| { | |
| "best_metric": 0.10144082456827164, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.37418147801683815, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007483629560336763, | |
| "grad_norm": 2668.53466796875, | |
| "learning_rate": 5e-05, | |
| "loss": 4.3827, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007483629560336763, | |
| "eval_loss": 4.760346412658691, | |
| "eval_runtime": 26.3843, | |
| "eval_samples_per_second": 34.149, | |
| "eval_steps_per_second": 4.283, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014967259120673527, | |
| "grad_norm": 2783.445068359375, | |
| "learning_rate": 0.0001, | |
| "loss": 4.4899, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02245088868101029, | |
| "grad_norm": 394.49444580078125, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.1667, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.029934518241347054, | |
| "grad_norm": 595.1309814453125, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.8192, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.037418147801683815, | |
| "grad_norm": 505.4878845214844, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.5339, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04490177736202058, | |
| "grad_norm": 969.9791259765625, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.5082, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.052385406922357346, | |
| "grad_norm": 246.9044189453125, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.1231, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05986903648269411, | |
| "grad_norm": 28.268033981323242, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0382, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06735266604303088, | |
| "grad_norm": 28.354206085205078, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.0281, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07483629560336763, | |
| "grad_norm": 20.920122146606445, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0122, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0823199251637044, | |
| "grad_norm": 16.22517204284668, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0104, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08980355472404115, | |
| "grad_norm": 20.09650421142578, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0057, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09728718428437792, | |
| "grad_norm": 1341.5556640625, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.342, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10477081384471469, | |
| "grad_norm": 277.5860900878906, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7457, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11225444340505145, | |
| "grad_norm": 130.9478302001953, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4444, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11973807296538821, | |
| "grad_norm": 233.44265747070312, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.398, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12722170252572498, | |
| "grad_norm": 54.11774444580078, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.2516, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.13470533208606175, | |
| "grad_norm": 24.96857452392578, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0276, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1421889616463985, | |
| "grad_norm": 26.93854522705078, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0369, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14967259120673526, | |
| "grad_norm": 16.38790512084961, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0276, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.15715622076707203, | |
| "grad_norm": 23.881519317626953, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0387, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1646398503274088, | |
| "grad_norm": 30.489585876464844, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.069, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.17212347988774557, | |
| "grad_norm": 15.927953720092773, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0301, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1796071094480823, | |
| "grad_norm": 553.0681762695312, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1495, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.18709073900841908, | |
| "grad_norm": 40.822509765625, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0246, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18709073900841908, | |
| "eval_loss": 0.22793392837047577, | |
| "eval_runtime": 26.3513, | |
| "eval_samples_per_second": 34.192, | |
| "eval_steps_per_second": 4.288, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19457436856875585, | |
| "grad_norm": 88.36663818359375, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4986, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.20205799812909261, | |
| "grad_norm": 71.94731903076172, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4428, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.20954162768942938, | |
| "grad_norm": 38.94894027709961, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.3858, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.21702525724976612, | |
| "grad_norm": 46.135990142822266, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3197, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2245088868101029, | |
| "grad_norm": 178.49417114257812, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.1487, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23199251637043966, | |
| "grad_norm": 62.31162643432617, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0742, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.23947614593077643, | |
| "grad_norm": 33.370609283447266, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0345, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2469597754911132, | |
| "grad_norm": 17.26993751525879, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0258, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.25444340505144997, | |
| "grad_norm": 14.258871078491211, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.027, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.26192703461178674, | |
| "grad_norm": 11.711955070495605, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0188, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2694106641721235, | |
| "grad_norm": 14.561089515686035, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0255, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2768942937324602, | |
| "grad_norm": 8.522704124450684, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0103, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.284377923292797, | |
| "grad_norm": 665.8914794921875, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8397, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.29186155285313375, | |
| "grad_norm": 717.4110717773438, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8972, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2993451824134705, | |
| "grad_norm": 291.5386047363281, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5768, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3068288119738073, | |
| "grad_norm": 176.5371551513672, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4695, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.31431244153414406, | |
| "grad_norm": 60.231441497802734, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2442, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.32179607109448083, | |
| "grad_norm": 14.835460662841797, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0233, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3292797006548176, | |
| "grad_norm": 6.386807918548584, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.011, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.33676333021515437, | |
| "grad_norm": 10.121891975402832, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0239, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.34424695977549113, | |
| "grad_norm": 11.264687538146973, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0104, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3517305893358279, | |
| "grad_norm": 7.20819091796875, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0104, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3592142188961646, | |
| "grad_norm": 9.249587059020996, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0109, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3666978484565014, | |
| "grad_norm": 19.556489944458008, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0141, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.37418147801683815, | |
| "grad_norm": 106.16588592529297, | |
| "learning_rate": 0.0, | |
| "loss": 0.016, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.37418147801683815, | |
| "eval_loss": 0.10144082456827164, | |
| "eval_runtime": 26.358, | |
| "eval_samples_per_second": 34.183, | |
| "eval_steps_per_second": 4.287, | |
| "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": 5.658027780734976e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |