| { |
| "best_global_step": 750, |
| "best_metric": 3.810453414916992, |
| "best_model_checkpoint": "/Users/alexgrigoras/Library/Mobile Documents/com~apple~CloudDocs/[5] Software/github/dif-pi/artifacts/models/sdg_chronos_t5_small_dunnhumby/checkpoint-750", |
| "epoch": 0.1045460089561081, |
| "eval_steps": 25, |
| "global_step": 750, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0034848669652036033, |
| "grad_norm": 0.2964903712272644, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 37.88656494140625, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.0034848669652036033, |
| "eval_loss": 4.6062092781066895, |
| "eval_runtime": 134.4005, |
| "eval_samples_per_second": 94.895, |
| "eval_steps_per_second": 47.448, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.006969733930407207, |
| "grad_norm": 0.34245482087135315, |
| "learning_rate": 1.6333333333333335e-05, |
| "loss": 37.61192138671875, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.006969733930407207, |
| "eval_loss": 4.552639007568359, |
| "eval_runtime": 131.7871, |
| "eval_samples_per_second": 96.777, |
| "eval_steps_per_second": 48.389, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.01045460089561081, |
| "grad_norm": 0.3815608024597168, |
| "learning_rate": 2.466666666666667e-05, |
| "loss": 37.09659912109375, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.01045460089561081, |
| "eval_loss": 4.443544864654541, |
| "eval_runtime": 154.9254, |
| "eval_samples_per_second": 82.323, |
| "eval_steps_per_second": 41.162, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.013939467860814413, |
| "grad_norm": 0.3647356331348419, |
| "learning_rate": 2.498250672211728e-05, |
| "loss": 36.29866943359375, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.013939467860814413, |
| "eval_loss": 4.3369669914245605, |
| "eval_runtime": 138.8908, |
| "eval_samples_per_second": 91.828, |
| "eval_steps_per_second": 45.914, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.017424334826018018, |
| "grad_norm": 0.3683606684207916, |
| "learning_rate": 2.4927134858925575e-05, |
| "loss": 35.8759912109375, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.017424334826018018, |
| "eval_loss": 4.242681980133057, |
| "eval_runtime": 125.8059, |
| "eval_samples_per_second": 101.378, |
| "eval_steps_per_second": 50.689, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.02090920179122162, |
| "grad_norm": 0.41745099425315857, |
| "learning_rate": 2.4834022195605383e-05, |
| "loss": 34.71609375, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.02090920179122162, |
| "eval_loss": 4.15211820602417, |
| "eval_runtime": 144.0648, |
| "eval_samples_per_second": 88.53, |
| "eval_steps_per_second": 44.265, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.024394068756425222, |
| "grad_norm": 0.5502339601516724, |
| "learning_rate": 2.470345151225491e-05, |
| "loss": 34.4389111328125, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.024394068756425222, |
| "eval_loss": 4.065174579620361, |
| "eval_runtime": 164.1963, |
| "eval_samples_per_second": 77.675, |
| "eval_steps_per_second": 38.838, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.027878935721628827, |
| "grad_norm": 0.5007655024528503, |
| "learning_rate": 2.4535819347748074e-05, |
| "loss": 33.89746337890625, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.027878935721628827, |
| "eval_loss": 3.987807035446167, |
| "eval_runtime": 141.6182, |
| "eval_samples_per_second": 90.059, |
| "eval_steps_per_second": 45.03, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.03136380268683243, |
| "grad_norm": 0.48552975058555603, |
| "learning_rate": 2.433163479545898e-05, |
| "loss": 34.3608935546875, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.03136380268683243, |
| "eval_loss": 3.951249361038208, |
| "eval_runtime": 178.1207, |
| "eval_samples_per_second": 71.603, |
| "eval_steps_per_second": 35.802, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.034848669652036035, |
| "grad_norm": 0.4646497964859009, |
| "learning_rate": 2.4091517957162068e-05, |
| "loss": 33.36589599609375, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.034848669652036035, |
| "eval_loss": 3.9345061779022217, |
| "eval_runtime": 191.2882, |
| "eval_samples_per_second": 66.674, |
| "eval_steps_per_second": 33.337, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.038333536617239636, |
| "grad_norm": 0.5384636521339417, |
| "learning_rate": 2.3816198059803415e-05, |
| "loss": 32.43830810546875, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.038333536617239636, |
| "eval_loss": 3.919111967086792, |
| "eval_runtime": 157.7724, |
| "eval_samples_per_second": 80.838, |
| "eval_steps_per_second": 40.419, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.04181840358244324, |
| "grad_norm": 0.5843191742897034, |
| "learning_rate": 2.350651124086246e-05, |
| "loss": 33.16199462890625, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.04181840358244324, |
| "eval_loss": 3.907341957092285, |
| "eval_runtime": 137.2039, |
| "eval_samples_per_second": 92.957, |
| "eval_steps_per_second": 46.478, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.045303270547646844, |
| "grad_norm": 0.6355782151222229, |
| "learning_rate": 2.316339800902997e-05, |
| "loss": 31.9848095703125, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.045303270547646844, |
| "eval_loss": 3.904228925704956, |
| "eval_runtime": 142.1459, |
| "eval_samples_per_second": 89.725, |
| "eval_steps_per_second": 44.862, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.048788137512850445, |
| "grad_norm": 0.6354503035545349, |
| "learning_rate": 2.2787900387914035e-05, |
| "loss": 32.89923095703125, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.048788137512850445, |
| "eval_loss": 3.889650344848633, |
| "eval_runtime": 135.6805, |
| "eval_samples_per_second": 94.0, |
| "eval_steps_per_second": 47.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.05227300447805405, |
| "grad_norm": 0.4500903785228729, |
| "learning_rate": 2.238115875144865e-05, |
| "loss": 31.9859375, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.05227300447805405, |
| "eval_loss": 3.881140947341919, |
| "eval_runtime": 137.1013, |
| "eval_samples_per_second": 93.026, |
| "eval_steps_per_second": 46.513, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.05575787144325765, |
| "grad_norm": 0.7105244994163513, |
| "learning_rate": 2.1944408360615527e-05, |
| "loss": 31.830234375, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.05575787144325765, |
| "eval_loss": 3.876532554626465, |
| "eval_runtime": 138.0891, |
| "eval_samples_per_second": 92.361, |
| "eval_steps_per_second": 46.18, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.059242738408461254, |
| "grad_norm": 0.5426522493362427, |
| "learning_rate": 2.147897561199711e-05, |
| "loss": 32.8569921875, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.059242738408461254, |
| "eval_loss": 3.869863510131836, |
| "eval_runtime": 137.3068, |
| "eval_samples_per_second": 92.887, |
| "eval_steps_per_second": 46.443, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.06272760537366485, |
| "grad_norm": 0.6868773698806763, |
| "learning_rate": 2.0986274009553747e-05, |
| "loss": 33.1663525390625, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.06272760537366485, |
| "eval_loss": 3.858783483505249, |
| "eval_runtime": 136.4747, |
| "eval_samples_per_second": 93.453, |
| "eval_steps_per_second": 46.727, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.06621247233886847, |
| "grad_norm": 0.6488957405090332, |
| "learning_rate": 2.0467799871858624e-05, |
| "loss": 32.170732421875, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.06621247233886847, |
| "eval_loss": 3.857388496398926, |
| "eval_runtime": 138.5464, |
| "eval_samples_per_second": 92.056, |
| "eval_steps_per_second": 46.028, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.06969733930407207, |
| "grad_norm": 0.5700647830963135, |
| "learning_rate": 1.9925127787827415e-05, |
| "loss": 32.3882470703125, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.06969733930407207, |
| "eval_loss": 3.852177619934082, |
| "eval_runtime": 137.7764, |
| "eval_samples_per_second": 92.57, |
| "eval_steps_per_second": 46.285, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.07318220626927567, |
| "grad_norm": 0.6471461653709412, |
| "learning_rate": 1.9359905834743513e-05, |
| "loss": 32.83000244140625, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.07318220626927567, |
| "eval_loss": 3.8465960025787354, |
| "eval_runtime": 137.4128, |
| "eval_samples_per_second": 92.815, |
| "eval_steps_per_second": 46.408, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.07666707323447927, |
| "grad_norm": 0.6369190812110901, |
| "learning_rate": 1.8773850573101503e-05, |
| "loss": 32.35257080078125, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.07666707323447927, |
| "eval_loss": 3.842385768890381, |
| "eval_runtime": 140.2355, |
| "eval_samples_per_second": 90.947, |
| "eval_steps_per_second": 45.474, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.08015194019968287, |
| "grad_norm": 0.5800191164016724, |
| "learning_rate": 1.8168741833469327e-05, |
| "loss": 31.9875244140625, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.08015194019968287, |
| "eval_loss": 3.8325023651123047, |
| "eval_runtime": 137.4074, |
| "eval_samples_per_second": 92.819, |
| "eval_steps_per_second": 46.409, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.08363680716488649, |
| "grad_norm": 0.655426025390625, |
| "learning_rate": 1.7546417311201357e-05, |
| "loss": 31.470654296875, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.08363680716488649, |
| "eval_loss": 3.82979416847229, |
| "eval_runtime": 136.3318, |
| "eval_samples_per_second": 93.551, |
| "eval_steps_per_second": 46.776, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.08712167413009009, |
| "grad_norm": 0.5678662657737732, |
| "learning_rate": 1.690876698541802e-05, |
| "loss": 32.25173828125, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.08712167413009009, |
| "eval_loss": 3.828555107116699, |
| "eval_runtime": 142.3008, |
| "eval_samples_per_second": 89.627, |
| "eval_steps_per_second": 44.814, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.09060654109529369, |
| "grad_norm": 0.6696360111236572, |
| "learning_rate": 1.625772737920128e-05, |
| "loss": 32.847529296875, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.09060654109529369, |
| "eval_loss": 3.8212130069732666, |
| "eval_runtime": 145.4915, |
| "eval_samples_per_second": 87.661, |
| "eval_steps_per_second": 43.831, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.09409140806049729, |
| "grad_norm": 0.6813345551490784, |
| "learning_rate": 1.5595275678437756e-05, |
| "loss": 32.22562744140625, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.09409140806049729, |
| "eval_loss": 3.8163504600524902, |
| "eval_runtime": 135.9053, |
| "eval_samples_per_second": 93.845, |
| "eval_steps_per_second": 46.922, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.09757627502570089, |
| "grad_norm": 0.6201620101928711, |
| "learning_rate": 1.4923423727170106e-05, |
| "loss": 32.73896240234375, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.09757627502570089, |
| "eval_loss": 3.8148138523101807, |
| "eval_runtime": 140.771, |
| "eval_samples_per_second": 90.601, |
| "eval_steps_per_second": 45.301, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.10106114199090449, |
| "grad_norm": 0.6953298449516296, |
| "learning_rate": 1.4244211917692812e-05, |
| "loss": 32.32746826171875, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.10106114199090449, |
| "eval_loss": 3.8123884201049805, |
| "eval_runtime": 141.0245, |
| "eval_samples_per_second": 90.438, |
| "eval_steps_per_second": 45.219, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.1045460089561081, |
| "grad_norm": 0.7098183035850525, |
| "learning_rate": 1.355970299394786e-05, |
| "loss": 32.90800048828125, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.1045460089561081, |
| "eval_loss": 3.810453414916992, |
| "eval_runtime": 138.6332, |
| "eval_samples_per_second": 91.998, |
| "eval_steps_per_second": 45.999, |
| "step": 750 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 1500, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 750, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 574777589760000.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
