| { | |
| "best_metric": 0.9616518616676331, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.22955523672883787, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004591104734576757, | |
| "grad_norm": 258.8543701171875, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6363, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004591104734576757, | |
| "eval_loss": 4.508436679840088, | |
| "eval_runtime": 43.2411, | |
| "eval_samples_per_second": 33.949, | |
| "eval_steps_per_second": 4.255, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009182209469153515, | |
| "grad_norm": 288.6246337890625, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6012, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013773314203730272, | |
| "grad_norm": 193.73492431640625, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.899, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01836441893830703, | |
| "grad_norm": 156.01956176757812, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.2296, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02295552367288379, | |
| "grad_norm": 397.571533203125, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.6775, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.027546628407460545, | |
| "grad_norm": 297.1980285644531, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.3943, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0321377331420373, | |
| "grad_norm": 421.78607177734375, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.0063, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03672883787661406, | |
| "grad_norm": 3396.533203125, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.1958, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04131994261119082, | |
| "grad_norm": 4567.48681640625, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.193, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04591104734576758, | |
| "grad_norm": 1472.339111328125, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.0046, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05050215208034433, | |
| "grad_norm": 638.1349487304688, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.0747, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05509325681492109, | |
| "grad_norm": 2513.052734375, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 4.2219, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05968436154949785, | |
| "grad_norm": 682.025634765625, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.0715, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0642754662840746, | |
| "grad_norm": 193.63963317871094, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8845, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06886657101865136, | |
| "grad_norm": 78.0231704711914, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.3962, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07345767575322812, | |
| "grad_norm": 59.6154899597168, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.2781, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07804878048780488, | |
| "grad_norm": 25.36161231994629, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1904, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08263988522238164, | |
| "grad_norm": 30.39041519165039, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1466, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0872309899569584, | |
| "grad_norm": 81.36200714111328, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3125, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09182209469153516, | |
| "grad_norm": 2049.070556640625, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.3596, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09641319942611191, | |
| "grad_norm": 2821.229736328125, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 4.6067, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10100430416068866, | |
| "grad_norm": 1627.783203125, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.206, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10559540889526542, | |
| "grad_norm": 599.2235717773438, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.8774, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11018651362984218, | |
| "grad_norm": 572.1763305664062, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.8936, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11477761836441894, | |
| "grad_norm": 596.761962890625, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.6843, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11477761836441894, | |
| "eval_loss": 1.709513545036316, | |
| "eval_runtime": 43.2682, | |
| "eval_samples_per_second": 33.928, | |
| "eval_steps_per_second": 4.253, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1193687230989957, | |
| "grad_norm": 74.11042022705078, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7463, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12395982783357246, | |
| "grad_norm": 34.46171569824219, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.3697, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1285509325681492, | |
| "grad_norm": 21.73426628112793, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2139, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13314203730272597, | |
| "grad_norm": 10.719658851623535, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1253, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.13773314203730272, | |
| "grad_norm": 14.40205192565918, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.1023, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1423242467718795, | |
| "grad_norm": 28.01376724243164, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0992, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14691535150645624, | |
| "grad_norm": 740.5331420898438, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.7911, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.151506456241033, | |
| "grad_norm": 1348.0220947265625, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 6.519, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.15609756097560976, | |
| "grad_norm": 1065.9749755859375, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.5851, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1606886657101865, | |
| "grad_norm": 732.408447265625, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.0265, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16527977044476327, | |
| "grad_norm": 716.4056396484375, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.8283, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.16987087517934002, | |
| "grad_norm": 457.7398376464844, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.1625, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1744619799139168, | |
| "grad_norm": 105.070068359375, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1766, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17905308464849354, | |
| "grad_norm": 31.545076370239258, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3267, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1836441893830703, | |
| "grad_norm": 23.66084098815918, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2023, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18823529411764706, | |
| "grad_norm": 11.72018814086914, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.1194, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.19282639885222383, | |
| "grad_norm": 8.387150764465332, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0795, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.19741750358680057, | |
| "grad_norm": 9.269184112548828, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0675, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.20200860832137732, | |
| "grad_norm": 47.77657699584961, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6034, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2065997130559541, | |
| "grad_norm": 180.4890899658203, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.0342, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.21119081779053084, | |
| "grad_norm": 320.1153564453125, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.859, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2157819225251076, | |
| "grad_norm": 491.2322998046875, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.6845, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.22037302725968436, | |
| "grad_norm": 501.812744140625, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.8207, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.22496413199426113, | |
| "grad_norm": 318.70819091796875, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.6314, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.22955523672883787, | |
| "grad_norm": 515.6896362304688, | |
| "learning_rate": 0.0, | |
| "loss": 1.5723, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22955523672883787, | |
| "eval_loss": 0.9616518616676331, | |
| "eval_runtime": 43.2639, | |
| "eval_samples_per_second": 33.931, | |
| "eval_steps_per_second": 4.253, | |
| "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 | |
| } | |