| { | |
| "best_metric": 0.3891792595386505, | |
| "best_model_checkpoint": "autotrain-xblock-twitter-1/checkpoint-210", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 210, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 13.318061828613281, | |
| "learning_rate": 4.7619047619047615e-06, | |
| "loss": 0.8613, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 10.021459579467773, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 0.8653, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 9.035711288452148, | |
| "learning_rate": 1.9047619047619046e-05, | |
| "loss": 0.6439, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 6.433827877044678, | |
| "learning_rate": 2.6190476190476192e-05, | |
| "loss": 0.6497, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.095238095238095e-05, | |
| "loss": 0.6613, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 15.247386932373047, | |
| "learning_rate": 3.809523809523809e-05, | |
| "loss": 1.1368, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 13.3652982711792, | |
| "learning_rate": 4.523809523809524e-05, | |
| "loss": 0.7526, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 5.259400367736816, | |
| "learning_rate": 4.973544973544973e-05, | |
| "loss": 0.6684, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 9.16520881652832, | |
| "learning_rate": 4.894179894179895e-05, | |
| "loss": 0.6681, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 6.597314357757568, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.4601, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 5.8065385818481445, | |
| "learning_rate": 4.7354497354497356e-05, | |
| "loss": 0.6782, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 5.5024566650390625, | |
| "learning_rate": 4.656084656084656e-05, | |
| "loss": 0.5565, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 6.190059661865234, | |
| "learning_rate": 4.576719576719577e-05, | |
| "loss": 0.52, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 15.302659034729004, | |
| "learning_rate": 4.4973544973544974e-05, | |
| "loss": 0.7737, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 4.845982074737549, | |
| "learning_rate": 4.417989417989418e-05, | |
| "loss": 0.549, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 5.293482780456543, | |
| "learning_rate": 4.3386243386243384e-05, | |
| "loss": 0.7392, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 7.307839870452881, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.5303, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 6.7569661140441895, | |
| "learning_rate": 4.17989417989418e-05, | |
| "loss": 0.4638, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 6.70114803314209, | |
| "learning_rate": 4.100529100529101e-05, | |
| "loss": 0.4203, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 11.536452293395996, | |
| "learning_rate": 4.021164021164021e-05, | |
| "loss": 0.6686, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 7.2152934074401855, | |
| "learning_rate": 3.941798941798942e-05, | |
| "loss": 0.596, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 4.001399040222168, | |
| "learning_rate": 3.862433862433863e-05, | |
| "loss": 0.3098, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 7.049214839935303, | |
| "learning_rate": 3.7830687830687835e-05, | |
| "loss": 0.5719, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7050359712230215, | |
| "eval_auc": 0.6505034446210917, | |
| "eval_f1": 0.8144796380090497, | |
| "eval_loss": 0.5788741111755371, | |
| "eval_precision": 0.7563025210084033, | |
| "eval_recall": 0.8823529411764706, | |
| "eval_runtime": 5.1352, | |
| "eval_samples_per_second": 27.068, | |
| "eval_steps_per_second": 1.753, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 8.485621452331543, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.8083, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 8.083047866821289, | |
| "learning_rate": 3.6243386243386245e-05, | |
| "loss": 0.5378, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 4.286181926727295, | |
| "learning_rate": 3.5449735449735446e-05, | |
| "loss": 0.4745, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 6.330202579498291, | |
| "learning_rate": 3.465608465608466e-05, | |
| "loss": 0.4858, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 5.901049613952637, | |
| "learning_rate": 3.386243386243386e-05, | |
| "loss": 0.4534, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 4.458903789520264, | |
| "learning_rate": 3.306878306878307e-05, | |
| "loss": 0.4565, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "grad_norm": 8.628113746643066, | |
| "learning_rate": 3.227513227513227e-05, | |
| "loss": 0.5021, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 12.450860023498535, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.6712, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "grad_norm": 6.316427230834961, | |
| "learning_rate": 3.068783068783069e-05, | |
| "loss": 0.3929, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "grad_norm": 7.734628200531006, | |
| "learning_rate": 2.9894179894179897e-05, | |
| "loss": 0.5408, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 6.100373268127441, | |
| "learning_rate": 2.91005291005291e-05, | |
| "loss": 0.6207, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 6.035886764526367, | |
| "learning_rate": 2.830687830687831e-05, | |
| "loss": 0.6811, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 5.461982250213623, | |
| "learning_rate": 2.7513227513227512e-05, | |
| "loss": 0.5054, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "grad_norm": 8.910785675048828, | |
| "learning_rate": 2.6719576719576723e-05, | |
| "loss": 0.6739, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 4.59702205657959, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.4551, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 2.666771173477173, | |
| "learning_rate": 2.5132275132275137e-05, | |
| "loss": 0.3917, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "grad_norm": 3.653053045272827, | |
| "learning_rate": 2.4338624338624338e-05, | |
| "loss": 0.4881, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 1.8620728254318237, | |
| "learning_rate": 2.3544973544973546e-05, | |
| "loss": 0.2256, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 15.068528175354004, | |
| "learning_rate": 2.275132275132275e-05, | |
| "loss": 0.8185, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "grad_norm": 2.865483045578003, | |
| "learning_rate": 2.1957671957671956e-05, | |
| "loss": 0.6451, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "grad_norm": 1.9436465501785278, | |
| "learning_rate": 2.1164021164021164e-05, | |
| "loss": 0.294, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 2.666163921356201, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.4637, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 3.914135217666626, | |
| "learning_rate": 1.9576719576719577e-05, | |
| "loss": 0.4303, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7841726618705036, | |
| "eval_auc": 0.8285638579756226, | |
| "eval_f1": 0.8684210526315789, | |
| "eval_loss": 0.4182623028755188, | |
| "eval_precision": 0.7857142857142857, | |
| "eval_recall": 0.9705882352941176, | |
| "eval_runtime": 5.2653, | |
| "eval_samples_per_second": 26.399, | |
| "eval_steps_per_second": 1.709, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 6.129709243774414, | |
| "learning_rate": 1.8783068783068782e-05, | |
| "loss": 0.5329, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 6.085241317749023, | |
| "learning_rate": 1.798941798941799e-05, | |
| "loss": 0.4188, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 7.526946067810059, | |
| "learning_rate": 1.7195767195767195e-05, | |
| "loss": 0.4073, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 3.7981059551239014, | |
| "learning_rate": 1.6402116402116404e-05, | |
| "loss": 0.3207, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": 5.229352951049805, | |
| "learning_rate": 1.560846560846561e-05, | |
| "loss": 0.5247, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "grad_norm": 3.7582530975341797, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.2936, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "grad_norm": 6.107592582702637, | |
| "learning_rate": 1.4021164021164022e-05, | |
| "loss": 0.4513, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "grad_norm": 8.501120567321777, | |
| "learning_rate": 1.3227513227513228e-05, | |
| "loss": 0.4808, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "grad_norm": 3.4457428455352783, | |
| "learning_rate": 1.2433862433862433e-05, | |
| "loss": 0.27, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 5.215019702911377, | |
| "learning_rate": 1.164021164021164e-05, | |
| "loss": 0.3364, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "grad_norm": 6.2070794105529785, | |
| "learning_rate": 1.0846560846560846e-05, | |
| "loss": 0.4075, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "grad_norm": 5.491907119750977, | |
| "learning_rate": 1.0052910052910053e-05, | |
| "loss": 0.5218, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "grad_norm": 7.795518398284912, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.329, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "grad_norm": 3.6145973205566406, | |
| "learning_rate": 8.465608465608466e-06, | |
| "loss": 0.3696, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "grad_norm": 5.689661502838135, | |
| "learning_rate": 7.671957671957672e-06, | |
| "loss": 0.6274, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "grad_norm": 4.555980682373047, | |
| "learning_rate": 6.878306878306878e-06, | |
| "loss": 0.3477, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 6.758476257324219, | |
| "learning_rate": 6.0846560846560845e-06, | |
| "loss": 0.3809, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "grad_norm": 3.1286351680755615, | |
| "learning_rate": 5.291005291005291e-06, | |
| "loss": 0.35, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 8.514357566833496, | |
| "learning_rate": 4.497354497354498e-06, | |
| "loss": 0.5799, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "grad_norm": 4.899698734283447, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.5754, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "grad_norm": 9.083395004272461, | |
| "learning_rate": 2.91005291005291e-06, | |
| "loss": 0.3895, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "grad_norm": 2.1063151359558105, | |
| "learning_rate": 2.1164021164021164e-06, | |
| "loss": 0.2194, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 5.722929954528809, | |
| "learning_rate": 1.3227513227513228e-06, | |
| "loss": 0.2762, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.7745004892349243, | |
| "learning_rate": 5.291005291005291e-07, | |
| "loss": 0.1982, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8201438848920863, | |
| "eval_auc": 0.8559883412824589, | |
| "eval_f1": 0.8878923766816144, | |
| "eval_loss": 0.3891792595386505, | |
| "eval_precision": 0.8181818181818182, | |
| "eval_recall": 0.9705882352941176, | |
| "eval_runtime": 5.0466, | |
| "eval_samples_per_second": 27.543, | |
| "eval_steps_per_second": 1.783, | |
| "step": 210 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 210, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.2925663867713946e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |