| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02900199033266989, | |
| "eval_steps": 34, | |
| "global_step": 102, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002843332385555871, | |
| "eval_loss": 1.5018354654312134, | |
| "eval_runtime": 166.295, | |
| "eval_samples_per_second": 35.623, | |
| "eval_steps_per_second": 4.456, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008529997156667614, | |
| "grad_norm": 0.7210565209388733, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.5223, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017059994313335229, | |
| "grad_norm": 0.6832892298698425, | |
| "learning_rate": 3e-05, | |
| "loss": 1.5221, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0025589991470002845, | |
| "grad_norm": 0.7228020429611206, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.408, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0034119988626670457, | |
| "grad_norm": 0.6384875774383545, | |
| "learning_rate": 4.999675562428437e-05, | |
| "loss": 1.4404, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004264998578333807, | |
| "grad_norm": 0.3351251482963562, | |
| "learning_rate": 4.9979724954289244e-05, | |
| "loss": 1.3736, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005117998294000569, | |
| "grad_norm": 0.182565838098526, | |
| "learning_rate": 4.994810682835951e-05, | |
| "loss": 1.3079, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00597099800966733, | |
| "grad_norm": 0.19113591313362122, | |
| "learning_rate": 4.990191971059033e-05, | |
| "loss": 1.316, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0068239977253340914, | |
| "grad_norm": 0.1948336660861969, | |
| "learning_rate": 4.984119057295783e-05, | |
| "loss": 1.2426, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007676997441000853, | |
| "grad_norm": 0.18684643507003784, | |
| "learning_rate": 4.976595487956823e-05, | |
| "loss": 1.2503, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008529997156667614, | |
| "grad_norm": 0.18414735794067383, | |
| "learning_rate": 4.967625656594782e-05, | |
| "loss": 1.2323, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009382996872334376, | |
| "grad_norm": 0.17294025421142578, | |
| "learning_rate": 4.957214801338581e-05, | |
| "loss": 1.1942, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009667330110889964, | |
| "eval_loss": 1.1813108921051025, | |
| "eval_runtime": 167.7438, | |
| "eval_samples_per_second": 35.316, | |
| "eval_steps_per_second": 4.417, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.010235996588001138, | |
| "grad_norm": 0.16702412068843842, | |
| "learning_rate": 4.9453690018345144e-05, | |
| "loss": 1.1981, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.011088996303667898, | |
| "grad_norm": 0.1968175172805786, | |
| "learning_rate": 4.932095175695911e-05, | |
| "loss": 1.1675, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01194199601933466, | |
| "grad_norm": 0.18244469165802002, | |
| "learning_rate": 4.917401074463441e-05, | |
| "loss": 1.1584, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01279499573500142, | |
| "grad_norm": 0.16749081015586853, | |
| "learning_rate": 4.901295279078431e-05, | |
| "loss": 1.1134, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.013647995450668183, | |
| "grad_norm": 0.17398597300052643, | |
| "learning_rate": 4.883787194871841e-05, | |
| "loss": 1.1139, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.014500995166334945, | |
| "grad_norm": 0.17164087295532227, | |
| "learning_rate": 4.864887046071813e-05, | |
| "loss": 1.079, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.015353994882001705, | |
| "grad_norm": 0.1644001007080078, | |
| "learning_rate": 4.8446058698330115e-05, | |
| "loss": 1.0646, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.01620699459766847, | |
| "grad_norm": 0.16490623354911804, | |
| "learning_rate": 4.822955509791233e-05, | |
| "loss": 1.0739, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.017059994313335228, | |
| "grad_norm": 0.17708458006381989, | |
| "learning_rate": 4.799948609147061e-05, | |
| "loss": 1.0897, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01791299402900199, | |
| "grad_norm": 0.15597032010555267, | |
| "learning_rate": 4.7755986032825864e-05, | |
| "loss": 1.0566, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.018765993744668752, | |
| "grad_norm": 0.17728550732135773, | |
| "learning_rate": 4.74991971191553e-05, | |
| "loss": 1.0275, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.019334660221779928, | |
| "eval_loss": 1.0011852979660034, | |
| "eval_runtime": 168.1174, | |
| "eval_samples_per_second": 35.237, | |
| "eval_steps_per_second": 4.408, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.019618993460335514, | |
| "grad_norm": 0.16994404792785645, | |
| "learning_rate": 4.7229269307953235e-05, | |
| "loss": 0.9841, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.020471993176002276, | |
| "grad_norm": 0.17181497812271118, | |
| "learning_rate": 4.694636022946012e-05, | |
| "loss": 0.9944, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.021324992891669035, | |
| "grad_norm": 0.21411621570587158, | |
| "learning_rate": 4.665063509461097e-05, | |
| "loss": 1.0013, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.022177992607335797, | |
| "grad_norm": 0.19594340026378632, | |
| "learning_rate": 4.6342266598556814e-05, | |
| "loss": 0.9969, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.02303099232300256, | |
| "grad_norm": 0.2057276964187622, | |
| "learning_rate": 4.6021434819815555e-05, | |
| "loss": 0.9808, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.02388399203866932, | |
| "grad_norm": 0.21778051555156708, | |
| "learning_rate": 4.568832711511125e-05, | |
| "loss": 0.9456, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.024736991754336083, | |
| "grad_norm": 0.21349306404590607, | |
| "learning_rate": 4.534313800996299e-05, | |
| "loss": 0.953, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.02558999147000284, | |
| "grad_norm": 0.21818219125270844, | |
| "learning_rate": 4.498606908508754e-05, | |
| "loss": 0.9133, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.026442991185669604, | |
| "grad_norm": 0.2510223388671875, | |
| "learning_rate": 4.46173288586818e-05, | |
| "loss": 0.9125, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.027295990901336366, | |
| "grad_norm": 0.24031595885753632, | |
| "learning_rate": 4.4237132664654154e-05, | |
| "loss": 0.8784, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.028148990617003128, | |
| "grad_norm": 0.2543729543685913, | |
| "learning_rate": 4.384570252687542e-05, | |
| "loss": 0.8984, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.02900199033266989, | |
| "grad_norm": 0.27020716667175293, | |
| "learning_rate": 4.344326702952326e-05, | |
| "loss": 0.8719, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.02900199033266989, | |
| "eval_loss": 0.8574855923652649, | |
| "eval_runtime": 168.0651, | |
| "eval_samples_per_second": 35.248, | |
| "eval_steps_per_second": 4.409, | |
| "step": 102 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 34, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.2664001796112384e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |