| { | |
| "best_metric": 0.8988173831404782, | |
| "best_model_checkpoint": "/home/felix/kubhist2-testing/SuperLim-2-Testing/results/trainer_output/run-9c892_00006/checkpoint-720", | |
| "epoch": 8.0, | |
| "eval_steps": 500, | |
| "global_step": 720, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_krippendorff_interval": 0.8530320271374063, | |
| "eval_loss": 0.6099120378494263, | |
| "eval_rmse": 0.7809716463088989, | |
| "eval_runtime": 172.8024, | |
| "eval_samples_per_second": 8.675, | |
| "eval_steps_per_second": 0.069, | |
| "learning_rate": 2.872340425531915e-05, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_krippendorff_interval": 0.8847593598404591, | |
| "eval_loss": 0.5006210803985596, | |
| "eval_rmse": 0.707514762878418, | |
| "eval_runtime": 204.4981, | |
| "eval_samples_per_second": 7.33, | |
| "eval_steps_per_second": 0.059, | |
| "learning_rate": 2.5531914893617022e-05, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_krippendorff_interval": 0.8890608821312243, | |
| "eval_loss": 0.47553256154060364, | |
| "eval_rmse": 0.6895508170127869, | |
| "eval_runtime": 237.8039, | |
| "eval_samples_per_second": 6.304, | |
| "eval_steps_per_second": 0.05, | |
| "learning_rate": 2.2340425531914894e-05, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_krippendorff_interval": 0.8923376746095839, | |
| "eval_loss": 0.4671941101551056, | |
| "eval_rmse": 0.6834725737571716, | |
| "eval_runtime": 204.1101, | |
| "eval_samples_per_second": 7.344, | |
| "eval_steps_per_second": 0.059, | |
| "learning_rate": 1.914893617021277e-05, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_krippendorff_interval": 0.8954049836526707, | |
| "eval_loss": 0.4449359178543091, | |
| "eval_rmse": 0.6670365333557129, | |
| "eval_runtime": 196.013, | |
| "eval_samples_per_second": 7.647, | |
| "eval_steps_per_second": 0.061, | |
| "learning_rate": 1.5957446808510637e-05, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 1.4184397163120568e-05, | |
| "loss": 0.5805, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_krippendorff_interval": 0.8982659725855372, | |
| "eval_loss": 0.43518519401550293, | |
| "eval_rmse": 0.6596892476081848, | |
| "eval_runtime": 193.2167, | |
| "eval_samples_per_second": 7.758, | |
| "eval_steps_per_second": 0.062, | |
| "learning_rate": 1.2765957446808511e-05, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_krippendorff_interval": 0.8951961364533456, | |
| "eval_loss": 0.4422130882740021, | |
| "eval_rmse": 0.6649948954582214, | |
| "eval_runtime": 211.7822, | |
| "eval_samples_per_second": 7.078, | |
| "eval_steps_per_second": 0.057, | |
| "learning_rate": 9.574468085106385e-06, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_krippendorff_interval": 0.8988173831404782, | |
| "eval_loss": 0.4380922019481659, | |
| "eval_rmse": 0.6618611216545105, | |
| "eval_runtime": 172.2164, | |
| "eval_samples_per_second": 8.704, | |
| "eval_steps_per_second": 0.07, | |
| "learning_rate": 6.3829787234042555e-06, | |
| "step": 720 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 900, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 2090069679955200.0, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 3e-05, | |
| "per_device_train_batch_size": 32 | |
| } | |
| } | |