| { | |
| "best_metric": 0.4444444444444444, | |
| "best_model_checkpoint": "./save_phi2_ft_lora/checkpoint-500", | |
| "epoch": 0.1453699665649077, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0029073993312981536, | |
| "grad_norm": 4.615232944488525, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 6.6211, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005814798662596307, | |
| "grad_norm": 5.528043746948242, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 6.5222, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00872219799389446, | |
| "grad_norm": 6.019925594329834, | |
| "learning_rate": 3e-06, | |
| "loss": 6.4104, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011629597325192614, | |
| "grad_norm": 7.163036823272705, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 6.0366, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01453699665649077, | |
| "grad_norm": 7.888458251953125, | |
| "learning_rate": 5e-06, | |
| "loss": 5.4618, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01744439598778892, | |
| "grad_norm": 9.86289119720459, | |
| "learning_rate": 6e-06, | |
| "loss": 4.526, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.020351795319087075, | |
| "grad_norm": 9.114004135131836, | |
| "learning_rate": 7.000000000000001e-06, | |
| "loss": 3.2234, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.02325919465038523, | |
| "grad_norm": 6.198110103607178, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.6796, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.026166593981683386, | |
| "grad_norm": 1.2424126863479614, | |
| "learning_rate": 9e-06, | |
| "loss": 0.6189, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02907399331298154, | |
| "grad_norm": 0.20757392048835754, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2989, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03198139264427969, | |
| "grad_norm": 0.19180330634117126, | |
| "learning_rate": 1.1000000000000001e-05, | |
| "loss": 0.3434, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03488879197557784, | |
| "grad_norm": 0.17373745143413544, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.2775, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.037796191306876, | |
| "grad_norm": 0.14247311651706696, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.291, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.04070359063817415, | |
| "grad_norm": 0.1189289391040802, | |
| "learning_rate": 1.4000000000000001e-05, | |
| "loss": 0.2549, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.043610989969472304, | |
| "grad_norm": 0.11715172231197357, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.2334, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.04651838930077046, | |
| "grad_norm": 0.16550108790397644, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.2515, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.04942578863206862, | |
| "grad_norm": 0.13685165345668793, | |
| "learning_rate": 1.7000000000000003e-05, | |
| "loss": 0.2757, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.05233318796336677, | |
| "grad_norm": 0.13247624039649963, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.2336, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.055240587294664925, | |
| "grad_norm": 0.13763906061649323, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.2169, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.05814798662596308, | |
| "grad_norm": 0.1327727884054184, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2007, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06105538595726123, | |
| "grad_norm": 0.1083875447511673, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.2181, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.06396278528855938, | |
| "grad_norm": 0.12445604056119919, | |
| "learning_rate": 2.2000000000000003e-05, | |
| "loss": 0.2969, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.06687018461985754, | |
| "grad_norm": 0.15511994063854218, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 0.1868, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.06977758395115569, | |
| "grad_norm": 0.13466577231884003, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.25, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.07268498328245385, | |
| "grad_norm": 0.06756726652383804, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.1809, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.075592382613752, | |
| "grad_norm": 0.1573372632265091, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.1963, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.07849978194505015, | |
| "grad_norm": 0.13099811971187592, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 0.1984, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.0814071812763483, | |
| "grad_norm": 0.11419626325368881, | |
| "learning_rate": 2.8000000000000003e-05, | |
| "loss": 0.1665, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.08431458060764646, | |
| "grad_norm": 0.10189209878444672, | |
| "learning_rate": 2.9e-05, | |
| "loss": 0.1749, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.08722197993894461, | |
| "grad_norm": 0.12042666226625443, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1528, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.09012937927024277, | |
| "grad_norm": 0.08344505727291107, | |
| "learning_rate": 3.1e-05, | |
| "loss": 0.181, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.09303677860154091, | |
| "grad_norm": 0.11566774547100067, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.1363, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.09594417793283908, | |
| "grad_norm": 0.1531219631433487, | |
| "learning_rate": 3.3e-05, | |
| "loss": 0.1564, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.09885157726413724, | |
| "grad_norm": 0.08966905623674393, | |
| "learning_rate": 3.4000000000000007e-05, | |
| "loss": 0.1281, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.10175897659543538, | |
| "grad_norm": 0.08444681763648987, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.1258, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.10466637592673354, | |
| "grad_norm": 0.10482101142406464, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.1292, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.10757377525803169, | |
| "grad_norm": 0.14638499915599823, | |
| "learning_rate": 3.7e-05, | |
| "loss": 0.1829, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.11048117458932985, | |
| "grad_norm": 0.1461925059556961, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.2158, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.113388573920628, | |
| "grad_norm": 0.16068245470523834, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.2219, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.11629597325192616, | |
| "grad_norm": 0.13314808905124664, | |
| "learning_rate": 4e-05, | |
| "loss": 0.1622, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1192033725832243, | |
| "grad_norm": 0.13541767001152039, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.1363, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.12211077191452246, | |
| "grad_norm": 0.14549389481544495, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.1664, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.12501817124582063, | |
| "grad_norm": 0.09966716170310974, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.1446, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.12792557057711876, | |
| "grad_norm": 0.10374356061220169, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.1302, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.13083296990841692, | |
| "grad_norm": 0.10534253716468811, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.1612, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.13374036923971508, | |
| "grad_norm": 0.14981906116008759, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.1782, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.13664776857101324, | |
| "grad_norm": 0.08772515505552292, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.1303, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.13955516790231137, | |
| "grad_norm": 0.14555956423282623, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.1259, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.14246256723360953, | |
| "grad_norm": 0.08366917818784714, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.1827, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.1453699665649077, | |
| "grad_norm": 0.13676565885543823, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1563, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1453699665649077, | |
| "eval_accuracy": 0.4444444444444444, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1453699665649077, | |
| "eval_loss": 0.15286579728126526, | |
| "eval_runtime": 120.6585, | |
| "eval_samples_per_second": 2.014, | |
| "eval_steps_per_second": 2.014, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3439, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.573652967424e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |