5.440807342529297, | |
| "learning_rate": 8.85427135678392e-06, | |
| "loss": 1.1215, | |
| "step": 11900 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 8.692358016967773, | |
| "learning_rate": 8.84422110552764e-06, | |
| "loss": 1.163, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.1826081275939941, | |
| "eval_runtime": 106.0303, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 2.820358991622925, | |
| "learning_rate": 8.834170854271358e-06, | |
| "loss": 1.103, | |
| "step": 12100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 7.24362850189209, | |
| "learning_rate": 8.824120603015077e-06, | |
| "loss": 1.0791, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 3.441662311553955, | |
| "learning_rate": 8.814070351758794e-06, | |
| "loss": 1.1786, | |
| "step": 12300 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 2.2167410850524902, | |
| "learning_rate": 8.804020100502513e-06, | |
| "loss": 1.1805, | |
| "step": 12400 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 5.339104652404785, | |
| "learning_rate": 8.793969849246232e-06, | |
| "loss": 1.0919, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 1.1974951028823853, | |
| "eval_runtime": 106.035, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 5.801215171813965, | |
| "learning_rate": 8.78391959798995e-06, | |
| "loss": 1.0955, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 10.506399154663086, | |
| "learning_rate": 8.773869346733668e-06, | |
| "loss": 1.2134, | |
| "step": 12700 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 4.50074577331543, | |
| "learning_rate": 8.763819095477387e-06, | |
| "loss": 1.1828, | |
| "step": 12800 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 2.6549763679504395, | |
| "learning_rate": 8.753768844221106e-06, | |
| "loss": 1.1031, | |
| "step": 12900 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 5.622566223144531, | |
| "learning_rate": 8.743718592964825e-06, | |
| "loss": 1.108, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.206725835800171, | |
| "eval_runtime": 106.0479, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 5.7196221351623535, | |
| "learning_rate": 8.733668341708544e-06, | |
| "loss": 1.1414, | |
| "step": 13100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 3.0874502658843994, | |
| "learning_rate": 8.723618090452261e-06, | |
| "loss": 1.1779, | |
| "step": 13200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 3.2144765853881836, | |
| "learning_rate": 8.71356783919598e-06, | |
| "loss": 1.1189, | |
| "step": 13300 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 3.149327039718628, | |
| "learning_rate": 8.7035175879397e-06, | |
| "loss": 1.2085, | |
| "step": 13400 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 2.726438522338867, | |
| "learning_rate": 8.693467336683418e-06, | |
| "loss": 1.0836, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 1.1935946941375732, | |
| "eval_runtime": 106.028, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 4.5727105140686035, | |
| "learning_rate": 8.683417085427136e-06, | |
| "loss": 1.0865, | |
| "step": 13600 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 6.883179187774658, | |
| "learning_rate": 8.673366834170856e-06, | |
| "loss": 1.1212, | |
| "step": 13700 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 4.398787498474121, | |
| "learning_rate": 8.663316582914574e-06, | |
| "loss": 1.1267, | |
| "step": 13800 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 3.785742998123169, | |
| "learning_rate": 8.653266331658293e-06, | |
| "loss": 1.135, | |
| "step": 13900 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 4.241240978240967, | |
| "learning_rate": 8.64321608040201e-06, | |
| "loss": 1.1242, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 1.1758685111999512, | |
| "eval_runtime": 106.0542, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 4.4116621017456055, | |
| "learning_rate": 8.63316582914573e-06, | |
| "loss": 1.0878, | |
| "step": 14100 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 6.320282459259033, | |
| "learning_rate": 8.623115577889448e-06, | |
| "loss": 1.1523, | |
| "step": 14200 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 8.830348014831543, | |
| "learning_rate": 8.613065326633167e-06, | |
| "loss": 1.0909, | |
| "step": 14300 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 3.5644683837890625, | |
| "learning_rate": 8.603015075376884e-06, | |
| "loss": 1.196, | |
| "step": 14400 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 6.190166473388672, | |
| "learning_rate": 8.592964824120603e-06, | |
| "loss": 1.1618, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": 1.1882929801940918, | |
| "eval_runtime": 106.0551, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 17.052867889404297, | |
| "learning_rate": 8.582914572864322e-06, | |
| "loss": 1.1788, | |
| "step": 14600 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 7.739620685577393, | |
| "learning_rate": 8.572864321608041e-06, | |
| "loss": 1.1384, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 9.18273639678955, | |
| "learning_rate": 8.56281407035176e-06, | |
| "loss": 1.1222, | |
| "step": 14800 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 3.9803543090820312, | |
| "learning_rate": 8.552763819095477e-06, | |
| "loss": 1.1078, | |
| "step": 14900 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 3.8314757347106934, | |
| "learning_rate": 8.542713567839196e-06, | |
| "loss": 1.1153, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.1791757345199585, | |
| "eval_runtime": 106.2981, | |
| "eval_samples_per_second": 9.408, | |
| "eval_steps_per_second": 2.352, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 7.389952659606934, | |
| "learning_rate": 8.532663316582915e-06, | |
| "loss": 1.0997, | |
| "step": 15100 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 4.7773051261901855, | |
| "learning_rate": 8.522613065326634e-06, | |
| "loss": 1.1291, | |
| "step": 15200 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 5.93678092956543, | |
| "learning_rate": 8.512562814070352e-06, | |
| "loss": 1.1771, | |
| "step": 15300 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 5.244768142700195, | |
| "learning_rate": 8.50251256281407e-06, | |
| "loss": 1.1455, | |
| "step": 15400 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 3.881159543991089, | |
| "learning_rate": 8.49246231155779e-06, | |
| "loss": 1.1593, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.174180030822754, | |
| "eval_runtime": 106.0212, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 1.6950880289077759, | |
| "learning_rate": 8.482412060301509e-06, | |
| "loss": 1.1111, | |
| "step": 15600 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 4.720574855804443, | |
| "learning_rate": 8.472361809045226e-06, | |
| "loss": 1.1277, | |
| "step": 15700 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 1.957318902015686, | |
| "learning_rate": 8.462311557788947e-06, | |
| "loss": 1.1213, | |
| "step": 15800 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 3.463331937789917, | |
| "learning_rate": 8.452261306532664e-06, | |
| "loss": 1.1348, | |
| "step": 15900 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 4.911657810211182, | |
| "learning_rate": 8.442211055276383e-06, | |
| "loss": 1.183, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.1880648136138916, | |
| "eval_runtime": 106.0399, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 3.685622215270996, | |
| "learning_rate": 8.4321608040201e-06, | |
| "loss": 1.0885, | |
| "step": 16100 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 6.106893539428711, | |
| "learning_rate": 8.42211055276382e-06, | |
| "loss": 1.1155, | |
| "step": 16200 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 3.5625643730163574, | |
| "learning_rate": 8.412060301507538e-06, | |
| "loss": 1.1509, | |
| "step": 16300 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 2.4601857662200928, | |
| "learning_rate": 8.402010050251257e-06, | |
| "loss": 1.1641, | |
| "step": 16400 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 3.221052408218384, | |
| "learning_rate": 8.391959798994976e-06, | |
| "loss": 1.1614, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 1.2177305221557617, | |
| "eval_runtime": 106.0442, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 7.0826416015625, | |
| "learning_rate": 8.381909547738695e-06, | |
| "loss": 1.2206, | |
| "step": 16600 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 8.027673721313477, | |
| "learning_rate": 8.371859296482412e-06, | |
| "loss": 1.1221, | |
| "step": 16700 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 3.402815103530884, | |
| "learning_rate": 8.361809045226131e-06, | |
| "loss": 1.1168, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 3.39699125289917, | |
| "learning_rate": 8.35175879396985e-06, | |
| "loss": 1.2223, | |
| "step": 16900 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 7.322509288787842, | |
| "learning_rate": 8.341708542713568e-06, | |
| "loss": 1.13, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": 1.20486319065094, | |
| "eval_runtime": 106.0286, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 8.754172325134277, | |
| "learning_rate": 8.331658291457287e-06, | |
| "loss": 1.0929, | |
| "step": 17100 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 5.245049476623535, | |
| "learning_rate": 8.321608040201006e-06, | |
| "loss": 1.0899, | |
| "step": 17200 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 3.368318557739258, | |
| "learning_rate": 8.311557788944725e-06, | |
| "loss": 1.1458, | |
| "step": 17300 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 3.112353563308716, | |
| "learning_rate": 8.301507537688442e-06, | |
| "loss": 1.1361, | |
| "step": 17400 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 5.4094953536987305, | |
| "learning_rate": 8.291457286432163e-06, | |
| "loss": 1.1214, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.249082088470459, | |
| "eval_runtime": 106.0393, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 6.122429370880127, | |
| "learning_rate": 8.28140703517588e-06, | |
| "loss": 1.1201, | |
| "step": 17600 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 8.071257591247559, | |
| "learning_rate": 8.271356783919599e-06, | |
| "loss": 1.0958, | |
| "step": 17700 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 4.817784309387207, | |
| "learning_rate": 8.261306532663316e-06, | |
| "loss": 1.1187, | |
| "step": 17800 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 1.626766324043274, | |
| "learning_rate": 8.251256281407037e-06, | |
| "loss": 1.1443, | |
| "step": 17900 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 3.9109134674072266, | |
| "learning_rate": 8.241206030150754e-06, | |
| "loss": 1.1612, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 1.168979287147522, | |
| "eval_runtime": 106.0316, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 5.2552337646484375, | |
| "learning_rate": 8.231155778894473e-06, | |
| "loss": 1.1636, | |
| "step": 18100 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 4.994833946228027, | |
| "learning_rate": 8.221105527638192e-06, | |
| "loss": 1.1199, | |
| "step": 18200 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 6.6655449867248535, | |
| "learning_rate": 8.211055276381911e-06, | |
| "loss": 1.1118, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 7.384323596954346, | |
| "learning_rate": 8.201005025125628e-06, | |
| "loss": 1.1713, | |
| "step": 18400 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 4.516322612762451, | |
| "learning_rate": 8.190954773869347e-06, | |
| "loss": 1.2118, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": 1.1855034828186035, | |
| "eval_runtime": 106.0276, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 2.098135471343994, | |
| "learning_rate": 8.180904522613066e-06, | |
| "loss": 1.1457, | |
| "step": 18600 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 6.398161888122559, | |
| "learning_rate": 8.170854271356785e-06, | |
| "loss": 1.1211, | |
| "step": 18700 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 10.372193336486816, | |
| "learning_rate": 8.160804020100503e-06, | |
| "loss": 1.1691, | |
| "step": 18800 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 8.23112678527832, | |
| "learning_rate": 8.150753768844222e-06, | |
| "loss": 1.1251, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 4.921475887298584, | |
| "learning_rate": 8.14070351758794e-06, | |
| "loss": 1.092, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 1.20026433467865, | |
| "eval_runtime": 106.017, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 5.03338623046875, | |
| "learning_rate": 8.130653266331658e-06, | |
| "loss": 1.1199, | |
| "step": 19100 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 10.756241798400879, | |
| "learning_rate": 8.120603015075379e-06, | |
| "loss": 1.121, | |
| "step": 19200 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 5.687259674072266, | |
| "learning_rate": 8.110552763819096e-06, | |
| "loss": 1.1623, | |
| "step": 19300 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 2.741285562515259, | |
| "learning_rate": 8.100502512562815e-06, | |
| "loss": 1.089, | |
| "step": 19400 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 2.4017832279205322, | |
| "learning_rate": 8.090452261306532e-06, | |
| "loss": 1.1537, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.210019588470459, | |
| "eval_runtime": 106.0274, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 27.84754753112793, | |
| "learning_rate": 8.080402010050253e-06, | |
| "loss": 1.1101, | |
| "step": 19600 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 15.681364059448242, | |
| "learning_rate": 8.07035175879397e-06, | |
| "loss": 1.1033, | |
| "step": 19700 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 4.995880603790283, | |
| "learning_rate": 8.060301507537689e-06, | |
| "loss": 1.1781, | |
| "step": 19800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 11.795672416687012, | |
| "learning_rate": 8.050251256281408e-06, | |
| "loss": 1.0692, | |
| "step": 19900 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 7.25331449508667, | |
| "learning_rate": 8.040201005025127e-06, | |
| "loss": 1.1582, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.1762893199920654, | |
| "eval_runtime": 106.0116, | |
| "eval_samples_per_second": 9.433, | |
| "eval_steps_per_second": 2.358, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 6.3939690589904785, | |
| "learning_rate": 8.030150753768844e-06, | |
| "loss": 1.1748, | |
| "step": 20100 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 4.918806552886963, | |
| "learning_rate": 8.020100502512563e-06, | |
| "loss": 1.1929, | |
| "step": 20200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 9.905332565307617, | |
| "learning_rate": 8.010050251256282e-06, | |
| "loss": 1.1741, | |
| "step": 20300 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 2.9581973552703857, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.1134, | |
| "step": 20400 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 3.484316349029541, | |
| "learning_rate": 7.989949748743719e-06, | |
| "loss": 1.1542, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.2277439832687378, | |
| "eval_runtime": 106.0241, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 4.826357841491699, | |
| "learning_rate": 7.979899497487438e-06, | |
| "loss": 1.1211, | |
| "step": 20600 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 4.551624774932861, | |
| "learning_rate": 7.969849246231157e-06, | |
| "loss": 1.1811, | |
| "step": 20700 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 2.7033650875091553, | |
| "learning_rate": 7.959798994974876e-06, | |
| "loss": 1.1529, | |
| "step": 20800 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 3.31227445602417, | |
| "learning_rate": 7.949748743718595e-06, | |
| "loss": 1.1559, | |
| "step": 20900 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 8.757655143737793, | |
| "learning_rate": 7.939698492462312e-06, | |
| "loss": 1.166, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.2115482091903687, | |
| "eval_runtime": 106.0189, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 4.111684322357178, | |
| "learning_rate": 7.929648241206031e-06, | |
| "loss": 1.1683, | |
| "step": 21100 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 3.45263409614563, | |
| "learning_rate": 7.91959798994975e-06, | |
| "loss": 1.1146, | |
| "step": 21200 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 3.8724279403686523, | |
| "learning_rate": 7.909547738693469e-06, | |
| "loss": 1.1648, | |
| "step": 21300 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 4.8003387451171875, | |
| "learning_rate": 7.899497487437186e-06, | |
| "loss": 1.1802, | |
| "step": 21400 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 8.398045539855957, | |
| "learning_rate": 7.889447236180905e-06, | |
| "loss": 1.1438, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": 1.1905258893966675, | |
| "eval_runtime": 106.016, | |
| "eval_samples_per_second": 9.433, | |
| "eval_steps_per_second": 2.358, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 5.731268882751465, | |
| "learning_rate": 7.879396984924622e-06, | |
| "loss": 1.0726, | |
| "step": 21600 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 9.864482879638672, | |
| "learning_rate": 7.869346733668343e-06, | |
| "loss": 1.1604, | |
| "step": 21700 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 3.624190092086792, | |
| "learning_rate": 7.85929648241206e-06, | |
| "loss": 1.1831, | |
| "step": 21800 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 6.659609317779541, | |
| "learning_rate": 7.84924623115578e-06, | |
| "loss": 1.0539, | |
| "step": 21900 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 6.585338592529297, | |
| "learning_rate": 7.839195979899498e-06, | |
| "loss": 1.2157, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.199148178100586, | |
| "eval_runtime": 106.0429, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 4.8435893058776855, | |
| "learning_rate": 7.829145728643217e-06, | |
| "loss": 1.07, | |
| "step": 22100 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 5.895426273345947, | |
| "learning_rate": 7.819095477386935e-06, | |
| "loss": 1.115, | |
| "step": 22200 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 7.716872692108154, | |
| "learning_rate": 7.809045226130654e-06, | |
| "loss": 1.1016, | |
| "step": 22300 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 2.7104599475860596, | |
| "learning_rate": 7.798994974874373e-06, | |
| "loss": 1.0983, | |
| "step": 22400 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 4.22263240814209, | |
| "learning_rate": 7.788944723618092e-06, | |
| "loss": 1.0981, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": 1.2477768659591675, | |
| "eval_runtime": 106.0531, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 12.602644920349121, | |
| "learning_rate": 7.77889447236181e-06, | |
| "loss": 1.1739, | |
| "step": 22600 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 6.040693283081055, | |
| "learning_rate": 7.768844221105528e-06, | |
| "loss": 1.1364, | |
| "step": 22700 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 4.136214733123779, | |
| "learning_rate": 7.758793969849247e-06, | |
| "loss": 1.1374, | |
| "step": 22800 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 6.945772647857666, | |
| "learning_rate": 7.748743718592966e-06, | |
| "loss": 1.1533, | |
| "step": 22900 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 3.4912397861480713, | |
| "learning_rate": 7.738693467336685e-06, | |
| "loss": 1.0981, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": 1.2318669557571411, | |
| "eval_runtime": 106.0223, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 4.470850944519043, | |
| "learning_rate": 7.728643216080402e-06, | |
| "loss": 1.1453, | |
| "step": 23100 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 2.3996975421905518, | |
| "learning_rate": 7.718592964824121e-06, | |
| "loss": 1.1357, | |
| "step": 23200 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 4.165435314178467, | |
| "learning_rate": 7.70854271356784e-06, | |
| "loss": 1.0431, | |
| "step": 23300 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 3.5636632442474365, | |
| "learning_rate": 7.698492462311559e-06, | |
| "loss": 1.1245, | |
| "step": 23400 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 5.408770561218262, | |
| "learning_rate": 7.688442211055276e-06, | |
| "loss": 1.131, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 1.1715679168701172, | |
| "eval_runtime": 106.0287, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 8.558609008789062, | |
| "learning_rate": 7.678391959798995e-06, | |
| "loss": 1.0817, | |
| "step": 23600 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 4.554088115692139, | |
| "learning_rate": 7.668341708542714e-06, | |
| "loss": 1.1049, | |
| "step": 23700 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 4.769896507263184, | |
| "learning_rate": 7.658291457286433e-06, | |
| "loss": 1.1414, | |
| "step": 23800 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 6.120572566986084, | |
| "learning_rate": 7.64824120603015e-06, | |
| "loss": 1.1546, | |
| "step": 23900 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 9.137899398803711, | |
| "learning_rate": 7.63819095477387e-06, | |
| "loss": 1.0968, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.1701098680496216, | |
| "eval_runtime": 106.0427, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 5.275972843170166, | |
| "learning_rate": 7.628140703517588e-06, | |
| "loss": 1.0813, | |
| "step": 24100 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 4.437551975250244, | |
| "learning_rate": 7.618090452261308e-06, | |
| "loss": 1.1649, | |
| "step": 24200 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 3.896280527114868, | |
| "learning_rate": 7.608040201005026e-06, | |
| "loss": 1.1536, | |
| "step": 24300 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 6.638348579406738, | |
| "learning_rate": 7.597989949748744e-06, | |
| "loss": 1.1122, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 4.344515800476074, | |
| "learning_rate": 7.587939698492463e-06, | |
| "loss": 1.1265, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.1937814950942993, | |
| "eval_runtime": 106.0359, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 12.144390106201172, | |
| "learning_rate": 7.577889447236182e-06, | |
| "loss": 1.0717, | |
| "step": 24600 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 5.6124162673950195, | |
| "learning_rate": 7.5678391959799e-06, | |
| "loss": 1.1462, | |
| "step": 24700 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 8.556794166564941, | |
| "learning_rate": 7.557788944723619e-06, | |
| "loss": 1.1072, | |
| "step": 24800 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 9.116814613342285, | |
| "learning_rate": 7.547738693467337e-06, | |
| "loss": 1.1318, | |
| "step": 24900 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 9.45323371887207, | |
| "learning_rate": 7.537688442211056e-06, | |
| "loss": 1.1285, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 1.2085939645767212, | |
| "eval_runtime": 106.0572, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 4.843000411987305, | |
| "learning_rate": 7.527638190954774e-06, | |
| "loss": 1.1281, | |
| "step": 25100 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 2.768526792526245, | |
| "learning_rate": 7.517587939698493e-06, | |
| "loss": 1.1034, | |
| "step": 25200 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 3.8277149200439453, | |
| "learning_rate": 7.507537688442211e-06, | |
| "loss": 1.1364, | |
| "step": 25300 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 4.662463665008545, | |
| "learning_rate": 7.49748743718593e-06, | |
| "loss": 1.0998, | |
| "step": 25400 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 4.321447372436523, | |
| "learning_rate": 7.487437185929649e-06, | |
| "loss": 1.0505, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.1745121479034424, | |
| "eval_runtime": 106.0373, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 6.473324775695801, | |
| "learning_rate": 7.4773869346733675e-06, | |
| "loss": 1.1277, | |
| "step": 25600 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 8.012463569641113, | |
| "learning_rate": 7.467336683417086e-06, | |
| "loss": 1.171, | |
| "step": 25700 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 3.7822492122650146, | |
| "learning_rate": 7.4572864321608055e-06, | |
| "loss": 1.1144, | |
| "step": 25800 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 6.848889350891113, | |
| "learning_rate": 7.447236180904524e-06, | |
| "loss": 1.1733, | |
| "step": 25900 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 5.613380432128906, | |
| "learning_rate": 7.437185929648242e-06, | |
| "loss": 1.1166, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 1.1962485313415527, | |
| "eval_runtime": 106.0399, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 9.13502311706543, | |
| "learning_rate": 7.42713567839196e-06, | |
| "loss": 1.1202, | |
| "step": 26100 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 2.9282798767089844, | |
| "learning_rate": 7.417085427135679e-06, | |
| "loss": 1.146, | |
| "step": 26200 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 2.336259365081787, | |
| "learning_rate": 7.407035175879398e-06, | |
| "loss": 1.139, | |
| "step": 26300 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 6.539892673492432, | |
| "learning_rate": 7.396984924623116e-06, | |
| "loss": 1.101, | |
| "step": 26400 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 3.7083210945129395, | |
| "learning_rate": 7.386934673366835e-06, | |
| "loss": 1.2061, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.208566665649414, | |
| "eval_runtime": 105.9891, | |
| "eval_samples_per_second": 9.435, | |
| "eval_steps_per_second": 2.359, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 2.5254299640655518, | |
| "learning_rate": 7.376884422110553e-06, | |
| "loss": 1.1518, | |
| "step": 26600 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 3.481236457824707, | |
| "learning_rate": 7.366834170854272e-06, | |
| "loss": 1.1229, | |
| "step": 26700 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 3.710301399230957, | |
| "learning_rate": 7.35678391959799e-06, | |
| "loss": 1.1179, | |
| "step": 26800 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 5.444150924682617, | |
| "learning_rate": 7.346733668341709e-06, | |
| "loss": 1.1705, | |
| "step": 26900 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 5.206109046936035, | |
| "learning_rate": 7.336683417085427e-06, | |
| "loss": 1.0838, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 1.1918013095855713, | |
| "eval_runtime": 106.0214, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 10.437155723571777, | |
| "learning_rate": 7.326633165829146e-06, | |
| "loss": 1.1246, | |
| "step": 27100 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 2.975705862045288, | |
| "learning_rate": 7.316582914572865e-06, | |
| "loss": 1.1462, | |
| "step": 27200 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 4.456331729888916, | |
| "learning_rate": 7.3065326633165835e-06, | |
| "loss": 1.1436, | |
| "step": 27300 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 3.7051470279693604, | |
| "learning_rate": 7.296482412060302e-06, | |
| "loss": 1.127, | |
| "step": 27400 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 6.190571308135986, | |
| "learning_rate": 7.2864321608040215e-06, | |
| "loss": 1.1008, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 1.1216787099838257, | |
| "eval_runtime": 106.009, | |
| "eval_samples_per_second": 9.433, | |
| "eval_steps_per_second": 2.358, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 3.3411688804626465, | |
| "learning_rate": 7.27638190954774e-06, | |
| "loss": 1.1983, | |
| "step": 27600 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 4.207643032073975, | |
| "learning_rate": 7.266331658291458e-06, | |
| "loss": 1.1391, | |
| "step": 27700 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 12.340192794799805, | |
| "learning_rate": 7.256281407035176e-06, | |
| "loss": 1.1098, | |
| "step": 27800 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 5.5857367515563965, | |
| "learning_rate": 7.246231155778896e-06, | |
| "loss": 1.1246, | |
| "step": 27900 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 3.554783821105957, | |
| "learning_rate": 7.236180904522614e-06, | |
| "loss": 1.0962, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 1.1856356859207153, | |
| "eval_runtime": 106.0327, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 1.0475980043411255, | |
| "learning_rate": 7.226130653266332e-06, | |
| "loss": 1.1436, | |
| "step": 28100 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 15.718121528625488, | |
| "learning_rate": 7.21608040201005e-06, | |
| "loss": 1.141, | |
| "step": 28200 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 2.8623883724212646, | |
| "learning_rate": 7.206030150753769e-06, | |
| "loss": 1.1262, | |
| "step": 28300 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 5.101434230804443, | |
| "learning_rate": 7.195979899497488e-06, | |
| "loss": 1.096, | |
| "step": 28400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 8.572381019592285, | |
| "learning_rate": 7.185929648241206e-06, | |
| "loss": 1.156, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.2090998888015747, | |
| "eval_runtime": 106.033, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 6.753989219665527, | |
| "learning_rate": 7.175879396984925e-06, | |
| "loss": 1.1645, | |
| "step": 28600 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 4.745002269744873, | |
| "learning_rate": 7.165829145728643e-06, | |
| "loss": 1.1904, | |
| "step": 28700 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 4.988409042358398, | |
| "learning_rate": 7.155778894472362e-06, | |
| "loss": 1.14, | |
| "step": 28800 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 12.388657569885254, | |
| "learning_rate": 7.145728643216081e-06, | |
| "loss": 1.1043, | |
| "step": 28900 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 7.307866096496582, | |
| "learning_rate": 7.1356783919597995e-06, | |
| "loss": 1.1395, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 1.1706377267837524, | |
| "eval_runtime": 106.0325, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 3.388065814971924, | |
| "learning_rate": 7.125628140703518e-06, | |
| "loss": 1.1336, | |
| "step": 29100 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 2.8489246368408203, | |
| "learning_rate": 7.1155778894472375e-06, | |
| "loss": 1.098, | |
| "step": 29200 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 9.67976188659668, | |
| "learning_rate": 7.105527638190956e-06, | |
| "loss": 1.0673, | |
| "step": 29300 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 2.9133048057556152, | |
| "learning_rate": 7.095477386934674e-06, | |
| "loss": 1.0832, | |
| "step": 29400 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 5.992185115814209, | |
| "learning_rate": 7.085427135678392e-06, | |
| "loss": 1.1449, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": 1.1525543928146362, | |
| "eval_runtime": 106.0329, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 1.5347836017608643, | |
| "learning_rate": 7.075376884422112e-06, | |
| "loss": 1.1152, | |
| "step": 29600 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 6.405416965484619, | |
| "learning_rate": 7.06532663316583e-06, | |
| "loss": 1.1239, | |
| "step": 29700 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 10.704813957214355, | |
| "learning_rate": 7.055276381909548e-06, | |
| "loss": 1.1007, | |
| "step": 29800 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 6.187832355499268, | |
| "learning_rate": 7.045226130653266e-06, | |
| "loss": 1.1903, | |
| "step": 29900 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 2.4171247482299805, | |
| "learning_rate": 7.035175879396986e-06, | |
| "loss": 1.1101, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.1943550109863281, | |
| "eval_runtime": 106.0234, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 10.25555419921875, | |
| "learning_rate": 7.025125628140704e-06, | |
| "loss": 1.1009, | |
| "step": 30100 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 3.6381895542144775, | |
| "learning_rate": 7.015075376884422e-06, | |
| "loss": 1.1136, | |
| "step": 30200 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 10.197813034057617, | |
| "learning_rate": 7.005025125628141e-06, | |
| "loss": 1.1178, | |
| "step": 30300 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 7.947491645812988, | |
| "learning_rate": 6.99497487437186e-06, | |
| "loss": 1.0774, | |
| "step": 30400 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 5.598392009735107, | |
| "learning_rate": 6.984924623115578e-06, | |
| "loss": 1.155, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": 1.1524125337600708, | |
| "eval_runtime": 106.0253, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 3.098531723022461, | |
| "learning_rate": 6.974874371859297e-06, | |
| "loss": 1.1064, | |
| "step": 30600 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 4.466740131378174, | |
| "learning_rate": 6.9648241206030155e-06, | |
| "loss": 1.1111, | |
| "step": 30700 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 4.58650541305542, | |
| "learning_rate": 6.954773869346734e-06, | |
| "loss": 1.129, | |
| "step": 30800 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 1.4121707677841187, | |
| "learning_rate": 6.9447236180904535e-06, | |
| "loss": 1.138, | |
| "step": 30900 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 3.7431671619415283, | |
| "learning_rate": 6.934673366834172e-06, | |
| "loss": 1.1675, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": 1.1724088191986084, | |
| "eval_runtime": 106.0356, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 4.1336212158203125, | |
| "learning_rate": 6.92462311557789e-06, | |
| "loss": 1.1452, | |
| "step": 31100 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 3.988180637359619, | |
| "learning_rate": 6.914572864321608e-06, | |
| "loss": 1.1288, | |
| "step": 31200 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 4.099323749542236, | |
| "learning_rate": 6.904522613065328e-06, | |
| "loss": 1.1179, | |
| "step": 31300 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 4.779965877532959, | |
| "learning_rate": 6.894472361809046e-06, | |
| "loss": 1.0647, | |
| "step": 31400 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 8.382486343383789, | |
| "learning_rate": 6.884422110552764e-06, | |
| "loss": 1.0933, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.2039211988449097, | |
| "eval_runtime": 106.0501, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 5.752281665802002, | |
| "learning_rate": 6.874371859296482e-06, | |
| "loss": 1.0914, | |
| "step": 31600 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 7.070209980010986, | |
| "learning_rate": 6.864321608040202e-06, | |
| "loss": 1.0789, | |
| "step": 31700 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 10.135692596435547, | |
| "learning_rate": 6.85427135678392e-06, | |
| "loss": 1.1318, | |
| "step": 31800 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 10.787989616394043, | |
| "learning_rate": 6.844221105527638e-06, | |
| "loss": 1.1505, | |
| "step": 31900 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 3.4322993755340576, | |
| "learning_rate": 6.834170854271357e-06, | |
| "loss": 1.1121, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.2028348445892334, | |
| "eval_runtime": 106.0697, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 6.8712568283081055, | |
| "learning_rate": 6.824120603015076e-06, | |
| "loss": 1.0593, | |
| "step": 32100 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 8.722804069519043, | |
| "learning_rate": 6.814070351758794e-06, | |
| "loss": 1.1287, | |
| "step": 32200 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 4.802107334136963, | |
| "learning_rate": 6.804020100502513e-06, | |
| "loss": 1.1291, | |
| "step": 32300 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 14.779809951782227, | |
| "learning_rate": 6.7939698492462315e-06, | |
| "loss": 1.124, | |
| "step": 32400 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 12.029526710510254, | |
| "learning_rate": 6.7839195979899505e-06, | |
| "loss": 1.1146, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": 1.2012832164764404, | |
| "eval_runtime": 106.0411, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 4.80298376083374, | |
| "learning_rate": 6.7738693467336695e-06, | |
| "loss": 1.1362, | |
| "step": 32600 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 2.3808014392852783, | |
| "learning_rate": 6.763819095477388e-06, | |
| "loss": 1.1042, | |
| "step": 32700 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 3.032790184020996, | |
| "learning_rate": 6.753768844221106e-06, | |
| "loss": 1.183, | |
| "step": 32800 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 21.967342376708984, | |
| "learning_rate": 6.743718592964824e-06, | |
| "loss": 1.1154, | |
| "step": 32900 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 3.282263994216919, | |
| "learning_rate": 6.733668341708544e-06, | |
| "loss": 1.0703, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.1923493146896362, | |
| "eval_runtime": 106.0475, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 11.197218894958496, | |
| "learning_rate": 6.723618090452262e-06, | |
| "loss": 1.0949, | |
| "step": 33100 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 4.288850784301758, | |
| "learning_rate": 6.71356783919598e-06, | |
| "loss": 1.1465, | |
| "step": 33200 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 5.537724018096924, | |
| "learning_rate": 6.703517587939698e-06, | |
| "loss": 1.1354, | |
| "step": 33300 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 10.037650108337402, | |
| "learning_rate": 6.693467336683418e-06, | |
| "loss": 1.0584, | |
| "step": 33400 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 8.176264762878418, | |
| "learning_rate": 6.683417085427136e-06, | |
| "loss": 1.1543, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": 1.1587566137313843, | |
| "eval_runtime": 106.0403, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 5.638991832733154, | |
| "learning_rate": 6.673366834170854e-06, | |
| "loss": 1.1664, | |
| "step": 33600 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 6.490970134735107, | |
| "learning_rate": 6.663316582914573e-06, | |
| "loss": 1.1154, | |
| "step": 33700 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 5.5730061531066895, | |
| "learning_rate": 6.653266331658292e-06, | |
| "loss": 1.1113, | |
| "step": 33800 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 4.730175495147705, | |
| "learning_rate": 6.64321608040201e-06, | |
| "loss": 1.1427, | |
| "step": 33900 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 3.3499104976654053, | |
| "learning_rate": 6.633165829145729e-06, | |
| "loss": 1.1063, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.193935751914978, | |
| "eval_runtime": 106.0279, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 10.057549476623535, | |
| "learning_rate": 6.6231155778894475e-06, | |
| "loss": 1.1197, | |
| "step": 34100 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 15.203615188598633, | |
| "learning_rate": 6.6130653266331665e-06, | |
| "loss": 1.1391, | |
| "step": 34200 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 7.671562671661377, | |
| "learning_rate": 6.6030150753768855e-06, | |
| "loss": 1.0629, | |
| "step": 34300 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 3.142216205596924, | |
| "learning_rate": 6.592964824120604e-06, | |
| "loss": 1.1066, | |
| "step": 34400 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 7.480587005615234, | |
| "learning_rate": 6.582914572864322e-06, | |
| "loss": 1.1141, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 1.2126845121383667, | |
| "eval_runtime": 106.0466, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 5.307888984680176, | |
| "learning_rate": 6.572864321608042e-06, | |
| "loss": 1.1767, | |
| "step": 34600 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 5.546361446380615, | |
| "learning_rate": 6.56281407035176e-06, | |
| "loss": 1.0825, | |
| "step": 34700 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 3.469991445541382, | |
| "learning_rate": 6.552763819095478e-06, | |
| "loss": 1.09, | |
| "step": 34800 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 9.490703582763672, | |
| "learning_rate": 6.542713567839196e-06, | |
| "loss": 1.1252, | |
| "step": 34900 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 3.142402172088623, | |
| "learning_rate": 6.532663316582916e-06, | |
| "loss": 1.1048, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.1838258504867554, | |
| "eval_runtime": 106.0204, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 2.945019483566284, | |
| "learning_rate": 6.522613065326634e-06, | |
| "loss": 1.163, | |
| "step": 35100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 9.670687675476074, | |
| "learning_rate": 6.512562814070352e-06, | |
| "loss": 1.1424, | |
| "step": 35200 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 7.109795093536377, | |
| "learning_rate": 6.50251256281407e-06, | |
| "loss": 1.0786, | |
| "step": 35300 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 11.224685668945312, | |
| "learning_rate": 6.492462311557789e-06, | |
| "loss": 1.0738, | |
| "step": 35400 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 5.65909481048584, | |
| "learning_rate": 6.482412060301508e-06, | |
| "loss": 1.1332, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": 1.1802384853363037, | |
| "eval_runtime": 106.0242, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 5.420670032501221, | |
| "learning_rate": 6.472361809045226e-06, | |
| "loss": 1.0465, | |
| "step": 35600 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 8.849187850952148, | |
| "learning_rate": 6.462311557788945e-06, | |
| "loss": 1.1075, | |
| "step": 35700 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 5.64987325668335, | |
| "learning_rate": 6.4522613065326635e-06, | |
| "loss": 1.0641, | |
| "step": 35800 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 5.252566337585449, | |
| "learning_rate": 6.4422110552763825e-06, | |
| "loss": 1.1164, | |
| "step": 35900 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 8.550498008728027, | |
| "learning_rate": 6.4321608040201015e-06, | |
| "loss": 1.1399, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": 1.1574853658676147, | |
| "eval_runtime": 106.0269, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 4.474692344665527, | |
| "learning_rate": 6.42211055276382e-06, | |
| "loss": 1.0862, | |
| "step": 36100 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 4.71559476852417, | |
| "learning_rate": 6.412060301507538e-06, | |
| "loss": 1.1035, | |
| "step": 36200 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 5.566168785095215, | |
| "learning_rate": 6.402010050251258e-06, | |
| "loss": 1.114, | |
| "step": 36300 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 6.755014419555664, | |
| "learning_rate": 6.391959798994976e-06, | |
| "loss": 1.1105, | |
| "step": 36400 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 7.986637592315674, | |
| "learning_rate": 6.381909547738694e-06, | |
| "loss": 1.1106, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.1570751667022705, | |
| "eval_runtime": 106.0272, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 4.5939812660217285, | |
| "learning_rate": 6.371859296482412e-06, | |
| "loss": 1.1091, | |
| "step": 36600 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 6.492833137512207, | |
| "learning_rate": 6.361809045226132e-06, | |
| "loss": 1.1201, | |
| "step": 36700 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 2.1696550846099854, | |
| "learning_rate": 6.35175879396985e-06, | |
| "loss": 1.1464, | |
| "step": 36800 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 4.580470085144043, | |
| "learning_rate": 6.341708542713568e-06, | |
| "loss": 1.087, | |
| "step": 36900 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 9.039238929748535, | |
| "learning_rate": 6.331658291457286e-06, | |
| "loss": 1.0744, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.172175407409668, | |
| "eval_runtime": 106.0477, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 6.3673601150512695, | |
| "learning_rate": 6.321608040201006e-06, | |
| "loss": 1.1054, | |
| "step": 37100 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 3.981923818588257, | |
| "learning_rate": 6.311557788944724e-06, | |
| "loss": 1.1256, | |
| "step": 37200 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 4.649021148681641, | |
| "learning_rate": 6.301507537688442e-06, | |
| "loss": 1.1943, | |
| "step": 37300 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 4.58133602142334, | |
| "learning_rate": 6.291457286432161e-06, | |
| "loss": 1.0715, | |
| "step": 37400 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 3.975027322769165, | |
| "learning_rate": 6.28140703517588e-06, | |
| "loss": 1.1326, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 1.1794663667678833, | |
| "eval_runtime": 106.2486, | |
| "eval_samples_per_second": 9.412, | |
| "eval_steps_per_second": 2.353, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 4.90846586227417, | |
| "learning_rate": 6.2713567839195985e-06, | |
| "loss": 1.1318, | |
| "step": 37600 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 2.7073814868927, | |
| "learning_rate": 6.2613065326633175e-06, | |
| "loss": 1.1162, | |
| "step": 37700 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 4.579253673553467, | |
| "learning_rate": 6.251256281407036e-06, | |
| "loss": 1.164, | |
| "step": 37800 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 7.598400592803955, | |
| "learning_rate": 6.241206030150754e-06, | |
| "loss": 1.1825, | |
| "step": 37900 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 4.532858848571777, | |
| "learning_rate": 6.231155778894474e-06, | |
| "loss": 1.1073, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": 1.1997580528259277, | |
| "eval_runtime": 106.0241, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 3.0677943229675293, | |
| "learning_rate": 6.221105527638192e-06, | |
| "loss": 1.1517, | |
| "step": 38100 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 5.746025562286377, | |
| "learning_rate": 6.21105527638191e-06, | |
| "loss": 1.1354, | |
| "step": 38200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 11.519875526428223, | |
| "learning_rate": 6.201005025125628e-06, | |
| "loss": 1.1621, | |
| "step": 38300 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 5.125645160675049, | |
| "learning_rate": 6.190954773869348e-06, | |
| "loss": 1.1307, | |
| "step": 38400 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 8.785491943359375, | |
| "learning_rate": 6.180904522613066e-06, | |
| "loss": 1.1468, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": 1.1801879405975342, | |
| "eval_runtime": 106.031, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 4.312779426574707, | |
| "learning_rate": 6.170854271356784e-06, | |
| "loss": 1.0977, | |
| "step": 38600 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 10.210089683532715, | |
| "learning_rate": 6.160804020100502e-06, | |
| "loss": 1.1212, | |
| "step": 38700 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 14.815506935119629, | |
| "learning_rate": 6.150753768844222e-06, | |
| "loss": 1.0945, | |
| "step": 38800 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 5.335196495056152, | |
| "learning_rate": 6.14070351758794e-06, | |
| "loss": 1.0615, | |
| "step": 38900 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 7.525231838226318, | |
| "learning_rate": 6.130653266331658e-06, | |
| "loss": 1.1338, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 1.1894632577896118, | |
| "eval_runtime": 106.0138, | |
| "eval_samples_per_second": 9.433, | |
| "eval_steps_per_second": 2.358, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 3.6122279167175293, | |
| "learning_rate": 6.120603015075377e-06, | |
| "loss": 1.1506, | |
| "step": 39100 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 6.508030414581299, | |
| "learning_rate": 6.110552763819096e-06, | |
| "loss": 1.1407, | |
| "step": 39200 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 4.020355701446533, | |
| "learning_rate": 6.1005025125628145e-06, | |
| "loss": 1.1289, | |
| "step": 39300 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 8.432185173034668, | |
| "learning_rate": 6.0904522613065335e-06, | |
| "loss": 1.085, | |
| "step": 39400 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 6.687023639678955, | |
| "learning_rate": 6.080402010050252e-06, | |
| "loss": 1.0099, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.170699954032898, | |
| "eval_runtime": 106.0277, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 4.077007293701172, | |
| "learning_rate": 6.070351758793971e-06, | |
| "loss": 1.1303, | |
| "step": 39600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 7.5526251792907715, | |
| "learning_rate": 6.06030150753769e-06, | |
| "loss": 1.1067, | |
| "step": 39700 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 4.360392093658447, | |
| "learning_rate": 6.050251256281408e-06, | |
| "loss": 1.0872, | |
| "step": 39800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 3.9685182571411133, | |
| "learning_rate": 6.040201005025126e-06, | |
| "loss": 1.0929, | |
| "step": 39900 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 6.292672157287598, | |
| "learning_rate": 6.030150753768844e-06, | |
| "loss": 1.0774, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.157470464706421, | |
| "eval_runtime": 106.0466, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 9.378790855407715, | |
| "learning_rate": 6.020100502512564e-06, | |
| "loss": 1.0823, | |
| "step": 40100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 5.2826924324035645, | |
| "learning_rate": 6.010050251256282e-06, | |
| "loss": 1.153, | |
| "step": 40200 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 7.502425193786621, | |
| "learning_rate": 6e-06, | |
| "loss": 1.0995, | |
| "step": 40300 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 5.4071478843688965, | |
| "learning_rate": 5.989949748743718e-06, | |
| "loss": 1.0838, | |
| "step": 40400 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 9.192337989807129, | |
| "learning_rate": 5.979899497487438e-06, | |
| "loss": 1.0842, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_loss": 1.1935093402862549, | |
| "eval_runtime": 106.0184, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 5.097936630249023, | |
| "learning_rate": 5.969849246231156e-06, | |
| "loss": 1.0933, | |
| "step": 40600 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 5.131293296813965, | |
| "learning_rate": 5.959798994974874e-06, | |
| "loss": 1.1113, | |
| "step": 40700 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 3.551987886428833, | |
| "learning_rate": 5.949748743718593e-06, | |
| "loss": 1.1403, | |
| "step": 40800 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 3.4648571014404297, | |
| "learning_rate": 5.939698492462312e-06, | |
| "loss": 1.0558, | |
| "step": 40900 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 4.847639083862305, | |
| "learning_rate": 5.9296482412060305e-06, | |
| "loss": 1.1159, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 1.173964500427246, | |
| "eval_runtime": 106.0026, | |
| "eval_samples_per_second": 9.434, | |
| "eval_steps_per_second": 2.358, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 3.479746103286743, | |
| "learning_rate": 5.9195979899497495e-06, | |
| "loss": 1.0749, | |
| "step": 41100 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 3.6594090461730957, | |
| "learning_rate": 5.909547738693468e-06, | |
| "loss": 1.1112, | |
| "step": 41200 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 2.625340700149536, | |
| "learning_rate": 5.899497487437187e-06, | |
| "loss": 1.0512, | |
| "step": 41300 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 2.8171932697296143, | |
| "learning_rate": 5.889447236180905e-06, | |
| "loss": 1.0005, | |
| "step": 41400 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 8.219596862792969, | |
| "learning_rate": 5.879396984924624e-06, | |
| "loss": 1.0944, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 1.1878960132598877, | |
| "eval_runtime": 106.0059, | |
| "eval_samples_per_second": 9.433, | |
| "eval_steps_per_second": 2.358, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 6.593535423278809, | |
| "learning_rate": 5.869346733668342e-06, | |
| "loss": 1.1062, | |
| "step": 41600 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 12.300980567932129, | |
| "learning_rate": 5.859296482412061e-06, | |
| "loss": 1.0978, | |
| "step": 41700 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 5.79435396194458, | |
| "learning_rate": 5.84924623115578e-06, | |
| "loss": 1.1111, | |
| "step": 41800 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 4.353159427642822, | |
| "learning_rate": 5.839195979899498e-06, | |
| "loss": 0.9926, | |
| "step": 41900 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 4.977834224700928, | |
| "learning_rate": 5.829145728643216e-06, | |
| "loss": 1.1513, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_loss": 1.163717269897461, | |
| "eval_runtime": 106.0412, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 11.844463348388672, | |
| "learning_rate": 5.819095477386936e-06, | |
| "loss": 1.1136, | |
| "step": 42100 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 2.4753732681274414, | |
| "learning_rate": 5.809045226130654e-06, | |
| "loss": 1.0853, | |
| "step": 42200 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 12.580413818359375, | |
| "learning_rate": 5.798994974874372e-06, | |
| "loss": 1.1077, | |
| "step": 42300 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 5.60028600692749, | |
| "learning_rate": 5.78894472361809e-06, | |
| "loss": 1.1063, | |
| "step": 42400 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 1.8767462968826294, | |
| "learning_rate": 5.778894472361809e-06, | |
| "loss": 1.0604, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_loss": 1.165592074394226, | |
| "eval_runtime": 106.03, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 10.33289623260498, | |
| "learning_rate": 5.768844221105528e-06, | |
| "loss": 1.0902, | |
| "step": 42600 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 7.651864528656006, | |
| "learning_rate": 5.7587939698492465e-06, | |
| "loss": 1.104, | |
| "step": 42700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 8.54739761352539, | |
| "learning_rate": 5.7487437185929655e-06, | |
| "loss": 1.087, | |
| "step": 42800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 5.075497150421143, | |
| "learning_rate": 5.738693467336684e-06, | |
| "loss": 1.0538, | |
| "step": 42900 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 9.329207420349121, | |
| "learning_rate": 5.728643216080403e-06, | |
| "loss": 1.1125, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.1709275245666504, | |
| "eval_runtime": 106.005, | |
| "eval_samples_per_second": 9.434, | |
| "eval_steps_per_second": 2.358, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 6.580108642578125, | |
| "learning_rate": 5.718592964824121e-06, | |
| "loss": 1.1526, | |
| "step": 43100 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 3.0420515537261963, | |
| "learning_rate": 5.70854271356784e-06, | |
| "loss": 1.0622, | |
| "step": 43200 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 5.738161563873291, | |
| "learning_rate": 5.698492462311558e-06, | |
| "loss": 1.1277, | |
| "step": 43300 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 4.498201370239258, | |
| "learning_rate": 5.688442211055277e-06, | |
| "loss": 1.1508, | |
| "step": 43400 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 9.206507682800293, | |
| "learning_rate": 5.678391959798996e-06, | |
| "loss": 1.15, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_loss": 1.2386019229888916, | |
| "eval_runtime": 106.0267, | |
| "eval_samples_per_second": 9.432, | |
| "eval_steps_per_second": 2.358, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 4.026927471160889, | |
| "learning_rate": 5.668341708542714e-06, | |
| "loss": 1.1185, | |
| "step": 43600 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 6.961542129516602, | |
| "learning_rate": 5.658291457286432e-06, | |
| "loss": 1.0814, | |
| "step": 43700 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 9.742774963378906, | |
| "learning_rate": 5.648241206030152e-06, | |
| "loss": 1.1235, | |
| "step": 43800 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 7.585122108459473, | |
| "learning_rate": 5.63819095477387e-06, | |
| "loss": 1.0564, | |
| "step": 43900 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 9.282063484191895, | |
| "learning_rate": 5.628140703517588e-06, | |
| "loss": 1.1511, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 1.1688772439956665, | |
| "eval_runtime": 106.0117, | |
| "eval_samples_per_second": 9.433, | |
| "eval_steps_per_second": 2.358, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 7.329659938812256, | |
| "learning_rate": 5.618090452261306e-06, | |
| "loss": 1.101, | |
| "step": 44100 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 12.55649185180664, | |
| "learning_rate": 5.608040201005026e-06, | |
| "loss": 1.043, | |
| "step": 44200 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 2.476288318634033, | |
| "learning_rate": 5.597989949748744e-06, | |
| "loss": 1.097, | |
| "step": 44300 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 4.84243631362915, | |
| "learning_rate": 5.5879396984924625e-06, | |
| "loss": 1.0998, | |
| "step": 44400 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 5.389865398406982, | |
| "learning_rate": 5.577889447236181e-06, | |
| "loss": 1.128, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_loss": 1.1911169290542603, | |
| "eval_runtime": 106.0388, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 3.9024312496185303, | |
| "learning_rate": 5.5678391959799e-06, | |
| "loss": 1.0754, | |
| "step": 44600 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 9.319623947143555, | |
| "learning_rate": 5.557788944723619e-06, | |
| "loss": 1.1378, | |
| "step": 44700 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 3.1492748260498047, | |
| "learning_rate": 5.547738693467337e-06, | |
| "loss": 1.1004, | |
| "step": 44800 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 8.03979778289795, | |
| "learning_rate": 5.537688442211056e-06, | |
| "loss": 1.0497, | |
| "step": 44900 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 7.752456188201904, | |
| "learning_rate": 5.527638190954774e-06, | |
| "loss": 1.0543, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_loss": 1.1790896654129028, | |
| "eval_runtime": 106.0302, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 2.237823009490967, | |
| "learning_rate": 5.517587939698493e-06, | |
| "loss": 1.1139, | |
| "step": 45100 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 8.119503021240234, | |
| "learning_rate": 5.507537688442212e-06, | |
| "loss": 1.1112, | |
| "step": 45200 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "grad_norm": 12.357787132263184, | |
| "learning_rate": 5.49748743718593e-06, | |
| "loss": 1.0849, | |
| "step": 45300 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 13.721491813659668, | |
| "learning_rate": 5.487437185929648e-06, | |
| "loss": 1.0981, | |
| "step": 45400 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 10.318241119384766, | |
| "learning_rate": 5.477386934673368e-06, | |
| "loss": 1.1199, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "eval_loss": 1.179891586303711, | |
| "eval_runtime": 106.0371, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 8.675165176391602, | |
| "learning_rate": 5.467336683417086e-06, | |
| "loss": 1.0626, | |
| "step": 45600 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 10.515371322631836, | |
| "learning_rate": 5.457286432160804e-06, | |
| "loss": 1.1091, | |
| "step": 45700 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 11.576639175415039, | |
| "learning_rate": 5.447236180904522e-06, | |
| "loss": 1.0725, | |
| "step": 45800 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 9.982847213745117, | |
| "learning_rate": 5.437185929648242e-06, | |
| "loss": 1.0723, | |
| "step": 45900 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 10.960646629333496, | |
| "learning_rate": 5.42713567839196e-06, | |
| "loss": 1.1203, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 1.1439155340194702, | |
| "eval_runtime": 106.0632, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 3.7092068195343018, | |
| "learning_rate": 5.4170854271356785e-06, | |
| "loss": 1.049, | |
| "step": 46100 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 3.488994836807251, | |
| "learning_rate": 5.407035175879397e-06, | |
| "loss": 1.0726, | |
| "step": 46200 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 3.420220375061035, | |
| "learning_rate": 5.3969849246231165e-06, | |
| "loss": 1.104, | |
| "step": 46300 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 3.8675038814544678, | |
| "learning_rate": 5.386934673366835e-06, | |
| "loss": 1.1328, | |
| "step": 46400 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 14.8497314453125, | |
| "learning_rate": 5.376884422110553e-06, | |
| "loss": 1.0603, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_loss": 1.1883912086486816, | |
| "eval_runtime": 106.0465, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 9.701748847961426, | |
| "learning_rate": 5.366834170854272e-06, | |
| "loss": 1.0552, | |
| "step": 46600 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 4.574182510375977, | |
| "learning_rate": 5.356783919597991e-06, | |
| "loss": 1.0861, | |
| "step": 46700 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 5.884522438049316, | |
| "learning_rate": 5.346733668341709e-06, | |
| "loss": 1.0978, | |
| "step": 46800 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 4.888044357299805, | |
| "learning_rate": 5.336683417085428e-06, | |
| "loss": 1.1089, | |
| "step": 46900 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 8.62630558013916, | |
| "learning_rate": 5.326633165829146e-06, | |
| "loss": 1.0617, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "eval_loss": 1.2093132734298706, | |
| "eval_runtime": 106.0518, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 4.283385276794434, | |
| "learning_rate": 5.316582914572864e-06, | |
| "loss": 1.0723, | |
| "step": 47100 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 2.514089584350586, | |
| "learning_rate": 5.306532663316584e-06, | |
| "loss": 1.0563, | |
| "step": 47200 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 4.744464874267578, | |
| "learning_rate": 5.296482412060302e-06, | |
| "loss": 1.0867, | |
| "step": 47300 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 4.583905220031738, | |
| "learning_rate": 5.28643216080402e-06, | |
| "loss": 1.0383, | |
| "step": 47400 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 4.338555812835693, | |
| "learning_rate": 5.2763819095477384e-06, | |
| "loss": 1.0783, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_loss": 1.1971614360809326, | |
| "eval_runtime": 106.0626, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 4.034645080566406, | |
| "learning_rate": 5.266331658291458e-06, | |
| "loss": 1.1005, | |
| "step": 47600 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 18.2078857421875, | |
| "learning_rate": 5.256281407035176e-06, | |
| "loss": 1.0802, | |
| "step": 47700 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 11.409656524658203, | |
| "learning_rate": 5.2462311557788945e-06, | |
| "loss": 1.0279, | |
| "step": 47800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 9.654501914978027, | |
| "learning_rate": 5.236180904522613e-06, | |
| "loss": 1.1281, | |
| "step": 47900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 2.338249444961548, | |
| "learning_rate": 5.2261306532663325e-06, | |
| "loss": 1.071, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.2035820484161377, | |
| "eval_runtime": 106.069, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 2.0878255367279053, | |
| "learning_rate": 5.216080402010051e-06, | |
| "loss": 1.0815, | |
| "step": 48100 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 3.829693078994751, | |
| "learning_rate": 5.206030150753769e-06, | |
| "loss": 1.0727, | |
| "step": 48200 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 8.797452926635742, | |
| "learning_rate": 5.195979899497488e-06, | |
| "loss": 1.111, | |
| "step": 48300 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 7.87650728225708, | |
| "learning_rate": 5.185929648241207e-06, | |
| "loss": 1.1124, | |
| "step": 48400 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 6.868736743927002, | |
| "learning_rate": 5.175879396984925e-06, | |
| "loss": 1.0428, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 1.205499291419983, | |
| "eval_runtime": 106.0571, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 11.863227844238281, | |
| "learning_rate": 5.165829145728644e-06, | |
| "loss": 1.0223, | |
| "step": 48600 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 4.662557125091553, | |
| "learning_rate": 5.155778894472362e-06, | |
| "loss": 1.0766, | |
| "step": 48700 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 6.566014766693115, | |
| "learning_rate": 5.145728643216081e-06, | |
| "loss": 1.0794, | |
| "step": 48800 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 4.543015003204346, | |
| "learning_rate": 5.1356783919598e-06, | |
| "loss": 1.089, | |
| "step": 48900 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 11.50754451751709, | |
| "learning_rate": 5.125628140703518e-06, | |
| "loss": 1.1178, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_loss": 1.1721173524856567, | |
| "eval_runtime": 106.5237, | |
| "eval_samples_per_second": 9.388, | |
| "eval_steps_per_second": 2.347, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 4.686221599578857, | |
| "learning_rate": 5.115577889447236e-06, | |
| "loss": 1.0752, | |
| "step": 49100 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 6.304415702819824, | |
| "learning_rate": 5.1055276381909544e-06, | |
| "loss": 1.0687, | |
| "step": 49200 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 14.939876556396484, | |
| "learning_rate": 5.095477386934674e-06, | |
| "loss": 1.0325, | |
| "step": 49300 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "grad_norm": 6.50522518157959, | |
| "learning_rate": 5.085427135678392e-06, | |
| "loss": 1.0694, | |
| "step": 49400 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 6.129203796386719, | |
| "learning_rate": 5.0753768844221105e-06, | |
| "loss": 1.0754, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "eval_loss": 1.1991491317749023, | |
| "eval_runtime": 106.0551, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 6.325349807739258, | |
| "learning_rate": 5.065326633165829e-06, | |
| "loss": 1.1652, | |
| "step": 49600 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 4.5157928466796875, | |
| "learning_rate": 5.0552763819095485e-06, | |
| "loss": 1.0868, | |
| "step": 49700 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 8.48715877532959, | |
| "learning_rate": 5.045226130653267e-06, | |
| "loss": 1.1151, | |
| "step": 49800 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 4.27447509765625, | |
| "learning_rate": 5.035175879396985e-06, | |
| "loss": 1.1102, | |
| "step": 49900 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 7.0696258544921875, | |
| "learning_rate": 5.025125628140704e-06, | |
| "loss": 1.1229, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "eval_loss": 1.19700026512146, | |
| "eval_runtime": 106.0396, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 4.845221519470215, | |
| "learning_rate": 5.015075376884423e-06, | |
| "loss": 1.0913, | |
| "step": 50100 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 3.8308610916137695, | |
| "learning_rate": 5.005025125628141e-06, | |
| "loss": 1.074, | |
| "step": 50200 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 11.193860054016113, | |
| "learning_rate": 4.99497487437186e-06, | |
| "loss": 1.0813, | |
| "step": 50300 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 9.640278816223145, | |
| "learning_rate": 4.984924623115578e-06, | |
| "loss": 1.092, | |
| "step": 50400 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 8.961405754089355, | |
| "learning_rate": 4.974874371859297e-06, | |
| "loss": 1.0906, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 1.2116854190826416, | |
| "eval_runtime": 106.3232, | |
| "eval_samples_per_second": 9.405, | |
| "eval_steps_per_second": 2.351, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 3.288750171661377, | |
| "learning_rate": 4.964824120603016e-06, | |
| "loss": 1.0906, | |
| "step": 50600 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 3.4457216262817383, | |
| "learning_rate": 4.954773869346734e-06, | |
| "loss": 1.0875, | |
| "step": 50700 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 7.605111598968506, | |
| "learning_rate": 4.944723618090453e-06, | |
| "loss": 1.0967, | |
| "step": 50800 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 9.561128616333008, | |
| "learning_rate": 4.934673366834171e-06, | |
| "loss": 1.0812, | |
| "step": 50900 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "grad_norm": 7.3962931632995605, | |
| "learning_rate": 4.92462311557789e-06, | |
| "loss": 1.0977, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_loss": 1.2100400924682617, | |
| "eval_runtime": 106.052, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 6.937880992889404, | |
| "learning_rate": 4.914572864321608e-06, | |
| "loss": 1.0975, | |
| "step": 51100 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 5.143784999847412, | |
| "learning_rate": 4.904522613065327e-06, | |
| "loss": 1.087, | |
| "step": 51200 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 3.9461379051208496, | |
| "learning_rate": 4.8944723618090455e-06, | |
| "loss": 1.1038, | |
| "step": 51300 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 5.973447322845459, | |
| "learning_rate": 4.8844221105527645e-06, | |
| "loss": 1.074, | |
| "step": 51400 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 6.638311386108398, | |
| "learning_rate": 4.874371859296483e-06, | |
| "loss": 1.0614, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_loss": 1.185408115386963, | |
| "eval_runtime": 106.2987, | |
| "eval_samples_per_second": 9.407, | |
| "eval_steps_per_second": 2.352, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 6.998035907745361, | |
| "learning_rate": 4.864321608040201e-06, | |
| "loss": 1.0744, | |
| "step": 51600 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 3.3675694465637207, | |
| "learning_rate": 4.85427135678392e-06, | |
| "loss": 1.096, | |
| "step": 51700 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 8.822165489196777, | |
| "learning_rate": 4.844221105527638e-06, | |
| "loss": 1.0922, | |
| "step": 51800 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 9.377400398254395, | |
| "learning_rate": 4.834170854271357e-06, | |
| "loss": 1.0192, | |
| "step": 51900 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 5.365954399108887, | |
| "learning_rate": 4.824120603015076e-06, | |
| "loss": 1.0852, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_loss": 1.1685329675674438, | |
| "eval_runtime": 106.0668, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 10.73094367980957, | |
| "learning_rate": 4.814070351758794e-06, | |
| "loss": 1.026, | |
| "step": 52100 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 8.08397102355957, | |
| "learning_rate": 4.804020100502513e-06, | |
| "loss": 1.1124, | |
| "step": 52200 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 5.968872547149658, | |
| "learning_rate": 4.793969849246232e-06, | |
| "loss": 1.0756, | |
| "step": 52300 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 8.512557983398438, | |
| "learning_rate": 4.78391959798995e-06, | |
| "loss": 1.1132, | |
| "step": 52400 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 15.78652286529541, | |
| "learning_rate": 4.773869346733669e-06, | |
| "loss": 1.0729, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 1.1879240274429321, | |
| "eval_runtime": 106.0637, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "grad_norm": 7.199432849884033, | |
| "learning_rate": 4.763819095477387e-06, | |
| "loss": 1.1142, | |
| "step": 52600 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 2.3736164569854736, | |
| "learning_rate": 4.753768844221106e-06, | |
| "loss": 1.0713, | |
| "step": 52700 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 6.64162540435791, | |
| "learning_rate": 4.743718592964824e-06, | |
| "loss": 1.0596, | |
| "step": 52800 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 5.036973476409912, | |
| "learning_rate": 4.733668341708543e-06, | |
| "loss": 1.1353, | |
| "step": 52900 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 13.622482299804688, | |
| "learning_rate": 4.7236180904522615e-06, | |
| "loss": 1.0713, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 1.2138935327529907, | |
| "eval_runtime": 106.0336, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 10.74639892578125, | |
| "learning_rate": 4.7135678391959805e-06, | |
| "loss": 1.1092, | |
| "step": 53100 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 2.7003939151763916, | |
| "learning_rate": 4.703517587939699e-06, | |
| "loss": 1.0927, | |
| "step": 53200 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 7.11260986328125, | |
| "learning_rate": 4.693467336683418e-06, | |
| "loss": 1.0905, | |
| "step": 53300 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 12.401396751403809, | |
| "learning_rate": 4.683417085427136e-06, | |
| "loss": 1.1015, | |
| "step": 53400 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 8.661816596984863, | |
| "learning_rate": 4.673366834170855e-06, | |
| "loss": 1.1312, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "eval_loss": 1.1807825565338135, | |
| "eval_runtime": 106.0587, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 5.789402008056641, | |
| "learning_rate": 4.663316582914573e-06, | |
| "loss": 1.0313, | |
| "step": 53600 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 10.267823219299316, | |
| "learning_rate": 4.653266331658292e-06, | |
| "loss": 1.1201, | |
| "step": 53700 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 7.390511512756348, | |
| "learning_rate": 4.64321608040201e-06, | |
| "loss": 1.1064, | |
| "step": 53800 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 3.220641613006592, | |
| "learning_rate": 4.633165829145729e-06, | |
| "loss": 1.0898, | |
| "step": 53900 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 4.595098972320557, | |
| "learning_rate": 4.623115577889448e-06, | |
| "loss": 1.0807, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "eval_loss": 1.1710258722305298, | |
| "eval_runtime": 106.0574, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 14.225842475891113, | |
| "learning_rate": 4.613065326633166e-06, | |
| "loss": 1.1179, | |
| "step": 54100 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 2.6075730323791504, | |
| "learning_rate": 4.603015075376885e-06, | |
| "loss": 1.1075, | |
| "step": 54200 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 8.72014045715332, | |
| "learning_rate": 4.592964824120603e-06, | |
| "loss": 1.0653, | |
| "step": 54300 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 13.056175231933594, | |
| "learning_rate": 4.582914572864322e-06, | |
| "loss": 1.106, | |
| "step": 54400 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 6.238776683807373, | |
| "learning_rate": 4.57286432160804e-06, | |
| "loss": 1.0797, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_loss": 1.1717697381973267, | |
| "eval_runtime": 106.0446, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "grad_norm": 4.283226490020752, | |
| "learning_rate": 4.562814070351759e-06, | |
| "loss": 1.0956, | |
| "step": 54600 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 4.9857282638549805, | |
| "learning_rate": 4.5527638190954775e-06, | |
| "loss": 1.1299, | |
| "step": 54700 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 2.51924204826355, | |
| "learning_rate": 4.5427135678391965e-06, | |
| "loss": 1.0938, | |
| "step": 54800 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 4.603549003601074, | |
| "learning_rate": 4.532663316582915e-06, | |
| "loss": 1.1509, | |
| "step": 54900 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 11.00109577178955, | |
| "learning_rate": 4.522613065326634e-06, | |
| "loss": 1.0956, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "eval_loss": 1.1807342767715454, | |
| "eval_runtime": 106.0599, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 4.154958724975586, | |
| "learning_rate": 4.512562814070352e-06, | |
| "loss": 1.0964, | |
| "step": 55100 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 4.329712867736816, | |
| "learning_rate": 4.502512562814071e-06, | |
| "loss": 1.1373, | |
| "step": 55200 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 5.342220783233643, | |
| "learning_rate": 4.492462311557789e-06, | |
| "loss": 1.0808, | |
| "step": 55300 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 5.705708980560303, | |
| "learning_rate": 4.482412060301508e-06, | |
| "loss": 1.062, | |
| "step": 55400 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 4.463514804840088, | |
| "learning_rate": 4.472361809045226e-06, | |
| "loss": 1.1105, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_loss": 1.1636874675750732, | |
| "eval_runtime": 106.046, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 3.2776780128479004, | |
| "learning_rate": 4.462311557788945e-06, | |
| "loss": 1.1123, | |
| "step": 55600 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "grad_norm": 7.7830491065979, | |
| "learning_rate": 4.452261306532664e-06, | |
| "loss": 1.0417, | |
| "step": 55700 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 4.776956081390381, | |
| "learning_rate": 4.442211055276382e-06, | |
| "loss": 1.1081, | |
| "step": 55800 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 8.097271919250488, | |
| "learning_rate": 4.432160804020101e-06, | |
| "loss": 1.1005, | |
| "step": 55900 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 7.190639019012451, | |
| "learning_rate": 4.42211055276382e-06, | |
| "loss": 1.0712, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_loss": 1.1957862377166748, | |
| "eval_runtime": 106.0581, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 12.115496635437012, | |
| "learning_rate": 4.412060301507538e-06, | |
| "loss": 1.0484, | |
| "step": 56100 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 3.0836589336395264, | |
| "learning_rate": 4.4020100502512564e-06, | |
| "loss": 1.0373, | |
| "step": 56200 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 5.282203197479248, | |
| "learning_rate": 4.391959798994975e-06, | |
| "loss": 1.1324, | |
| "step": 56300 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 15.216297149658203, | |
| "learning_rate": 4.3819095477386936e-06, | |
| "loss": 1.12, | |
| "step": 56400 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 5.781431674957275, | |
| "learning_rate": 4.3718592964824125e-06, | |
| "loss": 1.0372, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "eval_loss": 1.1856083869934082, | |
| "eval_runtime": 106.0461, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 7.501257419586182, | |
| "learning_rate": 4.361809045226131e-06, | |
| "loss": 1.049, | |
| "step": 56600 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 4.0562238693237305, | |
| "learning_rate": 4.35175879396985e-06, | |
| "loss": 1.0758, | |
| "step": 56700 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 4.510584831237793, | |
| "learning_rate": 4.341708542713568e-06, | |
| "loss": 1.0304, | |
| "step": 56800 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 11.4026517868042, | |
| "learning_rate": 4.331658291457287e-06, | |
| "loss": 1.0906, | |
| "step": 56900 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 2.8201565742492676, | |
| "learning_rate": 4.321608040201005e-06, | |
| "loss": 1.0806, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_loss": 1.1789506673812866, | |
| "eval_runtime": 106.0454, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 5.044394493103027, | |
| "learning_rate": 4.311557788944724e-06, | |
| "loss": 1.0585, | |
| "step": 57100 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 6.520532131195068, | |
| "learning_rate": 4.301507537688442e-06, | |
| "loss": 1.0524, | |
| "step": 57200 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "grad_norm": 5.544332981109619, | |
| "learning_rate": 4.291457286432161e-06, | |
| "loss": 1.0957, | |
| "step": 57300 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 5.975767612457275, | |
| "learning_rate": 4.28140703517588e-06, | |
| "loss": 1.0923, | |
| "step": 57400 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 8.338631629943848, | |
| "learning_rate": 4.271356783919598e-06, | |
| "loss": 1.05, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "eval_loss": 1.213557481765747, | |
| "eval_runtime": 106.0582, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 9.21115779876709, | |
| "learning_rate": 4.261306532663317e-06, | |
| "loss": 1.0633, | |
| "step": 57600 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 4.789947032928467, | |
| "learning_rate": 4.251256281407035e-06, | |
| "loss": 1.06, | |
| "step": 57700 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 3.622896909713745, | |
| "learning_rate": 4.241206030150754e-06, | |
| "loss": 1.0639, | |
| "step": 57800 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 8.646242141723633, | |
| "learning_rate": 4.231155778894473e-06, | |
| "loss": 1.0433, | |
| "step": 57900 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 5.949797630310059, | |
| "learning_rate": 4.221105527638191e-06, | |
| "loss": 1.0838, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "eval_loss": 1.2052046060562134, | |
| "eval_runtime": 106.0422, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 3.80587100982666, | |
| "learning_rate": 4.21105527638191e-06, | |
| "loss": 1.0948, | |
| "step": 58100 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 11.919468879699707, | |
| "learning_rate": 4.2010050251256285e-06, | |
| "loss": 1.078, | |
| "step": 58200 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 5.601760387420654, | |
| "learning_rate": 4.1909547738693475e-06, | |
| "loss": 1.0883, | |
| "step": 58300 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 9.78034782409668, | |
| "learning_rate": 4.180904522613066e-06, | |
| "loss": 1.0545, | |
| "step": 58400 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 10.80511474609375, | |
| "learning_rate": 4.170854271356784e-06, | |
| "loss": 1.1235, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 1.2118693590164185, | |
| "eval_runtime": 106.3097, | |
| "eval_samples_per_second": 9.406, | |
| "eval_steps_per_second": 2.352, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 3.7069671154022217, | |
| "learning_rate": 4.160804020100503e-06, | |
| "loss": 1.1136, | |
| "step": 58600 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 15.624918937683105, | |
| "learning_rate": 4.150753768844221e-06, | |
| "loss": 1.0553, | |
| "step": 58700 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 6.897815227508545, | |
| "learning_rate": 4.14070351758794e-06, | |
| "loss": 1.0706, | |
| "step": 58800 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 5.351986885070801, | |
| "learning_rate": 4.130653266331658e-06, | |
| "loss": 1.0226, | |
| "step": 58900 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 4.158387660980225, | |
| "learning_rate": 4.120603015075377e-06, | |
| "loss": 1.0865, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 1.16471529006958, | |
| "eval_runtime": 106.0354, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 2.942288398742676, | |
| "learning_rate": 4.110552763819096e-06, | |
| "loss": 1.098, | |
| "step": 59100 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 9.001307487487793, | |
| "learning_rate": 4.100502512562814e-06, | |
| "loss": 1.1024, | |
| "step": 59200 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 14.217978477478027, | |
| "learning_rate": 4.090452261306533e-06, | |
| "loss": 1.0029, | |
| "step": 59300 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 12.35381031036377, | |
| "learning_rate": 4.080402010050251e-06, | |
| "loss": 1.0757, | |
| "step": 59400 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 3.351334571838379, | |
| "learning_rate": 4.07035175879397e-06, | |
| "loss": 1.055, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_loss": 1.1809368133544922, | |
| "eval_runtime": 106.0646, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 5.989234447479248, | |
| "learning_rate": 4.060301507537689e-06, | |
| "loss": 1.034, | |
| "step": 59600 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 9.616496086120605, | |
| "learning_rate": 4.0502512562814074e-06, | |
| "loss": 1.0885, | |
| "step": 59700 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 7.053142547607422, | |
| "learning_rate": 4.040201005025126e-06, | |
| "loss": 1.0858, | |
| "step": 59800 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 12.209592819213867, | |
| "learning_rate": 4.0301507537688446e-06, | |
| "loss": 1.0442, | |
| "step": 59900 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 4.404716968536377, | |
| "learning_rate": 4.0201005025125635e-06, | |
| "loss": 1.0734, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_loss": 1.1983425617218018, | |
| "eval_runtime": 106.0576, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 5.645810604095459, | |
| "learning_rate": 4.010050251256282e-06, | |
| "loss": 1.0638, | |
| "step": 60100 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 4.7631940841674805, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.0657, | |
| "step": 60200 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 2.6057679653167725, | |
| "learning_rate": 3.989949748743719e-06, | |
| "loss": 1.0556, | |
| "step": 60300 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 9.091955184936523, | |
| "learning_rate": 3.979899497487438e-06, | |
| "loss": 1.1244, | |
| "step": 60400 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 6.215171813964844, | |
| "learning_rate": 3.969849246231156e-06, | |
| "loss": 1.1504, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_loss": 1.1710612773895264, | |
| "eval_runtime": 106.0549, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 7.309828758239746, | |
| "learning_rate": 3.959798994974875e-06, | |
| "loss": 1.0624, | |
| "step": 60600 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 5.1372880935668945, | |
| "learning_rate": 3.949748743718593e-06, | |
| "loss": 1.1102, | |
| "step": 60700 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 2.1944918632507324, | |
| "learning_rate": 3.939698492462311e-06, | |
| "loss": 1.0699, | |
| "step": 60800 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 11.555052757263184, | |
| "learning_rate": 3.92964824120603e-06, | |
| "loss": 1.0467, | |
| "step": 60900 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 8.433820724487305, | |
| "learning_rate": 3.919597989949749e-06, | |
| "loss": 1.0355, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_loss": 1.1772249937057495, | |
| "eval_runtime": 106.0454, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 2.291175365447998, | |
| "learning_rate": 3.909547738693467e-06, | |
| "loss": 1.0655, | |
| "step": 61100 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 2.7827377319335938, | |
| "learning_rate": 3.899497487437186e-06, | |
| "loss": 1.0947, | |
| "step": 61200 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 12.351645469665527, | |
| "learning_rate": 3.889447236180905e-06, | |
| "loss": 1.0826, | |
| "step": 61300 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 10.359111785888672, | |
| "learning_rate": 3.8793969849246234e-06, | |
| "loss": 1.0938, | |
| "step": 61400 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 4.723474979400635, | |
| "learning_rate": 3.869346733668342e-06, | |
| "loss": 1.0753, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "eval_loss": 1.1773525476455688, | |
| "eval_runtime": 106.0341, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 7.097861289978027, | |
| "learning_rate": 3.8592964824120606e-06, | |
| "loss": 1.039, | |
| "step": 61600 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 2.926146984100342, | |
| "learning_rate": 3.8492462311557795e-06, | |
| "loss": 1.1176, | |
| "step": 61700 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 9.322738647460938, | |
| "learning_rate": 3.839195979899498e-06, | |
| "loss": 1.0327, | |
| "step": 61800 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 13.57543659210205, | |
| "learning_rate": 3.829145728643217e-06, | |
| "loss": 1.1169, | |
| "step": 61900 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 4.7055535316467285, | |
| "learning_rate": 3.819095477386935e-06, | |
| "loss": 1.0436, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 1.1872432231903076, | |
| "eval_runtime": 106.0793, | |
| "eval_samples_per_second": 9.427, | |
| "eval_steps_per_second": 2.357, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 3.1538665294647217, | |
| "learning_rate": 3.809045226130654e-06, | |
| "loss": 1.0537, | |
| "step": 62100 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 8.150029182434082, | |
| "learning_rate": 3.798994974874372e-06, | |
| "loss": 1.0598, | |
| "step": 62200 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 4.418848037719727, | |
| "learning_rate": 3.788944723618091e-06, | |
| "loss": 1.0996, | |
| "step": 62300 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 5.905966281890869, | |
| "learning_rate": 3.7788944723618095e-06, | |
| "loss": 1.0735, | |
| "step": 62400 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 3.2698171138763428, | |
| "learning_rate": 3.768844221105528e-06, | |
| "loss": 1.0281, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_loss": 1.2369818687438965, | |
| "eval_runtime": 106.0418, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 8.885529518127441, | |
| "learning_rate": 3.7587939698492466e-06, | |
| "loss": 1.056, | |
| "step": 62600 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 6.061652660369873, | |
| "learning_rate": 3.748743718592965e-06, | |
| "loss": 1.0571, | |
| "step": 62700 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 6.784704685211182, | |
| "learning_rate": 3.7386934673366837e-06, | |
| "loss": 1.0289, | |
| "step": 62800 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 5.635735034942627, | |
| "learning_rate": 3.7286432160804027e-06, | |
| "loss": 1.0872, | |
| "step": 62900 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "grad_norm": 7.111885070800781, | |
| "learning_rate": 3.718592964824121e-06, | |
| "loss": 1.0963, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_loss": 1.1708903312683105, | |
| "eval_runtime": 106.032, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 3.6875112056732178, | |
| "learning_rate": 3.7085427135678394e-06, | |
| "loss": 1.0496, | |
| "step": 63100 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 6.22719669342041, | |
| "learning_rate": 3.698492462311558e-06, | |
| "loss": 1.0766, | |
| "step": 63200 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 5.189857482910156, | |
| "learning_rate": 3.6884422110552766e-06, | |
| "loss": 1.0274, | |
| "step": 63300 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 5.517366409301758, | |
| "learning_rate": 3.678391959798995e-06, | |
| "loss": 1.0942, | |
| "step": 63400 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 9.920944213867188, | |
| "learning_rate": 3.6683417085427137e-06, | |
| "loss": 1.0694, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 1.1612495183944702, | |
| "eval_runtime": 106.0488, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 30.120113372802734, | |
| "learning_rate": 3.6582914572864327e-06, | |
| "loss": 1.0943, | |
| "step": 63600 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 6.0459771156311035, | |
| "learning_rate": 3.648241206030151e-06, | |
| "loss": 1.0807, | |
| "step": 63700 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 6.1749653816223145, | |
| "learning_rate": 3.63819095477387e-06, | |
| "loss": 1.1387, | |
| "step": 63800 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 4.901200771331787, | |
| "learning_rate": 3.628140703517588e-06, | |
| "loss": 1.0758, | |
| "step": 63900 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 12.518453598022461, | |
| "learning_rate": 3.618090452261307e-06, | |
| "loss": 1.0996, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 1.1155891418457031, | |
| "eval_runtime": 106.0569, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 5.017581462860107, | |
| "learning_rate": 3.608040201005025e-06, | |
| "loss": 1.0532, | |
| "step": 64100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.2370281219482422, | |
| "learning_rate": 3.597989949748744e-06, | |
| "loss": 1.0878, | |
| "step": 64200 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 11.514025688171387, | |
| "learning_rate": 3.5879396984924626e-06, | |
| "loss": 1.0529, | |
| "step": 64300 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 5.596809387207031, | |
| "learning_rate": 3.577889447236181e-06, | |
| "loss": 1.038, | |
| "step": 64400 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 5.313028335571289, | |
| "learning_rate": 3.5678391959798997e-06, | |
| "loss": 1.0532, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "eval_loss": 1.1719648838043213, | |
| "eval_runtime": 106.0478, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 10.414960861206055, | |
| "learning_rate": 3.5577889447236187e-06, | |
| "loss": 1.0048, | |
| "step": 64600 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 13.392841339111328, | |
| "learning_rate": 3.547738693467337e-06, | |
| "loss": 1.1014, | |
| "step": 64700 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 3.2335710525512695, | |
| "learning_rate": 3.537688442211056e-06, | |
| "loss": 1.1013, | |
| "step": 64800 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 4.216681003570557, | |
| "learning_rate": 3.527638190954774e-06, | |
| "loss": 1.0363, | |
| "step": 64900 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 3.247030735015869, | |
| "learning_rate": 3.517587939698493e-06, | |
| "loss": 1.0747, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "eval_loss": 1.1740339994430542, | |
| "eval_runtime": 106.0636, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 10.313753128051758, | |
| "learning_rate": 3.507537688442211e-06, | |
| "loss": 1.0048, | |
| "step": 65100 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 2.487821102142334, | |
| "learning_rate": 3.49748743718593e-06, | |
| "loss": 1.0597, | |
| "step": 65200 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 5.214561462402344, | |
| "learning_rate": 3.4874371859296487e-06, | |
| "loss": 1.0923, | |
| "step": 65300 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 7.987942218780518, | |
| "learning_rate": 3.477386934673367e-06, | |
| "loss": 1.0697, | |
| "step": 65400 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 21.811670303344727, | |
| "learning_rate": 3.467336683417086e-06, | |
| "loss": 1.0922, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 1.1970088481903076, | |
| "eval_runtime": 106.0745, | |
| "eval_samples_per_second": 9.427, | |
| "eval_steps_per_second": 2.357, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 2.0042884349823, | |
| "learning_rate": 3.457286432160804e-06, | |
| "loss": 1.0802, | |
| "step": 65600 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "grad_norm": 7.716630935668945, | |
| "learning_rate": 3.447236180904523e-06, | |
| "loss": 1.0439, | |
| "step": 65700 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 10.984993934631348, | |
| "learning_rate": 3.437185929648241e-06, | |
| "loss": 1.0531, | |
| "step": 65800 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 7.731362819671631, | |
| "learning_rate": 3.42713567839196e-06, | |
| "loss": 1.0971, | |
| "step": 65900 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 7.619626522064209, | |
| "learning_rate": 3.4170854271356786e-06, | |
| "loss": 1.0754, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "eval_loss": 1.185581088066101, | |
| "eval_runtime": 106.0575, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 10.193381309509277, | |
| "learning_rate": 3.407035175879397e-06, | |
| "loss": 1.0544, | |
| "step": 66100 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 2.2454402446746826, | |
| "learning_rate": 3.3969849246231158e-06, | |
| "loss": 1.142, | |
| "step": 66200 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 9.75003433227539, | |
| "learning_rate": 3.3869346733668347e-06, | |
| "loss": 1.0923, | |
| "step": 66300 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 7.709816932678223, | |
| "learning_rate": 3.376884422110553e-06, | |
| "loss": 1.0747, | |
| "step": 66400 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "grad_norm": 6.4221696853637695, | |
| "learning_rate": 3.366834170854272e-06, | |
| "loss": 1.0434, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_loss": 1.1786295175552368, | |
| "eval_runtime": 106.0416, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 7.951330661773682, | |
| "learning_rate": 3.35678391959799e-06, | |
| "loss": 1.0725, | |
| "step": 66600 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 6.741400718688965, | |
| "learning_rate": 3.346733668341709e-06, | |
| "loss": 1.0469, | |
| "step": 66700 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 14.190262794494629, | |
| "learning_rate": 3.336683417085427e-06, | |
| "loss": 1.0687, | |
| "step": 66800 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 9.906428337097168, | |
| "learning_rate": 3.326633165829146e-06, | |
| "loss": 1.0962, | |
| "step": 66900 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 4.775923728942871, | |
| "learning_rate": 3.3165829145728647e-06, | |
| "loss": 1.0659, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "eval_loss": 1.1667512655258179, | |
| "eval_runtime": 106.0757, | |
| "eval_samples_per_second": 9.427, | |
| "eval_steps_per_second": 2.357, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 10.69369888305664, | |
| "learning_rate": 3.3065326633165833e-06, | |
| "loss": 1.0384, | |
| "step": 67100 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 4.059796333312988, | |
| "learning_rate": 3.296482412060302e-06, | |
| "loss": 1.0502, | |
| "step": 67200 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "grad_norm": 3.5036587715148926, | |
| "learning_rate": 3.286432160804021e-06, | |
| "loss": 1.0406, | |
| "step": 67300 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 7.150821685791016, | |
| "learning_rate": 3.276381909547739e-06, | |
| "loss": 1.0384, | |
| "step": 67400 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 4.669068813323975, | |
| "learning_rate": 3.266331658291458e-06, | |
| "loss": 1.0755, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "eval_loss": 1.1525746583938599, | |
| "eval_runtime": 106.0609, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 9.362273216247559, | |
| "learning_rate": 3.256281407035176e-06, | |
| "loss": 1.0794, | |
| "step": 67600 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 3.6637213230133057, | |
| "learning_rate": 3.2462311557788946e-06, | |
| "loss": 1.0654, | |
| "step": 67700 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "grad_norm": 5.397108554840088, | |
| "learning_rate": 3.236180904522613e-06, | |
| "loss": 1.0832, | |
| "step": 67800 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 2.418199300765991, | |
| "learning_rate": 3.2261306532663318e-06, | |
| "loss": 1.0634, | |
| "step": 67900 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 9.751249313354492, | |
| "learning_rate": 3.2160804020100507e-06, | |
| "loss": 1.0813, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 1.1616853475570679, | |
| "eval_runtime": 106.044, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 5.580630302429199, | |
| "learning_rate": 3.206030150753769e-06, | |
| "loss": 1.0981, | |
| "step": 68100 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 5.4495530128479, | |
| "learning_rate": 3.195979899497488e-06, | |
| "loss": 1.0737, | |
| "step": 68200 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 12.089224815368652, | |
| "learning_rate": 3.185929648241206e-06, | |
| "loss": 1.0539, | |
| "step": 68300 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 10.440498352050781, | |
| "learning_rate": 3.175879396984925e-06, | |
| "loss": 1.0803, | |
| "step": 68400 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 10.229782104492188, | |
| "learning_rate": 3.165829145728643e-06, | |
| "loss": 1.0979, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "eval_loss": 1.159399151802063, | |
| "eval_runtime": 106.0674, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 3.6945924758911133, | |
| "learning_rate": 3.155778894472362e-06, | |
| "loss": 1.0627, | |
| "step": 68600 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 5.110106468200684, | |
| "learning_rate": 3.1457286432160807e-06, | |
| "loss": 1.0585, | |
| "step": 68700 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 7.140746593475342, | |
| "learning_rate": 3.1356783919597993e-06, | |
| "loss": 1.0597, | |
| "step": 68800 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 16.83041000366211, | |
| "learning_rate": 3.125628140703518e-06, | |
| "loss": 0.9972, | |
| "step": 68900 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 5.084952354431152, | |
| "learning_rate": 3.115577889447237e-06, | |
| "loss": 0.9752, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 1.144303798675537, | |
| "eval_runtime": 106.0475, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 9.237672805786133, | |
| "learning_rate": 3.105527638190955e-06, | |
| "loss": 1.0702, | |
| "step": 69100 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 10.925599098205566, | |
| "learning_rate": 3.095477386934674e-06, | |
| "loss": 1.0242, | |
| "step": 69200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 13.037814140319824, | |
| "learning_rate": 3.085427135678392e-06, | |
| "loss": 1.0663, | |
| "step": 69300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "grad_norm": 9.554988861083984, | |
| "learning_rate": 3.075376884422111e-06, | |
| "loss": 1.1384, | |
| "step": 69400 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 3.325300455093384, | |
| "learning_rate": 3.065326633165829e-06, | |
| "loss": 1.0099, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 1.1666878461837769, | |
| "eval_runtime": 106.0586, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 5.020545959472656, | |
| "learning_rate": 3.055276381909548e-06, | |
| "loss": 1.0712, | |
| "step": 69600 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 9.31608772277832, | |
| "learning_rate": 3.0452261306532668e-06, | |
| "loss": 1.0718, | |
| "step": 69700 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 4.576101779937744, | |
| "learning_rate": 3.0351758793969853e-06, | |
| "loss": 0.9786, | |
| "step": 69800 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 5.823631286621094, | |
| "learning_rate": 3.025125628140704e-06, | |
| "loss": 1.0892, | |
| "step": 69900 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 7.814849376678467, | |
| "learning_rate": 3.015075376884422e-06, | |
| "loss": 1.0544, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 1.1586934328079224, | |
| "eval_runtime": 106.0553, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 20.614145278930664, | |
| "learning_rate": 3.005025125628141e-06, | |
| "loss": 1.0971, | |
| "step": 70100 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 6.837667942047119, | |
| "learning_rate": 2.994974874371859e-06, | |
| "loss": 1.0629, | |
| "step": 70200 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 11.336121559143066, | |
| "learning_rate": 2.984924623115578e-06, | |
| "loss": 1.0624, | |
| "step": 70300 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 13.510031700134277, | |
| "learning_rate": 2.9748743718592967e-06, | |
| "loss": 1.1043, | |
| "step": 70400 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 5.644843578338623, | |
| "learning_rate": 2.9648241206030153e-06, | |
| "loss": 1.0754, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "eval_loss": 1.1812278032302856, | |
| "eval_runtime": 106.029, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 6.993515968322754, | |
| "learning_rate": 2.954773869346734e-06, | |
| "loss": 1.0704, | |
| "step": 70600 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 9.949378967285156, | |
| "learning_rate": 2.9447236180904524e-06, | |
| "loss": 1.0647, | |
| "step": 70700 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 11.08406925201416, | |
| "learning_rate": 2.934673366834171e-06, | |
| "loss": 1.0978, | |
| "step": 70800 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 9.99530029296875, | |
| "learning_rate": 2.92462311557789e-06, | |
| "loss": 1.0333, | |
| "step": 70900 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 12.340422630310059, | |
| "learning_rate": 2.914572864321608e-06, | |
| "loss": 1.0597, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_loss": 1.1510303020477295, | |
| "eval_runtime": 106.3062, | |
| "eval_samples_per_second": 9.407, | |
| "eval_steps_per_second": 2.352, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 3.573578119277954, | |
| "learning_rate": 2.904522613065327e-06, | |
| "loss": 1.1165, | |
| "step": 71100 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 5.8838629722595215, | |
| "learning_rate": 2.894472361809045e-06, | |
| "loss": 1.0916, | |
| "step": 71200 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 7.589781761169434, | |
| "learning_rate": 2.884422110552764e-06, | |
| "loss": 1.0535, | |
| "step": 71300 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 4.135651111602783, | |
| "learning_rate": 2.8743718592964828e-06, | |
| "loss": 1.0768, | |
| "step": 71400 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 8.806633949279785, | |
| "learning_rate": 2.8643216080402013e-06, | |
| "loss": 1.0945, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "eval_loss": 1.200325846672058, | |
| "eval_runtime": 106.0463, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 3.913125991821289, | |
| "learning_rate": 2.85427135678392e-06, | |
| "loss": 1.0631, | |
| "step": 71600 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 5.196088790893555, | |
| "learning_rate": 2.8442211055276384e-06, | |
| "loss": 1.0687, | |
| "step": 71700 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 8.308272361755371, | |
| "learning_rate": 2.834170854271357e-06, | |
| "loss": 1.1081, | |
| "step": 71800 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 8.516919136047363, | |
| "learning_rate": 2.824120603015076e-06, | |
| "loss": 1.0712, | |
| "step": 71900 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 10.68675422668457, | |
| "learning_rate": 2.814070351758794e-06, | |
| "loss": 1.1194, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_loss": 1.1641302108764648, | |
| "eval_runtime": 106.0419, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 9.415139198303223, | |
| "learning_rate": 2.804020100502513e-06, | |
| "loss": 1.0774, | |
| "step": 72100 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 3.7503983974456787, | |
| "learning_rate": 2.7939698492462313e-06, | |
| "loss": 1.1268, | |
| "step": 72200 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 1.8224315643310547, | |
| "learning_rate": 2.78391959798995e-06, | |
| "loss": 1.0452, | |
| "step": 72300 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 13.259425163269043, | |
| "learning_rate": 2.7738693467336684e-06, | |
| "loss": 1.0463, | |
| "step": 72400 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 5.253272533416748, | |
| "learning_rate": 2.763819095477387e-06, | |
| "loss": 1.0794, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 1.1821850538253784, | |
| "eval_runtime": 106.0523, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 14.562149047851562, | |
| "learning_rate": 2.753768844221106e-06, | |
| "loss": 1.1187, | |
| "step": 72600 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 13.231179237365723, | |
| "learning_rate": 2.743718592964824e-06, | |
| "loss": 1.0532, | |
| "step": 72700 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 5.84453010559082, | |
| "learning_rate": 2.733668341708543e-06, | |
| "loss": 1.066, | |
| "step": 72800 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 8.251835823059082, | |
| "learning_rate": 2.723618090452261e-06, | |
| "loss": 1.0764, | |
| "step": 72900 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "grad_norm": 6.283970832824707, | |
| "learning_rate": 2.71356783919598e-06, | |
| "loss": 1.1205, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "eval_loss": 1.137833833694458, | |
| "eval_runtime": 106.0617, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 5.204836845397949, | |
| "learning_rate": 2.7035175879396983e-06, | |
| "loss": 1.0788, | |
| "step": 73100 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 12.395988464355469, | |
| "learning_rate": 2.6934673366834173e-06, | |
| "loss": 1.0342, | |
| "step": 73200 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 7.316469669342041, | |
| "learning_rate": 2.683417085427136e-06, | |
| "loss": 1.1122, | |
| "step": 73300 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 5.458342552185059, | |
| "learning_rate": 2.6733668341708545e-06, | |
| "loss": 1.0277, | |
| "step": 73400 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 4.2949981689453125, | |
| "learning_rate": 2.663316582914573e-06, | |
| "loss": 1.0895, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "eval_loss": 1.1763978004455566, | |
| "eval_runtime": 106.047, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 3.5636932849884033, | |
| "learning_rate": 2.653266331658292e-06, | |
| "loss": 1.0559, | |
| "step": 73600 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 10.85332202911377, | |
| "learning_rate": 2.64321608040201e-06, | |
| "loss": 1.0593, | |
| "step": 73700 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 7.5514750480651855, | |
| "learning_rate": 2.633165829145729e-06, | |
| "loss": 1.0819, | |
| "step": 73800 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 9.394440650939941, | |
| "learning_rate": 2.6231155778894473e-06, | |
| "loss": 1.0498, | |
| "step": 73900 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 9.17789363861084, | |
| "learning_rate": 2.6130653266331663e-06, | |
| "loss": 1.1306, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "eval_loss": 1.1681709289550781, | |
| "eval_runtime": 106.0499, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 18.37449073791504, | |
| "learning_rate": 2.6030150753768844e-06, | |
| "loss": 1.051, | |
| "step": 74100 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 2.33835768699646, | |
| "learning_rate": 2.5929648241206034e-06, | |
| "loss": 1.0613, | |
| "step": 74200 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 6.537227630615234, | |
| "learning_rate": 2.582914572864322e-06, | |
| "loss": 1.1065, | |
| "step": 74300 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 15.826942443847656, | |
| "learning_rate": 2.5728643216080405e-06, | |
| "loss": 1.0764, | |
| "step": 74400 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 6.798605918884277, | |
| "learning_rate": 2.562814070351759e-06, | |
| "loss": 1.0653, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 1.1853090524673462, | |
| "eval_runtime": 106.0658, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 5.614243984222412, | |
| "learning_rate": 2.5527638190954772e-06, | |
| "loss": 1.0322, | |
| "step": 74600 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 4.611671447753906, | |
| "learning_rate": 2.542713567839196e-06, | |
| "loss": 1.0867, | |
| "step": 74700 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 13.089502334594727, | |
| "learning_rate": 2.5326633165829143e-06, | |
| "loss": 1.0698, | |
| "step": 74800 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "grad_norm": 7.631048679351807, | |
| "learning_rate": 2.5226130653266333e-06, | |
| "loss": 1.0094, | |
| "step": 74900 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 8.738151550292969, | |
| "learning_rate": 2.512562814070352e-06, | |
| "loss": 1.0388, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "eval_loss": 1.1503615379333496, | |
| "eval_runtime": 106.071, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 3.997983932495117, | |
| "learning_rate": 2.5025125628140705e-06, | |
| "loss": 1.039, | |
| "step": 75100 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 3.2443947792053223, | |
| "learning_rate": 2.492462311557789e-06, | |
| "loss": 1.0644, | |
| "step": 75200 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 3.138190507888794, | |
| "learning_rate": 2.482412060301508e-06, | |
| "loss": 1.0382, | |
| "step": 75300 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 8.46721363067627, | |
| "learning_rate": 2.4723618090452266e-06, | |
| "loss": 1.0846, | |
| "step": 75400 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 6.676329135894775, | |
| "learning_rate": 2.462311557788945e-06, | |
| "loss": 1.1071, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 1.1840382814407349, | |
| "eval_runtime": 106.0594, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 4.778306484222412, | |
| "learning_rate": 2.4522613065326637e-06, | |
| "loss": 1.0251, | |
| "step": 75600 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 10.008584022521973, | |
| "learning_rate": 2.4422110552763823e-06, | |
| "loss": 1.0547, | |
| "step": 75700 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 7.311899185180664, | |
| "learning_rate": 2.4321608040201004e-06, | |
| "loss": 1.04, | |
| "step": 75800 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 18.295940399169922, | |
| "learning_rate": 2.422110552763819e-06, | |
| "loss": 1.0708, | |
| "step": 75900 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 8.365277290344238, | |
| "learning_rate": 2.412060301507538e-06, | |
| "loss": 0.9736, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_loss": 1.1644206047058105, | |
| "eval_runtime": 106.0488, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 7.482743263244629, | |
| "learning_rate": 2.4020100502512565e-06, | |
| "loss": 1.0588, | |
| "step": 76100 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 6.637324333190918, | |
| "learning_rate": 2.391959798994975e-06, | |
| "loss": 1.0029, | |
| "step": 76200 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 4.1734089851379395, | |
| "learning_rate": 2.3819095477386936e-06, | |
| "loss": 1.089, | |
| "step": 76300 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 16.437904357910156, | |
| "learning_rate": 2.371859296482412e-06, | |
| "loss": 1.0594, | |
| "step": 76400 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 7.176886081695557, | |
| "learning_rate": 2.3618090452261308e-06, | |
| "loss": 1.0755, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "eval_loss": 1.1777397394180298, | |
| "eval_runtime": 106.0428, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 5.481789588928223, | |
| "learning_rate": 2.3517587939698493e-06, | |
| "loss": 1.0636, | |
| "step": 76600 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 8.8861083984375, | |
| "learning_rate": 2.341708542713568e-06, | |
| "loss": 1.0088, | |
| "step": 76700 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 9.045199394226074, | |
| "learning_rate": 2.3316582914572865e-06, | |
| "loss": 1.0385, | |
| "step": 76800 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 8.271011352539062, | |
| "learning_rate": 2.321608040201005e-06, | |
| "loss": 1.0585, | |
| "step": 76900 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 5.93958854675293, | |
| "learning_rate": 2.311557788944724e-06, | |
| "loss": 1.0454, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_loss": 1.1677011251449585, | |
| "eval_runtime": 106.0657, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 4.292805194854736, | |
| "learning_rate": 2.3015075376884426e-06, | |
| "loss": 1.1054, | |
| "step": 77100 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 6.812904357910156, | |
| "learning_rate": 2.291457286432161e-06, | |
| "loss": 1.104, | |
| "step": 77200 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 5.912458896636963, | |
| "learning_rate": 2.2814070351758797e-06, | |
| "loss": 1.0717, | |
| "step": 77300 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 11.724600791931152, | |
| "learning_rate": 2.2713567839195983e-06, | |
| "loss": 1.0796, | |
| "step": 77400 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 8.604060173034668, | |
| "learning_rate": 2.261306532663317e-06, | |
| "loss": 1.0793, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_loss": 1.1650307178497314, | |
| "eval_runtime": 106.053, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 6.0530476570129395, | |
| "learning_rate": 2.2512562814070354e-06, | |
| "loss": 1.0121, | |
| "step": 77600 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 4.569116115570068, | |
| "learning_rate": 2.241206030150754e-06, | |
| "loss": 1.0333, | |
| "step": 77700 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 6.292867660522461, | |
| "learning_rate": 2.2311557788944725e-06, | |
| "loss": 1.0363, | |
| "step": 77800 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 5.912831783294678, | |
| "learning_rate": 2.221105527638191e-06, | |
| "loss": 1.0515, | |
| "step": 77900 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 7.606415271759033, | |
| "learning_rate": 2.21105527638191e-06, | |
| "loss": 1.0151, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_loss": 1.1836047172546387, | |
| "eval_runtime": 106.0598, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 4.176692008972168, | |
| "learning_rate": 2.2010050251256282e-06, | |
| "loss": 1.0719, | |
| "step": 78100 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 15.275976181030273, | |
| "learning_rate": 2.1909547738693468e-06, | |
| "loss": 1.0158, | |
| "step": 78200 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 5.714578151702881, | |
| "learning_rate": 2.1809045226130653e-06, | |
| "loss": 1.0678, | |
| "step": 78300 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 1.8382607698440552, | |
| "learning_rate": 2.170854271356784e-06, | |
| "loss": 1.045, | |
| "step": 78400 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 7.254737377166748, | |
| "learning_rate": 2.1608040201005025e-06, | |
| "loss": 1.0161, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "eval_loss": 1.1580357551574707, | |
| "eval_runtime": 106.0396, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 8.868572235107422, | |
| "learning_rate": 2.150753768844221e-06, | |
| "loss": 1.0734, | |
| "step": 78600 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 10.592870712280273, | |
| "learning_rate": 2.14070351758794e-06, | |
| "loss": 1.0544, | |
| "step": 78700 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 8.468735694885254, | |
| "learning_rate": 2.1306532663316586e-06, | |
| "loss": 1.1248, | |
| "step": 78800 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 5.241983890533447, | |
| "learning_rate": 2.120603015075377e-06, | |
| "loss": 1.0655, | |
| "step": 78900 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 4.542044162750244, | |
| "learning_rate": 2.1105527638190957e-06, | |
| "loss": 1.0258, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "eval_loss": 1.1469522714614868, | |
| "eval_runtime": 106.139, | |
| "eval_samples_per_second": 9.422, | |
| "eval_steps_per_second": 2.355, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 9.26364803314209, | |
| "learning_rate": 2.1005025125628143e-06, | |
| "loss": 1.0528, | |
| "step": 79100 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 4.515612602233887, | |
| "learning_rate": 2.090452261306533e-06, | |
| "loss": 1.0788, | |
| "step": 79200 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 16.94777488708496, | |
| "learning_rate": 2.0804020100502514e-06, | |
| "loss": 1.0541, | |
| "step": 79300 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 3.827336549758911, | |
| "learning_rate": 2.07035175879397e-06, | |
| "loss": 1.0475, | |
| "step": 79400 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 2.7908217906951904, | |
| "learning_rate": 2.0603015075376885e-06, | |
| "loss": 1.1173, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "eval_loss": 1.2008851766586304, | |
| "eval_runtime": 106.0493, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 4.2991623878479, | |
| "learning_rate": 2.050251256281407e-06, | |
| "loss": 1.029, | |
| "step": 79600 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "grad_norm": 6.991485595703125, | |
| "learning_rate": 2.0402010050251257e-06, | |
| "loss": 1.0284, | |
| "step": 79700 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 12.238316535949707, | |
| "learning_rate": 2.0301507537688446e-06, | |
| "loss": 1.1032, | |
| "step": 79800 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.9090447425842285, | |
| "learning_rate": 2.020100502512563e-06, | |
| "loss": 1.0962, | |
| "step": 79900 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.7181665897369385, | |
| "learning_rate": 2.0100502512562818e-06, | |
| "loss": 0.9719, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.1909617185592651, | |
| "eval_runtime": 106.0461, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 10.567878723144531, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.0297, | |
| "step": 80100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 18.70653533935547, | |
| "learning_rate": 1.989949748743719e-06, | |
| "loss": 0.9519, | |
| "step": 80200 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 9.118350982666016, | |
| "learning_rate": 1.9798994974874375e-06, | |
| "loss": 1.0837, | |
| "step": 80300 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 7.65001916885376, | |
| "learning_rate": 1.9698492462311556e-06, | |
| "loss": 1.0141, | |
| "step": 80400 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 10.12730598449707, | |
| "learning_rate": 1.9597989949748746e-06, | |
| "loss": 0.9636, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_loss": 1.2351462841033936, | |
| "eval_runtime": 106.0686, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 4.90811824798584, | |
| "learning_rate": 1.949748743718593e-06, | |
| "loss": 1.0283, | |
| "step": 80600 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 13.02475357055664, | |
| "learning_rate": 1.9396984924623117e-06, | |
| "loss": 1.0575, | |
| "step": 80700 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 6.416511535644531, | |
| "learning_rate": 1.9296482412060303e-06, | |
| "loss": 1.0341, | |
| "step": 80800 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 3.5513508319854736, | |
| "learning_rate": 1.919597989949749e-06, | |
| "loss": 0.9724, | |
| "step": 80900 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 9.833860397338867, | |
| "learning_rate": 1.9095477386934674e-06, | |
| "loss": 0.9616, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 1.2099558115005493, | |
| "eval_runtime": 106.0421, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 2.1147024631500244, | |
| "learning_rate": 1.899497487437186e-06, | |
| "loss": 1.0576, | |
| "step": 81100 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 11.194029808044434, | |
| "learning_rate": 1.8894472361809047e-06, | |
| "loss": 1.02, | |
| "step": 81200 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "grad_norm": 8.503270149230957, | |
| "learning_rate": 1.8793969849246233e-06, | |
| "loss": 1.0283, | |
| "step": 81300 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 8.470173835754395, | |
| "learning_rate": 1.8693467336683419e-06, | |
| "loss": 1.124, | |
| "step": 81400 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 5.411770343780518, | |
| "learning_rate": 1.8592964824120604e-06, | |
| "loss": 1.0552, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 1.1827166080474854, | |
| "eval_runtime": 106.0475, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 12.674576759338379, | |
| "learning_rate": 1.849246231155779e-06, | |
| "loss": 1.0509, | |
| "step": 81600 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 11.850838661193848, | |
| "learning_rate": 1.8391959798994976e-06, | |
| "loss": 1.0259, | |
| "step": 81700 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 13.24087142944336, | |
| "learning_rate": 1.8291457286432163e-06, | |
| "loss": 0.9819, | |
| "step": 81800 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 4.519367694854736, | |
| "learning_rate": 1.819095477386935e-06, | |
| "loss": 0.9872, | |
| "step": 81900 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 9.235967636108398, | |
| "learning_rate": 1.8090452261306535e-06, | |
| "loss": 1.0907, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "eval_loss": 1.2134792804718018, | |
| "eval_runtime": 106.0602, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 20.29911994934082, | |
| "learning_rate": 1.798994974874372e-06, | |
| "loss": 1.064, | |
| "step": 82100 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 14.744649887084961, | |
| "learning_rate": 1.7889447236180906e-06, | |
| "loss": 0.935, | |
| "step": 82200 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 13.829286575317383, | |
| "learning_rate": 1.7788944723618094e-06, | |
| "loss": 1.0424, | |
| "step": 82300 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 29.574548721313477, | |
| "learning_rate": 1.768844221105528e-06, | |
| "loss": 0.9826, | |
| "step": 82400 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 24.981372833251953, | |
| "learning_rate": 1.7587939698492465e-06, | |
| "loss": 1.0717, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 1.2202541828155518, | |
| "eval_runtime": 106.0305, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 4.073423862457275, | |
| "learning_rate": 1.748743718592965e-06, | |
| "loss": 1.0153, | |
| "step": 82600 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 4.531286716461182, | |
| "learning_rate": 1.7386934673366834e-06, | |
| "loss": 1.0284, | |
| "step": 82700 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 17.423730850219727, | |
| "learning_rate": 1.728643216080402e-06, | |
| "loss": 1.0107, | |
| "step": 82800 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 11.03442096710205, | |
| "learning_rate": 1.7185929648241205e-06, | |
| "loss": 1.0691, | |
| "step": 82900 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 6.14145565032959, | |
| "learning_rate": 1.7085427135678393e-06, | |
| "loss": 1.008, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 1.1811891794204712, | |
| "eval_runtime": 106.0519, | |
| "eval_samples_per_second": 9.429, | |
| "eval_steps_per_second": 2.357, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 7.994312286376953, | |
| "learning_rate": 1.6984924623115579e-06, | |
| "loss": 1.045, | |
| "step": 83100 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 9.712363243103027, | |
| "learning_rate": 1.6884422110552764e-06, | |
| "loss": 0.9937, | |
| "step": 83200 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 6.869166851043701, | |
| "learning_rate": 1.678391959798995e-06, | |
| "loss": 1.0208, | |
| "step": 83300 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 6.159416675567627, | |
| "learning_rate": 1.6683417085427136e-06, | |
| "loss": 0.955, | |
| "step": 83400 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 11.284279823303223, | |
| "learning_rate": 1.6582914572864323e-06, | |
| "loss": 0.9479, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_loss": 1.1792709827423096, | |
| "eval_runtime": 106.0661, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 4.538952350616455, | |
| "learning_rate": 1.648241206030151e-06, | |
| "loss": 0.9935, | |
| "step": 83600 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 8.99368953704834, | |
| "learning_rate": 1.6381909547738695e-06, | |
| "loss": 1.0084, | |
| "step": 83700 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 6.514503002166748, | |
| "learning_rate": 1.628140703517588e-06, | |
| "loss": 0.9761, | |
| "step": 83800 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 11.572303771972656, | |
| "learning_rate": 1.6180904522613066e-06, | |
| "loss": 1.0081, | |
| "step": 83900 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 7.4358673095703125, | |
| "learning_rate": 1.6080402010050254e-06, | |
| "loss": 1.0011, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_loss": 1.201202392578125, | |
| "eval_runtime": 106.042, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 6.303736209869385, | |
| "learning_rate": 1.597989949748744e-06, | |
| "loss": 1.0016, | |
| "step": 84100 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 16.139482498168945, | |
| "learning_rate": 1.5879396984924625e-06, | |
| "loss": 1.0374, | |
| "step": 84200 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "grad_norm": 9.819048881530762, | |
| "learning_rate": 1.577889447236181e-06, | |
| "loss": 1.0411, | |
| "step": 84300 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "grad_norm": 4.718905925750732, | |
| "learning_rate": 1.5678391959798996e-06, | |
| "loss": 1.0069, | |
| "step": 84400 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "grad_norm": 7.538113117218018, | |
| "learning_rate": 1.5577889447236184e-06, | |
| "loss": 0.9829, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_loss": 1.1614010334014893, | |
| "eval_runtime": 106.0653, | |
| "eval_samples_per_second": 9.428, | |
| "eval_steps_per_second": 2.357, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 10.54318904876709, | |
| "learning_rate": 1.547738693467337e-06, | |
| "loss": 1.0193, | |
| "step": 84600 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 5.262185096740723, | |
| "learning_rate": 1.5376884422110555e-06, | |
| "loss": 0.9674, | |
| "step": 84700 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 3.759582281112671, | |
| "learning_rate": 1.527638190954774e-06, | |
| "loss": 0.9791, | |
| "step": 84800 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 9.718276977539062, | |
| "learning_rate": 1.5175879396984927e-06, | |
| "loss": 1.0632, | |
| "step": 84900 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 3.3487863540649414, | |
| "learning_rate": 1.507537688442211e-06, | |
| "loss": 1.0127, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "eval_loss": 1.2236921787261963, | |
| "eval_runtime": 106.0375, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 11.309074401855469, | |
| "learning_rate": 1.4974874371859296e-06, | |
| "loss": 1.0514, | |
| "step": 85100 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 7.24993896484375, | |
| "learning_rate": 1.4874371859296483e-06, | |
| "loss": 1.0591, | |
| "step": 85200 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 14.747005462646484, | |
| "learning_rate": 1.477386934673367e-06, | |
| "loss": 1.014, | |
| "step": 85300 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "grad_norm": 5.064266204833984, | |
| "learning_rate": 1.4673366834170855e-06, | |
| "loss": 1.0337, | |
| "step": 85400 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 3.267292022705078, | |
| "learning_rate": 1.457286432160804e-06, | |
| "loss": 1.0187, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 1.1988115310668945, | |
| "eval_runtime": 106.0389, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.358, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 7.9214863777160645, | |
| "learning_rate": 1.4472361809045226e-06, | |
| "loss": 1.0343, | |
| "step": 85600 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 3.9712471961975098, | |
| "learning_rate": 1.4371859296482414e-06, | |
| "loss": 1.0237, | |
| "step": 85700 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 15.225872039794922, | |
| "learning_rate": 1.42713567839196e-06, | |
| "loss": 0.9932, | |
| "step": 85800 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 13.813911437988281, | |
| "learning_rate": 1.4170854271356785e-06, | |
| "loss": 0.9916, | |
| "step": 85900 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 9.51653003692627, | |
| "learning_rate": 1.407035175879397e-06, | |
| "loss": 0.9697, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "eval_loss": 1.1969990730285645, | |
| "eval_runtime": 106.0377, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 2.477295398712158, | |
| "learning_rate": 1.3969849246231156e-06, | |
| "loss": 1.0454, | |
| "step": 86100 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 20.349689483642578, | |
| "learning_rate": 1.3869346733668342e-06, | |
| "loss": 1.034, | |
| "step": 86200 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 13.855409622192383, | |
| "learning_rate": 1.376884422110553e-06, | |
| "loss": 1.0126, | |
| "step": 86300 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 6.404795169830322, | |
| "learning_rate": 1.3668341708542715e-06, | |
| "loss": 1.0157, | |
| "step": 86400 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 24.46071434020996, | |
| "learning_rate": 1.35678391959799e-06, | |
| "loss": 0.9319, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 1.2477246522903442, | |
| "eval_runtime": 106.0459, | |
| "eval_samples_per_second": 9.43, | |
| "eval_steps_per_second": 2.357, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 8.004197120666504, | |
| "learning_rate": 1.3467336683417087e-06, | |
| "loss": 0.9952, | |
| "step": 86600 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 14.353170394897461, | |
| "learning_rate": 1.3366834170854272e-06, | |
| "loss": 1.0468, | |
| "step": 86700 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 17.298402786254883, | |
| "learning_rate": 1.326633165829146e-06, | |
| "loss": 1.0275, | |
| "step": 86800 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 12.817279815673828, | |
| "learning_rate": 1.3165829145728646e-06, | |
| "loss": 1.04, | |
| "step": 86900 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 7.053438186645508, | |
| "learning_rate": 1.3065326633165831e-06, | |
| "loss": 0.9107, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_loss": 1.2399846315383911, | |
| "eval_runtime": 106.0347, | |
| "eval_samples_per_second": 9.431, | |
| "eval_steps_per_second": 2.358, | |
| "step": 87000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 100000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.400884961476608e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |