| { | |
| "best_metric": 0.7626183364552219, | |
| "best_model_checkpoint": "robertabase-subjectivity-1-actual/checkpoint-40000", | |
| "epoch": 2.0, | |
| "global_step": 40000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.875750000000001e-06, | |
| "loss": 0.6845, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 9.751250000000001e-06, | |
| "loss": 0.6182, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.6265e-06, | |
| "loss": 0.6045, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.501500000000002e-06, | |
| "loss": 0.6057, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.3765e-06, | |
| "loss": 0.5845, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.251500000000001e-06, | |
| "loss": 0.5819, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.1265e-06, | |
| "loss": 0.6158, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 9.00175e-06, | |
| "loss": 0.5941, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.876750000000001e-06, | |
| "loss": 0.5953, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.751750000000001e-06, | |
| "loss": 0.5965, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 8.62675e-06, | |
| "loss": 0.6077, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.50175e-06, | |
| "loss": 0.5663, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 8.37675e-06, | |
| "loss": 0.5649, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 8.251750000000001e-06, | |
| "loss": 0.6021, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 8.126750000000001e-06, | |
| "loss": 0.5803, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.00175e-06, | |
| "loss": 0.5851, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 7.877000000000001e-06, | |
| "loss": 0.5872, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.752000000000001e-06, | |
| "loss": 0.5597, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.6272500000000005e-06, | |
| "loss": 0.5764, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 7.502250000000001e-06, | |
| "loss": 0.5588, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 7.37725e-06, | |
| "loss": 0.5993, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 7.252250000000001e-06, | |
| "loss": 0.5873, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 7.127250000000001e-06, | |
| "loss": 0.5928, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.002500000000001e-06, | |
| "loss": 0.5655, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 6.877500000000001e-06, | |
| "loss": 0.5705, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 6.752500000000001e-06, | |
| "loss": 0.5528, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 6.6275e-06, | |
| "loss": 0.59, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.502500000000001e-06, | |
| "loss": 0.5587, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 6.377500000000001e-06, | |
| "loss": 0.5601, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 6.2525e-06, | |
| "loss": 0.5804, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 6.127500000000001e-06, | |
| "loss": 0.5639, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 6.0025e-06, | |
| "loss": 0.5722, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 5.8775e-06, | |
| "loss": 0.5601, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 5.752500000000001e-06, | |
| "loss": 0.5758, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 5.6275e-06, | |
| "loss": 0.5648, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 5.5025e-06, | |
| "loss": 0.5723, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 5.37775e-06, | |
| "loss": 0.5714, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 5.252750000000001e-06, | |
| "loss": 0.5639, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 5.128000000000001e-06, | |
| "loss": 0.5499, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5.003e-06, | |
| "loss": 0.5463, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7495, | |
| "eval_f1": 0.7516359309934564, | |
| "eval_loss": 0.564261257648468, | |
| "eval_runtime": 133.9593, | |
| "eval_samples_per_second": 149.299, | |
| "eval_steps_per_second": 37.325, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 4.8780000000000006e-06, | |
| "loss": 0.5198, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.753e-06, | |
| "loss": 0.566, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.62825e-06, | |
| "loss": 0.5717, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.5035e-06, | |
| "loss": 0.5588, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 4.3785000000000005e-06, | |
| "loss": 0.5626, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.2535e-06, | |
| "loss": 0.5428, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 4.1285e-06, | |
| "loss": 0.575, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.0035e-06, | |
| "loss": 0.5605, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.8785e-06, | |
| "loss": 0.5632, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.7535000000000006e-06, | |
| "loss": 0.6156, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.6285000000000005e-06, | |
| "loss": 0.5611, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.5035000000000004e-06, | |
| "loss": 0.564, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.37875e-06, | |
| "loss": 0.6065, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.2537500000000004e-06, | |
| "loss": 0.593, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 3.1287500000000003e-06, | |
| "loss": 0.6235, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 3.0037500000000003e-06, | |
| "loss": 0.5948, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.87875e-06, | |
| "loss": 0.5809, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 2.754e-06, | |
| "loss": 0.5674, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.6292500000000003e-06, | |
| "loss": 0.6117, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.50425e-06, | |
| "loss": 0.6033, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.3795000000000003e-06, | |
| "loss": 0.612, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.2545e-06, | |
| "loss": 0.616, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.1295e-06, | |
| "loss": 0.6101, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.0045e-06, | |
| "loss": 0.5966, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 1.8795000000000002e-06, | |
| "loss": 0.5791, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 1.7545e-06, | |
| "loss": 0.5769, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 1.6295000000000002e-06, | |
| "loss": 0.5649, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 1.5045000000000002e-06, | |
| "loss": 0.569, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 1.3795e-06, | |
| "loss": 0.5982, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 1.2545000000000002e-06, | |
| "loss": 0.5422, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.1295e-06, | |
| "loss": 0.5664, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.0045e-06, | |
| "loss": 0.6063, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 8.795000000000001e-07, | |
| "loss": 0.5577, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 7.545000000000001e-07, | |
| "loss": 0.5846, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 6.297500000000001e-07, | |
| "loss": 0.5746, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 5.0475e-07, | |
| "loss": 0.6285, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 3.7975000000000005e-07, | |
| "loss": 0.6408, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 2.5475000000000003e-07, | |
| "loss": 0.5656, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 1.3e-07, | |
| "loss": 0.622, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 5e-09, | |
| "loss": 0.6327, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.76555, | |
| "eval_f1": 0.7626183364552219, | |
| "eval_loss": 0.7705514430999756, | |
| "eval_runtime": 133.8772, | |
| "eval_samples_per_second": 149.391, | |
| "eval_steps_per_second": 37.348, | |
| "step": 40000 | |
| } | |
| ], | |
| "max_steps": 40000, | |
| "num_train_epochs": 2, | |
| "total_flos": 1.289539965645768e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |