| { | |
| "best_metric": 2.3195319954538718e-05, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.07547169811320754, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015094339622641509, | |
| "grad_norm": 9.727989196777344, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.9383, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015094339622641509, | |
| "eval_loss": 5.682714939117432, | |
| "eval_runtime": 4.6749, | |
| "eval_samples_per_second": 10.695, | |
| "eval_steps_per_second": 1.497, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0030188679245283017, | |
| "grad_norm": 9.845698356628418, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 3.161, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004528301886792453, | |
| "grad_norm": 9.684377670288086, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.9913, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0060377358490566035, | |
| "grad_norm": 11.722749710083008, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.3506, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007547169811320755, | |
| "grad_norm": 10.132170677185059, | |
| "learning_rate": 0.00015, | |
| "loss": 0.6881, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009056603773584906, | |
| "grad_norm": 4.307816028594971, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.1223, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010566037735849057, | |
| "grad_norm": 0.7658965587615967, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.0231, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012075471698113207, | |
| "grad_norm": 0.04265095666050911, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.0011, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013584905660377358, | |
| "grad_norm": 0.017767086625099182, | |
| "learning_rate": 0.00027, | |
| "loss": 0.0003, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01509433962264151, | |
| "grad_norm": 0.011602415703237057, | |
| "learning_rate": 0.0003, | |
| "loss": 0.0002, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01660377358490566, | |
| "grad_norm": 0.03181695565581322, | |
| "learning_rate": 0.0002999794957488703, | |
| "loss": 0.0004, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.018113207547169812, | |
| "grad_norm": 0.05330698564648628, | |
| "learning_rate": 0.0002999179886011389, | |
| "loss": 0.0005, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.019622641509433963, | |
| "grad_norm": 0.025343570858240128, | |
| "learning_rate": 0.0002998154953722457, | |
| "loss": 0.0002, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.021132075471698115, | |
| "grad_norm": 0.0021175649017095566, | |
| "learning_rate": 0.00029967204408281613, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.022641509433962263, | |
| "grad_norm": 0.0011911799665540457, | |
| "learning_rate": 0.00029948767395100045, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.024150943396226414, | |
| "grad_norm": 0.0003560419427230954, | |
| "learning_rate": 0.0002992624353817517, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.025660377358490565, | |
| "grad_norm": 0.00067779456730932, | |
| "learning_rate": 0.0002989963899530457, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.027169811320754716, | |
| "grad_norm": 0.0009647771366871893, | |
| "learning_rate": 0.00029868961039904624, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.028679245283018868, | |
| "grad_norm": 0.0003761858679354191, | |
| "learning_rate": 0.00029834218059022024, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03018867924528302, | |
| "grad_norm": 0.0005870265304110944, | |
| "learning_rate": 0.00029795419551040833, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03169811320754717, | |
| "grad_norm": 0.000383986858651042, | |
| "learning_rate": 0.00029752576123085736, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03320754716981132, | |
| "grad_norm": 0.005932660773396492, | |
| "learning_rate": 0.0002970569948812214, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03471698113207547, | |
| "grad_norm": 36.32376480102539, | |
| "learning_rate": 0.0002965480246175399, | |
| "loss": 0.2835, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.036226415094339624, | |
| "grad_norm": 2.1993796825408936, | |
| "learning_rate": 0.0002959989895872009, | |
| "loss": 0.0043, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03773584905660377, | |
| "grad_norm": 0.00012767089356202632, | |
| "learning_rate": 0.0002954100398908995, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03773584905660377, | |
| "eval_loss": 7.517421181546524e-05, | |
| "eval_runtime": 4.2094, | |
| "eval_samples_per_second": 11.878, | |
| "eval_steps_per_second": 1.663, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03924528301886793, | |
| "grad_norm": 0.0003870428481604904, | |
| "learning_rate": 0.0002947813365416023, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.040754716981132075, | |
| "grad_norm": 0.005472894757986069, | |
| "learning_rate": 0.0002941130514205272, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04226415094339623, | |
| "grad_norm": 0.07725609093904495, | |
| "learning_rate": 0.0002934053672301536, | |
| "loss": 0.0004, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04377358490566038, | |
| "grad_norm": 0.02922365628182888, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.0001, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.045283018867924525, | |
| "grad_norm": 0.022537946701049805, | |
| "learning_rate": 0.00029187258625509513, | |
| "loss": 0.0001, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04679245283018868, | |
| "grad_norm": 0.003779177786782384, | |
| "learning_rate": 0.00029104790851742417, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04830188679245283, | |
| "grad_norm": 0.0010583605617284775, | |
| "learning_rate": 0.0002901846696899191, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04981132075471698, | |
| "grad_norm": 0.00034484267234802246, | |
| "learning_rate": 0.00028928310577345606, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05132075471698113, | |
| "grad_norm": 0.00039084404124878347, | |
| "learning_rate": 0.0002883434632466077, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.052830188679245285, | |
| "grad_norm": 0.0004337659338489175, | |
| "learning_rate": 0.00028736599899825856, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05433962264150943, | |
| "grad_norm": 0.0008137256954796612, | |
| "learning_rate": 0.00028635098025737434, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05584905660377359, | |
| "grad_norm": 0.0009190964046865702, | |
| "learning_rate": 0.00028529868451994384, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.057358490566037736, | |
| "grad_norm": 0.0008511942578479648, | |
| "learning_rate": 0.0002842093994731145, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05886792452830188, | |
| "grad_norm": 0.0011096836533397436, | |
| "learning_rate": 0.00028308342291654174, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06037735849056604, | |
| "grad_norm": 0.0015806319424882531, | |
| "learning_rate": 0.00028192106268097334, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.061886792452830186, | |
| "grad_norm": 0.0018580264877527952, | |
| "learning_rate": 0.00028072263654409154, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06339622641509433, | |
| "grad_norm": 0.0010565021075308323, | |
| "learning_rate": 0.0002794884721436361, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0649056603773585, | |
| "grad_norm": 0.0007690914790146053, | |
| "learning_rate": 0.00027821890688783083, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06641509433962264, | |
| "grad_norm": 0.004054183140397072, | |
| "learning_rate": 0.0002769142878631403, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06792452830188679, | |
| "grad_norm": 0.000730887521058321, | |
| "learning_rate": 0.00027557497173937923, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06943396226415094, | |
| "grad_norm": 0.00044435824383981526, | |
| "learning_rate": 0.000274201324672203, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0709433962264151, | |
| "grad_norm": 0.00042757357005029917, | |
| "learning_rate": 0.00027279372220300385, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07245283018867925, | |
| "grad_norm": 0.0003725688438862562, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0739622641509434, | |
| "grad_norm": 0.001020943047478795, | |
| "learning_rate": 0.00026987819953423867, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07547169811320754, | |
| "grad_norm": 0.0002570598153397441, | |
| "learning_rate": 0.00026837107640945905, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07547169811320754, | |
| "eval_loss": 2.3195319954538718e-05, | |
| "eval_runtime": 4.2144, | |
| "eval_samples_per_second": 11.864, | |
| "eval_steps_per_second": 1.661, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.88255238782976e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |