| { | |
| "best_metric": 1.3169686794281006, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.008112356132434214, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016224712264868428, | |
| "grad_norm": 0.6465702652931213, | |
| "learning_rate": 5e-05, | |
| "loss": 1.483, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016224712264868428, | |
| "eval_loss": 1.6033128499984741, | |
| "eval_runtime": 2245.9928, | |
| "eval_samples_per_second": 18.487, | |
| "eval_steps_per_second": 2.311, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032449424529736856, | |
| "grad_norm": 0.7896801829338074, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3015, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004867413679460528, | |
| "grad_norm": 0.6627933382987976, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.3071, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006489884905947371, | |
| "grad_norm": 0.549625813961029, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.3581, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008112356132434214, | |
| "grad_norm": 0.5422409772872925, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.3636, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009734827358921056, | |
| "grad_norm": 0.6067570447921753, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.4688, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00113572985854079, | |
| "grad_norm": 0.4786202013492584, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.4878, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0012979769811894742, | |
| "grad_norm": 0.3874378800392151, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5256, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014602241038381585, | |
| "grad_norm": 0.35884571075439453, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.5006, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016224712264868428, | |
| "grad_norm": 0.46932095289230347, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5832, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0017847183491355272, | |
| "grad_norm": 0.5992789268493652, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.7294, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0019469654717842112, | |
| "grad_norm": 0.598483681678772, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.6019, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0021092125944328958, | |
| "grad_norm": 0.29254594445228577, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.1496, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00227145971708158, | |
| "grad_norm": 0.272531658411026, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.169, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002433706839730264, | |
| "grad_norm": 0.28825843334198, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.2479, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0025959539623789485, | |
| "grad_norm": 0.3147728741168976, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.2838, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0027582010850276326, | |
| "grad_norm": 0.3250277042388916, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.3268, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.002920448207676317, | |
| "grad_norm": 0.2931220829486847, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.4459, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003082695330325001, | |
| "grad_norm": 0.3241807818412781, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.37, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0032449424529736857, | |
| "grad_norm": 0.32053127884864807, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.5049, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00340718957562237, | |
| "grad_norm": 0.32842928171157837, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.5068, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0035694366982710543, | |
| "grad_norm": 0.3623358905315399, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.4789, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0037316838209197384, | |
| "grad_norm": 0.3769468665122986, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5706, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0038939309435684225, | |
| "grad_norm": 0.4450576901435852, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5749, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004056178066217107, | |
| "grad_norm": 0.6323398351669312, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.3689, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004056178066217107, | |
| "eval_loss": 1.3327997922897339, | |
| "eval_runtime": 2248.1163, | |
| "eval_samples_per_second": 18.47, | |
| "eval_steps_per_second": 2.309, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0042184251888657915, | |
| "grad_norm": 0.23920784890651703, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1888, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004380672311514475, | |
| "grad_norm": 0.2944607138633728, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.242, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00454291943416316, | |
| "grad_norm": 0.2730006277561188, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.3177, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.004705166556811844, | |
| "grad_norm": 0.27331778407096863, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.149, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.004867413679460528, | |
| "grad_norm": 0.30295857787132263, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.3522, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005029660802109212, | |
| "grad_norm": 0.28588980436325073, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.3939, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005191907924757897, | |
| "grad_norm": 0.30419930815696716, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3981, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0053541550474065815, | |
| "grad_norm": 0.32927200198173523, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.4497, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005516402170055265, | |
| "grad_norm": 0.3404857814311981, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.4873, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00567864929270395, | |
| "grad_norm": 0.39585205912590027, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4754, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005840896415352634, | |
| "grad_norm": 0.4302978813648224, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.605, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006003143538001319, | |
| "grad_norm": 0.47387707233428955, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.49, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006165390660650002, | |
| "grad_norm": 0.26334431767463684, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1987, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006327637783298687, | |
| "grad_norm": 0.21667051315307617, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.121, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006489884905947371, | |
| "grad_norm": 0.235555037856102, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.1678, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006652132028596055, | |
| "grad_norm": 0.26329222321510315, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.238, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.00681437915124474, | |
| "grad_norm": 0.26046666502952576, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.2941, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006976626273893424, | |
| "grad_norm": 0.2660744786262512, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.3638, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.007138873396542109, | |
| "grad_norm": 0.28398439288139343, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3769, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007301120519190792, | |
| "grad_norm": 0.2969786524772644, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.4264, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007463367641839477, | |
| "grad_norm": 0.33156681060791016, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.4549, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.007625614764488161, | |
| "grad_norm": 0.3665097951889038, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.4171, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.007787861887136845, | |
| "grad_norm": 0.408587247133255, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.545, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.00795010900978553, | |
| "grad_norm": 0.4407505393028259, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.6181, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008112356132434214, | |
| "grad_norm": 0.6196596026420593, | |
| "learning_rate": 0.0, | |
| "loss": 1.333, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008112356132434214, | |
| "eval_loss": 1.3169686794281006, | |
| "eval_runtime": 2247.4174, | |
| "eval_samples_per_second": 18.475, | |
| "eval_steps_per_second": 2.31, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.969948642440643e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |