| { | |
| "best_metric": 0.717391304347826, | |
| "best_model_checkpoint": "swiftformer-xs-DMAE\\checkpoint-66", | |
| "epoch": 34.285714285714285, | |
| "eval_steps": 500, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.86, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 1.370601773262024, | |
| "eval_runtime": 0.6692, | |
| "eval_samples_per_second": 68.744, | |
| "eval_steps_per_second": 4.483, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 1.1519584655761719, | |
| "eval_runtime": 0.6777, | |
| "eval_samples_per_second": 67.88, | |
| "eval_steps_per_second": 4.427, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.004166666666666667, | |
| "loss": 1.2948, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 1.293420433998108, | |
| "eval_runtime": 0.6372, | |
| "eval_samples_per_second": 72.195, | |
| "eval_steps_per_second": 4.708, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 1.213881254196167, | |
| "eval_runtime": 0.8102, | |
| "eval_samples_per_second": 56.775, | |
| "eval_steps_per_second": 3.703, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "eval_accuracy": 0.5217391304347826, | |
| "eval_loss": 2.594619035720825, | |
| "eval_runtime": 0.6367, | |
| "eval_samples_per_second": 72.253, | |
| "eval_steps_per_second": 4.712, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 5.71, | |
| "learning_rate": 0.004629629629629629, | |
| "loss": 1.1888, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4782608695652174, | |
| "eval_loss": 1.121720314025879, | |
| "eval_runtime": 0.6392, | |
| "eval_samples_per_second": 71.969, | |
| "eval_steps_per_second": 4.694, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 6.86, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 1.1050187349319458, | |
| "eval_runtime": 0.6016, | |
| "eval_samples_per_second": 76.458, | |
| "eval_steps_per_second": 4.986, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.391304347826087, | |
| "eval_loss": 1.6684364080429077, | |
| "eval_runtime": 0.6072, | |
| "eval_samples_per_second": 75.764, | |
| "eval_steps_per_second": 4.941, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 8.57, | |
| "learning_rate": 0.004166666666666667, | |
| "loss": 1.1236, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 8.86, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8967575430870056, | |
| "eval_runtime": 0.6271, | |
| "eval_samples_per_second": 73.349, | |
| "eval_steps_per_second": 4.784, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5652173913043478, | |
| "eval_loss": 1.2403887510299683, | |
| "eval_runtime": 0.6136, | |
| "eval_samples_per_second": 74.962, | |
| "eval_steps_per_second": 4.889, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 10.86, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.9956691861152649, | |
| "eval_runtime": 0.6206, | |
| "eval_samples_per_second": 74.116, | |
| "eval_steps_per_second": 4.834, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 11.43, | |
| "learning_rate": 0.0037037037037037034, | |
| "loss": 1.0477, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5, | |
| "eval_loss": 1.169378399848938, | |
| "eval_runtime": 0.6266, | |
| "eval_samples_per_second": 73.407, | |
| "eval_steps_per_second": 4.787, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 12.86, | |
| "eval_accuracy": 0.6956521739130435, | |
| "eval_loss": 0.9246761202812195, | |
| "eval_runtime": 0.6251, | |
| "eval_samples_per_second": 73.583, | |
| "eval_steps_per_second": 4.799, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 0.9464444518089294, | |
| "eval_runtime": 0.6056, | |
| "eval_samples_per_second": 75.952, | |
| "eval_steps_per_second": 4.953, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 14.29, | |
| "learning_rate": 0.0032407407407407406, | |
| "loss": 1.0264, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 14.86, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.8716233968734741, | |
| "eval_runtime": 0.6542, | |
| "eval_samples_per_second": 70.319, | |
| "eval_steps_per_second": 4.586, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8908547759056091, | |
| "eval_runtime": 0.5941, | |
| "eval_samples_per_second": 77.424, | |
| "eval_steps_per_second": 5.049, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 16.86, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8653961420059204, | |
| "eval_runtime": 0.6262, | |
| "eval_samples_per_second": 73.464, | |
| "eval_steps_per_second": 4.791, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 17.14, | |
| "learning_rate": 0.002777777777777778, | |
| "loss": 0.909, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.9091392755508423, | |
| "eval_runtime": 0.5961, | |
| "eval_samples_per_second": 77.164, | |
| "eval_steps_per_second": 5.032, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 18.86, | |
| "eval_accuracy": 0.717391304347826, | |
| "eval_loss": 0.8398311734199524, | |
| "eval_runtime": 0.6447, | |
| "eval_samples_per_second": 71.356, | |
| "eval_steps_per_second": 4.654, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.0023148148148148147, | |
| "loss": 0.8914, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6521739130434783, | |
| "eval_loss": 0.9392647743225098, | |
| "eval_runtime": 0.5991, | |
| "eval_samples_per_second": 76.776, | |
| "eval_steps_per_second": 5.007, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 20.86, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9566595554351807, | |
| "eval_runtime": 0.6272, | |
| "eval_samples_per_second": 73.347, | |
| "eval_steps_per_second": 4.783, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.9479435086250305, | |
| "eval_runtime": 0.6122, | |
| "eval_samples_per_second": 75.145, | |
| "eval_steps_per_second": 4.901, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "learning_rate": 0.0018518518518518517, | |
| "loss": 0.8573, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 22.86, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9308140873908997, | |
| "eval_runtime": 0.6176, | |
| "eval_samples_per_second": 74.477, | |
| "eval_steps_per_second": 4.857, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.8986259698867798, | |
| "eval_runtime": 0.6021, | |
| "eval_samples_per_second": 76.395, | |
| "eval_steps_per_second": 4.982, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 24.86, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9345232844352722, | |
| "eval_runtime": 0.6651, | |
| "eval_samples_per_second": 69.157, | |
| "eval_steps_per_second": 4.51, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 25.71, | |
| "learning_rate": 0.001388888888888889, | |
| "loss": 0.8249, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.9843014478683472, | |
| "eval_runtime": 0.8742, | |
| "eval_samples_per_second": 52.618, | |
| "eval_steps_per_second": 3.432, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 26.86, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.9945157766342163, | |
| "eval_runtime": 0.9362, | |
| "eval_samples_per_second": 49.133, | |
| "eval_steps_per_second": 3.204, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.5869565217391305, | |
| "eval_loss": 0.9493198394775391, | |
| "eval_runtime": 0.6161, | |
| "eval_samples_per_second": 74.659, | |
| "eval_steps_per_second": 4.869, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 28.57, | |
| "learning_rate": 0.0009259259259259259, | |
| "loss": 0.8307, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 28.86, | |
| "eval_accuracy": 0.6739130434782609, | |
| "eval_loss": 0.9074158072471619, | |
| "eval_runtime": 0.9137, | |
| "eval_samples_per_second": 50.344, | |
| "eval_steps_per_second": 3.283, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 0.949679970741272, | |
| "eval_runtime": 0.5932, | |
| "eval_samples_per_second": 77.552, | |
| "eval_steps_per_second": 5.058, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 30.86, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.9572489261627197, | |
| "eval_runtime": 0.6501, | |
| "eval_samples_per_second": 70.753, | |
| "eval_steps_per_second": 4.614, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 31.43, | |
| "learning_rate": 0.0004629629629629629, | |
| "loss": 0.7781, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.9732490181922913, | |
| "eval_runtime": 0.6066, | |
| "eval_samples_per_second": 75.827, | |
| "eval_steps_per_second": 4.945, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 32.86, | |
| "eval_accuracy": 0.6304347826086957, | |
| "eval_loss": 0.9417593479156494, | |
| "eval_runtime": 0.6372, | |
| "eval_samples_per_second": 72.195, | |
| "eval_steps_per_second": 4.708, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.9532932043075562, | |
| "eval_runtime": 0.6031, | |
| "eval_samples_per_second": 76.268, | |
| "eval_steps_per_second": 4.974, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "learning_rate": 0.0, | |
| "loss": 0.8104, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "eval_accuracy": 0.6086956521739131, | |
| "eval_loss": 0.9481474757194519, | |
| "eval_runtime": 0.6322, | |
| "eval_samples_per_second": 72.766, | |
| "eval_steps_per_second": 4.746, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 34.29, | |
| "step": 120, | |
| "total_flos": 2.0027429927092224e+16, | |
| "train_loss": 0.965270467599233, | |
| "train_runtime": 137.441, | |
| "train_samples_per_second": 61.99, | |
| "train_steps_per_second": 0.873 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 120, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 40, | |
| "save_steps": 500, | |
| "total_flos": 2.0027429927092224e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |