| { | |
| "best_metric": 0.26727595925331116, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.8465608465608465, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016931216931216932, | |
| "grad_norm": 2.467500686645508, | |
| "learning_rate": 5e-05, | |
| "loss": 1.912, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016931216931216932, | |
| "eval_loss": 6.23634147644043, | |
| "eval_runtime": 12.1382, | |
| "eval_samples_per_second": 32.789, | |
| "eval_steps_per_second": 4.119, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.033862433862433865, | |
| "grad_norm": 4.0213189125061035, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4499, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.050793650793650794, | |
| "grad_norm": 4.339459419250488, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.8843, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06772486772486773, | |
| "grad_norm": 4.242490768432617, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.2246, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08465608465608465, | |
| "grad_norm": 5.68541145324707, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.8738, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10158730158730159, | |
| "grad_norm": 6.79937219619751, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.9631, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 5.610718250274658, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3192, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13544973544973546, | |
| "grad_norm": 7.737128734588623, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.114, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1523809523809524, | |
| "grad_norm": 2.812722682952881, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.791, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1693121693121693, | |
| "grad_norm": 4.20097017288208, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.776, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18624338624338624, | |
| "grad_norm": 2.1821651458740234, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.5763, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.20317460317460317, | |
| "grad_norm": 1.962411642074585, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6162, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2201058201058201, | |
| "grad_norm": 3.9622223377227783, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.3598, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 2.1822211742401123, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4503, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.25396825396825395, | |
| "grad_norm": 2.4039320945739746, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3811, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2708994708994709, | |
| "grad_norm": 1.4816944599151611, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3518, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2878306878306878, | |
| "grad_norm": 1.4528988599777222, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3467, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3047619047619048, | |
| "grad_norm": 1.2522661685943604, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3018, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3216931216931217, | |
| "grad_norm": 1.4755431413650513, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.303, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3386243386243386, | |
| "grad_norm": 1.4966477155685425, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.29, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 1.1641327142715454, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.2272, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3724867724867725, | |
| "grad_norm": 1.18482506275177, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.2795, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.38941798941798944, | |
| "grad_norm": 1.9664446115493774, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.2656, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.40634920634920635, | |
| "grad_norm": 1.5987533330917358, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.3109, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.42328042328042326, | |
| "grad_norm": 2.464764356613159, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3271, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.42328042328042326, | |
| "eval_loss": 0.3290276825428009, | |
| "eval_runtime": 12.1166, | |
| "eval_samples_per_second": 32.847, | |
| "eval_steps_per_second": 4.127, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4402116402116402, | |
| "grad_norm": 2.553032398223877, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2123, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 2.527278184890747, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2425, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 1.3259862661361694, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2149, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.491005291005291, | |
| "grad_norm": 0.9057004451751709, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1846, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5079365079365079, | |
| "grad_norm": 2.1379523277282715, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2631, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5248677248677248, | |
| "grad_norm": 1.7521412372589111, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2363, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5417989417989418, | |
| "grad_norm": 1.938287615776062, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2474, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5587301587301587, | |
| "grad_norm": 1.5582822561264038, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.2299, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5756613756613757, | |
| "grad_norm": 1.065468668937683, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2233, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.8618595600128174, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1876, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6095238095238096, | |
| "grad_norm": 1.1647229194641113, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1651, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6264550264550265, | |
| "grad_norm": 1.375846266746521, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.243, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6433862433862434, | |
| "grad_norm": 1.3024173974990845, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.145, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6603174603174603, | |
| "grad_norm": 1.9372594356536865, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2139, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6772486772486772, | |
| "grad_norm": 1.7783533334732056, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.1954, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6941798941798942, | |
| "grad_norm": 1.3502763509750366, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1917, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.9650064706802368, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.175, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.728042328042328, | |
| "grad_norm": 0.9830562472343445, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2051, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.744973544973545, | |
| "grad_norm": 1.0555146932601929, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1936, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 0.937089204788208, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1957, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7788359788359789, | |
| "grad_norm": 1.1521154642105103, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.2199, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7957671957671958, | |
| "grad_norm": 1.1540207862854004, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.2073, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8126984126984127, | |
| "grad_norm": 1.0548319816589355, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1964, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 1.3886256217956543, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2309, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8465608465608465, | |
| "grad_norm": 2.104114055633545, | |
| "learning_rate": 0.0, | |
| "loss": 0.2309, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8465608465608465, | |
| "eval_loss": 0.26727595925331116, | |
| "eval_runtime": 12.1192, | |
| "eval_samples_per_second": 32.84, | |
| "eval_steps_per_second": 4.126, | |
| "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 | |
| } | |