| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 60361, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9585825284538036e-05, | |
| "loss": 3.214, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.917165056907606e-05, | |
| "loss": 3.135, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.8757475853614095e-05, | |
| "loss": 3.0685, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.834330113815212e-05, | |
| "loss": 2.9915, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.792912642269015e-05, | |
| "loss": 2.9904, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.7514951707228175e-05, | |
| "loss": 2.9511, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.710077699176621e-05, | |
| "loss": 3.4783, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.6686602276304234e-05, | |
| "loss": 3.6374, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.627242756084227e-05, | |
| "loss": 3.5449, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.5858252845380294e-05, | |
| "loss": 3.4766, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_gen_len": 512.0, | |
| "eval_loss": 3.423976182937622, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 33489.752, | |
| "eval_samples_per_second": 0.1, | |
| "eval_steps_per_second": 0.1, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.544407812991833e-05, | |
| "loss": 3.4597, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.502990341445636e-05, | |
| "loss": 3.4448, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.461572869899439e-05, | |
| "loss": 3.4208, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.420155398353242e-05, | |
| "loss": 3.3875, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.378737926807045e-05, | |
| "loss": 3.353, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.337320455260847e-05, | |
| "loss": 3.3374, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.29590298371465e-05, | |
| "loss": 3.3529, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.254485512168453e-05, | |
| "loss": 3.3346, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.213068040622256e-05, | |
| "loss": 3.3373, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.171650569076059e-05, | |
| "loss": 3.2549, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_gen_len": 512.0, | |
| "eval_loss": 3.290836811065674, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 35051.5686, | |
| "eval_samples_per_second": 0.096, | |
| "eval_steps_per_second": 0.096, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.130233097529862e-05, | |
| "loss": 3.278, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.088815625983665e-05, | |
| "loss": 3.296, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.047398154437468e-05, | |
| "loss": 3.2679, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.005980682891271e-05, | |
| "loss": 3.2592, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.9645632113450745e-05, | |
| "loss": 3.2258, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.923145739798877e-05, | |
| "loss": 3.2517, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.88172826825268e-05, | |
| "loss": 3.2308, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.8403107967064825e-05, | |
| "loss": 3.2478, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.798893325160286e-05, | |
| "loss": 3.2494, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.7574758536140885e-05, | |
| "loss": 3.2295, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_gen_len": 512.0, | |
| "eval_loss": 3.1861765384674072, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 33590.4082, | |
| "eval_samples_per_second": 0.1, | |
| "eval_steps_per_second": 0.1, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.716058382067892e-05, | |
| "loss": 3.255, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.6746409105216944e-05, | |
| "loss": 3.2286, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.633223438975498e-05, | |
| "loss": 3.2272, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.5918059674293004e-05, | |
| "loss": 3.1344, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.550388495883104e-05, | |
| "loss": 3.183, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.508971024336907e-05, | |
| "loss": 3.1636, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.46755355279071e-05, | |
| "loss": 3.2012, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.4261360812445123e-05, | |
| "loss": 3.1692, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.384718609698315e-05, | |
| "loss": 3.1662, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.343301138152118e-05, | |
| "loss": 3.1455, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_gen_len": 512.0, | |
| "eval_loss": 3.1290640830993652, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 33228.1925, | |
| "eval_samples_per_second": 0.101, | |
| "eval_steps_per_second": 0.101, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.301883666605921e-05, | |
| "loss": 3.1712, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.260466195059724e-05, | |
| "loss": 3.1635, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.219048723513527e-05, | |
| "loss": 3.1245, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.17763125196733e-05, | |
| "loss": 3.1126, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.136213780421133e-05, | |
| "loss": 3.1048, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.094796308874936e-05, | |
| "loss": 3.0999, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.053378837328739e-05, | |
| "loss": 3.0668, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.011961365782542e-05, | |
| "loss": 3.1067, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9705438942363452e-05, | |
| "loss": 3.1002, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.929126422690148e-05, | |
| "loss": 3.0526, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_gen_len": 512.0, | |
| "eval_loss": 3.0683774948120117, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 33776.1312, | |
| "eval_samples_per_second": 0.099, | |
| "eval_steps_per_second": 0.099, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.8877089511439508e-05, | |
| "loss": 3.0995, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8462914795977535e-05, | |
| "loss": 3.0783, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.8048740080515568e-05, | |
| "loss": 3.0942, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.7634565365053594e-05, | |
| "loss": 3.0476, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.7220390649591628e-05, | |
| "loss": 3.0406, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.6806215934129654e-05, | |
| "loss": 3.0502, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.6392041218667684e-05, | |
| "loss": 3.0155, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.597786650320571e-05, | |
| "loss": 3.0567, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.5563691787743744e-05, | |
| "loss": 2.9966, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.5149517072281774e-05, | |
| "loss": 3.0024, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_gen_len": 512.0, | |
| "eval_loss": 3.0133895874023438, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 33411.4705, | |
| "eval_samples_per_second": 0.1, | |
| "eval_steps_per_second": 0.1, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.47353423568198e-05, | |
| "loss": 3.0206, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.432116764135783e-05, | |
| "loss": 3.0544, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.390699292589586e-05, | |
| "loss": 3.0369, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.349281821043389e-05, | |
| "loss": 3.0274, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.307864349497192e-05, | |
| "loss": 2.9874, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.266446877950995e-05, | |
| "loss": 2.987, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.225029406404798e-05, | |
| "loss": 3.0012, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.183611934858601e-05, | |
| "loss": 3.0, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.142194463312404e-05, | |
| "loss": 3.0094, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.100776991766207e-05, | |
| "loss": 2.9671, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_gen_len": 512.0, | |
| "eval_loss": 2.9696106910705566, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 34950.6467, | |
| "eval_samples_per_second": 0.096, | |
| "eval_steps_per_second": 0.096, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.05935952022001e-05, | |
| "loss": 3.0045, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.0179420486738125e-05, | |
| "loss": 2.9679, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.9765245771276155e-05, | |
| "loss": 2.9779, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.9351071055814185e-05, | |
| "loss": 2.9329, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.8936896340352215e-05, | |
| "loss": 2.9559, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.8522721624890245e-05, | |
| "loss": 2.9192, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.8108546909428274e-05, | |
| "loss": 2.9561, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7694372193966304e-05, | |
| "loss": 2.9513, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7280197478504334e-05, | |
| "loss": 2.9413, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.6866022763042364e-05, | |
| "loss": 2.9862, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_gen_len": 512.0, | |
| "eval_loss": 2.9430978298187256, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 34028.0479, | |
| "eval_samples_per_second": 0.099, | |
| "eval_steps_per_second": 0.099, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.6451848047580394e-05, | |
| "loss": 2.954, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.603767333211842e-05, | |
| "loss": 2.8837, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.562349861665645e-05, | |
| "loss": 2.9123, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.520932390119448e-05, | |
| "loss": 2.9279, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.479514918573251e-05, | |
| "loss": 2.9545, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.438097447027054e-05, | |
| "loss": 2.9532, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.3966799754808568e-05, | |
| "loss": 2.8969, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3552625039346598e-05, | |
| "loss": 2.9036, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.3138450323884628e-05, | |
| "loss": 2.9632, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.272427560842266e-05, | |
| "loss": 2.9168, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_gen_len": 512.0, | |
| "eval_loss": 2.8988711833953857, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 33486.9056, | |
| "eval_samples_per_second": 0.1, | |
| "eval_steps_per_second": 0.1, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2310100892960687e-05, | |
| "loss": 2.8766, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.1895926177498716e-05, | |
| "loss": 2.8882, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.1481751462036747e-05, | |
| "loss": 2.8865, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.1067576746574775e-05, | |
| "loss": 2.9103, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0653402031112805e-05, | |
| "loss": 2.9249, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.0239227315650835e-05, | |
| "loss": 2.8929, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 9.825052600188863e-06, | |
| "loss": 2.8976, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 9.410877884726893e-06, | |
| "loss": 2.836, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 8.996703169264925e-06, | |
| "loss": 2.8391, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 8.582528453802953e-06, | |
| "loss": 2.9063, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_gen_len": 512.0, | |
| "eval_loss": 2.8559486865997314, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 33629.3949, | |
| "eval_samples_per_second": 0.1, | |
| "eval_steps_per_second": 0.1, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.168353738340983e-06, | |
| "loss": 2.8414, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 7.75417902287901e-06, | |
| "loss": 2.9115, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.3400043074170406e-06, | |
| "loss": 2.8717, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.9258295919550704e-06, | |
| "loss": 2.8795, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 6.5116548764931e-06, | |
| "loss": 2.8756, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 6.09748016103113e-06, | |
| "loss": 2.8803, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.683305445569159e-06, | |
| "loss": 2.8836, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 5.269130730107188e-06, | |
| "loss": 2.8006, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.854956014645219e-06, | |
| "loss": 2.8351, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.440781299183248e-06, | |
| "loss": 2.8417, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_gen_len": 512.0, | |
| "eval_loss": 2.8397700786590576, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 33806.5515, | |
| "eval_samples_per_second": 0.099, | |
| "eval_steps_per_second": 0.099, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 4.026606583721277e-06, | |
| "loss": 2.8479, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.6124318682593068e-06, | |
| "loss": 2.819, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 3.198257152797336e-06, | |
| "loss": 2.8276, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.784082437335366e-06, | |
| "loss": 2.8281, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 2.369907721873395e-06, | |
| "loss": 2.8357, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.955733006411425e-06, | |
| "loss": 2.8233, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.5415582909494541e-06, | |
| "loss": 2.8692, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.1273835754874836e-06, | |
| "loss": 2.8224, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 7.132088600255132e-07, | |
| "loss": 2.8211, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.9903414456354266e-07, | |
| "loss": 2.7853, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_gen_len": 512.0, | |
| "eval_loss": 2.824021816253662, | |
| "eval_rouge1": 0.0, | |
| "eval_rouge2": 0.0, | |
| "eval_rougeL": 0.0, | |
| "eval_rougeLsum": 0.0, | |
| "eval_runtime": 33244.3107, | |
| "eval_samples_per_second": 0.101, | |
| "eval_steps_per_second": 0.101, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 60361, | |
| "total_flos": 1.4376309178343424e+17, | |
| "train_loss": 3.0559221936556717, | |
| "train_runtime": 448912.3672, | |
| "train_samples_per_second": 0.134, | |
| "train_steps_per_second": 0.134 | |
| } | |
| ], | |
| "max_steps": 60361, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.4376309178343424e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |