| { | |
| "best_metric": 0.039766620844602585, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.6996699669966997, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.052805280528052806, | |
| "grad_norm": 240.08116149902344, | |
| "learning_rate": 5e-05, | |
| "loss": 61.3338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.052805280528052806, | |
| "eval_loss": 3.5627546310424805, | |
| "eval_runtime": 4.3057, | |
| "eval_samples_per_second": 29.728, | |
| "eval_steps_per_second": 3.716, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10561056105610561, | |
| "grad_norm": 311.3833923339844, | |
| "learning_rate": 0.0001, | |
| "loss": 55.4131, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": 186.2847137451172, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 35.886, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.21122112211221122, | |
| "grad_norm": 109.15618896484375, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 20.0972, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.264026402640264, | |
| "grad_norm": 88.25745391845703, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 24.9318, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": 140.07655334472656, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 18.6597, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3696369636963696, | |
| "grad_norm": 134.88388061523438, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 14.9552, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.42244224422442245, | |
| "grad_norm": 63.23054122924805, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.7139, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": 71.05472564697266, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 9.8416, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.528052805280528, | |
| "grad_norm": 97.5541763305664, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 19.9574, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5808580858085809, | |
| "grad_norm": 69.11842346191406, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.0275, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "grad_norm": 56.24506759643555, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.1437, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6864686468646864, | |
| "grad_norm": 54.2360954284668, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 7.8817, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7392739273927392, | |
| "grad_norm": 65.11487579345703, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 9.9734, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "grad_norm": 63.567726135253906, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 8.4856, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8448844884488449, | |
| "grad_norm": 54.104248046875, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 5.8322, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8976897689768977, | |
| "grad_norm": 41.041969299316406, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.4734, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "grad_norm": 51.88878631591797, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.058, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.033003300330033, | |
| "grad_norm": 63.439964294433594, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 5.4253, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0858085808580857, | |
| "grad_norm": 48.61954116821289, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.854, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1386138613861387, | |
| "grad_norm": 55.616329193115234, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.0837, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.1914191419141915, | |
| "grad_norm": 50.29981231689453, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.5129, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2442244224422443, | |
| "grad_norm": 48.272666931152344, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.6346, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.297029702970297, | |
| "grad_norm": 82.75598907470703, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.8828, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3498349834983498, | |
| "grad_norm": 55.31129837036133, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.9758, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3498349834983498, | |
| "eval_loss": 0.11382482945919037, | |
| "eval_runtime": 4.569, | |
| "eval_samples_per_second": 28.015, | |
| "eval_steps_per_second": 3.502, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4026402640264026, | |
| "grad_norm": 80.16549682617188, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9275, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.4554455445544554, | |
| "grad_norm": 44.94060516357422, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6253, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.5082508250825084, | |
| "grad_norm": 53.476905822753906, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.6445, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.561056105610561, | |
| "grad_norm": 72.94212341308594, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9836, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.613861386138614, | |
| "grad_norm": 51.1599235534668, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.539, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 18.60490608215332, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2169, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.7194719471947195, | |
| "grad_norm": 47.54155349731445, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7477, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.7722772277227723, | |
| "grad_norm": 68.19134521484375, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.846, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.825082508250825, | |
| "grad_norm": 39.737762451171875, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4499, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.8778877887788779, | |
| "grad_norm": 22.386844635009766, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1428, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.9306930693069306, | |
| "grad_norm": 8.85619068145752, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0899, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.0132013201320134, | |
| "grad_norm": 13.05267333984375, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4039, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.066006600660066, | |
| "grad_norm": 10.15993881225586, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2195, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.118811881188119, | |
| "grad_norm": 4.588918685913086, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0582, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.1716171617161715, | |
| "grad_norm": 17.074146270751953, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0406, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.2244224422442245, | |
| "grad_norm": 1.4361339807510376, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0148, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.2772277227722775, | |
| "grad_norm": 19.55823516845703, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3258, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.33003300330033, | |
| "grad_norm": 23.317541122436523, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1395, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.382838283828383, | |
| "grad_norm": 3.5347235202789307, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0133, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.4356435643564356, | |
| "grad_norm": 48.761112213134766, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1465, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.4884488448844886, | |
| "grad_norm": 64.77693176269531, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5884, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.541254125412541, | |
| "grad_norm": 21.97736167907715, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0732, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.594059405940594, | |
| "grad_norm": 19.152101516723633, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.162, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.6468646864686467, | |
| "grad_norm": 14.94710636138916, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.1771, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.6996699669966997, | |
| "grad_norm": 8.99813461303711, | |
| "learning_rate": 0.0, | |
| "loss": 0.2619, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.6996699669966997, | |
| "eval_loss": 0.039766620844602585, | |
| "eval_runtime": 4.8436, | |
| "eval_samples_per_second": 26.427, | |
| "eval_steps_per_second": 3.303, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 5.932088473514148e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |