| { | |
| "best_metric": 1.1910210847854614, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.059417706476530004, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011883541295306002, | |
| "grad_norm": 26.55430793762207, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6588, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011883541295306002, | |
| "eval_loss": 1.6709991693496704, | |
| "eval_runtime": 166.6094, | |
| "eval_samples_per_second": 34.026, | |
| "eval_steps_per_second": 4.255, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023767082590612004, | |
| "grad_norm": 32.85348892211914, | |
| "learning_rate": 0.0001, | |
| "loss": 1.765, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0035650623885918, | |
| "grad_norm": 20.48172378540039, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.6475, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004753416518122401, | |
| "grad_norm": 27.701419830322266, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.5966, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0059417706476530005, | |
| "grad_norm": 22.22398567199707, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.5637, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0071301247771836, | |
| "grad_norm": 16.52712631225586, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.4803, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008318478906714201, | |
| "grad_norm": 14.630942344665527, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3969, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009506833036244802, | |
| "grad_norm": 16.13384246826172, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2954, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0106951871657754, | |
| "grad_norm": 18.945266723632812, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.408, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011883541295306001, | |
| "grad_norm": 26.285686492919922, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3286, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013071895424836602, | |
| "grad_norm": 93.21305847167969, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.1867, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0142602495543672, | |
| "grad_norm": 31.982948303222656, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.0114, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015448603683897801, | |
| "grad_norm": 36.17901611328125, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.3851, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.016636957813428402, | |
| "grad_norm": 26.595048904418945, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4674, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017825311942959002, | |
| "grad_norm": 14.14030647277832, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.4781, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019013666072489603, | |
| "grad_norm": 13.048796653747559, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.4555, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.020202020202020204, | |
| "grad_norm": 11.20543098449707, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.3655, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0213903743315508, | |
| "grad_norm": 11.113212585449219, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3139, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0225787284610814, | |
| "grad_norm": 11.72054672241211, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.3233, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.023767082590612002, | |
| "grad_norm": 11.633936882019043, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2198, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.024955436720142603, | |
| "grad_norm": 13.149057388305664, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2254, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.026143790849673203, | |
| "grad_norm": 16.921953201293945, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2976, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.027332144979203804, | |
| "grad_norm": 21.67167091369629, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.1837, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0285204991087344, | |
| "grad_norm": 23.87586212158203, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.0194, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.029708853238265002, | |
| "grad_norm": 35.1786003112793, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.0452, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029708853238265002, | |
| "eval_loss": 1.5183314085006714, | |
| "eval_runtime": 167.1956, | |
| "eval_samples_per_second": 33.906, | |
| "eval_steps_per_second": 4.241, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.030897207367795602, | |
| "grad_norm": 274.412841796875, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7169, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03208556149732621, | |
| "grad_norm": 149.68296813964844, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.5095, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.033273915626856804, | |
| "grad_norm": 25.888473510742188, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.3772, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0344622697563874, | |
| "grad_norm": 14.580528259277344, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.3296, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.035650623885918005, | |
| "grad_norm": 12.936845779418945, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.2996, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0368389780154486, | |
| "grad_norm": 11.484175682067871, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.2468, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.038027332144979206, | |
| "grad_norm": 11.391379356384277, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2111, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0392156862745098, | |
| "grad_norm": 12.249479293823242, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.1536, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04040404040404041, | |
| "grad_norm": 17.404399871826172, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.2524, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.041592394533571005, | |
| "grad_norm": 23.930089950561523, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.209, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "grad_norm": 35.380741119384766, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.0254, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.043969102792632206, | |
| "grad_norm": 44.73492431640625, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.9604, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0451574569221628, | |
| "grad_norm": 32.5949821472168, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2433, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04634581105169341, | |
| "grad_norm": 12.151544570922852, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.3159, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.047534165181224004, | |
| "grad_norm": 13.319056510925293, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.333, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0487225193107546, | |
| "grad_norm": 12.818878173828125, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.3444, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.049910873440285206, | |
| "grad_norm": 12.929219245910645, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.3271, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0510992275698158, | |
| "grad_norm": 12.480031967163086, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.254, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05228758169934641, | |
| "grad_norm": 13.18757152557373, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2245, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.053475935828877004, | |
| "grad_norm": 16.51483917236328, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.1654, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05466428995840761, | |
| "grad_norm": 17.32997703552246, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.1569, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.055852644087938205, | |
| "grad_norm": 17.273448944091797, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.3149, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0570409982174688, | |
| "grad_norm": 19.1171932220459, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.0405, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.058229352346999406, | |
| "grad_norm": 22.05423355102539, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.9513, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.059417706476530004, | |
| "grad_norm": 28.549123764038086, | |
| "learning_rate": 0.0, | |
| "loss": 0.9478, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.059417706476530004, | |
| "eval_loss": 1.1910210847854614, | |
| "eval_runtime": 166.9658, | |
| "eval_samples_per_second": 33.953, | |
| "eval_steps_per_second": 4.246, | |
| "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": 5.6633321727197184e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |