| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 27.149321266968325, | |
| "eval_steps": 1000, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.9201030731201172, | |
| "eval_runtime": 10.5666, | |
| "eval_samples_per_second": 20.915, | |
| "eval_steps_per_second": 5.3, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.8042283058166504, | |
| "eval_runtime": 10.5219, | |
| "eval_samples_per_second": 21.004, | |
| "eval_steps_per_second": 5.322, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 4.622926093514329e-05, | |
| "loss": 2.1534, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.7254605293273926, | |
| "eval_runtime": 10.5492, | |
| "eval_samples_per_second": 20.95, | |
| "eval_steps_per_second": 5.308, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.653130054473877, | |
| "eval_runtime": 10.5858, | |
| "eval_samples_per_second": 20.877, | |
| "eval_steps_per_second": 5.29, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 4.52, | |
| "learning_rate": 4.2458521870286574e-05, | |
| "loss": 1.8808, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.5984195470809937, | |
| "eval_runtime": 10.5172, | |
| "eval_samples_per_second": 21.013, | |
| "eval_steps_per_second": 5.325, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.5462396144866943, | |
| "eval_runtime": 10.5813, | |
| "eval_samples_per_second": 20.886, | |
| "eval_steps_per_second": 5.292, | |
| "step": 1326 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 3.868778280542987e-05, | |
| "loss": 1.7597, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.4970717430114746, | |
| "eval_runtime": 10.5617, | |
| "eval_samples_per_second": 20.925, | |
| "eval_steps_per_second": 5.302, | |
| "step": 1547 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.4608112573623657, | |
| "eval_runtime": 10.5482, | |
| "eval_samples_per_second": 20.952, | |
| "eval_steps_per_second": 5.309, | |
| "step": 1768 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.426717758178711, | |
| "eval_runtime": 10.5377, | |
| "eval_samples_per_second": 20.972, | |
| "eval_steps_per_second": 5.314, | |
| "step": 1989 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 3.491704374057315e-05, | |
| "loss": 1.673, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.3964918851852417, | |
| "eval_runtime": 10.5931, | |
| "eval_samples_per_second": 20.863, | |
| "eval_steps_per_second": 5.286, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.3659923076629639, | |
| "eval_runtime": 10.5424, | |
| "eval_samples_per_second": 20.963, | |
| "eval_steps_per_second": 5.312, | |
| "step": 2431 | |
| }, | |
| { | |
| "epoch": 11.31, | |
| "learning_rate": 3.114630467571644e-05, | |
| "loss": 1.6087, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.3398691415786743, | |
| "eval_runtime": 10.5482, | |
| "eval_samples_per_second": 20.951, | |
| "eval_steps_per_second": 5.309, | |
| "step": 2652 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.3123878240585327, | |
| "eval_runtime": 10.4901, | |
| "eval_samples_per_second": 21.067, | |
| "eval_steps_per_second": 5.338, | |
| "step": 2873 | |
| }, | |
| { | |
| "epoch": 13.57, | |
| "learning_rate": 2.737556561085973e-05, | |
| "loss": 1.5523, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.2912379503250122, | |
| "eval_runtime": 10.5302, | |
| "eval_samples_per_second": 20.987, | |
| "eval_steps_per_second": 5.318, | |
| "step": 3094 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.2690876722335815, | |
| "eval_runtime": 10.5127, | |
| "eval_samples_per_second": 21.022, | |
| "eval_steps_per_second": 5.327, | |
| "step": 3315 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 2.3604826546003017e-05, | |
| "loss": 1.5072, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.2487969398498535, | |
| "eval_runtime": 10.5677, | |
| "eval_samples_per_second": 20.913, | |
| "eval_steps_per_second": 5.299, | |
| "step": 3536 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.2326879501342773, | |
| "eval_runtime": 10.5424, | |
| "eval_samples_per_second": 20.963, | |
| "eval_steps_per_second": 5.312, | |
| "step": 3757 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.2160953283309937, | |
| "eval_runtime": 10.5427, | |
| "eval_samples_per_second": 20.962, | |
| "eval_steps_per_second": 5.312, | |
| "step": 3978 | |
| }, | |
| { | |
| "epoch": 18.1, | |
| "learning_rate": 1.9834087481146303e-05, | |
| "loss": 1.4711, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.2029471397399902, | |
| "eval_runtime": 10.5308, | |
| "eval_samples_per_second": 20.986, | |
| "eval_steps_per_second": 5.318, | |
| "step": 4199 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.1921287775039673, | |
| "eval_runtime": 10.5502, | |
| "eval_samples_per_second": 20.948, | |
| "eval_steps_per_second": 5.308, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 20.36, | |
| "learning_rate": 1.6063348416289596e-05, | |
| "loss": 1.4329, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 1.1807990074157715, | |
| "eval_runtime": 10.5791, | |
| "eval_samples_per_second": 20.89, | |
| "eval_steps_per_second": 5.293, | |
| "step": 4641 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 1.170788288116455, | |
| "eval_runtime": 10.5201, | |
| "eval_samples_per_second": 21.007, | |
| "eval_steps_per_second": 5.323, | |
| "step": 4862 | |
| }, | |
| { | |
| "epoch": 22.62, | |
| "learning_rate": 1.229260935143288e-05, | |
| "loss": 1.4091, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 1.1616638898849487, | |
| "eval_runtime": 10.541, | |
| "eval_samples_per_second": 20.966, | |
| "eval_steps_per_second": 5.313, | |
| "step": 5083 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 1.1520771980285645, | |
| "eval_runtime": 10.5678, | |
| "eval_samples_per_second": 20.913, | |
| "eval_steps_per_second": 5.299, | |
| "step": 5304 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 8.52187028657617e-06, | |
| "loss": 1.392, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 1.1455986499786377, | |
| "eval_runtime": 10.5773, | |
| "eval_samples_per_second": 20.894, | |
| "eval_steps_per_second": 5.294, | |
| "step": 5525 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_loss": 1.1402668952941895, | |
| "eval_runtime": 10.5575, | |
| "eval_samples_per_second": 20.933, | |
| "eval_steps_per_second": 5.304, | |
| "step": 5746 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_loss": 1.1367387771606445, | |
| "eval_runtime": 10.5633, | |
| "eval_samples_per_second": 20.921, | |
| "eval_steps_per_second": 5.301, | |
| "step": 5967 | |
| }, | |
| { | |
| "epoch": 27.15, | |
| "learning_rate": 4.751131221719457e-06, | |
| "loss": 1.3771, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6630, | |
| "num_train_epochs": 30, | |
| "save_steps": 1000, | |
| "total_flos": 9484103172096000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |