| { | |
| "best_metric": 1.2373801469802856, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.026963262554769128, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005392652510953826, | |
| "grad_norm": 1.2818739414215088, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8932, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005392652510953826, | |
| "eval_loss": 3.3459784984588623, | |
| "eval_runtime": 154.8088, | |
| "eval_samples_per_second": 161.393, | |
| "eval_steps_per_second": 10.09, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010785305021907652, | |
| "grad_norm": 4.193954944610596, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9087, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016177957532861476, | |
| "grad_norm": 2.616204023361206, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.9316, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0021570610043815303, | |
| "grad_norm": 2.7958908081054688, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.5486, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002696326255476913, | |
| "grad_norm": 3.3829877376556396, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.4023, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0032355915065722953, | |
| "grad_norm": 2.914790630340576, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.1707, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0037748567576676778, | |
| "grad_norm": 4.009759902954102, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.0133, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004314122008763061, | |
| "grad_norm": 71.06979370117188, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0792, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004853387259858443, | |
| "grad_norm": 21.696056365966797, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.7576, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005392652510953826, | |
| "grad_norm": 5.2918291091918945, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4723, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005931917762049208, | |
| "grad_norm": 4.822276592254639, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.2576, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006471183013144591, | |
| "grad_norm": 3.6242246627807617, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.1194, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007010448264239973, | |
| "grad_norm": 1.343307375907898, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.8579, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0075497135153353555, | |
| "grad_norm": 3.319385290145874, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.4633, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008088978766430738, | |
| "grad_norm": 1.871975064277649, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.1579, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008628244017526121, | |
| "grad_norm": 1.5677542686462402, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.6793, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009167509268621503, | |
| "grad_norm": 1.7499879598617554, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.3543, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009706774519716885, | |
| "grad_norm": 1.2721295356750488, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3193, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010246039770812268, | |
| "grad_norm": 1.1565001010894775, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1652, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.010785305021907651, | |
| "grad_norm": 0.9505112171173096, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.0094, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011324570273003034, | |
| "grad_norm": 0.6880257725715637, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.9634, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011863835524098415, | |
| "grad_norm": 0.757514476776123, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.9322, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.012403100775193798, | |
| "grad_norm": 0.7356706261634827, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.8386, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012942366026289181, | |
| "grad_norm": 1.2924965620040894, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.9268, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013481631277384564, | |
| "grad_norm": 2.103581190109253, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.0122, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013481631277384564, | |
| "eval_loss": 1.281962513923645, | |
| "eval_runtime": 154.971, | |
| "eval_samples_per_second": 161.224, | |
| "eval_steps_per_second": 10.079, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.014020896528479945, | |
| "grad_norm": 0.6915966272354126, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7684, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.014560161779575328, | |
| "grad_norm": 1.183508038520813, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.0521, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.015099427030670711, | |
| "grad_norm": 1.1337106227874756, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.6086, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.015638692281766092, | |
| "grad_norm": 0.9918910264968872, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.2684, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.016177957532861477, | |
| "grad_norm": 0.8533536791801453, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.2259, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016717222783956858, | |
| "grad_norm": 0.7464625239372253, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1288, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.017256488035052243, | |
| "grad_norm": 0.7595018148422241, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0143, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.017795753286147624, | |
| "grad_norm": 0.7032437324523926, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.0123, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.018335018537243005, | |
| "grad_norm": 0.6670097708702087, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.9041, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01887428378833839, | |
| "grad_norm": 0.611680805683136, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.8395, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01941354903943377, | |
| "grad_norm": 0.6346780061721802, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.8197, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.019952814290529156, | |
| "grad_norm": 1.5375241041183472, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0206, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.020492079541624537, | |
| "grad_norm": 0.4851534068584442, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.6551, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.021031344792719918, | |
| "grad_norm": 0.7288507223129272, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.1959, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.021570610043815303, | |
| "grad_norm": 0.6835736036300659, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.7378, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.022109875294910684, | |
| "grad_norm": 0.8178367018699646, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.3294, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02264914054600607, | |
| "grad_norm": 0.8485854864120483, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.1328, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02318840579710145, | |
| "grad_norm": 0.5767989158630371, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.1029, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02372767104819683, | |
| "grad_norm": 0.6219594478607178, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0409, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.024266936299292215, | |
| "grad_norm": 0.37479478120803833, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.9684, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.024806201550387597, | |
| "grad_norm": 0.3662634789943695, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.9145, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.025345466801482978, | |
| "grad_norm": 0.40091606974601746, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.856, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.025884732052578362, | |
| "grad_norm": 0.4234645664691925, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7905, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.026423997303673744, | |
| "grad_norm": 0.6059905290603638, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.8682, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.026963262554769128, | |
| "grad_norm": 1.4071378707885742, | |
| "learning_rate": 0.0, | |
| "loss": 0.964, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.026963262554769128, | |
| "eval_loss": 1.2373801469802856, | |
| "eval_runtime": 155.0212, | |
| "eval_samples_per_second": 161.171, | |
| "eval_steps_per_second": 10.076, | |
| "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": 5.90601825288192e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |