| { | |
| "best_metric": 1.8846580982208252, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0377643504531722, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007552870090634441, | |
| "grad_norm": 20.618200302124023, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0645, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007552870090634441, | |
| "eval_loss": 2.11383318901062, | |
| "eval_runtime": 366.0639, | |
| "eval_samples_per_second": 24.367, | |
| "eval_steps_per_second": 3.046, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015105740181268882, | |
| "grad_norm": 23.598108291625977, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0896, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0022658610271903325, | |
| "grad_norm": 12.609061241149902, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.0368, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0030211480362537764, | |
| "grad_norm": 8.108500480651855, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.9773, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0037764350453172208, | |
| "grad_norm": 6.823090553283691, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.9741, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004531722054380665, | |
| "grad_norm": 6.6352739334106445, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.9757, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005287009063444109, | |
| "grad_norm": 6.2974772453308105, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.9942, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006042296072507553, | |
| "grad_norm": 6.511254787445068, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9675, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006797583081570997, | |
| "grad_norm": 6.925810813903809, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9193, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0075528700906344415, | |
| "grad_norm": 7.368894100189209, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.9753, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008308157099697885, | |
| "grad_norm": 7.824017524719238, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.9022, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00906344410876133, | |
| "grad_norm": 9.331262588500977, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.8619, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009818731117824773, | |
| "grad_norm": 15.385412216186523, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.9448, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010574018126888218, | |
| "grad_norm": 11.004483222961426, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.0179, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011329305135951661, | |
| "grad_norm": 6.976226806640625, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.9587, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012084592145015106, | |
| "grad_norm": 6.1534881591796875, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.9875, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01283987915407855, | |
| "grad_norm": 6.997747898101807, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.9685, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013595166163141994, | |
| "grad_norm": 8.139199256896973, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.927, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014350453172205438, | |
| "grad_norm": 9.120523452758789, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.9285, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015105740181268883, | |
| "grad_norm": 6.644983768463135, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.9388, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015861027190332326, | |
| "grad_norm": 6.8376078605651855, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.8765, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01661631419939577, | |
| "grad_norm": 8.992157936096191, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.8938, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.017371601208459216, | |
| "grad_norm": 6.931112289428711, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.8956, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01812688821752266, | |
| "grad_norm": 6.5712175369262695, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.8923, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0188821752265861, | |
| "grad_norm": 7.558088779449463, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.8419, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0188821752265861, | |
| "eval_loss": 1.9013075828552246, | |
| "eval_runtime": 368.4853, | |
| "eval_samples_per_second": 24.207, | |
| "eval_steps_per_second": 3.026, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.019637462235649546, | |
| "grad_norm": 6.776696681976318, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8883, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02039274924471299, | |
| "grad_norm": 7.159153938293457, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.9433, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.021148036253776436, | |
| "grad_norm": 6.303608417510986, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.9532, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02190332326283988, | |
| "grad_norm": 5.578258037567139, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.9145, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.022658610271903322, | |
| "grad_norm": 5.26440954208374, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.8993, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023413897280966767, | |
| "grad_norm": 5.3654985427856445, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.8948, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02416918429003021, | |
| "grad_norm": 5.753653526306152, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9263, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.024924471299093656, | |
| "grad_norm": 5.539957523345947, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.881, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0256797583081571, | |
| "grad_norm": 5.666808128356934, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.8992, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.026435045317220542, | |
| "grad_norm": 6.2148332595825195, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.8657, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.027190332326283987, | |
| "grad_norm": 6.8241424560546875, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.8997, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.027945619335347432, | |
| "grad_norm": 7.615296840667725, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.8148, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.028700906344410877, | |
| "grad_norm": 6.124070167541504, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.8583, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02945619335347432, | |
| "grad_norm": 4.771143913269043, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.9552, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.030211480362537766, | |
| "grad_norm": 4.553677558898926, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.888, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.030966767371601207, | |
| "grad_norm": 4.59923791885376, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.9062, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03172205438066465, | |
| "grad_norm": 5.005655288696289, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.9308, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0324773413897281, | |
| "grad_norm": 4.9266486167907715, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.909, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03323262839879154, | |
| "grad_norm": 5.109602928161621, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.9391, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.033987915407854986, | |
| "grad_norm": 4.969670295715332, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.9203, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03474320241691843, | |
| "grad_norm": 5.118282318115234, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.8753, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.035498489425981876, | |
| "grad_norm": 5.58473539352417, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.864, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03625377643504532, | |
| "grad_norm": 5.797006130218506, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.8489, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03700906344410876, | |
| "grad_norm": 6.1970906257629395, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.7839, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0377643504531722, | |
| "grad_norm": 7.363020896911621, | |
| "learning_rate": 0.0, | |
| "loss": 1.7918, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0377643504531722, | |
| "eval_loss": 1.8846580982208252, | |
| "eval_runtime": 366.273, | |
| "eval_samples_per_second": 24.353, | |
| "eval_steps_per_second": 3.044, | |
| "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": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |