| { |
| "best_global_step": 300, |
| "best_metric": 4.177750110626221, |
| "best_model_checkpoint": "/Users/alexgrigoras/Library/Mobile Documents/com~apple~CloudDocs/[5] Software/github/dif-pi/artifacts/models/sdg_chronos_t5_small_dunnhumby/checkpoint-300", |
| "epoch": 0.04181840358244324, |
| "eval_steps": 25, |
| "global_step": 300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0034848669652036033, |
| "grad_norm": 0.2658565640449524, |
| "learning_rate": 2.4938536281812643e-05, |
| "loss": 50.4958984375, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0034848669652036033, |
| "eval_loss": 4.513997554779053, |
| "eval_runtime": 126.0711, |
| "eval_samples_per_second": 101.165, |
| "eval_steps_per_second": 50.583, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.006969733930407207, |
| "grad_norm": 0.3027424216270447, |
| "learning_rate": 2.4132322535191482e-05, |
| "loss": 49.5675048828125, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.006969733930407207, |
| "eval_loss": 4.422898769378662, |
| "eval_runtime": 135.5543, |
| "eval_samples_per_second": 94.088, |
| "eval_steps_per_second": 47.044, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.01045460089561081, |
| "grad_norm": 0.34238171577453613, |
| "learning_rate": 2.2448287207969232e-05, |
| "loss": 48.3637109375, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.01045460089561081, |
| "eval_loss": 4.359263896942139, |
| "eval_runtime": 138.5997, |
| "eval_samples_per_second": 92.02, |
| "eval_steps_per_second": 46.01, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.013939467860814413, |
| "grad_norm": 0.3021143674850464, |
| "learning_rate": 2.0013514341037815e-05, |
| "loss": 47.3734521484375, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.013939467860814413, |
| "eval_loss": 4.318150997161865, |
| "eval_runtime": 136.3222, |
| "eval_samples_per_second": 93.558, |
| "eval_steps_per_second": 46.779, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.017424334826018018, |
| "grad_norm": 0.28853410482406616, |
| "learning_rate": 1.7011741632521437e-05, |
| "loss": 48.521357421875, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.017424334826018018, |
| "eval_loss": 4.282954692840576, |
| "eval_runtime": 132.1879, |
| "eval_samples_per_second": 96.484, |
| "eval_steps_per_second": 48.242, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.02090920179122162, |
| "grad_norm": 0.3650856614112854, |
| "learning_rate": 1.3669494856238973e-05, |
| "loss": 47.43091796875, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.02090920179122162, |
| "eval_loss": 4.249988555908203, |
| "eval_runtime": 145.2659, |
| "eval_samples_per_second": 87.798, |
| "eval_steps_per_second": 43.899, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.024394068756425222, |
| "grad_norm": 0.3505313992500305, |
| "learning_rate": 1.023899332084863e-05, |
| "loss": 46.525419921875, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.024394068756425222, |
| "eval_loss": 4.218865871429443, |
| "eval_runtime": 137.0969, |
| "eval_samples_per_second": 93.029, |
| "eval_steps_per_second": 46.515, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.027878935721628827, |
| "grad_norm": 0.3190622925758362, |
| "learning_rate": 6.979116392095325e-06, |
| "loss": 46.60708984375, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.027878935721628827, |
| "eval_loss": 4.196957588195801, |
| "eval_runtime": 140.7578, |
| "eval_samples_per_second": 90.61, |
| "eval_steps_per_second": 45.305, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.03136380268683243, |
| "grad_norm": 0.3062129318714142, |
| "learning_rate": 4.1358674205142765e-06, |
| "loss": 48.300791015625, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.03136380268683243, |
| "eval_loss": 4.185319900512695, |
| "eval_runtime": 134.3944, |
| "eval_samples_per_second": 94.9, |
| "eval_steps_per_second": 47.45, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.034848669652036035, |
| "grad_norm": 0.30869823694229126, |
| "learning_rate": 1.923809344738306e-06, |
| "loss": 47.4475341796875, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.034848669652036035, |
| "eval_loss": 4.180154323577881, |
| "eval_runtime": 142.7493, |
| "eval_samples_per_second": 89.345, |
| "eval_steps_per_second": 44.673, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.038333536617239636, |
| "grad_norm": 0.30447155237197876, |
| "learning_rate": 5.098729140296271e-07, |
| "loss": 47.397509765625, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.038333536617239636, |
| "eval_loss": 4.1781206130981445, |
| "eval_runtime": 150.242, |
| "eval_samples_per_second": 84.89, |
| "eval_steps_per_second": 42.445, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.04181840358244324, |
| "grad_norm": 0.3095584213733673, |
| "learning_rate": 7.594263207122421e-10, |
| "loss": 46.36583984375, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.04181840358244324, |
| "eval_loss": 4.177750110626221, |
| "eval_runtime": 144.6681, |
| "eval_samples_per_second": 88.16, |
| "eval_steps_per_second": 44.08, |
| "step": 300 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 300, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 300, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 229911035904000.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
