| { | |
| "best_metric": 6.430952072143555, | |
| "best_model_checkpoint": "finetuned-bert__java-8m-methods__jemma-java-bert-tokenizer__XXXM/checkpoint-45000", | |
| "epoch": 2.626185404569461, | |
| "global_step": 45000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0004998919902242132, | |
| "loss": 5.8968, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": 6.462705612182617, | |
| "eval_runtime": 1805.2005, | |
| "eval_samples_per_second": 27.514, | |
| "eval_steps_per_second": 6.879, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0004994534515508689, | |
| "loss": 5.9119, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 6.476224422454834, | |
| "eval_runtime": 1804.4274, | |
| "eval_samples_per_second": 27.526, | |
| "eval_steps_per_second": 6.882, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0004986784236353977, | |
| "loss": 5.9089, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 6.472481727600098, | |
| "eval_runtime": 1804.1115, | |
| "eval_samples_per_second": 27.531, | |
| "eval_steps_per_second": 6.883, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0004975676423415004, | |
| "loss": 5.9054, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_loss": 6.4574785232543945, | |
| "eval_runtime": 1804.4293, | |
| "eval_samples_per_second": 27.526, | |
| "eval_steps_per_second": 6.882, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.0004961227282936757, | |
| "loss": 5.9018, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_loss": 6.441328525543213, | |
| "eval_runtime": 1805.0751, | |
| "eval_samples_per_second": 27.516, | |
| "eval_steps_per_second": 6.879, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0004943460202721656, | |
| "loss": 5.9057, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 6.43818998336792, | |
| "eval_runtime": 1791.0913, | |
| "eval_samples_per_second": 27.731, | |
| "eval_steps_per_second": 6.933, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 0.0004922392052032267, | |
| "loss": 5.9076, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 6.455899238586426, | |
| "eval_runtime": 1805.3008, | |
| "eval_samples_per_second": 27.513, | |
| "eval_steps_per_second": 6.879, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0004898059684069413, | |
| "loss": 5.8996, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_loss": 6.460456848144531, | |
| "eval_runtime": 1805.5197, | |
| "eval_samples_per_second": 27.51, | |
| "eval_steps_per_second": 6.878, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.00048704920398382135, | |
| "loss": 5.9083, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "eval_loss": 6.430952072143555, | |
| "eval_runtime": 1807.4508, | |
| "eval_samples_per_second": 27.48, | |
| "eval_steps_per_second": 6.87, | |
| "step": 45000 | |
| } | |
| ], | |
| "max_steps": 428375, | |
| "num_train_epochs": 25, | |
| "total_flos": 7.5543354473762e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |