| { | |
| "best_metric": 0.5785123966942148, | |
| "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-tekno24/checkpoint-224", | |
| "epoch": 14.782608695652174, | |
| "eval_steps": 500, | |
| "global_step": 255, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5797101449275363, | |
| "grad_norm": 4.828278064727783, | |
| "learning_rate": 1.923076923076923e-05, | |
| "loss": 1.4008, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9855072463768116, | |
| "eval_accuracy": 0.40587695133149676, | |
| "eval_f1": 0.3220119812956281, | |
| "eval_loss": 1.2967476844787598, | |
| "eval_precision": 0.3790936482459676, | |
| "eval_recall": 0.40587695133149676, | |
| "eval_runtime": 5.7887, | |
| "eval_samples_per_second": 188.127, | |
| "eval_steps_per_second": 3.11, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.1594202898550725, | |
| "grad_norm": 3.097071409225464, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 1.3258, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.7391304347826086, | |
| "grad_norm": 3.920624256134033, | |
| "learning_rate": 4.912663755458515e-05, | |
| "loss": 1.2363, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.971014492753623, | |
| "eval_accuracy": 0.5032139577594124, | |
| "eval_f1": 0.41868311008776393, | |
| "eval_loss": 1.130901575088501, | |
| "eval_precision": 0.48705100222787945, | |
| "eval_recall": 0.5032139577594124, | |
| "eval_runtime": 6.0169, | |
| "eval_samples_per_second": 180.99, | |
| "eval_steps_per_second": 2.992, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.318840579710145, | |
| "grad_norm": 4.518988132476807, | |
| "learning_rate": 4.6943231441048036e-05, | |
| "loss": 1.1413, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.898550724637681, | |
| "grad_norm": 2.2280020713806152, | |
| "learning_rate": 4.475982532751092e-05, | |
| "loss": 1.1716, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.9565217391304346, | |
| "eval_accuracy": 0.5160697887970616, | |
| "eval_f1": 0.43845341130360466, | |
| "eval_loss": 1.0983200073242188, | |
| "eval_precision": 0.46095184546832213, | |
| "eval_recall": 0.5160697887970616, | |
| "eval_runtime": 5.9715, | |
| "eval_samples_per_second": 182.365, | |
| "eval_steps_per_second": 3.014, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.4782608695652173, | |
| "grad_norm": 4.956761837005615, | |
| "learning_rate": 4.2576419213973804e-05, | |
| "loss": 1.1479, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5408631772268135, | |
| "eval_f1": 0.5013630393836427, | |
| "eval_loss": 1.0550026893615723, | |
| "eval_precision": 0.5066784174960421, | |
| "eval_recall": 0.5408631772268135, | |
| "eval_runtime": 6.0323, | |
| "eval_samples_per_second": 180.528, | |
| "eval_steps_per_second": 2.984, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 4.057971014492754, | |
| "grad_norm": 2.8600962162017822, | |
| "learning_rate": 4.039301310043668e-05, | |
| "loss": 1.098, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.63768115942029, | |
| "grad_norm": 2.5968716144561768, | |
| "learning_rate": 3.8209606986899565e-05, | |
| "loss": 1.1058, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 4.9855072463768115, | |
| "eval_accuracy": 0.5500459136822773, | |
| "eval_f1": 0.4942077921670986, | |
| "eval_loss": 1.039696455001831, | |
| "eval_precision": 0.5207943123811102, | |
| "eval_recall": 0.5500459136822773, | |
| "eval_runtime": 6.023, | |
| "eval_samples_per_second": 180.807, | |
| "eval_steps_per_second": 2.989, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.217391304347826, | |
| "grad_norm": 4.285628318786621, | |
| "learning_rate": 3.602620087336245e-05, | |
| "loss": 1.0882, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.797101449275362, | |
| "grad_norm": 2.5915679931640625, | |
| "learning_rate": 3.384279475982533e-05, | |
| "loss": 1.0656, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 5.971014492753623, | |
| "eval_accuracy": 0.5555555555555556, | |
| "eval_f1": 0.539618105421093, | |
| "eval_loss": 1.055788278579712, | |
| "eval_precision": 0.5486152071828155, | |
| "eval_recall": 0.5555555555555556, | |
| "eval_runtime": 6.049, | |
| "eval_samples_per_second": 180.029, | |
| "eval_steps_per_second": 2.976, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 6.3768115942028984, | |
| "grad_norm": 3.3794102668762207, | |
| "learning_rate": 3.165938864628821e-05, | |
| "loss": 1.0333, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.956521739130435, | |
| "grad_norm": 3.542375326156616, | |
| "learning_rate": 2.9475982532751094e-05, | |
| "loss": 1.0328, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 6.956521739130435, | |
| "eval_accuracy": 0.5730027548209367, | |
| "eval_f1": 0.5465172742823081, | |
| "eval_loss": 1.0216330289840698, | |
| "eval_precision": 0.5512656679762724, | |
| "eval_recall": 0.5730027548209367, | |
| "eval_runtime": 5.949, | |
| "eval_samples_per_second": 183.057, | |
| "eval_steps_per_second": 3.026, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.536231884057971, | |
| "grad_norm": 4.52678108215332, | |
| "learning_rate": 2.7510917030567685e-05, | |
| "loss": 1.0116, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5362718089990818, | |
| "eval_f1": 0.5186530261287737, | |
| "eval_loss": 1.0468671321868896, | |
| "eval_precision": 0.5119022081965966, | |
| "eval_recall": 0.5362718089990818, | |
| "eval_runtime": 6.032, | |
| "eval_samples_per_second": 180.536, | |
| "eval_steps_per_second": 2.984, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.115942028985508, | |
| "grad_norm": 3.202193021774292, | |
| "learning_rate": 2.5327510917030566e-05, | |
| "loss": 1.0344, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.695652173913043, | |
| "grad_norm": 4.579655647277832, | |
| "learning_rate": 2.3144104803493453e-05, | |
| "loss": 1.012, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 8.985507246376812, | |
| "eval_accuracy": 0.5629017447199265, | |
| "eval_f1": 0.5226383764667623, | |
| "eval_loss": 1.0215554237365723, | |
| "eval_precision": 0.5344130335534324, | |
| "eval_recall": 0.5629017447199265, | |
| "eval_runtime": 6.005, | |
| "eval_samples_per_second": 181.348, | |
| "eval_steps_per_second": 2.997, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 9.27536231884058, | |
| "grad_norm": 4.717169284820557, | |
| "learning_rate": 2.096069868995633e-05, | |
| "loss": 1.0312, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.855072463768115, | |
| "grad_norm": 4.781270503997803, | |
| "learning_rate": 1.8777292576419214e-05, | |
| "loss": 1.0076, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 9.971014492753623, | |
| "eval_accuracy": 0.5674931129476584, | |
| "eval_f1": 0.5274537313386477, | |
| "eval_loss": 1.0186196565628052, | |
| "eval_precision": 0.5379365299560036, | |
| "eval_recall": 0.5674931129476584, | |
| "eval_runtime": 6.0992, | |
| "eval_samples_per_second": 178.549, | |
| "eval_steps_per_second": 2.951, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.434782608695652, | |
| "grad_norm": 4.275968551635742, | |
| "learning_rate": 1.6593886462882098e-05, | |
| "loss": 0.9714, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.956521739130435, | |
| "eval_accuracy": 0.5638200183654729, | |
| "eval_f1": 0.5498769817492152, | |
| "eval_loss": 1.0204566717147827, | |
| "eval_precision": 0.5549239770702264, | |
| "eval_recall": 0.5638200183654729, | |
| "eval_runtime": 5.9924, | |
| "eval_samples_per_second": 181.73, | |
| "eval_steps_per_second": 3.004, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 11.014492753623188, | |
| "grad_norm": 10.067936897277832, | |
| "learning_rate": 1.4410480349344979e-05, | |
| "loss": 0.9775, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.594202898550725, | |
| "grad_norm": 3.973658323287964, | |
| "learning_rate": 1.222707423580786e-05, | |
| "loss": 0.9843, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5656565656565656, | |
| "eval_f1": 0.548837023367577, | |
| "eval_loss": 1.011660099029541, | |
| "eval_precision": 0.5494958647042864, | |
| "eval_recall": 0.5656565656565656, | |
| "eval_runtime": 5.945, | |
| "eval_samples_per_second": 183.179, | |
| "eval_steps_per_second": 3.028, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 12.173913043478262, | |
| "grad_norm": 3.4741806983947754, | |
| "learning_rate": 1.0043668122270743e-05, | |
| "loss": 0.947, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 12.753623188405797, | |
| "grad_norm": 3.447770118713379, | |
| "learning_rate": 7.860262008733626e-06, | |
| "loss": 0.9427, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 12.985507246376812, | |
| "eval_accuracy": 0.5785123966942148, | |
| "eval_f1": 0.5642688943190026, | |
| "eval_loss": 1.007211446762085, | |
| "eval_precision": 0.5601763323294238, | |
| "eval_recall": 0.5785123966942148, | |
| "eval_runtime": 5.9174, | |
| "eval_samples_per_second": 184.034, | |
| "eval_steps_per_second": 3.042, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 3.590308666229248, | |
| "learning_rate": 5.676855895196507e-06, | |
| "loss": 0.9503, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 13.91304347826087, | |
| "grad_norm": 3.6937625408172607, | |
| "learning_rate": 3.493449781659389e-06, | |
| "loss": 0.9268, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 13.971014492753623, | |
| "eval_accuracy": 0.5785123966942148, | |
| "eval_f1": 0.565188401679607, | |
| "eval_loss": 1.0067576169967651, | |
| "eval_precision": 0.562081206107597, | |
| "eval_recall": 0.5785123966942148, | |
| "eval_runtime": 5.9299, | |
| "eval_samples_per_second": 183.645, | |
| "eval_steps_per_second": 3.035, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 14.492753623188406, | |
| "grad_norm": 4.805427074432373, | |
| "learning_rate": 1.3100436681222706e-06, | |
| "loss": 0.9525, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 14.782608695652174, | |
| "eval_accuracy": 0.5785123966942148, | |
| "eval_f1": 0.5641357580424653, | |
| "eval_loss": 1.0072529315948486, | |
| "eval_precision": 0.5641234911012597, | |
| "eval_recall": 0.5785123966942148, | |
| "eval_runtime": 6.1926, | |
| "eval_samples_per_second": 175.856, | |
| "eval_steps_per_second": 2.907, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 14.782608695652174, | |
| "step": 255, | |
| "total_flos": 4.988285676013732e+18, | |
| "train_loss": 1.0613567090501972, | |
| "train_runtime": 1231.6208, | |
| "train_samples_per_second": 53.016, | |
| "train_steps_per_second": 0.207 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 255, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.988285676013732e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |