| { | |
| "best_metric": 0.588494598865509, | |
| "best_model_checkpoint": "autotrain-f8u3m-1w0uc/checkpoint-129", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 129, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 17.909360885620117, | |
| "learning_rate": 3.846153846153847e-06, | |
| "loss": 1.7009, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 13.120195388793945, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 1.4648, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 14.559846878051758, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 1.4937, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 8.80319881439209, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 1.1978, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 10.07514476776123, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 1.2436, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 5.79322624206543, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.8964, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 15.918188095092773, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 1.5669, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 8.671540260314941, | |
| "learning_rate": 4.9568965517241384e-05, | |
| "loss": 0.9671, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 6.892113208770752, | |
| "learning_rate": 4.870689655172414e-05, | |
| "loss": 0.9687, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 6.245675563812256, | |
| "learning_rate": 4.78448275862069e-05, | |
| "loss": 0.5675, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 11.2545804977417, | |
| "learning_rate": 4.698275862068966e-05, | |
| "loss": 1.2117, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 5.111425399780273, | |
| "learning_rate": 4.612068965517242e-05, | |
| "loss": 0.9048, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 5.0768232345581055, | |
| "learning_rate": 4.5258620689655176e-05, | |
| "loss": 0.7902, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 8.407731056213379, | |
| "learning_rate": 4.4396551724137933e-05, | |
| "loss": 0.941, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 12.011809349060059, | |
| "learning_rate": 4.353448275862069e-05, | |
| "loss": 1.1812, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 6.191880702972412, | |
| "learning_rate": 4.267241379310345e-05, | |
| "loss": 0.7905, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 5.270814418792725, | |
| "learning_rate": 4.1810344827586205e-05, | |
| "loss": 0.7904, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 5.346973896026611, | |
| "learning_rate": 4.094827586206897e-05, | |
| "loss": 0.6126, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 6.431284427642822, | |
| "learning_rate": 4.0086206896551726e-05, | |
| "loss": 0.9431, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 5.295109748840332, | |
| "learning_rate": 3.922413793103448e-05, | |
| "loss": 0.8013, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 7.394813060760498, | |
| "learning_rate": 3.8362068965517246e-05, | |
| "loss": 0.5561, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6511627906976745, | |
| "eval_f1_macro": 0.5219298245614035, | |
| "eval_f1_micro": 0.6511627906976745, | |
| "eval_f1_weighted": 0.5661464708282333, | |
| "eval_loss": 0.8391300439834595, | |
| "eval_precision_macro": 0.5958528951486698, | |
| "eval_precision_micro": 0.6511627906976745, | |
| "eval_precision_weighted": 0.5547548859045747, | |
| "eval_recall_macro": 0.5166666666666667, | |
| "eval_recall_micro": 0.6511627906976745, | |
| "eval_recall_weighted": 0.6511627906976745, | |
| "eval_runtime": 0.5055, | |
| "eval_samples_per_second": 170.128, | |
| "eval_steps_per_second": 11.869, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 12.433929443359375, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.8422, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "grad_norm": 9.662508010864258, | |
| "learning_rate": 3.663793103448276e-05, | |
| "loss": 0.8562, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 6.504687309265137, | |
| "learning_rate": 3.5775862068965524e-05, | |
| "loss": 0.6381, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 12.690322875976562, | |
| "learning_rate": 3.4913793103448275e-05, | |
| "loss": 0.5752, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "grad_norm": 5.9632792472839355, | |
| "learning_rate": 3.405172413793103e-05, | |
| "loss": 0.6849, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 8.237900733947754, | |
| "learning_rate": 3.3189655172413796e-05, | |
| "loss": 0.6422, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 5.977579593658447, | |
| "learning_rate": 3.232758620689655e-05, | |
| "loss": 0.6344, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 6.388967037200928, | |
| "learning_rate": 3.146551724137931e-05, | |
| "loss": 0.6051, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 6.785774230957031, | |
| "learning_rate": 3.060344827586207e-05, | |
| "loss": 0.5379, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 6.693228244781494, | |
| "learning_rate": 2.974137931034483e-05, | |
| "loss": 0.4483, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "grad_norm": 4.33690071105957, | |
| "learning_rate": 2.8879310344827588e-05, | |
| "loss": 0.5161, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "grad_norm": 7.381749629974365, | |
| "learning_rate": 2.8017241379310345e-05, | |
| "loss": 0.7829, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 11.129793167114258, | |
| "learning_rate": 2.7155172413793105e-05, | |
| "loss": 0.7715, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "grad_norm": 11.77314281463623, | |
| "learning_rate": 2.6293103448275862e-05, | |
| "loss": 1.114, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "grad_norm": 7.2926130294799805, | |
| "learning_rate": 2.543103448275862e-05, | |
| "loss": 0.938, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 5.774272441864014, | |
| "learning_rate": 2.456896551724138e-05, | |
| "loss": 0.7925, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "grad_norm": 9.42758560180664, | |
| "learning_rate": 2.370689655172414e-05, | |
| "loss": 0.6834, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "grad_norm": 7.223062038421631, | |
| "learning_rate": 2.2844827586206897e-05, | |
| "loss": 0.8257, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "grad_norm": 9.974703788757324, | |
| "learning_rate": 2.1982758620689654e-05, | |
| "loss": 0.5291, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "grad_norm": 11.898812294006348, | |
| "learning_rate": 2.1120689655172415e-05, | |
| "loss": 0.8295, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 5.932551383972168, | |
| "learning_rate": 2.0258620689655172e-05, | |
| "loss": 0.5594, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 8.01093864440918, | |
| "learning_rate": 1.9396551724137932e-05, | |
| "loss": 0.7166, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7790697674418605, | |
| "eval_f1_macro": 0.7326664355062412, | |
| "eval_f1_micro": 0.7790697674418605, | |
| "eval_f1_weighted": 0.7589375221752733, | |
| "eval_loss": 0.6218534708023071, | |
| "eval_precision_macro": 0.8907051282051283, | |
| "eval_precision_micro": 0.7790697674418605, | |
| "eval_precision_weighted": 0.831499701848539, | |
| "eval_recall_macro": 0.6805555555555556, | |
| "eval_recall_micro": 0.7790697674418605, | |
| "eval_recall_weighted": 0.7790697674418605, | |
| "eval_runtime": 0.4535, | |
| "eval_samples_per_second": 189.622, | |
| "eval_steps_per_second": 13.229, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 4.2975664138793945, | |
| "learning_rate": 1.8534482758620693e-05, | |
| "loss": 0.5073, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 8.290116310119629, | |
| "learning_rate": 1.767241379310345e-05, | |
| "loss": 0.606, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "grad_norm": 5.366226673126221, | |
| "learning_rate": 1.6810344827586207e-05, | |
| "loss": 0.4448, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "grad_norm": 6.743834495544434, | |
| "learning_rate": 1.5948275862068967e-05, | |
| "loss": 0.7529, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "grad_norm": 6.312230587005615, | |
| "learning_rate": 1.5086206896551724e-05, | |
| "loss": 0.662, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "grad_norm": 9.200089454650879, | |
| "learning_rate": 1.4224137931034485e-05, | |
| "loss": 0.9112, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "grad_norm": 3.5302746295928955, | |
| "learning_rate": 1.336206896551724e-05, | |
| "loss": 0.2405, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "grad_norm": 13.742111206054688, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.5303, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "grad_norm": 8.292695045471191, | |
| "learning_rate": 1.163793103448276e-05, | |
| "loss": 0.5544, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "grad_norm": 9.335094451904297, | |
| "learning_rate": 1.0775862068965516e-05, | |
| "loss": 0.7992, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "grad_norm": 4.947837829589844, | |
| "learning_rate": 9.913793103448277e-06, | |
| "loss": 0.4896, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 11.157235145568848, | |
| "learning_rate": 9.051724137931036e-06, | |
| "loss": 0.6746, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 10.61878776550293, | |
| "learning_rate": 8.189655172413793e-06, | |
| "loss": 0.6722, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "grad_norm": 4.7017621994018555, | |
| "learning_rate": 7.3275862068965514e-06, | |
| "loss": 0.5214, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 3.746359348297119, | |
| "learning_rate": 6.465517241379311e-06, | |
| "loss": 0.592, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "grad_norm": 5.942258358001709, | |
| "learning_rate": 5.603448275862069e-06, | |
| "loss": 0.5589, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "grad_norm": 13.716927528381348, | |
| "learning_rate": 4.741379310344828e-06, | |
| "loss": 1.0046, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 3.577460765838623, | |
| "learning_rate": 3.8793103448275865e-06, | |
| "loss": 0.4807, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 6.835740566253662, | |
| "learning_rate": 3.017241379310345e-06, | |
| "loss": 0.5735, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "grad_norm": 7.47273588180542, | |
| "learning_rate": 2.1551724137931035e-06, | |
| "loss": 0.569, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "grad_norm": 6.011229991912842, | |
| "learning_rate": 1.293103448275862e-06, | |
| "loss": 0.3485, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7674418604651163, | |
| "eval_f1_macro": 0.726419878296146, | |
| "eval_f1_micro": 0.7674418604651162, | |
| "eval_f1_weighted": 0.7444926647483373, | |
| "eval_loss": 0.588494598865509, | |
| "eval_precision_macro": 0.8743946731234866, | |
| "eval_precision_micro": 0.7674418604651163, | |
| "eval_precision_weighted": 0.8185567881074384, | |
| "eval_recall_macro": 0.6858527131782945, | |
| "eval_recall_micro": 0.7674418604651163, | |
| "eval_recall_weighted": 0.7674418604651163, | |
| "eval_runtime": 0.4559, | |
| "eval_samples_per_second": 188.618, | |
| "eval_steps_per_second": 13.159, | |
| "step": 129 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 129, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 7.97406866688983e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |