| { | |
| "best_metric": 2.1690759658813477, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.020733445639497215, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004146689127899443, | |
| "grad_norm": 1.5964183807373047, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0418, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004146689127899443, | |
| "eval_loss": 3.7286314964294434, | |
| "eval_runtime": 1097.9176, | |
| "eval_samples_per_second": 14.798, | |
| "eval_steps_per_second": 1.85, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008293378255798886, | |
| "grad_norm": 1.9051933288574219, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1972, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001244006738369833, | |
| "grad_norm": 1.829821228981018, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.2401, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016586756511597772, | |
| "grad_norm": 1.5044752359390259, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.9393, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0020733445639497215, | |
| "grad_norm": 1.792417049407959, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.7587, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002488013476739666, | |
| "grad_norm": 1.804439902305603, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.6823, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00290268238952961, | |
| "grad_norm": 1.4878047704696655, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.5697, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0033173513023195544, | |
| "grad_norm": 1.2159953117370605, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.4598, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0037320202151094983, | |
| "grad_norm": 1.1826621294021606, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.4348, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004146689127899443, | |
| "grad_norm": 1.2541757822036743, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.3304, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004561358040689387, | |
| "grad_norm": 1.3609563112258911, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.2775, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004976026953479332, | |
| "grad_norm": 1.4925411939620972, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.1956, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005390695866269276, | |
| "grad_norm": 1.5248774290084839, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.5986, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00580536477905922, | |
| "grad_norm": 1.6769380569458008, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.6598, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006220033691849165, | |
| "grad_norm": 1.3728498220443726, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.4445, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006634702604639109, | |
| "grad_norm": 0.9670044779777527, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.3514, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007049371517429052, | |
| "grad_norm": 1.1572895050048828, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.3628, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.007464040430218997, | |
| "grad_norm": 1.265485405921936, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3407, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007878709343008942, | |
| "grad_norm": 1.2644094228744507, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.2855, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.008293378255798886, | |
| "grad_norm": 1.1387994289398193, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.3051, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00870804716858883, | |
| "grad_norm": 0.9954199194908142, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.2049, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009122716081378775, | |
| "grad_norm": 0.921543300151825, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.2111, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.009537384994168719, | |
| "grad_norm": 0.9990856647491455, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.1035, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009952053906958663, | |
| "grad_norm": 1.143900752067566, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.0762, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010366722819748608, | |
| "grad_norm": 1.5277453660964966, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.0656, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010366722819748608, | |
| "eval_loss": 2.2520217895507812, | |
| "eval_runtime": 1098.2454, | |
| "eval_samples_per_second": 14.794, | |
| "eval_steps_per_second": 1.849, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010781391732538552, | |
| "grad_norm": 1.0906449556350708, | |
| "learning_rate": 5e-05, | |
| "loss": 2.43, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.011196060645328496, | |
| "grad_norm": 1.1582051515579224, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.4405, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01161072955811844, | |
| "grad_norm": 1.1142066717147827, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.354, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.012025398470908385, | |
| "grad_norm": 1.0841790437698364, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.3621, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01244006738369833, | |
| "grad_norm": 0.9841034412384033, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.3249, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012854736296488273, | |
| "grad_norm": 1.0224250555038452, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.2604, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.013269405209278218, | |
| "grad_norm": 0.8767861723899841, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.1979, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.013684074122068162, | |
| "grad_norm": 0.8886589407920837, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.2309, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.014098743034858105, | |
| "grad_norm": 1.1102007627487183, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.0605, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.014513411947648049, | |
| "grad_norm": 1.4647661447525024, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.1955, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014928080860437993, | |
| "grad_norm": 1.925478458404541, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.1027, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.015342749773227938, | |
| "grad_norm": 2.8022842407226562, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.0967, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.015757418686017884, | |
| "grad_norm": 0.7166653871536255, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3004, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.016172087598807828, | |
| "grad_norm": 0.7799428701400757, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.318, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.016586756511597772, | |
| "grad_norm": 0.7969001531600952, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.2889, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017001425424387717, | |
| "grad_norm": 0.7274399399757385, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.2631, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01741609433717766, | |
| "grad_norm": 0.7271828055381775, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.2522, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.017830763249967605, | |
| "grad_norm": 0.7675609588623047, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.2168, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01824543216275755, | |
| "grad_norm": 0.7360167503356934, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1654, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.018660101075547494, | |
| "grad_norm": 0.7525986433029175, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.2119, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.019074769988337438, | |
| "grad_norm": 0.8221715688705444, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.1148, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.019489438901127382, | |
| "grad_norm": 0.8812233209609985, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.0394, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.019904107813917327, | |
| "grad_norm": 1.018441915512085, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.096, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02031877672670727, | |
| "grad_norm": 1.3734047412872314, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.1067, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.020733445639497215, | |
| "grad_norm": 2.5341591835021973, | |
| "learning_rate": 0.0, | |
| "loss": 2.0195, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.020733445639497215, | |
| "eval_loss": 2.1690759658813477, | |
| "eval_runtime": 1096.4634, | |
| "eval_samples_per_second": 14.818, | |
| "eval_steps_per_second": 1.852, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |