| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 78, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01282051282051282, | |
| "grad_norm": 23.535282117342813, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.9389, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02564102564102564, | |
| "grad_norm": 30.95165111144086, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.1153, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.038461538461538464, | |
| "grad_norm": 21.427477034083225, | |
| "learning_rate": 2e-05, | |
| "loss": 0.908, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05128205128205128, | |
| "grad_norm": 17.928895689942703, | |
| "learning_rate": 1.9991228300988586e-05, | |
| "loss": 0.7206, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0641025641025641, | |
| "grad_norm": 20.46581420059138, | |
| "learning_rate": 1.9964928592495046e-05, | |
| "loss": 0.8048, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 9.533694744269097, | |
| "learning_rate": 1.9921147013144782e-05, | |
| "loss": 0.6909, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08974358974358974, | |
| "grad_norm": 7.154372229051495, | |
| "learning_rate": 1.985996037070505e-05, | |
| "loss": 0.7208, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 6.050595599777209, | |
| "learning_rate": 1.9781476007338058e-05, | |
| "loss": 0.5383, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11538461538461539, | |
| "grad_norm": 4.81529735005149, | |
| "learning_rate": 1.9685831611286312e-05, | |
| "loss": 0.5185, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1282051282051282, | |
| "grad_norm": 5.904610892485658, | |
| "learning_rate": 1.9573194975320672e-05, | |
| "loss": 0.5649, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14102564102564102, | |
| "grad_norm": 5.012548893301235, | |
| "learning_rate": 1.944376370237481e-05, | |
| "loss": 0.6025, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 3.4664366084608105, | |
| "learning_rate": 1.9297764858882516e-05, | |
| "loss": 0.4299, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 4.713790985225752, | |
| "learning_rate": 1.913545457642601e-05, | |
| "loss": 0.6949, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1794871794871795, | |
| "grad_norm": 4.777031980778873, | |
| "learning_rate": 1.895711760239413e-05, | |
| "loss": 0.5172, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19230769230769232, | |
| "grad_norm": 3.3607607535520345, | |
| "learning_rate": 1.8763066800438638e-05, | |
| "loss": 0.4786, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 4.861766646485932, | |
| "learning_rate": 1.855364260160507e-05, | |
| "loss": 0.4538, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.21794871794871795, | |
| "grad_norm": 4.173446943768888, | |
| "learning_rate": 1.8329212407100996e-05, | |
| "loss": 0.6317, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 3.857794925631418, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 0.5543, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24358974358974358, | |
| "grad_norm": 3.589848386643151, | |
| "learning_rate": 1.78369345732584e-05, | |
| "loss": 0.5853, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 5.135379268595713, | |
| "learning_rate": 1.7569950556517566e-05, | |
| "loss": 0.5254, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2692307692307692, | |
| "grad_norm": 4.251176222586967, | |
| "learning_rate": 1.7289686274214116e-05, | |
| "loss": 0.5944, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.28205128205128205, | |
| "grad_norm": 3.870818396954739, | |
| "learning_rate": 1.6996633405133656e-05, | |
| "loss": 0.5656, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2948717948717949, | |
| "grad_norm": 3.342745967846155, | |
| "learning_rate": 1.6691306063588583e-05, | |
| "loss": 0.5327, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 4.502112335496065, | |
| "learning_rate": 1.63742398974869e-05, | |
| "loss": 0.5252, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.32051282051282054, | |
| "grad_norm": 4.61897270876649, | |
| "learning_rate": 1.6045991148623752e-05, | |
| "loss": 0.7316, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 4.630378520341254, | |
| "learning_rate": 1.570713567684432e-05, | |
| "loss": 0.5961, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.34615384615384615, | |
| "grad_norm": 3.4435955161971847, | |
| "learning_rate": 1.5358267949789968e-05, | |
| "loss": 0.3898, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.358974358974359, | |
| "grad_norm": 3.6296714817244355, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.5917, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3717948717948718, | |
| "grad_norm": 3.553076230658495, | |
| "learning_rate": 1.463296035119862e-05, | |
| "loss": 0.4686, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 3.3205165192761865, | |
| "learning_rate": 1.4257792915650728e-05, | |
| "loss": 0.5327, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3974358974358974, | |
| "grad_norm": 4.258971760384096, | |
| "learning_rate": 1.3875155864521031e-05, | |
| "loss": 0.5969, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 4.160699064174649, | |
| "learning_rate": 1.3485720473218153e-05, | |
| "loss": 0.5726, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4230769230769231, | |
| "grad_norm": 3.8858738820549443, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 0.481, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4358974358974359, | |
| "grad_norm": 3.5923086165234364, | |
| "learning_rate": 1.2689198206152657e-05, | |
| "loss": 0.4831, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.44871794871794873, | |
| "grad_norm": 3.040207060233123, | |
| "learning_rate": 1.2283508701106559e-05, | |
| "loss": 0.4379, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 4.835462956087315, | |
| "learning_rate": 1.187381314585725e-05, | |
| "loss": 0.5842, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.47435897435897434, | |
| "grad_norm": 3.430545038253428, | |
| "learning_rate": 1.1460830285624119e-05, | |
| "loss": 0.4721, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.48717948717948717, | |
| "grad_norm": 3.550867514464785, | |
| "learning_rate": 1.1045284632676535e-05, | |
| "loss": 0.5327, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 4.25197469639109, | |
| "learning_rate": 1.0627905195293135e-05, | |
| "loss": 0.5851, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 5.301567871121325, | |
| "learning_rate": 1.0209424198833571e-05, | |
| "loss": 0.6567, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5256410256410257, | |
| "grad_norm": 4.76666007720682, | |
| "learning_rate": 9.790575801166432e-06, | |
| "loss": 0.5344, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 4.628624999659393, | |
| "learning_rate": 9.372094804706867e-06, | |
| "loss": 0.5901, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5512820512820513, | |
| "grad_norm": 2.7785526596724655, | |
| "learning_rate": 8.954715367323468e-06, | |
| "loss": 0.4797, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5641025641025641, | |
| "grad_norm": 3.793194400617578, | |
| "learning_rate": 8.539169714375885e-06, | |
| "loss": 0.5728, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5769230769230769, | |
| "grad_norm": 3.016128749634024, | |
| "learning_rate": 8.126186854142752e-06, | |
| "loss": 0.4808, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5897435897435898, | |
| "grad_norm": 3.992077099503845, | |
| "learning_rate": 7.716491298893443e-06, | |
| "loss": 0.5197, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6025641025641025, | |
| "grad_norm": 4.490369000424712, | |
| "learning_rate": 7.310801793847344e-06, | |
| "loss": 0.4184, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 2.33159901322508, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 0.3481, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6282051282051282, | |
| "grad_norm": 2.550092727870004, | |
| "learning_rate": 6.5142795267818505e-06, | |
| "loss": 0.3653, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6410256410256411, | |
| "grad_norm": 2.6572708529729487, | |
| "learning_rate": 6.124844135478971e-06, | |
| "loss": 0.4036, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6538461538461539, | |
| "grad_norm": 4.037851736171114, | |
| "learning_rate": 5.742207084349274e-06, | |
| "loss": 0.5075, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 2.9926759956064877, | |
| "learning_rate": 5.367039648801386e-06, | |
| "loss": 0.4551, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.6794871794871795, | |
| "grad_norm": 2.8400263733822477, | |
| "learning_rate": 5.000000000000003e-06, | |
| "loss": 0.515, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 3.8124291528622973, | |
| "learning_rate": 4.641732050210032e-06, | |
| "loss": 0.5086, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.7051282051282052, | |
| "grad_norm": 2.841356103484977, | |
| "learning_rate": 4.292864323155684e-06, | |
| "loss": 0.4376, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 3.142335016274588, | |
| "learning_rate": 3.954008851376252e-06, | |
| "loss": 0.4039, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.7307692307692307, | |
| "grad_norm": 2.852087372917465, | |
| "learning_rate": 3.625760102513103e-06, | |
| "loss": 0.5008, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.7435897435897436, | |
| "grad_norm": 3.324712819809194, | |
| "learning_rate": 3.308693936411421e-06, | |
| "loss": 0.4739, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.7564102564102564, | |
| "grad_norm": 2.9649459892785535, | |
| "learning_rate": 3.003366594866345e-06, | |
| "loss": 0.5892, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 3.044018836047704, | |
| "learning_rate": 2.7103137257858867e-06, | |
| "loss": 0.4852, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.782051282051282, | |
| "grad_norm": 4.050018523402415, | |
| "learning_rate": 2.4300494434824373e-06, | |
| "loss": 0.591, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.7948717948717948, | |
| "grad_norm": 2.3281157099809398, | |
| "learning_rate": 2.163065426741603e-06, | |
| "loss": 0.4416, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.8076923076923077, | |
| "grad_norm": 2.9262958648242883, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 0.4393, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 3.884834370223603, | |
| "learning_rate": 1.6707875928990059e-06, | |
| "loss": 0.5305, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 3.5229544410053544, | |
| "learning_rate": 1.446357398394934e-06, | |
| "loss": 0.5226, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 3.550541933958789, | |
| "learning_rate": 1.2369331995613664e-06, | |
| "loss": 0.6602, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.8589743589743589, | |
| "grad_norm": 3.077396885216065, | |
| "learning_rate": 1.042882397605871e-06, | |
| "loss": 0.4248, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.8717948717948718, | |
| "grad_norm": 3.1902818565830784, | |
| "learning_rate": 8.645454235739903e-07, | |
| "loss": 0.4756, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.8846153846153846, | |
| "grad_norm": 2.9790818845625346, | |
| "learning_rate": 7.022351411174866e-07, | |
| "loss": 0.4006, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.8974358974358975, | |
| "grad_norm": 4.103022950661447, | |
| "learning_rate": 5.562362976251901e-07, | |
| "loss": 0.5541, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9102564102564102, | |
| "grad_norm": 3.414968428161163, | |
| "learning_rate": 4.268050246793276e-07, | |
| "loss": 0.5879, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 2.992490474364374, | |
| "learning_rate": 3.1416838871368925e-07, | |
| "loss": 0.435, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.9358974358974359, | |
| "grad_norm": 3.207632291423965, | |
| "learning_rate": 2.1852399266194312e-07, | |
| "loss": 0.4987, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.9487179487179487, | |
| "grad_norm": 2.9139113123937044, | |
| "learning_rate": 1.400396292949513e-07, | |
| "loss": 0.4156, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.9615384615384616, | |
| "grad_norm": 2.536721514944869, | |
| "learning_rate": 7.885298685522235e-08, | |
| "loss": 0.4533, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.9743589743589743, | |
| "grad_norm": 2.586955803538133, | |
| "learning_rate": 3.50714075049563e-08, | |
| "loss": 0.4356, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.9871794871794872, | |
| "grad_norm": 2.8019180608719463, | |
| "learning_rate": 8.771699011416169e-09, | |
| "loss": 0.3865, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.8737311595523893, | |
| "learning_rate": 0.0, | |
| "loss": 0.4296, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 78, | |
| "total_flos": 112793145835520.0, | |
| "train_loss": 0.5409963910396283, | |
| "train_runtime": 7617.3016, | |
| "train_samples_per_second": 1.147, | |
| "train_steps_per_second": 0.01 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 78, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 112793145835520.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |