| { | |
| "best_metric": 3.2050249576568604, | |
| "best_model_checkpoint": "outputs-small/checkpoint-232000", | |
| "epoch": 9.961698984937223, | |
| "eval_steps": 4000, | |
| "global_step": 232000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.000399312685252803, | |
| "loss": 2.7854, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0003984535418188067, | |
| "loss": 2.7344, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00039759439838481036, | |
| "loss": 2.7156, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00039673525495081404, | |
| "loss": 2.6988, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00039587611151681773, | |
| "loss": 2.6938, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0003950169680828214, | |
| "loss": 2.6735, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00039415782464882515, | |
| "loss": 2.6691, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00039329868121482884, | |
| "loss": 2.6607, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 3.4210398197174072, | |
| "eval_runtime": 69.8141, | |
| "eval_samples_per_second": 35.809, | |
| "eval_steps_per_second": 8.952, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0003924395377808325, | |
| "loss": 2.6441, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0003915803943468362, | |
| "loss": 2.6413, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0003907212509128399, | |
| "loss": 2.6438, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0003898621074788436, | |
| "loss": 2.64, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00038900296404484726, | |
| "loss": 2.6249, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.000388143820610851, | |
| "loss": 2.6251, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0003872846771768547, | |
| "loss": 2.6362, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00038642553374285837, | |
| "loss": 2.6154, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 3.375439167022705, | |
| "eval_runtime": 69.7038, | |
| "eval_samples_per_second": 35.866, | |
| "eval_steps_per_second": 8.967, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00038556639030886205, | |
| "loss": 2.6244, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0003847072468748658, | |
| "loss": 2.605, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0003838481034408695, | |
| "loss": 2.607, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00038298896000687316, | |
| "loss": 2.5968, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0003821298165728769, | |
| "loss": 2.6011, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0003812706731388806, | |
| "loss": 2.6044, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00038041152970488427, | |
| "loss": 2.6152, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00037955238627088796, | |
| "loss": 2.5931, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": 3.3464293479919434, | |
| "eval_runtime": 70.0461, | |
| "eval_samples_per_second": 35.691, | |
| "eval_steps_per_second": 8.923, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00037869324283689164, | |
| "loss": 2.6057, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0003778340994028953, | |
| "loss": 2.5971, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00037697495596889907, | |
| "loss": 2.5972, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00037611581253490275, | |
| "loss": 2.5886, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00037525666910090644, | |
| "loss": 2.6032, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0003743975256669101, | |
| "loss": 2.5948, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0003735383822329138, | |
| "loss": 2.5832, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.0003726792387989175, | |
| "loss": 2.5915, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": 3.3282320499420166, | |
| "eval_runtime": 69.8767, | |
| "eval_samples_per_second": 35.777, | |
| "eval_steps_per_second": 8.944, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0003718200953649212, | |
| "loss": 2.5876, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0003709609519309249, | |
| "loss": 2.5797, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.0003701018084969286, | |
| "loss": 2.5902, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0003692426650629323, | |
| "loss": 2.5837, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00036838352162893597, | |
| "loss": 2.5814, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00036752437819493965, | |
| "loss": 2.5798, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00036666523476094334, | |
| "loss": 2.5868, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.000365806091326947, | |
| "loss": 2.5812, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": 3.3161280155181885, | |
| "eval_runtime": 69.8895, | |
| "eval_samples_per_second": 35.771, | |
| "eval_steps_per_second": 8.943, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.00036494694789295076, | |
| "loss": 2.5681, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.00036408780445895445, | |
| "loss": 2.583, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.00036322866102495813, | |
| "loss": 2.5875, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 0.0003623695175909618, | |
| "loss": 2.5692, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 0.0003615103741569655, | |
| "loss": 2.5728, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.0003606512307229692, | |
| "loss": 2.58, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00035979208728897287, | |
| "loss": 2.5674, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0003589329438549766, | |
| "loss": 2.5685, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_loss": 3.305285930633545, | |
| "eval_runtime": 70.0352, | |
| "eval_samples_per_second": 35.696, | |
| "eval_steps_per_second": 8.924, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0003580738004209803, | |
| "loss": 2.5612, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.000357214656986984, | |
| "loss": 2.5571, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 0.00035635551355298766, | |
| "loss": 2.5599, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00035549637011899135, | |
| "loss": 2.5691, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00035463722668499503, | |
| "loss": 2.5652, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.0003537780832509988, | |
| "loss": 2.5615, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 0.00035291893981700246, | |
| "loss": 2.5624, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00035205979638300614, | |
| "loss": 2.5551, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 3.3031015396118164, | |
| "eval_runtime": 70.3897, | |
| "eval_samples_per_second": 35.517, | |
| "eval_steps_per_second": 8.879, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0003512006529490099, | |
| "loss": 2.5608, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00035034150951501357, | |
| "loss": 2.5662, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.00034948236608101725, | |
| "loss": 2.5642, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.00034862322264702094, | |
| "loss": 2.5727, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.0003477640792130247, | |
| "loss": 2.5536, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.00034690493577902836, | |
| "loss": 2.5683, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.00034604579234503205, | |
| "loss": 2.5515, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00034518664891103573, | |
| "loss": 2.5568, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 3.2884230613708496, | |
| "eval_runtime": 70.9923, | |
| "eval_samples_per_second": 35.215, | |
| "eval_steps_per_second": 8.804, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.0003443275054770394, | |
| "loss": 2.5517, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.0003434683620430431, | |
| "loss": 2.5621, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 0.0003426092186090468, | |
| "loss": 2.5494, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0003417500751750505, | |
| "loss": 2.55, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0003408909317410542, | |
| "loss": 2.5584, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0003400317883070579, | |
| "loss": 2.5564, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 0.0003391726448730616, | |
| "loss": 2.5529, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 0.00033831350143906526, | |
| "loss": 2.5552, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "eval_loss": 3.2850100994110107, | |
| "eval_runtime": 69.9369, | |
| "eval_samples_per_second": 35.747, | |
| "eval_steps_per_second": 8.937, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00033745435800506895, | |
| "loss": 2.5711, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00033659521457107263, | |
| "loss": 2.5477, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 0.00033573607113707637, | |
| "loss": 2.5592, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00033487692770308006, | |
| "loss": 2.5594, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.00033401778426908374, | |
| "loss": 2.5456, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 0.0003331586408350874, | |
| "loss": 2.5583, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.0003322994974010911, | |
| "loss": 2.5503, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 0.0003314403539670948, | |
| "loss": 2.5502, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "eval_loss": 3.289710521697998, | |
| "eval_runtime": 69.6403, | |
| "eval_samples_per_second": 35.899, | |
| "eval_steps_per_second": 8.975, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0003305812105330985, | |
| "loss": 2.5422, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.0003297220670991022, | |
| "loss": 2.5566, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.0003288629236651059, | |
| "loss": 2.5492, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0003280037802311096, | |
| "loss": 2.5482, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 0.0003271446367971133, | |
| "loss": 2.5538, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 0.00032628549336311696, | |
| "loss": 2.5482, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00032542634992912064, | |
| "loss": 2.5499, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.0003245672064951244, | |
| "loss": 2.5553, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "eval_loss": 3.2857840061187744, | |
| "eval_runtime": 69.6297, | |
| "eval_samples_per_second": 35.904, | |
| "eval_steps_per_second": 8.976, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 0.00032370806306112807, | |
| "loss": 2.5506, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 0.00032284891962713175, | |
| "loss": 2.5452, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.00032198977619313544, | |
| "loss": 2.5505, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.0003211306327591392, | |
| "loss": 2.5403, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.00032027148932514286, | |
| "loss": 2.5493, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.00031941234589114655, | |
| "loss": 2.5413, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.00031855320245715023, | |
| "loss": 2.538, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00031769405902315397, | |
| "loss": 2.5408, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_loss": 3.2898008823394775, | |
| "eval_runtime": 68.7611, | |
| "eval_samples_per_second": 36.358, | |
| "eval_steps_per_second": 9.089, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.00031683491558915765, | |
| "loss": 2.5362, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 0.00031597577215516134, | |
| "loss": 2.5368, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.000315116628721165, | |
| "loss": 2.5366, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 0.0003142574852871687, | |
| "loss": 2.5375, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 0.0003133983418531724, | |
| "loss": 2.5455, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 0.00031253919841917613, | |
| "loss": 2.5465, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 0.0003116800549851798, | |
| "loss": 2.5352, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 0.0003108209115511835, | |
| "loss": 2.5377, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "eval_loss": 3.282806158065796, | |
| "eval_runtime": 69.9972, | |
| "eval_samples_per_second": 35.716, | |
| "eval_steps_per_second": 8.929, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.0003099617681171872, | |
| "loss": 2.5459, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 0.00030910262468319087, | |
| "loss": 2.5332, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 0.00030824348124919456, | |
| "loss": 2.5324, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 0.00030738433781519824, | |
| "loss": 2.5464, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 0.000306525194381202, | |
| "loss": 2.538, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 0.00030566605094720567, | |
| "loss": 2.5338, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 0.00030480690751320935, | |
| "loss": 2.5329, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.00030394776407921304, | |
| "loss": 2.5418, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 3.2688469886779785, | |
| "eval_runtime": 69.5754, | |
| "eval_samples_per_second": 35.932, | |
| "eval_steps_per_second": 8.983, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 0.0003030886206452167, | |
| "loss": 2.5293, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 0.0003022294772112204, | |
| "loss": 2.53, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 0.0003013703337772241, | |
| "loss": 2.5316, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 0.00030051119034322783, | |
| "loss": 2.5439, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 0.0002996520469092315, | |
| "loss": 2.5343, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002987929034752352, | |
| "loss": 2.5396, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 0.0002979337600412389, | |
| "loss": 2.5536, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.00029707461660724257, | |
| "loss": 2.5441, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_loss": 3.2687106132507324, | |
| "eval_runtime": 68.9594, | |
| "eval_samples_per_second": 36.253, | |
| "eval_steps_per_second": 9.063, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 0.00029621547317324625, | |
| "loss": 2.5359, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 0.00029535632973925, | |
| "loss": 2.5327, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 0.0002944971863052537, | |
| "loss": 2.5418, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 0.00029363804287125736, | |
| "loss": 2.5382, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 0.00029277889943726105, | |
| "loss": 2.529, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.00029191975600326473, | |
| "loss": 2.5239, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 0.0002910606125692684, | |
| "loss": 2.538, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 0.00029020146913527216, | |
| "loss": 2.5468, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_loss": 3.265432357788086, | |
| "eval_runtime": 70.53, | |
| "eval_samples_per_second": 35.446, | |
| "eval_steps_per_second": 8.861, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 2.77, | |
| "learning_rate": 0.00028934232570127584, | |
| "loss": 2.5357, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.0002884831822672795, | |
| "loss": 2.5266, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 2.81, | |
| "learning_rate": 0.00028762403883328326, | |
| "loss": 2.5329, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 0.00028676489539928695, | |
| "loss": 2.5356, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00028590575196529063, | |
| "loss": 2.5332, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 0.0002850466085312943, | |
| "loss": 2.531, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 0.000284187465097298, | |
| "loss": 2.5347, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 0.00028332832166330174, | |
| "loss": 2.545, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_loss": 3.2531003952026367, | |
| "eval_runtime": 69.6224, | |
| "eval_samples_per_second": 35.908, | |
| "eval_steps_per_second": 8.977, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 0.00028246917822930543, | |
| "loss": 2.5359, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 0.0002816100347953091, | |
| "loss": 2.5332, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "learning_rate": 0.0002807508913613128, | |
| "loss": 2.5355, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.0002798917479273165, | |
| "loss": 2.5359, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 0.00027903260449332017, | |
| "loss": 2.514, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 0.00027817346105932385, | |
| "loss": 2.5217, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.0002773143176253276, | |
| "loss": 2.5188, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 0.0002764551741913313, | |
| "loss": 2.5232, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "eval_loss": 3.2648589611053467, | |
| "eval_runtime": 69.9722, | |
| "eval_samples_per_second": 35.728, | |
| "eval_steps_per_second": 8.932, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 0.00027559603075733496, | |
| "loss": 2.51, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 0.00027473688732333865, | |
| "loss": 2.5234, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.00027387774388934233, | |
| "loss": 2.5139, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 0.000273018600455346, | |
| "loss": 2.5233, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 0.0002721594570213497, | |
| "loss": 2.5247, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 0.00027130031358735344, | |
| "loss": 2.5225, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 3.24, | |
| "learning_rate": 0.0002704411701533571, | |
| "loss": 2.528, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 0.0002695820267193608, | |
| "loss": 2.5187, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "eval_loss": 3.2556352615356445, | |
| "eval_runtime": 70.0453, | |
| "eval_samples_per_second": 35.691, | |
| "eval_steps_per_second": 8.923, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 0.0002687228832853645, | |
| "loss": 2.5246, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 0.0002678637398513682, | |
| "loss": 2.521, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 0.00026700459641737186, | |
| "loss": 2.5226, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 0.0002661454529833756, | |
| "loss": 2.5239, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 0.0002652863095493793, | |
| "loss": 2.5243, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 0.00026442716611538297, | |
| "loss": 2.5316, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 3.41, | |
| "learning_rate": 0.00026356802268138666, | |
| "loss": 2.531, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 0.00026270887924739034, | |
| "loss": 2.5125, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "eval_loss": 3.2571377754211426, | |
| "eval_runtime": 69.7633, | |
| "eval_samples_per_second": 35.835, | |
| "eval_steps_per_second": 8.959, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 0.000261849735813394, | |
| "loss": 2.5253, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 0.0002609905923793977, | |
| "loss": 2.5195, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 0.00026013144894540145, | |
| "loss": 2.5314, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 0.00025927230551140514, | |
| "loss": 2.5207, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "learning_rate": 0.0002584131620774088, | |
| "loss": 2.5342, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 0.0002575540186434125, | |
| "loss": 2.5344, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 0.00025669487520941624, | |
| "loss": 2.5287, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 0.00025583573177541993, | |
| "loss": 2.5225, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "eval_loss": 3.2613072395324707, | |
| "eval_runtime": 70.5525, | |
| "eval_samples_per_second": 35.435, | |
| "eval_steps_per_second": 8.859, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 3.63, | |
| "learning_rate": 0.0002549765883414236, | |
| "loss": 2.522, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 0.00025411744490742735, | |
| "loss": 2.5343, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "learning_rate": 0.00025325830147343104, | |
| "loss": 2.5234, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 3.69, | |
| "learning_rate": 0.0002523991580394347, | |
| "loss": 2.5293, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 0.0002515400146054384, | |
| "loss": 2.527, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 0.0002506808711714421, | |
| "loss": 2.5245, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.0002498217277374458, | |
| "loss": 2.529, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "learning_rate": 0.00024896258430344946, | |
| "loss": 2.5259, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "eval_loss": 3.2457616329193115, | |
| "eval_runtime": 69.6751, | |
| "eval_samples_per_second": 35.881, | |
| "eval_steps_per_second": 8.97, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 0.0002481034408694532, | |
| "loss": 2.5205, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 3.82, | |
| "learning_rate": 0.0002472442974354569, | |
| "loss": 2.5183, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 0.00024638515400146057, | |
| "loss": 2.5257, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 3.86, | |
| "learning_rate": 0.00024552601056746426, | |
| "loss": 2.5272, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 3.89, | |
| "learning_rate": 0.00024466686713346794, | |
| "loss": 2.5228, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 0.00024380772369947163, | |
| "loss": 2.5306, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 3.93, | |
| "learning_rate": 0.0002429485802654753, | |
| "loss": 2.5149, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 0.00024208943683147905, | |
| "loss": 2.5303, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "eval_loss": 3.2447612285614014, | |
| "eval_runtime": 78.9548, | |
| "eval_samples_per_second": 31.664, | |
| "eval_steps_per_second": 7.916, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 3.97, | |
| "learning_rate": 0.00024123029339748273, | |
| "loss": 2.5277, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "learning_rate": 0.00024037114996348642, | |
| "loss": 2.5204, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "learning_rate": 0.0002395120065294901, | |
| "loss": 2.5176, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 0.0002386528630954938, | |
| "loss": 2.5151, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 0.00023779371966149747, | |
| "loss": 2.5152, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "learning_rate": 0.0002369345762275012, | |
| "loss": 2.5124, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 0.0002360754327935049, | |
| "loss": 2.5208, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "learning_rate": 0.00023521628935950858, | |
| "loss": 2.5129, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 4.12, | |
| "eval_loss": 3.2467501163482666, | |
| "eval_runtime": 69.6325, | |
| "eval_samples_per_second": 35.903, | |
| "eval_steps_per_second": 8.976, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.00023435714592551227, | |
| "loss": 2.5189, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "learning_rate": 0.00023349800249151598, | |
| "loss": 2.5064, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 0.00023263885905751966, | |
| "loss": 2.5088, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.00023177971562352335, | |
| "loss": 2.5204, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 4.23, | |
| "learning_rate": 0.00023092057218952706, | |
| "loss": 2.523, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 0.00023006142875553077, | |
| "loss": 2.5147, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 0.00022920228532153446, | |
| "loss": 2.5034, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.00022834314188753814, | |
| "loss": 2.5081, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "eval_loss": 3.2460429668426514, | |
| "eval_runtime": 69.2535, | |
| "eval_samples_per_second": 36.099, | |
| "eval_steps_per_second": 9.025, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 0.00022748399845354183, | |
| "loss": 2.5043, | |
| "step": 100500 | |
| }, | |
| { | |
| "epoch": 4.34, | |
| "learning_rate": 0.0002266248550195455, | |
| "loss": 2.5175, | |
| "step": 101000 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.0002257657115855492, | |
| "loss": 2.5049, | |
| "step": 101500 | |
| }, | |
| { | |
| "epoch": 4.38, | |
| "learning_rate": 0.00022490656815155294, | |
| "loss": 2.5042, | |
| "step": 102000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 0.00022404742471755662, | |
| "loss": 2.5209, | |
| "step": 102500 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 0.0002231882812835603, | |
| "loss": 2.5175, | |
| "step": 103000 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.000222329137849564, | |
| "loss": 2.5228, | |
| "step": 103500 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "learning_rate": 0.00022146999441556767, | |
| "loss": 2.5198, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 4.47, | |
| "eval_loss": 3.2494592666625977, | |
| "eval_runtime": 70.2669, | |
| "eval_samples_per_second": 35.579, | |
| "eval_steps_per_second": 8.895, | |
| "step": 104000 | |
| }, | |
| { | |
| "epoch": 4.49, | |
| "learning_rate": 0.00022061085098157136, | |
| "loss": 2.5168, | |
| "step": 104500 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 0.00021975170754757507, | |
| "loss": 2.514, | |
| "step": 105000 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 0.00021889256411357878, | |
| "loss": 2.5276, | |
| "step": 105500 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 0.00021803342067958247, | |
| "loss": 2.5154, | |
| "step": 106000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 0.00021717427724558615, | |
| "loss": 2.5151, | |
| "step": 106500 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 0.00021631513381158987, | |
| "loss": 2.5186, | |
| "step": 107000 | |
| }, | |
| { | |
| "epoch": 4.62, | |
| "learning_rate": 0.00021545599037759355, | |
| "loss": 2.5236, | |
| "step": 107500 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 0.00021459684694359724, | |
| "loss": 2.5123, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "eval_loss": 3.2353665828704834, | |
| "eval_runtime": 69.8092, | |
| "eval_samples_per_second": 35.812, | |
| "eval_steps_per_second": 8.953, | |
| "step": 108000 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 0.00021373770350960092, | |
| "loss": 2.5078, | |
| "step": 108500 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 0.00021287856007560466, | |
| "loss": 2.5114, | |
| "step": 109000 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 0.00021201941664160834, | |
| "loss": 2.5164, | |
| "step": 109500 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "learning_rate": 0.00021116027320761203, | |
| "loss": 2.5136, | |
| "step": 110000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 0.0002103011297736157, | |
| "loss": 2.5181, | |
| "step": 110500 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "learning_rate": 0.0002094419863396194, | |
| "loss": 2.5091, | |
| "step": 111000 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 0.00020858284290562308, | |
| "loss": 2.4991, | |
| "step": 111500 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 0.00020772369947162677, | |
| "loss": 2.5035, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "eval_loss": 3.242424726486206, | |
| "eval_runtime": 70.3737, | |
| "eval_samples_per_second": 35.525, | |
| "eval_steps_per_second": 8.881, | |
| "step": 112000 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 0.0002068645560376305, | |
| "loss": 2.5244, | |
| "step": 112500 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 0.0002060054126036342, | |
| "loss": 2.5139, | |
| "step": 113000 | |
| }, | |
| { | |
| "epoch": 4.87, | |
| "learning_rate": 0.00020514626916963788, | |
| "loss": 2.5144, | |
| "step": 113500 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 0.00020428712573564156, | |
| "loss": 2.4944, | |
| "step": 114000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 0.00020342798230164525, | |
| "loss": 2.5014, | |
| "step": 114500 | |
| }, | |
| { | |
| "epoch": 4.94, | |
| "learning_rate": 0.00020256883886764896, | |
| "loss": 2.5067, | |
| "step": 115000 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 0.00020170969543365267, | |
| "loss": 2.5061, | |
| "step": 115500 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 0.00020085055199965636, | |
| "loss": 2.5177, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "eval_loss": 3.2430241107940674, | |
| "eval_runtime": 69.1442, | |
| "eval_samples_per_second": 36.156, | |
| "eval_steps_per_second": 9.039, | |
| "step": 116000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.00019999140856566007, | |
| "loss": 2.5116, | |
| "step": 116500 | |
| }, | |
| { | |
| "epoch": 5.02, | |
| "learning_rate": 0.00019913226513166375, | |
| "loss": 2.501, | |
| "step": 117000 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 0.00019827312169766744, | |
| "loss": 2.4926, | |
| "step": 117500 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 0.00019741397826367115, | |
| "loss": 2.4918, | |
| "step": 118000 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 0.00019655483482967483, | |
| "loss": 2.4971, | |
| "step": 118500 | |
| }, | |
| { | |
| "epoch": 5.11, | |
| "learning_rate": 0.00019569569139567852, | |
| "loss": 2.4957, | |
| "step": 119000 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "learning_rate": 0.0001948365479616822, | |
| "loss": 2.5049, | |
| "step": 119500 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 0.00019397740452768592, | |
| "loss": 2.4946, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "eval_loss": 3.233226776123047, | |
| "eval_runtime": 69.9335, | |
| "eval_samples_per_second": 35.748, | |
| "eval_steps_per_second": 8.937, | |
| "step": 120000 | |
| }, | |
| { | |
| "epoch": 5.17, | |
| "learning_rate": 0.0001931182610936896, | |
| "loss": 2.5004, | |
| "step": 120500 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 0.00019225911765969328, | |
| "loss": 2.5101, | |
| "step": 121000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 0.000191399974225697, | |
| "loss": 2.4973, | |
| "step": 121500 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "learning_rate": 0.00019054083079170068, | |
| "loss": 2.5075, | |
| "step": 122000 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 0.00018968168735770437, | |
| "loss": 2.503, | |
| "step": 122500 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 0.00018882254392370805, | |
| "loss": 2.5034, | |
| "step": 123000 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 0.00018796340048971176, | |
| "loss": 2.5022, | |
| "step": 123500 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "learning_rate": 0.00018710425705571545, | |
| "loss": 2.501, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "eval_loss": 3.242777109146118, | |
| "eval_runtime": 69.4476, | |
| "eval_samples_per_second": 35.998, | |
| "eval_steps_per_second": 9.0, | |
| "step": 124000 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 0.00018624511362171916, | |
| "loss": 2.5108, | |
| "step": 124500 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 0.00018538597018772284, | |
| "loss": 2.5104, | |
| "step": 125000 | |
| }, | |
| { | |
| "epoch": 5.39, | |
| "learning_rate": 0.00018452682675372656, | |
| "loss": 2.5043, | |
| "step": 125500 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "learning_rate": 0.00018366768331973024, | |
| "loss": 2.5205, | |
| "step": 126000 | |
| }, | |
| { | |
| "epoch": 5.43, | |
| "learning_rate": 0.00018280853988573395, | |
| "loss": 2.4971, | |
| "step": 126500 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 0.00018194939645173764, | |
| "loss": 2.5098, | |
| "step": 127000 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 0.00018109025301774132, | |
| "loss": 2.5088, | |
| "step": 127500 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 0.000180231109583745, | |
| "loss": 2.4968, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "eval_loss": 3.2393054962158203, | |
| "eval_runtime": 70.4742, | |
| "eval_samples_per_second": 35.474, | |
| "eval_steps_per_second": 8.868, | |
| "step": 128000 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 0.00017937196614974872, | |
| "loss": 2.5051, | |
| "step": 128500 | |
| }, | |
| { | |
| "epoch": 5.54, | |
| "learning_rate": 0.0001785128227157524, | |
| "loss": 2.5041, | |
| "step": 129000 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 0.0001776536792817561, | |
| "loss": 2.5002, | |
| "step": 129500 | |
| }, | |
| { | |
| "epoch": 5.58, | |
| "learning_rate": 0.0001767945358477598, | |
| "loss": 2.5095, | |
| "step": 130000 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 0.0001759353924137635, | |
| "loss": 2.5044, | |
| "step": 130500 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 0.00017507624897976717, | |
| "loss": 2.508, | |
| "step": 131000 | |
| }, | |
| { | |
| "epoch": 5.65, | |
| "learning_rate": 0.00017421710554577086, | |
| "loss": 2.5052, | |
| "step": 131500 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 0.00017335796211177457, | |
| "loss": 2.5086, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "eval_loss": 3.2350261211395264, | |
| "eval_runtime": 70.6424, | |
| "eval_samples_per_second": 35.39, | |
| "eval_steps_per_second": 8.847, | |
| "step": 132000 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "learning_rate": 0.00017249881867777825, | |
| "loss": 2.5015, | |
| "step": 132500 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.00017163967524378194, | |
| "loss": 2.5, | |
| "step": 133000 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "learning_rate": 0.00017078053180978565, | |
| "loss": 2.5026, | |
| "step": 133500 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 0.00016992138837578933, | |
| "loss": 2.4933, | |
| "step": 134000 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 0.00016906224494179305, | |
| "loss": 2.5079, | |
| "step": 134500 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 0.00016820310150779676, | |
| "loss": 2.4959, | |
| "step": 135000 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 0.00016734395807380044, | |
| "loss": 2.5109, | |
| "step": 135500 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "learning_rate": 0.00016648481463980413, | |
| "loss": 2.5091, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 5.84, | |
| "eval_loss": 3.2328109741210938, | |
| "eval_runtime": 70.9654, | |
| "eval_samples_per_second": 35.228, | |
| "eval_steps_per_second": 8.807, | |
| "step": 136000 | |
| }, | |
| { | |
| "epoch": 5.86, | |
| "learning_rate": 0.0001656256712058078, | |
| "loss": 2.4965, | |
| "step": 136500 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 0.00016476652777181152, | |
| "loss": 2.509, | |
| "step": 137000 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 0.0001639073843378152, | |
| "loss": 2.5055, | |
| "step": 137500 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 0.0001630482409038189, | |
| "loss": 2.5145, | |
| "step": 138000 | |
| }, | |
| { | |
| "epoch": 5.95, | |
| "learning_rate": 0.0001621890974698226, | |
| "loss": 2.5099, | |
| "step": 138500 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 0.0001613299540358263, | |
| "loss": 2.497, | |
| "step": 139000 | |
| }, | |
| { | |
| "epoch": 5.99, | |
| "learning_rate": 0.00016047081060182998, | |
| "loss": 2.4981, | |
| "step": 139500 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 0.00015961166716783366, | |
| "loss": 2.4972, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "eval_loss": 3.2302370071411133, | |
| "eval_runtime": 71.0669, | |
| "eval_samples_per_second": 35.178, | |
| "eval_steps_per_second": 8.795, | |
| "step": 140000 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "learning_rate": 0.00015875252373383737, | |
| "loss": 2.4869, | |
| "step": 140500 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 0.00015789338029984106, | |
| "loss": 2.5036, | |
| "step": 141000 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 0.00015703423686584474, | |
| "loss": 2.4872, | |
| "step": 141500 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 0.00015617509343184845, | |
| "loss": 2.4802, | |
| "step": 142000 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 0.00015531594999785214, | |
| "loss": 2.4812, | |
| "step": 142500 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 0.00015445680656385585, | |
| "loss": 2.486, | |
| "step": 143000 | |
| }, | |
| { | |
| "epoch": 6.16, | |
| "learning_rate": 0.00015359766312985954, | |
| "loss": 2.5004, | |
| "step": 143500 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 0.00015273851969586325, | |
| "loss": 2.496, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "eval_loss": 3.224409341812134, | |
| "eval_runtime": 69.085, | |
| "eval_samples_per_second": 36.187, | |
| "eval_steps_per_second": 9.047, | |
| "step": 144000 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 0.00015187937626186693, | |
| "loss": 2.4869, | |
| "step": 144500 | |
| }, | |
| { | |
| "epoch": 6.23, | |
| "learning_rate": 0.00015102023282787062, | |
| "loss": 2.5018, | |
| "step": 145000 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 0.00015016108939387433, | |
| "loss": 2.5033, | |
| "step": 145500 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 0.00014930194595987801, | |
| "loss": 2.4944, | |
| "step": 146000 | |
| }, | |
| { | |
| "epoch": 6.29, | |
| "learning_rate": 0.0001484428025258817, | |
| "loss": 2.4889, | |
| "step": 146500 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 0.0001475836590918854, | |
| "loss": 2.4913, | |
| "step": 147000 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "learning_rate": 0.0001467245156578891, | |
| "loss": 2.5018, | |
| "step": 147500 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "learning_rate": 0.00014586537222389278, | |
| "loss": 2.4943, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 6.35, | |
| "eval_loss": 3.2242684364318848, | |
| "eval_runtime": 70.9743, | |
| "eval_samples_per_second": 35.224, | |
| "eval_steps_per_second": 8.806, | |
| "step": 148000 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "learning_rate": 0.00014500622878989647, | |
| "loss": 2.5, | |
| "step": 148500 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 0.00014414708535590018, | |
| "loss": 2.4994, | |
| "step": 149000 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 0.00014328794192190386, | |
| "loss": 2.4986, | |
| "step": 149500 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 0.00014242879848790755, | |
| "loss": 2.4934, | |
| "step": 150000 | |
| }, | |
| { | |
| "epoch": 6.46, | |
| "learning_rate": 0.00014156965505391126, | |
| "loss": 2.4887, | |
| "step": 150500 | |
| }, | |
| { | |
| "epoch": 6.48, | |
| "learning_rate": 0.00014071051161991494, | |
| "loss": 2.4922, | |
| "step": 151000 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "learning_rate": 0.00013985136818591863, | |
| "loss": 2.4943, | |
| "step": 151500 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 0.00013899222475192234, | |
| "loss": 2.491, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "eval_loss": 3.220249652862549, | |
| "eval_runtime": 70.6987, | |
| "eval_samples_per_second": 35.361, | |
| "eval_steps_per_second": 8.84, | |
| "step": 152000 | |
| }, | |
| { | |
| "epoch": 6.55, | |
| "learning_rate": 0.00013813308131792603, | |
| "loss": 2.4967, | |
| "step": 152500 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 0.00013727393788392974, | |
| "loss": 2.4959, | |
| "step": 153000 | |
| }, | |
| { | |
| "epoch": 6.59, | |
| "learning_rate": 0.00013641479444993342, | |
| "loss": 2.4777, | |
| "step": 153500 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "learning_rate": 0.00013555565101593713, | |
| "loss": 2.4931, | |
| "step": 154000 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 0.00013469650758194082, | |
| "loss": 2.497, | |
| "step": 154500 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 0.0001338373641479445, | |
| "loss": 2.4964, | |
| "step": 155000 | |
| }, | |
| { | |
| "epoch": 6.68, | |
| "learning_rate": 0.00013297822071394822, | |
| "loss": 2.4959, | |
| "step": 155500 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 0.0001321190772799519, | |
| "loss": 2.4913, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "eval_loss": 3.2231602668762207, | |
| "eval_runtime": 70.5445, | |
| "eval_samples_per_second": 35.439, | |
| "eval_steps_per_second": 8.86, | |
| "step": 156000 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 0.00013125993384595559, | |
| "loss": 2.4955, | |
| "step": 156500 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "learning_rate": 0.00013040079041195927, | |
| "loss": 2.4916, | |
| "step": 157000 | |
| }, | |
| { | |
| "epoch": 6.76, | |
| "learning_rate": 0.00012954164697796298, | |
| "loss": 2.4898, | |
| "step": 157500 | |
| }, | |
| { | |
| "epoch": 6.78, | |
| "learning_rate": 0.00012868250354396667, | |
| "loss": 2.5014, | |
| "step": 158000 | |
| }, | |
| { | |
| "epoch": 6.81, | |
| "learning_rate": 0.00012782336010997035, | |
| "loss": 2.4953, | |
| "step": 158500 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 0.00012696421667597406, | |
| "loss": 2.5013, | |
| "step": 159000 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 0.00012610507324197775, | |
| "loss": 2.5066, | |
| "step": 159500 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 0.00012524592980798143, | |
| "loss": 2.4968, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "eval_loss": 3.2243635654449463, | |
| "eval_runtime": 70.4612, | |
| "eval_samples_per_second": 35.481, | |
| "eval_steps_per_second": 8.87, | |
| "step": 160000 | |
| }, | |
| { | |
| "epoch": 6.89, | |
| "learning_rate": 0.00012438678637398515, | |
| "loss": 2.5027, | |
| "step": 160500 | |
| }, | |
| { | |
| "epoch": 6.91, | |
| "learning_rate": 0.00012352764293998883, | |
| "loss": 2.4855, | |
| "step": 161000 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "learning_rate": 0.00012266849950599252, | |
| "loss": 2.4915, | |
| "step": 161500 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "learning_rate": 0.00012180935607199621, | |
| "loss": 2.5066, | |
| "step": 162000 | |
| }, | |
| { | |
| "epoch": 6.98, | |
| "learning_rate": 0.00012095021263799993, | |
| "loss": 2.4947, | |
| "step": 162500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 0.00012009106920400361, | |
| "loss": 2.4971, | |
| "step": 163000 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "learning_rate": 0.0001192319257700073, | |
| "loss": 2.4976, | |
| "step": 163500 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 0.00011837278233601101, | |
| "loss": 2.4854, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "eval_loss": 3.2264649868011475, | |
| "eval_runtime": 69.9835, | |
| "eval_samples_per_second": 35.723, | |
| "eval_steps_per_second": 8.931, | |
| "step": 164000 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "learning_rate": 0.0001175136389020147, | |
| "loss": 2.4712, | |
| "step": 164500 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 0.00011665449546801839, | |
| "loss": 2.4761, | |
| "step": 165000 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 0.00011579535203402208, | |
| "loss": 2.4873, | |
| "step": 165500 | |
| }, | |
| { | |
| "epoch": 7.13, | |
| "learning_rate": 0.00011493620860002579, | |
| "loss": 2.4862, | |
| "step": 166000 | |
| }, | |
| { | |
| "epoch": 7.15, | |
| "learning_rate": 0.00011407706516602947, | |
| "loss": 2.4801, | |
| "step": 166500 | |
| }, | |
| { | |
| "epoch": 7.17, | |
| "learning_rate": 0.00011321792173203316, | |
| "loss": 2.4785, | |
| "step": 167000 | |
| }, | |
| { | |
| "epoch": 7.19, | |
| "learning_rate": 0.00011235877829803687, | |
| "loss": 2.4861, | |
| "step": 167500 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "learning_rate": 0.00011149963486404055, | |
| "loss": 2.4865, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 7.21, | |
| "eval_loss": 3.221519947052002, | |
| "eval_runtime": 70.7932, | |
| "eval_samples_per_second": 35.314, | |
| "eval_steps_per_second": 8.829, | |
| "step": 168000 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 0.00011064049143004425, | |
| "loss": 2.4908, | |
| "step": 168500 | |
| }, | |
| { | |
| "epoch": 7.26, | |
| "learning_rate": 0.00010978134799604795, | |
| "loss": 2.4814, | |
| "step": 169000 | |
| }, | |
| { | |
| "epoch": 7.28, | |
| "learning_rate": 0.00010892220456205165, | |
| "loss": 2.4759, | |
| "step": 169500 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 0.00010806306112805533, | |
| "loss": 2.495, | |
| "step": 170000 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "learning_rate": 0.00010720391769405902, | |
| "loss": 2.4837, | |
| "step": 170500 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "learning_rate": 0.00010634477426006273, | |
| "loss": 2.4946, | |
| "step": 171000 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 0.00010548563082606642, | |
| "loss": 2.4762, | |
| "step": 171500 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 0.0001046264873920701, | |
| "loss": 2.4854, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "eval_loss": 3.220597982406616, | |
| "eval_runtime": 69.1381, | |
| "eval_samples_per_second": 36.159, | |
| "eval_steps_per_second": 9.04, | |
| "step": 172000 | |
| }, | |
| { | |
| "epoch": 7.41, | |
| "learning_rate": 0.00010376734395807381, | |
| "loss": 2.4899, | |
| "step": 172500 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "learning_rate": 0.0001029082005240775, | |
| "loss": 2.486, | |
| "step": 173000 | |
| }, | |
| { | |
| "epoch": 7.45, | |
| "learning_rate": 0.0001020490570900812, | |
| "loss": 2.4792, | |
| "step": 173500 | |
| }, | |
| { | |
| "epoch": 7.47, | |
| "learning_rate": 0.00010118991365608488, | |
| "loss": 2.4907, | |
| "step": 174000 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 0.00010033077022208859, | |
| "loss": 2.486, | |
| "step": 174500 | |
| }, | |
| { | |
| "epoch": 7.51, | |
| "learning_rate": 9.947162678809228e-05, | |
| "loss": 2.4801, | |
| "step": 175000 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 9.861248335409598e-05, | |
| "loss": 2.4931, | |
| "step": 175500 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 9.775333992009966e-05, | |
| "loss": 2.4853, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "eval_loss": 3.2134642601013184, | |
| "eval_runtime": 70.239, | |
| "eval_samples_per_second": 35.593, | |
| "eval_steps_per_second": 8.898, | |
| "step": 176000 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 9.689419648610336e-05, | |
| "loss": 2.4821, | |
| "step": 176500 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 9.603505305210704e-05, | |
| "loss": 2.4801, | |
| "step": 177000 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 9.517590961811074e-05, | |
| "loss": 2.4888, | |
| "step": 177500 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "learning_rate": 9.431676618411444e-05, | |
| "loss": 2.4847, | |
| "step": 178000 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 9.345762275011814e-05, | |
| "loss": 2.4929, | |
| "step": 178500 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 9.259847931612184e-05, | |
| "loss": 2.4911, | |
| "step": 179000 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 9.173933588212552e-05, | |
| "loss": 2.4881, | |
| "step": 179500 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "learning_rate": 9.088019244812922e-05, | |
| "loss": 2.4894, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 7.73, | |
| "eval_loss": 3.2165322303771973, | |
| "eval_runtime": 70.2927, | |
| "eval_samples_per_second": 35.566, | |
| "eval_steps_per_second": 8.891, | |
| "step": 180000 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 9.002104901413292e-05, | |
| "loss": 2.4906, | |
| "step": 180500 | |
| }, | |
| { | |
| "epoch": 7.77, | |
| "learning_rate": 8.91619055801366e-05, | |
| "loss": 2.4783, | |
| "step": 181000 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 8.83027621461403e-05, | |
| "loss": 2.4734, | |
| "step": 181500 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "learning_rate": 8.744361871214399e-05, | |
| "loss": 2.4803, | |
| "step": 182000 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 8.658447527814769e-05, | |
| "loss": 2.489, | |
| "step": 182500 | |
| }, | |
| { | |
| "epoch": 7.86, | |
| "learning_rate": 8.572533184415138e-05, | |
| "loss": 2.4844, | |
| "step": 183000 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 8.486618841015508e-05, | |
| "loss": 2.4934, | |
| "step": 183500 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 8.400704497615878e-05, | |
| "loss": 2.4811, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "eval_loss": 3.214756727218628, | |
| "eval_runtime": 70.5306, | |
| "eval_samples_per_second": 35.446, | |
| "eval_steps_per_second": 8.861, | |
| "step": 184000 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 8.314790154216247e-05, | |
| "loss": 2.4828, | |
| "step": 184500 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "learning_rate": 8.228875810816616e-05, | |
| "loss": 2.4778, | |
| "step": 185000 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 8.142961467416985e-05, | |
| "loss": 2.4866, | |
| "step": 185500 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 8.057047124017355e-05, | |
| "loss": 2.4847, | |
| "step": 186000 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 7.971132780617725e-05, | |
| "loss": 2.4715, | |
| "step": 186500 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "learning_rate": 7.885218437218093e-05, | |
| "loss": 2.4782, | |
| "step": 187000 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 7.799304093818464e-05, | |
| "loss": 2.4781, | |
| "step": 187500 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 7.713389750418833e-05, | |
| "loss": 2.4789, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "eval_loss": 3.2158737182617188, | |
| "eval_runtime": 71.443, | |
| "eval_samples_per_second": 34.993, | |
| "eval_steps_per_second": 8.748, | |
| "step": 188000 | |
| }, | |
| { | |
| "epoch": 8.09, | |
| "learning_rate": 7.627475407019203e-05, | |
| "loss": 2.4867, | |
| "step": 188500 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "learning_rate": 7.541561063619572e-05, | |
| "loss": 2.4799, | |
| "step": 189000 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 7.455646720219941e-05, | |
| "loss": 2.4779, | |
| "step": 189500 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 7.369732376820311e-05, | |
| "loss": 2.4703, | |
| "step": 190000 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 7.283818033420679e-05, | |
| "loss": 2.4715, | |
| "step": 190500 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 7.197903690021049e-05, | |
| "loss": 2.4754, | |
| "step": 191000 | |
| }, | |
| { | |
| "epoch": 8.22, | |
| "learning_rate": 7.111989346621419e-05, | |
| "loss": 2.4819, | |
| "step": 191500 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "learning_rate": 7.026075003221789e-05, | |
| "loss": 2.4768, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 8.24, | |
| "eval_loss": 3.2115867137908936, | |
| "eval_runtime": 70.9666, | |
| "eval_samples_per_second": 35.228, | |
| "eval_steps_per_second": 8.807, | |
| "step": 192000 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 6.940160659822159e-05, | |
| "loss": 2.4697, | |
| "step": 192500 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 6.854246316422527e-05, | |
| "loss": 2.4843, | |
| "step": 193000 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 6.768331973022897e-05, | |
| "loss": 2.484, | |
| "step": 193500 | |
| }, | |
| { | |
| "epoch": 8.33, | |
| "learning_rate": 6.682417629623265e-05, | |
| "loss": 2.4753, | |
| "step": 194000 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "learning_rate": 6.596503286223635e-05, | |
| "loss": 2.4827, | |
| "step": 194500 | |
| }, | |
| { | |
| "epoch": 8.37, | |
| "learning_rate": 6.510588942824005e-05, | |
| "loss": 2.4798, | |
| "step": 195000 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "learning_rate": 6.424674599424374e-05, | |
| "loss": 2.4785, | |
| "step": 195500 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 6.338760256024743e-05, | |
| "loss": 2.4832, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "eval_loss": 3.2087242603302, | |
| "eval_runtime": 70.623, | |
| "eval_samples_per_second": 35.399, | |
| "eval_steps_per_second": 8.85, | |
| "step": 196000 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 6.252845912625113e-05, | |
| "loss": 2.4944, | |
| "step": 196500 | |
| }, | |
| { | |
| "epoch": 8.46, | |
| "learning_rate": 6.166931569225483e-05, | |
| "loss": 2.4881, | |
| "step": 197000 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 6.081017225825852e-05, | |
| "loss": 2.4742, | |
| "step": 197500 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 5.9951028824262214e-05, | |
| "loss": 2.478, | |
| "step": 198000 | |
| }, | |
| { | |
| "epoch": 8.52, | |
| "learning_rate": 5.909188539026591e-05, | |
| "loss": 2.4703, | |
| "step": 198500 | |
| }, | |
| { | |
| "epoch": 8.54, | |
| "learning_rate": 5.82327419562696e-05, | |
| "loss": 2.479, | |
| "step": 199000 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 5.7373598522273295e-05, | |
| "loss": 2.4808, | |
| "step": 199500 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "learning_rate": 5.651445508827699e-05, | |
| "loss": 2.4774, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 8.59, | |
| "eval_loss": 3.211932420730591, | |
| "eval_runtime": 70.6236, | |
| "eval_samples_per_second": 35.399, | |
| "eval_steps_per_second": 8.85, | |
| "step": 200000 | |
| }, | |
| { | |
| "epoch": 8.61, | |
| "learning_rate": 5.5655311654280685e-05, | |
| "loss": 2.4699, | |
| "step": 200500 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 5.4796168220284384e-05, | |
| "loss": 2.4727, | |
| "step": 201000 | |
| }, | |
| { | |
| "epoch": 8.65, | |
| "learning_rate": 5.393702478628807e-05, | |
| "loss": 2.4784, | |
| "step": 201500 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "learning_rate": 5.307788135229177e-05, | |
| "loss": 2.4695, | |
| "step": 202000 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 5.221873791829546e-05, | |
| "loss": 2.4829, | |
| "step": 202500 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "learning_rate": 5.135959448429916e-05, | |
| "loss": 2.4752, | |
| "step": 203000 | |
| }, | |
| { | |
| "epoch": 8.74, | |
| "learning_rate": 5.0500451050302855e-05, | |
| "loss": 2.4781, | |
| "step": 203500 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "learning_rate": 4.964130761630654e-05, | |
| "loss": 2.4748, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "eval_loss": 3.210552453994751, | |
| "eval_runtime": 69.9859, | |
| "eval_samples_per_second": 35.721, | |
| "eval_steps_per_second": 8.93, | |
| "step": 204000 | |
| }, | |
| { | |
| "epoch": 8.78, | |
| "learning_rate": 4.878216418231024e-05, | |
| "loss": 2.474, | |
| "step": 204500 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 4.792302074831394e-05, | |
| "loss": 2.463, | |
| "step": 205000 | |
| }, | |
| { | |
| "epoch": 8.82, | |
| "learning_rate": 4.706387731431763e-05, | |
| "loss": 2.4736, | |
| "step": 205500 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "learning_rate": 4.620473388032132e-05, | |
| "loss": 2.4883, | |
| "step": 206000 | |
| }, | |
| { | |
| "epoch": 8.87, | |
| "learning_rate": 4.534559044632501e-05, | |
| "loss": 2.4745, | |
| "step": 206500 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 4.448644701232871e-05, | |
| "loss": 2.4775, | |
| "step": 207000 | |
| }, | |
| { | |
| "epoch": 8.91, | |
| "learning_rate": 4.362730357833241e-05, | |
| "loss": 2.4785, | |
| "step": 207500 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 4.27681601443361e-05, | |
| "loss": 2.472, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "eval_loss": 3.2094578742980957, | |
| "eval_runtime": 70.3513, | |
| "eval_samples_per_second": 35.536, | |
| "eval_steps_per_second": 8.884, | |
| "step": 208000 | |
| }, | |
| { | |
| "epoch": 8.95, | |
| "learning_rate": 4.190901671033979e-05, | |
| "loss": 2.4694, | |
| "step": 208500 | |
| }, | |
| { | |
| "epoch": 8.97, | |
| "learning_rate": 4.1049873276343484e-05, | |
| "loss": 2.4754, | |
| "step": 209000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.019072984234718e-05, | |
| "loss": 2.4789, | |
| "step": 209500 | |
| }, | |
| { | |
| "epoch": 9.02, | |
| "learning_rate": 3.9331586408350874e-05, | |
| "loss": 2.4632, | |
| "step": 210000 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "learning_rate": 3.847244297435457e-05, | |
| "loss": 2.4676, | |
| "step": 210500 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 3.7613299540358264e-05, | |
| "loss": 2.4675, | |
| "step": 211000 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "learning_rate": 3.675415610636196e-05, | |
| "loss": 2.4588, | |
| "step": 211500 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 3.5895012672365654e-05, | |
| "loss": 2.4749, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "eval_loss": 3.204545497894287, | |
| "eval_runtime": 69.8241, | |
| "eval_samples_per_second": 35.804, | |
| "eval_steps_per_second": 8.951, | |
| "step": 212000 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 3.5035869238369345e-05, | |
| "loss": 2.4771, | |
| "step": 212500 | |
| }, | |
| { | |
| "epoch": 9.15, | |
| "learning_rate": 3.4176725804373044e-05, | |
| "loss": 2.4606, | |
| "step": 213000 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "learning_rate": 3.3317582370376735e-05, | |
| "loss": 2.4672, | |
| "step": 213500 | |
| }, | |
| { | |
| "epoch": 9.19, | |
| "learning_rate": 3.2458438936380434e-05, | |
| "loss": 2.4725, | |
| "step": 214000 | |
| }, | |
| { | |
| "epoch": 9.21, | |
| "learning_rate": 3.1599295502384125e-05, | |
| "loss": 2.4669, | |
| "step": 214500 | |
| }, | |
| { | |
| "epoch": 9.23, | |
| "learning_rate": 3.074015206838782e-05, | |
| "loss": 2.4674, | |
| "step": 215000 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 2.9881008634391512e-05, | |
| "loss": 2.4661, | |
| "step": 215500 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "learning_rate": 2.902186520039521e-05, | |
| "loss": 2.4722, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "eval_loss": 3.2078707218170166, | |
| "eval_runtime": 69.832, | |
| "eval_samples_per_second": 35.8, | |
| "eval_steps_per_second": 8.95, | |
| "step": 216000 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 2.8162721766398902e-05, | |
| "loss": 2.474, | |
| "step": 216500 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "learning_rate": 2.7303578332402597e-05, | |
| "loss": 2.4714, | |
| "step": 217000 | |
| }, | |
| { | |
| "epoch": 9.34, | |
| "learning_rate": 2.644443489840629e-05, | |
| "loss": 2.465, | |
| "step": 217500 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "learning_rate": 2.5585291464409983e-05, | |
| "loss": 2.4691, | |
| "step": 218000 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "learning_rate": 2.472614803041368e-05, | |
| "loss": 2.4803, | |
| "step": 218500 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 2.3867004596417373e-05, | |
| "loss": 2.4742, | |
| "step": 219000 | |
| }, | |
| { | |
| "epoch": 9.42, | |
| "learning_rate": 2.300786116242107e-05, | |
| "loss": 2.4675, | |
| "step": 219500 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "learning_rate": 2.214871772842476e-05, | |
| "loss": 2.4707, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "eval_loss": 3.203800678253174, | |
| "eval_runtime": 69.9274, | |
| "eval_samples_per_second": 35.751, | |
| "eval_steps_per_second": 8.938, | |
| "step": 220000 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 2.1289574294428455e-05, | |
| "loss": 2.4683, | |
| "step": 220500 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 2.043043086043215e-05, | |
| "loss": 2.4674, | |
| "step": 221000 | |
| }, | |
| { | |
| "epoch": 9.51, | |
| "learning_rate": 1.9571287426435845e-05, | |
| "loss": 2.4748, | |
| "step": 221500 | |
| }, | |
| { | |
| "epoch": 9.53, | |
| "learning_rate": 1.8712143992439537e-05, | |
| "loss": 2.462, | |
| "step": 222000 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 1.7853000558443235e-05, | |
| "loss": 2.4709, | |
| "step": 222500 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 1.6993857124446927e-05, | |
| "loss": 2.4593, | |
| "step": 223000 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 1.6134713690450622e-05, | |
| "loss": 2.4553, | |
| "step": 223500 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "learning_rate": 1.5275570256454317e-05, | |
| "loss": 2.4683, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 9.62, | |
| "eval_loss": 3.205549478530884, | |
| "eval_runtime": 69.3247, | |
| "eval_samples_per_second": 36.062, | |
| "eval_steps_per_second": 9.016, | |
| "step": 224000 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "learning_rate": 1.441642682245801e-05, | |
| "loss": 2.4676, | |
| "step": 224500 | |
| }, | |
| { | |
| "epoch": 9.66, | |
| "learning_rate": 1.3557283388461705e-05, | |
| "loss": 2.4728, | |
| "step": 225000 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 1.2698139954465398e-05, | |
| "loss": 2.468, | |
| "step": 225500 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 1.1838996520469092e-05, | |
| "loss": 2.4725, | |
| "step": 226000 | |
| }, | |
| { | |
| "epoch": 9.73, | |
| "learning_rate": 1.0979853086472787e-05, | |
| "loss": 2.4756, | |
| "step": 226500 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 1.0120709652476482e-05, | |
| "loss": 2.4708, | |
| "step": 227000 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "learning_rate": 9.261566218480177e-06, | |
| "loss": 2.4695, | |
| "step": 227500 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "learning_rate": 8.40242278448387e-06, | |
| "loss": 2.4601, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 9.79, | |
| "eval_loss": 3.203986406326294, | |
| "eval_runtime": 70.61, | |
| "eval_samples_per_second": 35.406, | |
| "eval_steps_per_second": 8.851, | |
| "step": 228000 | |
| }, | |
| { | |
| "epoch": 9.81, | |
| "learning_rate": 7.543279350487564e-06, | |
| "loss": 2.4745, | |
| "step": 228500 | |
| }, | |
| { | |
| "epoch": 9.83, | |
| "learning_rate": 6.684135916491259e-06, | |
| "loss": 2.4692, | |
| "step": 229000 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 5.824992482494953e-06, | |
| "loss": 2.4679, | |
| "step": 229500 | |
| }, | |
| { | |
| "epoch": 9.88, | |
| "learning_rate": 4.965849048498647e-06, | |
| "loss": 2.4675, | |
| "step": 230000 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 4.106705614502342e-06, | |
| "loss": 2.4678, | |
| "step": 230500 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 3.2475621805060358e-06, | |
| "loss": 2.4679, | |
| "step": 231000 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "learning_rate": 2.38841874650973e-06, | |
| "loss": 2.4683, | |
| "step": 231500 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "learning_rate": 1.529275312513424e-06, | |
| "loss": 2.4613, | |
| "step": 232000 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "eval_loss": 3.2050249576568604, | |
| "eval_runtime": 69.6048, | |
| "eval_samples_per_second": 35.917, | |
| "eval_steps_per_second": 8.979, | |
| "step": 232000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 232890, | |
| "num_train_epochs": 10, | |
| "save_steps": 8000, | |
| "total_flos": 5.270438359850582e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |