| { | |
| "best_metric": 1.2732304334640503, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04192432659050414, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008384865318100828, | |
| "grad_norm": 0.17721030116081238, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3701, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008384865318100828, | |
| "eval_loss": 1.5981723070144653, | |
| "eval_runtime": 164.1123, | |
| "eval_samples_per_second": 48.96, | |
| "eval_steps_per_second": 6.124, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016769730636201656, | |
| "grad_norm": 0.18971967697143555, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3332, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0025154595954302483, | |
| "grad_norm": 0.18822723627090454, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.4004, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003353946127240331, | |
| "grad_norm": 0.16532792150974274, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.3153, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004192432659050414, | |
| "grad_norm": 0.17661309242248535, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.3469, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005030919190860497, | |
| "grad_norm": 0.20450425148010254, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3733, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00586940572267058, | |
| "grad_norm": 0.21615220606327057, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3552, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006707892254480662, | |
| "grad_norm": 0.2360900342464447, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3783, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0075463787862907455, | |
| "grad_norm": 0.26735052466392517, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4238, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008384865318100829, | |
| "grad_norm": 0.2953568696975708, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.4245, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00922335184991091, | |
| "grad_norm": 0.5420729517936707, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.4679, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010061838381720993, | |
| "grad_norm": 1.0757503509521484, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.7134, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010900324913531077, | |
| "grad_norm": 0.17478539049625397, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.306, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01173881144534116, | |
| "grad_norm": 0.16675907373428345, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.2195, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012577297977151241, | |
| "grad_norm": 0.1896870732307434, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.2112, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013415784508961325, | |
| "grad_norm": 0.19617412984371185, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.234, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014254271040771408, | |
| "grad_norm": 0.2222306877374649, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.2211, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.015092757572581491, | |
| "grad_norm": 0.22559349238872528, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.272, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015931244104391572, | |
| "grad_norm": 0.19203859567642212, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.2469, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.016769730636201657, | |
| "grad_norm": 0.20538727939128876, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2428, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01760821716801174, | |
| "grad_norm": 0.19514307379722595, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3174, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01844670369982182, | |
| "grad_norm": 0.2092122882604599, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3558, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.019285190231631905, | |
| "grad_norm": 0.29141950607299805, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.3876, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.020123676763441987, | |
| "grad_norm": 0.5817326903343201, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.4805, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02096216329525207, | |
| "grad_norm": 1.1296993494033813, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.574, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02096216329525207, | |
| "eval_loss": 1.293853521347046, | |
| "eval_runtime": 164.0306, | |
| "eval_samples_per_second": 48.985, | |
| "eval_steps_per_second": 6.127, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.021800649827062153, | |
| "grad_norm": 0.1442486196756363, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2427, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.022639136358872235, | |
| "grad_norm": 0.1324678361415863, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.2241, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02347762289068232, | |
| "grad_norm": 0.13264364004135132, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.2278, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0243161094224924, | |
| "grad_norm": 0.132313534617424, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.2359, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.025154595954302483, | |
| "grad_norm": 0.1368257850408554, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.2163, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025993082486112568, | |
| "grad_norm": 0.14327384531497955, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.2459, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02683156901792265, | |
| "grad_norm": 0.1744619905948639, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2904, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.027670055549732734, | |
| "grad_norm": 0.17769135534763336, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.2816, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.028508542081542815, | |
| "grad_norm": 0.22097477316856384, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.2854, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.029347028613352897, | |
| "grad_norm": 0.2638107240200043, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.3145, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.030185515145162982, | |
| "grad_norm": 0.30326229333877563, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.395, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.031024001676973063, | |
| "grad_norm": 0.46151870489120483, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.4473, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.031862488208783145, | |
| "grad_norm": 0.16587065160274506, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2968, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.032700974740593226, | |
| "grad_norm": 0.14834366738796234, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.1843, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.033539461272403315, | |
| "grad_norm": 0.14233732223510742, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.2286, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.034377947804213396, | |
| "grad_norm": 0.13319115340709686, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.2131, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03521643433602348, | |
| "grad_norm": 0.13616111874580383, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.2021, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03605492086783356, | |
| "grad_norm": 0.1343865692615509, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2018, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03689340739964364, | |
| "grad_norm": 0.14616534113883972, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2465, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03773189393145373, | |
| "grad_norm": 0.16980408132076263, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.2885, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03857038046326381, | |
| "grad_norm": 0.1766597181558609, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2422, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03940886699507389, | |
| "grad_norm": 0.2097931057214737, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.2647, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.040247353526883974, | |
| "grad_norm": 0.2691362202167511, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.2763, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.041085840058694055, | |
| "grad_norm": 0.4423013925552368, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.2612, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04192432659050414, | |
| "grad_norm": 0.7524447441101074, | |
| "learning_rate": 0.0, | |
| "loss": 1.5119, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04192432659050414, | |
| "eval_loss": 1.2732304334640503, | |
| "eval_runtime": 164.028, | |
| "eval_samples_per_second": 48.986, | |
| "eval_steps_per_second": 6.127, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |