| { | |
| "best_metric": 0.45186951756477356, | |
| "best_model_checkpoint": "autotrain-cgknk-ucsd7/checkpoint-69", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 69, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 7.142857142857143e-06, | |
| "loss": 1.3729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.3925, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 1.3467, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 1.3622, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 1.3501, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 1.4273, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1846, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.9193548387096775e-05, | |
| "loss": 1.0239, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 1.1007, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.7580645161290326e-05, | |
| "loss": 0.8872, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.67741935483871e-05, | |
| "loss": 0.6495, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.596774193548387e-05, | |
| "loss": 0.8359, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.516129032258064e-05, | |
| "loss": 0.9285, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.435483870967742e-05, | |
| "loss": 0.8296, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.3548387096774194e-05, | |
| "loss": 0.4654, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.2741935483870973e-05, | |
| "loss": 0.743, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.1935483870967746e-05, | |
| "loss": 0.9514, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.112903225806452e-05, | |
| "loss": 1.0205, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 0.7075, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.951612903225806e-05, | |
| "loss": 0.9395, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.870967741935484e-05, | |
| "loss": 0.6195, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.7903225806451614e-05, | |
| "loss": 0.2973, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.7096774193548386e-05, | |
| "loss": 0.9383, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8260869565217391, | |
| "eval_f1_macro": 0.44425770308123247, | |
| "eval_f1_micro": 0.8260869565217391, | |
| "eval_f1_weighted": 0.7692607477773717, | |
| "eval_loss": 0.6277322173118591, | |
| "eval_precision_macro": 0.4186507936507936, | |
| "eval_precision_micro": 0.8260869565217391, | |
| "eval_precision_weighted": 0.7213595583160801, | |
| "eval_recall_macro": 0.4744245524296675, | |
| "eval_recall_micro": 0.8260869565217391, | |
| "eval_recall_weighted": 0.8260869565217391, | |
| "eval_runtime": 0.6688, | |
| "eval_samples_per_second": 68.776, | |
| "eval_steps_per_second": 4.485, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.6290322580645165e-05, | |
| "loss": 0.7685, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 3.548387096774194e-05, | |
| "loss": 0.3426, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.467741935483872e-05, | |
| "loss": 0.8852, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.387096774193548e-05, | |
| "loss": 0.2917, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.306451612903226e-05, | |
| "loss": 0.2149, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.5661, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 3.1451612903225806e-05, | |
| "loss": 0.8716, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.0645161290322585e-05, | |
| "loss": 0.5167, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.9838709677419357e-05, | |
| "loss": 0.4871, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.9032258064516133e-05, | |
| "loss": 0.5126, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.822580645161291e-05, | |
| "loss": 0.1555, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.7419354838709678e-05, | |
| "loss": 1.0101, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.661290322580645e-05, | |
| "loss": 0.1561, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.5806451612903226e-05, | |
| "loss": 0.7768, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.7654, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 0.4026, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 2.338709677419355e-05, | |
| "loss": 0.6544, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2.258064516129032e-05, | |
| "loss": 0.1682, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 2.1774193548387097e-05, | |
| "loss": 0.6621, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 2.0967741935483873e-05, | |
| "loss": 0.5287, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.0161290322580645e-05, | |
| "loss": 0.5501, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.935483870967742e-05, | |
| "loss": 0.4162, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8548387096774193e-05, | |
| "loss": 0.5118, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8478260869565217, | |
| "eval_f1_macro": 0.45611111111111113, | |
| "eval_f1_micro": 0.8478260869565218, | |
| "eval_f1_weighted": 0.7890338164251207, | |
| "eval_loss": 0.4621887505054474, | |
| "eval_precision_macro": 0.4273879142300195, | |
| "eval_precision_micro": 0.8478260869565217, | |
| "eval_precision_weighted": 0.7380710229680482, | |
| "eval_recall_macro": 0.4891304347826087, | |
| "eval_recall_micro": 0.8478260869565217, | |
| "eval_recall_weighted": 0.8478260869565217, | |
| "eval_runtime": 0.6179, | |
| "eval_samples_per_second": 74.442, | |
| "eval_steps_per_second": 4.855, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.774193548387097e-05, | |
| "loss": 0.3888, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.693548387096774e-05, | |
| "loss": 0.3377, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.593, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 1.5322580645161292e-05, | |
| "loss": 0.6547, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.4516129032258066e-05, | |
| "loss": 0.2477, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.3709677419354839e-05, | |
| "loss": 0.1499, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.2903225806451613e-05, | |
| "loss": 0.1146, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.2096774193548388e-05, | |
| "loss": 0.0913, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.129032258064516e-05, | |
| "loss": 0.1403, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.0483870967741936e-05, | |
| "loss": 0.3745, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 0.9547, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 8.870967741935484e-06, | |
| "loss": 0.0937, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 0.4696, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.258064516129033e-06, | |
| "loss": 0.436, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.451612903225806e-06, | |
| "loss": 0.7999, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.64516129032258e-06, | |
| "loss": 0.261, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 4.838709677419355e-06, | |
| "loss": 0.2922, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.032258064516129e-06, | |
| "loss": 0.958, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 3.225806451612903e-06, | |
| "loss": 0.121, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.4193548387096776e-06, | |
| "loss": 0.3745, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 1.6129032258064516e-06, | |
| "loss": 0.0963, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 8.064516129032258e-07, | |
| "loss": 0.4777, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.1715, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8695652173913043, | |
| "eval_f1_macro": 0.5878571428571429, | |
| "eval_f1_micro": 0.8695652173913043, | |
| "eval_f1_weighted": 0.8316149068322981, | |
| "eval_loss": 0.45186951756477356, | |
| "eval_precision_macro": 0.6898148148148148, | |
| "eval_precision_micro": 0.8695652173913043, | |
| "eval_precision_weighted": 0.8216586151368759, | |
| "eval_recall_macro": 0.572463768115942, | |
| "eval_recall_micro": 0.8695652173913043, | |
| "eval_recall_weighted": 0.8695652173913043, | |
| "eval_runtime": 0.5942, | |
| "eval_samples_per_second": 77.416, | |
| "eval_steps_per_second": 5.049, | |
| "step": 69 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 69, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 35717967148032.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |