| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 1.1201117318435754, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0223463687150838, | |
| "grad_norm": 0.7273042798042297, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5211, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0223463687150838, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2066, | |
| "eval_samples_per_second": 58.004, | |
| "eval_steps_per_second": 7.298, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0446927374301676, | |
| "grad_norm": 0.8414791822433472, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5344, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0670391061452514, | |
| "grad_norm": 0.7584518194198608, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.4888, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0893854748603352, | |
| "grad_norm": 0.7224532961845398, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.5179, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11173184357541899, | |
| "grad_norm": 0.8011540174484253, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.6189, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1340782122905028, | |
| "grad_norm": 1.1162501573562622, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.4959, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1564245810055866, | |
| "grad_norm": 0.8292059302330017, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.5304, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1787709497206704, | |
| "grad_norm": 0.7312890887260437, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.5171, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2011173184357542, | |
| "grad_norm": 0.8092410564422607, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.7047, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22346368715083798, | |
| "grad_norm": 0.8828912377357483, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.76, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24581005586592178, | |
| "grad_norm": 1.4495936632156372, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.027, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2681564245810056, | |
| "grad_norm": 0.68489009141922, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.3227, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2905027932960894, | |
| "grad_norm": 0.6434772610664368, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.2664, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.3128491620111732, | |
| "grad_norm": 0.6271873116493225, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.2793, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.33519553072625696, | |
| "grad_norm": 0.5901241898536682, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.2941, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3575418994413408, | |
| "grad_norm": 0.6838954091072083, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.407, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.37988826815642457, | |
| "grad_norm": 0.8338541388511658, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.2195, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4022346368715084, | |
| "grad_norm": 0.5875435471534729, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.4052, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4245810055865922, | |
| "grad_norm": 0.5944232940673828, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.39, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.44692737430167595, | |
| "grad_norm": 0.7437536120414734, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.6346, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4692737430167598, | |
| "grad_norm": 0.701321005821228, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.5239, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.49162011173184356, | |
| "grad_norm": 1.3199535608291626, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.6562, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5139664804469274, | |
| "grad_norm": 0.5730961561203003, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.2217, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5363128491620112, | |
| "grad_norm": 0.6202113032341003, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.2251, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5586592178770949, | |
| "grad_norm": 0.6694709658622742, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.1743, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5586592178770949, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.1989, | |
| "eval_samples_per_second": 58.089, | |
| "eval_steps_per_second": 7.309, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5810055865921788, | |
| "grad_norm": 0.5823168754577637, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2451, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6033519553072626, | |
| "grad_norm": 0.6771988272666931, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.2603, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6256983240223464, | |
| "grad_norm": 0.83906090259552, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.0626, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6480446927374302, | |
| "grad_norm": 0.6448845267295837, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.3127, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6703910614525139, | |
| "grad_norm": 0.6946954727172852, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.2754, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6927374301675978, | |
| "grad_norm": 0.6927757859230042, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.4821, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7150837988826816, | |
| "grad_norm": 0.7330152988433838, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.4882, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7374301675977654, | |
| "grad_norm": 1.3319170475006104, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.582, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7597765363128491, | |
| "grad_norm": 0.6171111464500427, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.2166, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7821229050279329, | |
| "grad_norm": 0.6328678727149963, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.1576, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8044692737430168, | |
| "grad_norm": 0.60038161277771, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.1738, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8268156424581006, | |
| "grad_norm": 0.5997684597969055, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.0954, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8491620111731844, | |
| "grad_norm": 0.7614952921867371, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.2288, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8715083798882681, | |
| "grad_norm": 0.7809704542160034, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.079, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8938547486033519, | |
| "grad_norm": 0.6555606722831726, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.3115, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9162011173184358, | |
| "grad_norm": 0.6785370111465454, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.3111, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.9385474860335196, | |
| "grad_norm": 0.6954032778739929, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.4374, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.9608938547486033, | |
| "grad_norm": 0.7169734835624695, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.3836, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9832402234636871, | |
| "grad_norm": 1.2481937408447266, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.4977, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0083798882681565, | |
| "grad_norm": 0.7138010859489441, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.1846, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0307262569832403, | |
| "grad_norm": 0.5319519639015198, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.0249, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.053072625698324, | |
| "grad_norm": 0.6440411806106567, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.1081, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0754189944134078, | |
| "grad_norm": 0.6161705851554871, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.2051, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0977653631284916, | |
| "grad_norm": 0.5636197924613953, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.0141, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1201117318435754, | |
| "grad_norm": 0.7595768570899963, | |
| "learning_rate": 0.0, | |
| "loss": 2.1503, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1201117318435754, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.1987, | |
| "eval_samples_per_second": 58.092, | |
| "eval_steps_per_second": 7.31, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.83042868150272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |