| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 8.706251088281386, | |
| "global_step": 100000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00010077567264729574, | |
| "loss": 0.5253, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00010075889723559493, | |
| "loss": 0.5001, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00010073092788158004, | |
| "loss": 0.4909, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00010069177148627061, | |
| "loss": 0.4848, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001006414377109213, | |
| "loss": 0.4811, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00010057993897463803, | |
| "loss": 0.4761, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00010050729045131372, | |
| "loss": 0.4736, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00010042351006588448, | |
| "loss": 0.4712, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00010032861848990674, | |
| "loss": 0.4694, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00010022263913645699, | |
| "loss": 0.4675, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 0.4460357427597046, | |
| "eval_runtime": 24.6462, | |
| "eval_samples_per_second": 202.871, | |
| "eval_steps_per_second": 3.205, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00010010559815435491, | |
| "loss": 0.4647, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 9.997779155931062e-05, | |
| "loss": 0.4633, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.983873864536092e-05, | |
| "loss": 0.4633, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.968871882446063e-05, | |
| "loss": 0.4599, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 9.952776911175577e-05, | |
| "loss": 0.4583, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.935592921917959e-05, | |
| "loss": 0.459, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 9.91732415456543e-05, | |
| "loss": 0.4574, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 9.897975116662973e-05, | |
| "loss": 0.4571, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.877550582296162e-05, | |
| "loss": 0.456, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 9.856099645730841e-05, | |
| "loss": 0.4546, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": 0.43266522884368896, | |
| "eval_runtime": 17.119, | |
| "eval_samples_per_second": 292.073, | |
| "eval_steps_per_second": 4.615, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 9.833541625738316e-05, | |
| "loss": 0.4531, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 9.809972296167543e-05, | |
| "loss": 0.4531, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.785303008093405e-05, | |
| "loss": 0.4522, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.759586023711756e-05, | |
| "loss": 0.4504, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 9.732827688303682e-05, | |
| "loss": 0.4503, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 9.705034604088048e-05, | |
| "loss": 0.4485, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 9.676213628592508e-05, | |
| "loss": 0.448, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 9.64637187296151e-05, | |
| "loss": 0.4487, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 9.615579416918834e-05, | |
| "loss": 0.4475, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 9.583720443927501e-05, | |
| "loss": 0.4468, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "eval_loss": 0.4257063567638397, | |
| "eval_runtime": 17.0089, | |
| "eval_samples_per_second": 293.963, | |
| "eval_steps_per_second": 4.645, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 9.550863512110018e-05, | |
| "loss": 0.4464, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.517016728422667e-05, | |
| "loss": 0.4457, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 9.482188444052858e-05, | |
| "loss": 0.4437, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 9.446387252358614e-05, | |
| "loss": 0.4443, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 9.40962198674828e-05, | |
| "loss": 0.4441, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 9.371901718501017e-05, | |
| "loss": 0.4438, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 9.333314023958391e-05, | |
| "loss": 0.4421, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 9.293713767144707e-05, | |
| "loss": 0.4415, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 9.253187106312908e-05, | |
| "loss": 0.442, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 9.211744040810141e-05, | |
| "loss": 0.441, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_loss": 0.4204435646533966, | |
| "eval_runtime": 18.5947, | |
| "eval_samples_per_second": 268.894, | |
| "eval_steps_per_second": 4.249, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 9.169480392040811e-05, | |
| "loss": 0.4408, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 9.126237198035999e-05, | |
| "loss": 0.441, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 9.082108922350493e-05, | |
| "loss": 0.4382, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 9.037106452976014e-05, | |
| "loss": 0.439, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 8.991240893598493e-05, | |
| "loss": 0.4387, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.944617837966915e-05, | |
| "loss": 0.4385, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 8.897157870163552e-05, | |
| "loss": 0.4385, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 8.848872653432954e-05, | |
| "loss": 0.4373, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 8.799674851241666e-05, | |
| "loss": 0.4363, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 8.749672541742298e-05, | |
| "loss": 0.4355, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "eval_loss": 0.41616591811180115, | |
| "eval_runtime": 16.3301, | |
| "eval_samples_per_second": 306.184, | |
| "eval_steps_per_second": 4.838, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 8.698878062256518e-05, | |
| "loss": 0.4355, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 8.647303945562088e-05, | |
| "loss": 0.4346, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 8.594962916800582e-05, | |
| "loss": 0.435, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 8.54186789033765e-05, | |
| "loss": 0.434, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 8.488031966576593e-05, | |
| "loss": 0.4341, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 8.433468428726034e-05, | |
| "loss": 0.4341, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 8.378190739522489e-05, | |
| "loss": 0.4336, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.322212537908629e-05, | |
| "loss": 0.4323, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 8.265547635668083e-05, | |
| "loss": 0.4331, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 8.208325351258954e-05, | |
| "loss": 0.4318, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "eval_loss": 0.4114779233932495, | |
| "eval_runtime": 17.3867, | |
| "eval_samples_per_second": 287.576, | |
| "eval_steps_per_second": 4.544, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 8.150447097896683e-05, | |
| "loss": 0.431, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 8.091809189852956e-05, | |
| "loss": 0.4312, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 8.032541429761075e-05, | |
| "loss": 0.4306, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 7.972778811233862e-05, | |
| "loss": 0.4306, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 7.912296555205017e-05, | |
| "loss": 0.431, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 7.851228739184511e-05, | |
| "loss": 0.4298, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 7.789590430742172e-05, | |
| "loss": 0.4291, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 7.727396838208297e-05, | |
| "loss": 0.4302, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.664663306921218e-05, | |
| "loss": 0.4291, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 7.601405315441079e-05, | |
| "loss": 0.4289, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "eval_loss": 0.4092726707458496, | |
| "eval_runtime": 16.8388, | |
| "eval_samples_per_second": 296.933, | |
| "eval_steps_per_second": 4.692, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 7.537638471730726e-05, | |
| "loss": 0.4281, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.473378509304684e-05, | |
| "loss": 0.426, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "learning_rate": 7.408641283347138e-05, | |
| "loss": 0.4266, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 3.22, | |
| "learning_rate": 7.343442766799908e-05, | |
| "loss": 0.4269, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "learning_rate": 7.27779904642137e-05, | |
| "loss": 0.4266, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 7.211726318817271e-05, | |
| "loss": 0.427, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 7.145240886444487e-05, | |
| "loss": 0.4254, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 7.078493301609684e-05, | |
| "loss": 0.4262, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "learning_rate": 7.011232513402331e-05, | |
| "loss": 0.4264, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "learning_rate": 6.943744088754813e-05, | |
| "loss": 0.4258, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 3.48, | |
| "eval_loss": 0.4074101150035858, | |
| "eval_runtime": 18.107, | |
| "eval_samples_per_second": 276.137, | |
| "eval_steps_per_second": 4.363, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 6.875774190311069e-05, | |
| "loss": 0.4253, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 3.57, | |
| "learning_rate": 6.807474478259389e-05, | |
| "loss": 0.424, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 6.738861804531726e-05, | |
| "loss": 0.4239, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 6.669953098278655e-05, | |
| "loss": 0.4241, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 6.600904004302253e-05, | |
| "loss": 0.4238, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 3.74, | |
| "learning_rate": 6.531454815259442e-05, | |
| "loss": 0.4225, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 6.461760768262325e-05, | |
| "loss": 0.4229, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 6.391839059274147e-05, | |
| "loss": 0.4238, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 6.321706940430336e-05, | |
| "loss": 0.421, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 6.25138171578181e-05, | |
| "loss": 0.4225, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_loss": 0.4011038839817047, | |
| "eval_runtime": 17.3314, | |
| "eval_samples_per_second": 288.494, | |
| "eval_steps_per_second": 4.558, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 6.18088073702545e-05, | |
| "loss": 0.4225, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.110221399222838e-05, | |
| "loss": 0.4211, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "learning_rate": 6.039562866071103e-05, | |
| "loss": 0.4213, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 5.9686393768070895e-05, | |
| "loss": 0.4207, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 5.897752048973475e-05, | |
| "loss": 0.4193, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 5.826634261264905e-05, | |
| "loss": 0.4192, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "learning_rate": 5.7554455195272715e-05, | |
| "loss": 0.4193, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "learning_rate": 5.684203388517376e-05, | |
| "loss": 0.418, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "learning_rate": 5.6129254461650316e-05, | |
| "loss": 0.4176, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 5.541629279235954e-05, | |
| "loss": 0.4185, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "eval_loss": 0.39864614605903625, | |
| "eval_runtime": 17.3653, | |
| "eval_samples_per_second": 287.93, | |
| "eval_steps_per_second": 4.549, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 5.470332478992507e-05, | |
| "loss": 0.4189, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 5.399052636853316e-05, | |
| "loss": 0.418, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 5.327807340052843e-05, | |
| "loss": 0.4174, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 4.53, | |
| "learning_rate": 5.25661416730201e-05, | |
| "loss": 0.4178, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 5.18563285019876e-05, | |
| "loss": 0.4172, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 4.61, | |
| "learning_rate": 5.114738388115157e-05, | |
| "loss": 0.4166, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 5.043806455560185e-05, | |
| "loss": 0.4175, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 4.972996720023507e-05, | |
| "loss": 0.4169, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 4.90232665274781e-05, | |
| "loss": 0.4159, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "learning_rate": 4.8318136905147416e-05, | |
| "loss": 0.4163, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 4.79, | |
| "eval_loss": 0.3956509530544281, | |
| "eval_runtime": 17.4712, | |
| "eval_samples_per_second": 286.186, | |
| "eval_steps_per_second": 4.522, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 4.83, | |
| "learning_rate": 4.7616157225640255e-05, | |
| "loss": 0.4173, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 4.88, | |
| "learning_rate": 4.6914687204096124e-05, | |
| "loss": 0.4152, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 4.92, | |
| "learning_rate": 4.621530849337495e-05, | |
| "loss": 0.4153, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 4.5518193654708575e-05, | |
| "loss": 0.4156, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "learning_rate": 4.48235146907523e-05, | |
| "loss": 0.4149, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 4.413282443085026e-05, | |
| "loss": 0.4138, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 4.344352505188909e-05, | |
| "loss": 0.4138, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "learning_rate": 4.2757173441071825e-05, | |
| "loss": 0.4129, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 4.2073938945388334e-05, | |
| "loss": 0.4128, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 4.1393990142726966e-05, | |
| "loss": 0.4133, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "eval_loss": 0.3932584524154663, | |
| "eval_runtime": 17.6982, | |
| "eval_samples_per_second": 282.515, | |
| "eval_steps_per_second": 4.464, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 5.27, | |
| "learning_rate": 4.071884423332296e-05, | |
| "loss": 0.4123, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 5.31, | |
| "learning_rate": 4.00459618594495e-05, | |
| "loss": 0.4122, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 5.35, | |
| "learning_rate": 3.937686555159882e-05, | |
| "loss": 0.4123, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 3.8711720399273034e-05, | |
| "loss": 0.4123, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 3.805069051708565e-05, | |
| "loss": 0.4118, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 5.48, | |
| "learning_rate": 3.739524812959698e-05, | |
| "loss": 0.4118, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "learning_rate": 3.6742927987935615e-05, | |
| "loss": 0.4116, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 5.57, | |
| "learning_rate": 3.6095208886480486e-05, | |
| "loss": 0.411, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 5.62, | |
| "learning_rate": 3.545225064022787e-05, | |
| "loss": 0.4113, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "learning_rate": 3.481548295250678e-05, | |
| "loss": 0.4111, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 5.66, | |
| "eval_loss": 0.3913000226020813, | |
| "eval_runtime": 16.5881, | |
| "eval_samples_per_second": 301.422, | |
| "eval_steps_per_second": 4.762, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 3.418251081369709e-05, | |
| "loss": 0.4107, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 3.355602161294165e-05, | |
| "loss": 0.4103, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 5.79, | |
| "learning_rate": 3.293365900004924e-05, | |
| "loss": 0.4095, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "learning_rate": 3.231683730748652e-05, | |
| "loss": 0.41, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 5.88, | |
| "learning_rate": 3.170570872677642e-05, | |
| "loss": 0.4084, | |
| "step": 67500 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 3.110042404475174e-05, | |
| "loss": 0.4091, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "learning_rate": 3.050113260635069e-05, | |
| "loss": 0.409, | |
| "step": 68500 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 2.990798227776831e-05, | |
| "loss": 0.4088, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 6.05, | |
| "learning_rate": 2.9321119409972645e-05, | |
| "loss": 0.4083, | |
| "step": 69500 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "learning_rate": 2.8740688802594957e-05, | |
| "loss": 0.4079, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 6.09, | |
| "eval_loss": 0.3888770639896393, | |
| "eval_runtime": 17.0838, | |
| "eval_samples_per_second": 292.674, | |
| "eval_steps_per_second": 4.624, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 6.14, | |
| "learning_rate": 2.8166833668202425e-05, | |
| "loss": 0.4067, | |
| "step": 70500 | |
| }, | |
| { | |
| "epoch": 6.18, | |
| "learning_rate": 2.759969559696268e-05, | |
| "loss": 0.4077, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 2.703941452170851e-05, | |
| "loss": 0.408, | |
| "step": 71500 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 2.648722818281383e-05, | |
| "loss": 0.4066, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 2.594105969789391e-05, | |
| "loss": 0.4067, | |
| "step": 72500 | |
| }, | |
| { | |
| "epoch": 6.36, | |
| "learning_rate": 2.5402157452548983e-05, | |
| "loss": 0.4072, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 2.487065441284431e-05, | |
| "loss": 0.4074, | |
| "step": 73500 | |
| }, | |
| { | |
| "epoch": 6.44, | |
| "learning_rate": 2.434772206306137e-05, | |
| "loss": 0.4067, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 2.3831393550873072e-05, | |
| "loss": 0.4066, | |
| "step": 74500 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "learning_rate": 2.3322851806813925e-05, | |
| "loss": 0.4065, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 6.53, | |
| "eval_loss": 0.38793495297431946, | |
| "eval_runtime": 17.4149, | |
| "eval_samples_per_second": 287.111, | |
| "eval_steps_per_second": 4.536, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 2.282222230594981e-05, | |
| "loss": 0.4061, | |
| "step": 75500 | |
| }, | |
| { | |
| "epoch": 6.62, | |
| "learning_rate": 2.2329628571118985e-05, | |
| "loss": 0.4064, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 6.66, | |
| "learning_rate": 2.1845192142454672e-05, | |
| "loss": 0.4056, | |
| "step": 76500 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 2.1369976527875413e-05, | |
| "loss": 0.4055, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 2.0902194347163136e-05, | |
| "loss": 0.4048, | |
| "step": 77500 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 2.0442921670652984e-05, | |
| "loss": 0.4054, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "learning_rate": 1.999227181700563e-05, | |
| "loss": 0.4054, | |
| "step": 78500 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 1.9551231019628344e-05, | |
| "loss": 0.4043, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 6.92, | |
| "learning_rate": 1.9118140436571432e-05, | |
| "loss": 0.4051, | |
| "step": 79500 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "learning_rate": 1.869399954632371e-05, | |
| "loss": 0.4044, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "eval_loss": 0.38538074493408203, | |
| "eval_runtime": 17.7787, | |
| "eval_samples_per_second": 281.235, | |
| "eval_steps_per_second": 4.444, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 1.8278912999303293e-05, | |
| "loss": 0.4046, | |
| "step": 80500 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 1.7873785866083376e-05, | |
| "loss": 0.4039, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 1.747709438313117e-05, | |
| "loss": 0.4041, | |
| "step": 81500 | |
| }, | |
| { | |
| "epoch": 7.14, | |
| "learning_rate": 1.7089757496546325e-05, | |
| "loss": 0.4029, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 7.18, | |
| "learning_rate": 1.671187077590979e-05, | |
| "loss": 0.4031, | |
| "step": 82500 | |
| }, | |
| { | |
| "epoch": 7.23, | |
| "learning_rate": 1.6343527459115402e-05, | |
| "loss": 0.404, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 7.27, | |
| "learning_rate": 1.5985526173180873e-05, | |
| "loss": 0.4021, | |
| "step": 83500 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 1.563652040423561e-05, | |
| "loss": 0.4028, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 1.5297323365745916e-05, | |
| "loss": 0.4028, | |
| "step": 84500 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 1.496801874950552e-05, | |
| "loss": 0.403, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "eval_loss": 0.3836823105812073, | |
| "eval_runtime": 17.7691, | |
| "eval_samples_per_second": 281.388, | |
| "eval_steps_per_second": 4.446, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 7.44, | |
| "learning_rate": 1.4648687806501003e-05, | |
| "loss": 0.4022, | |
| "step": 85500 | |
| }, | |
| { | |
| "epoch": 7.49, | |
| "learning_rate": 1.433940932686429e-05, | |
| "loss": 0.4029, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 7.53, | |
| "learning_rate": 1.4040847761852026e-05, | |
| "loss": 0.403, | |
| "step": 86500 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "learning_rate": 1.3752447867532768e-05, | |
| "loss": 0.403, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 7.62, | |
| "learning_rate": 1.3473733388145289e-05, | |
| "loss": 0.4027, | |
| "step": 87500 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "learning_rate": 1.3205361274547104e-05, | |
| "loss": 0.4016, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 1.2947397743541538e-05, | |
| "loss": 0.4024, | |
| "step": 88500 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 1.2699906443769858e-05, | |
| "loss": 0.4025, | |
| "step": 89000 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 1.2462948440006997e-05, | |
| "loss": 0.4016, | |
| "step": 89500 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 1.2236582198094697e-05, | |
| "loss": 0.403, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "eval_loss": 0.38297703862190247, | |
| "eval_runtime": 16.5367, | |
| "eval_samples_per_second": 302.358, | |
| "eval_steps_per_second": 4.777, | |
| "step": 90000 | |
| }, | |
| { | |
| "epoch": 7.88, | |
| "learning_rate": 1.2020863570515961e-05, | |
| "loss": 0.4009, | |
| "step": 90500 | |
| }, | |
| { | |
| "epoch": 7.92, | |
| "learning_rate": 1.1815845782614282e-05, | |
| "loss": 0.4028, | |
| "step": 91000 | |
| }, | |
| { | |
| "epoch": 7.97, | |
| "learning_rate": 1.162157941946108e-05, | |
| "loss": 0.4015, | |
| "step": 91500 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "learning_rate": 1.1438112413374588e-05, | |
| "loss": 0.4016, | |
| "step": 92000 | |
| }, | |
| { | |
| "epoch": 8.05, | |
| "learning_rate": 1.1265490032093274e-05, | |
| "loss": 0.4015, | |
| "step": 92500 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 1.1103754867606732e-05, | |
| "loss": 0.4009, | |
| "step": 93000 | |
| }, | |
| { | |
| "epoch": 8.14, | |
| "learning_rate": 1.0953237511280449e-05, | |
| "loss": 0.4, | |
| "step": 93500 | |
| }, | |
| { | |
| "epoch": 8.18, | |
| "learning_rate": 1.0813640603098685e-05, | |
| "loss": 0.4012, | |
| "step": 94000 | |
| }, | |
| { | |
| "epoch": 8.23, | |
| "learning_rate": 1.0684751669305436e-05, | |
| "loss": 0.4014, | |
| "step": 94500 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "learning_rate": 1.0566893240808188e-05, | |
| "loss": 0.3998, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 8.27, | |
| "eval_loss": 0.38168150186538696, | |
| "eval_runtime": 17.1028, | |
| "eval_samples_per_second": 292.35, | |
| "eval_steps_per_second": 4.619, | |
| "step": 95000 | |
| }, | |
| { | |
| "epoch": 8.31, | |
| "learning_rate": 1.0460094397410629e-05, | |
| "loss": 0.4004, | |
| "step": 95500 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 1.0364381490129294e-05, | |
| "loss": 0.4006, | |
| "step": 96000 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 1.0279778134691878e-05, | |
| "loss": 0.4007, | |
| "step": 96500 | |
| }, | |
| { | |
| "epoch": 8.45, | |
| "learning_rate": 1.0206441030895691e-05, | |
| "loss": 0.4001, | |
| "step": 97000 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "learning_rate": 1.0144094343341912e-05, | |
| "loss": 0.4005, | |
| "step": 97500 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "learning_rate": 1.0092911560189286e-05, | |
| "loss": 0.3995, | |
| "step": 98000 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 1.0052905310023697e-05, | |
| "loss": 0.401, | |
| "step": 98500 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "learning_rate": 1.0024085463788748e-05, | |
| "loss": 0.4002, | |
| "step": 99000 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 1.0006483210534733e-05, | |
| "loss": 0.4, | |
| "step": 99500 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "learning_rate": 1.0000032344694547e-05, | |
| "loss": 0.3999, | |
| "step": 100000 | |
| }, | |
| { | |
| "epoch": 8.71, | |
| "eval_loss": 0.3816235363483429, | |
| "eval_runtime": 41.2453, | |
| "eval_samples_per_second": 121.226, | |
| "eval_steps_per_second": 1.915, | |
| "step": 100000 | |
| } | |
| ], | |
| "max_steps": 100000, | |
| "num_train_epochs": 9, | |
| "total_flos": 4.7097123842386664e+21, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |