| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 310, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.935483870967742e-05, | |
| "loss": 0.6525, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.870967741935484e-05, | |
| "loss": 0.5089, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.806451612903226e-05, | |
| "loss": 0.422, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.741935483870968e-05, | |
| "loss": 0.3803, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.6774193548387098e-05, | |
| "loss": 0.3615, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.3453, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.2621971457019582, | |
| "eval_loss": 0.3179258704185486, | |
| "eval_runtime": 1.9933, | |
| "eval_samples_per_second": 496.167, | |
| "eval_steps_per_second": 8.027, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 1.5483870967741936e-05, | |
| "loss": 0.3319, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.4838709677419357e-05, | |
| "loss": 0.3196, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 1.4193548387096776e-05, | |
| "loss": 0.3168, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 1.3548387096774194e-05, | |
| "loss": 0.3119, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 1.2903225806451613e-05, | |
| "loss": 0.3049, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 1.2258064516129034e-05, | |
| "loss": 0.3017, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_f1": 0.37271619975639464, | |
| "eval_loss": 0.2839711308479309, | |
| "eval_runtime": 1.8261, | |
| "eval_samples_per_second": 541.593, | |
| "eval_steps_per_second": 8.762, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.1612903225806453e-05, | |
| "loss": 0.2931, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 1.096774193548387e-05, | |
| "loss": 0.2924, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 1.0322580645161291e-05, | |
| "loss": 0.2911, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 0.2857, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.74, | |
| "learning_rate": 9.03225806451613e-06, | |
| "loss": 0.2855, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 8.387096774193549e-06, | |
| "loss": 0.2828, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_f1": 0.4075178997613365, | |
| "eval_loss": 0.27112114429473877, | |
| "eval_runtime": 1.8327, | |
| "eval_samples_per_second": 539.642, | |
| "eval_steps_per_second": 8.73, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 7.741935483870968e-06, | |
| "loss": 0.2874, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 7.096774193548388e-06, | |
| "loss": 0.2774, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "learning_rate": 6.451612903225806e-06, | |
| "loss": 0.2729, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 5.806451612903226e-06, | |
| "loss": 0.2784, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.71, | |
| "learning_rate": 5.161290322580646e-06, | |
| "loss": 0.2726, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 4.516129032258065e-06, | |
| "loss": 0.2723, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_f1": 0.4506226469736461, | |
| "eval_loss": 0.26035064458847046, | |
| "eval_runtime": 1.8326, | |
| "eval_samples_per_second": 539.658, | |
| "eval_steps_per_second": 8.731, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 3.870967741935484e-06, | |
| "loss": 0.2688, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "learning_rate": 3.225806451612903e-06, | |
| "loss": 0.268, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.35, | |
| "learning_rate": 2.580645161290323e-06, | |
| "loss": 0.266, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 1.935483870967742e-06, | |
| "loss": 0.2657, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "learning_rate": 1.2903225806451614e-06, | |
| "loss": 0.2687, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 6.451612903225807e-07, | |
| "loss": 0.2679, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2653, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_f1": 0.46636259977194994, | |
| "eval_loss": 0.25748351216316223, | |
| "eval_runtime": 1.8325, | |
| "eval_samples_per_second": 539.71, | |
| "eval_steps_per_second": 8.731, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 310, | |
| "total_flos": 5243230627246080.0, | |
| "train_loss": 0.3167446336438579, | |
| "train_runtime": 225.8975, | |
| "train_samples_per_second": 175.168, | |
| "train_steps_per_second": 1.372 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 310, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 5243230627246080.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |