| { | |
| "best_metric": 1.0650867223739624, | |
| "best_model_checkpoint": "autotrain-byt8e-zygc3/checkpoint-1082", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1082, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02310536044362292, | |
| "grad_norm": 3.5127339363098145, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 1.0872, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04621072088724584, | |
| "grad_norm": 6.642369270324707, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 1.1215, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06931608133086876, | |
| "grad_norm": 6.217954158782959, | |
| "learning_rate": 0.0001153846153846154, | |
| "loss": 1.0733, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09242144177449169, | |
| "grad_norm": 2.9232001304626465, | |
| "learning_rate": 0.00015384615384615385, | |
| "loss": 1.1347, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11552680221811461, | |
| "grad_norm": 3.7540340423583984, | |
| "learning_rate": 0.00019230769230769233, | |
| "loss": 1.3273, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.13863216266173753, | |
| "grad_norm": 4.9391679763793945, | |
| "learning_rate": 0.0002307692307692308, | |
| "loss": 1.1507, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.16173752310536044, | |
| "grad_norm": 1.5326274633407593, | |
| "learning_rate": 0.0002692307692307692, | |
| "loss": 1.1118, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.18484288354898337, | |
| "grad_norm": 1.3186924457550049, | |
| "learning_rate": 0.0003076923076923077, | |
| "loss": 1.1426, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.20794824399260628, | |
| "grad_norm": 3.582869052886963, | |
| "learning_rate": 0.00034615384615384613, | |
| "loss": 1.175, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.23105360443622922, | |
| "grad_norm": 2.4438865184783936, | |
| "learning_rate": 0.00038461538461538467, | |
| "loss": 1.0483, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2541589648798521, | |
| "grad_norm": 6.818902492523193, | |
| "learning_rate": 0.0004230769230769231, | |
| "loss": 1.0661, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.27726432532347506, | |
| "grad_norm": 1.4846845865249634, | |
| "learning_rate": 0.0004615384615384616, | |
| "loss": 1.1412, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.300369685767098, | |
| "grad_norm": 1.0014742612838745, | |
| "learning_rate": 0.0005, | |
| "loss": 1.0968, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.3234750462107209, | |
| "grad_norm": 0.8473600745201111, | |
| "learning_rate": 0.0004957206436152003, | |
| "loss": 1.1779, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3465804066543438, | |
| "grad_norm": 3.419077157974243, | |
| "learning_rate": 0.0004914412872304005, | |
| "loss": 1.1943, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.36968576709796674, | |
| "grad_norm": 0.8151220083236694, | |
| "learning_rate": 0.00048716193084560086, | |
| "loss": 1.0639, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3927911275415896, | |
| "grad_norm": 1.3580329418182373, | |
| "learning_rate": 0.0004828825744608011, | |
| "loss": 1.2678, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.41589648798521256, | |
| "grad_norm": 0.5541791319847107, | |
| "learning_rate": 0.0004786032180760014, | |
| "loss": 1.1612, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4390018484288355, | |
| "grad_norm": 1.164920449256897, | |
| "learning_rate": 0.0004743238616912017, | |
| "loss": 1.1855, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.46210720887245843, | |
| "grad_norm": 4.518599987030029, | |
| "learning_rate": 0.0004700445053064019, | |
| "loss": 1.1385, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4852125693160813, | |
| "grad_norm": 0.9030762910842896, | |
| "learning_rate": 0.0004657651489216022, | |
| "loss": 1.1228, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5083179297597042, | |
| "grad_norm": 1.1489505767822266, | |
| "learning_rate": 0.00046148579253680244, | |
| "loss": 1.145, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5314232902033271, | |
| "grad_norm": 0.9008183479309082, | |
| "learning_rate": 0.00045720643615200274, | |
| "loss": 1.1385, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.5545286506469501, | |
| "grad_norm": 0.9687894582748413, | |
| "learning_rate": 0.00045292707976720304, | |
| "loss": 1.1424, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.577634011090573, | |
| "grad_norm": 0.43966954946517944, | |
| "learning_rate": 0.0004486477233824033, | |
| "loss": 1.1123, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.600739371534196, | |
| "grad_norm": 0.9648946523666382, | |
| "learning_rate": 0.0004443683669976036, | |
| "loss": 0.9658, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6238447319778189, | |
| "grad_norm": 1.1458590030670166, | |
| "learning_rate": 0.00044008901061280383, | |
| "loss": 1.1779, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.6469500924214417, | |
| "grad_norm": 1.6918909549713135, | |
| "learning_rate": 0.00043580965422800413, | |
| "loss": 1.0564, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6700554528650647, | |
| "grad_norm": 0.38883867859840393, | |
| "learning_rate": 0.00043153029784320443, | |
| "loss": 1.1518, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.6931608133086876, | |
| "grad_norm": 1.109215497970581, | |
| "learning_rate": 0.0004272509414584047, | |
| "loss": 1.0493, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7162661737523105, | |
| "grad_norm": 4.412217140197754, | |
| "learning_rate": 0.000422971585073605, | |
| "loss": 1.0994, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.7393715341959335, | |
| "grad_norm": 0.6967116594314575, | |
| "learning_rate": 0.00041869222868880517, | |
| "loss": 1.1258, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7624768946395564, | |
| "grad_norm": 1.0759273767471313, | |
| "learning_rate": 0.00041441287230400547, | |
| "loss": 1.0622, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.7855822550831792, | |
| "grad_norm": 1.6998566389083862, | |
| "learning_rate": 0.00041013351591920577, | |
| "loss": 1.0942, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.8086876155268022, | |
| "grad_norm": 1.0458375215530396, | |
| "learning_rate": 0.000405854159534406, | |
| "loss": 1.0698, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.8317929759704251, | |
| "grad_norm": 1.579179048538208, | |
| "learning_rate": 0.0004015748031496063, | |
| "loss": 0.9733, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.8548983364140481, | |
| "grad_norm": 1.5911906957626343, | |
| "learning_rate": 0.00039729544676480656, | |
| "loss": 1.1809, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.878003696857671, | |
| "grad_norm": 0.30177101492881775, | |
| "learning_rate": 0.00039301609038000686, | |
| "loss": 1.0625, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.9011090573012939, | |
| "grad_norm": 0.9385190606117249, | |
| "learning_rate": 0.00038873673399520716, | |
| "loss": 1.0929, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.9242144177449169, | |
| "grad_norm": 1.7940095663070679, | |
| "learning_rate": 0.0003844573776104074, | |
| "loss": 1.1022, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9473197781885397, | |
| "grad_norm": 0.8840867280960083, | |
| "learning_rate": 0.0003801780212256077, | |
| "loss": 1.0802, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.9704251386321626, | |
| "grad_norm": 0.9084434509277344, | |
| "learning_rate": 0.00037589866484080795, | |
| "loss": 1.1098, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.9935304990757856, | |
| "grad_norm": 1.4320096969604492, | |
| "learning_rate": 0.00037161930845600825, | |
| "loss": 1.1118, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.4584103512014787, | |
| "eval_f1_macro": 0.2095479509928179, | |
| "eval_f1_micro": 0.4584103512014787, | |
| "eval_f1_weighted": 0.2881768494245037, | |
| "eval_loss": 1.0650867223739624, | |
| "eval_precision_macro": 0.1528034504004929, | |
| "eval_precision_micro": 0.4584103512014787, | |
| "eval_precision_weighted": 0.21014005008866307, | |
| "eval_recall_macro": 0.3333333333333333, | |
| "eval_recall_micro": 0.4584103512014787, | |
| "eval_recall_weighted": 0.4584103512014787, | |
| "eval_runtime": 190.8807, | |
| "eval_samples_per_second": 5.668, | |
| "eval_steps_per_second": 0.712, | |
| "step": 1082 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 3246, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 284688717981696.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |