| { | |
| "best_metric": 0.6460928320884705, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06207806316442927, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012415612632885853, | |
| "grad_norm": 0.4326339662075043, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9528, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012415612632885853, | |
| "eval_loss": 0.8670604228973389, | |
| "eval_runtime": 86.7004, | |
| "eval_samples_per_second": 62.583, | |
| "eval_steps_per_second": 7.832, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024831225265771707, | |
| "grad_norm": 0.31606096029281616, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8354, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003724683789865756, | |
| "grad_norm": 0.34394755959510803, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.8952, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004966245053154341, | |
| "grad_norm": 0.2672635614871979, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.8739, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006207806316442927, | |
| "grad_norm": 0.245578333735466, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.8213, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007449367579731512, | |
| "grad_norm": 0.2544446289539337, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.828, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008690928843020097, | |
| "grad_norm": 0.26478007435798645, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7942, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009932490106308683, | |
| "grad_norm": 0.27469292283058167, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8026, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011174051369597269, | |
| "grad_norm": 0.2647610008716583, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.7335, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012415612632885854, | |
| "grad_norm": 0.25258561968803406, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01365717389617444, | |
| "grad_norm": 0.2425445020198822, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.6056, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.014898735159463024, | |
| "grad_norm": 0.2843758165836334, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5097, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01614029642275161, | |
| "grad_norm": 0.5850368738174438, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.894, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017381857686040194, | |
| "grad_norm": 0.2032504379749298, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6675, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01862341894932878, | |
| "grad_norm": 0.1841326802968979, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6916, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019864980212617366, | |
| "grad_norm": 0.1865765005350113, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7363, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021106541475905953, | |
| "grad_norm": 0.17130893468856812, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6748, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.022348102739194537, | |
| "grad_norm": 0.18940648436546326, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7294, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02358966400248312, | |
| "grad_norm": 0.18071648478507996, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.6936, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02483122526577171, | |
| "grad_norm": 0.18491078913211823, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7372, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026072786529060293, | |
| "grad_norm": 0.17880083620548248, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7103, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02731434779234888, | |
| "grad_norm": 0.16440188884735107, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6136, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.028555909055637464, | |
| "grad_norm": 0.17268064618110657, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.6092, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02979747031892605, | |
| "grad_norm": 0.17315348982810974, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4767, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.031039031582214636, | |
| "grad_norm": 0.23280172049999237, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3756, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.031039031582214636, | |
| "eval_loss": 0.6583801507949829, | |
| "eval_runtime": 85.9422, | |
| "eval_samples_per_second": 63.135, | |
| "eval_steps_per_second": 7.901, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03228059284550322, | |
| "grad_norm": 0.2256009429693222, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7063, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03352215410879181, | |
| "grad_norm": 0.15308834612369537, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6823, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03476371537208039, | |
| "grad_norm": 0.14822077751159668, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6787, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.036005276635368975, | |
| "grad_norm": 0.15348833799362183, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.7401, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03724683789865756, | |
| "grad_norm": 0.15910352766513824, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7295, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03848839916194615, | |
| "grad_norm": 0.14045007526874542, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.6509, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03972996042523473, | |
| "grad_norm": 0.14484994113445282, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6792, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04097152168852332, | |
| "grad_norm": 0.14491479098796844, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.6661, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.042213082951811906, | |
| "grad_norm": 0.13978998363018036, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.6713, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04345464421510049, | |
| "grad_norm": 0.15529781579971313, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6076, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.044696205478389074, | |
| "grad_norm": 0.15842097997665405, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5237, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04593776674167766, | |
| "grad_norm": 0.1823544204235077, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4294, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04717932800496624, | |
| "grad_norm": 0.45187708735466003, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7899, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04842088926825483, | |
| "grad_norm": 0.1284649819135666, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6492, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04966245053154342, | |
| "grad_norm": 0.13667044043540955, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.7075, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.050904011794832, | |
| "grad_norm": 0.1311858743429184, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.7165, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.052145573058120585, | |
| "grad_norm": 0.13079705834388733, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7097, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05338713432140917, | |
| "grad_norm": 0.13603699207305908, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6489, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05462869558469776, | |
| "grad_norm": 0.1422751545906067, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6811, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05587025684798634, | |
| "grad_norm": 0.13295882940292358, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6908, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05711181811127493, | |
| "grad_norm": 0.1368282288312912, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6654, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.058353379374563516, | |
| "grad_norm": 0.14943842589855194, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6069, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0595949406378521, | |
| "grad_norm": 0.1544649749994278, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5667, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.060836501901140684, | |
| "grad_norm": 0.16153788566589355, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4583, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06207806316442927, | |
| "grad_norm": 0.22390557825565338, | |
| "learning_rate": 0.0, | |
| "loss": 0.3561, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06207806316442927, | |
| "eval_loss": 0.6460928320884705, | |
| "eval_runtime": 86.0243, | |
| "eval_samples_per_second": 63.075, | |
| "eval_steps_per_second": 7.893, | |
| "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": 8.42792324479058e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |