| { | |
| "best_metric": 0.44097796082496643, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.026441036488630356, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005288207297726071, | |
| "grad_norm": 3.079803705215454, | |
| "learning_rate": 0.0001, | |
| "loss": 2.107, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005288207297726071, | |
| "eval_loss": 3.4710946083068848, | |
| "eval_runtime": 279.4296, | |
| "eval_samples_per_second": 2.852, | |
| "eval_steps_per_second": 1.428, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010576414595452142, | |
| "grad_norm": 3.9500977993011475, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2537, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0015864621893178213, | |
| "grad_norm": 3.463766574859619, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 2.084, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0021152829190904283, | |
| "grad_norm": 3.929175853729248, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 1.825, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0026441036488630354, | |
| "grad_norm": 3.6939759254455566, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 1.2347, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0031729243786356425, | |
| "grad_norm": 3.8677520751953125, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 1.2043, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0037017451084082496, | |
| "grad_norm": 2.874622344970703, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.8201, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004230565838180857, | |
| "grad_norm": 2.879485607147217, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.8926, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004759386567953464, | |
| "grad_norm": 4.38440465927124, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 0.8809, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005288207297726071, | |
| "grad_norm": 3.197903871536255, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.6542, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005817028027498678, | |
| "grad_norm": 2.5063633918762207, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.5457, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006345848757271285, | |
| "grad_norm": 2.595250129699707, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.4891, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006874669487043892, | |
| "grad_norm": 3.3837358951568604, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.8347, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007403490216816499, | |
| "grad_norm": 2.079376220703125, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.4495, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007932310946589107, | |
| "grad_norm": 2.317464828491211, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.6247, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008461131676361713, | |
| "grad_norm": 2.3306057453155518, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.3897, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008989952406134321, | |
| "grad_norm": 2.1108222007751465, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.5025, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009518773135906928, | |
| "grad_norm": 3.1157798767089844, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.7051, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010047593865679535, | |
| "grad_norm": 2.5793957710266113, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.6203, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.010576414595452142, | |
| "grad_norm": 1.315252661705017, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.3476, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01110523532522475, | |
| "grad_norm": 1.7388885021209717, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.4823, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011634056054997356, | |
| "grad_norm": 2.825782060623169, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.5343, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.012162876784769964, | |
| "grad_norm": 2.279564619064331, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.3226, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01269169751454257, | |
| "grad_norm": 1.5213063955307007, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.2932, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013220518244315178, | |
| "grad_norm": 2.1449546813964844, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.3167, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013220518244315178, | |
| "eval_loss": 0.49429598450660706, | |
| "eval_runtime": 280.2863, | |
| "eval_samples_per_second": 2.844, | |
| "eval_steps_per_second": 1.424, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013749338974087784, | |
| "grad_norm": 2.0070135593414307, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3063, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.014278159703860392, | |
| "grad_norm": 2.7425220012664795, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.5191, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.014806980433632998, | |
| "grad_norm": 1.8991012573242188, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.4107, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.015335801163405606, | |
| "grad_norm": 2.079669237136841, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.575, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.015864621893178214, | |
| "grad_norm": 1.5450035333633423, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.285, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01639344262295082, | |
| "grad_norm": 1.7861802577972412, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.3807, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.016922263352723427, | |
| "grad_norm": 1.9254704713821411, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.4574, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.017451084082496033, | |
| "grad_norm": 2.295936107635498, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.4582, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.017979904812268643, | |
| "grad_norm": 2.942246437072754, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.5926, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01850872554204125, | |
| "grad_norm": 1.30338454246521, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.2572, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.019037546271813855, | |
| "grad_norm": 2.0632126331329346, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.4064, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01956636700158646, | |
| "grad_norm": 1.9891884326934814, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.397, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02009518773135907, | |
| "grad_norm": 1.516108751296997, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.2141, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.020624008461131677, | |
| "grad_norm": 2.0183143615722656, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.2988, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.021152829190904283, | |
| "grad_norm": 1.2690092325210571, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.3371, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02168164992067689, | |
| "grad_norm": 1.9884178638458252, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.3387, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0222104706504495, | |
| "grad_norm": 1.528070092201233, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.275, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.022739291380222106, | |
| "grad_norm": 1.3429299592971802, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.2422, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.023268112109994712, | |
| "grad_norm": 2.5254251956939697, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.4689, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.023796932839767318, | |
| "grad_norm": 1.6032429933547974, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.371, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.024325753569539928, | |
| "grad_norm": 1.51561439037323, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.1822, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.024854574299312534, | |
| "grad_norm": 2.3901467323303223, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.3474, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02538339502908514, | |
| "grad_norm": 1.7008579969406128, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.2807, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.025912215758857746, | |
| "grad_norm": 5.191266059875488, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.5048, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.026441036488630356, | |
| "grad_norm": 2.155629873275757, | |
| "learning_rate": 0.0, | |
| "loss": 0.4876, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.026441036488630356, | |
| "eval_loss": 0.44097796082496643, | |
| "eval_runtime": 280.5295, | |
| "eval_samples_per_second": 2.841, | |
| "eval_steps_per_second": 1.422, | |
| "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": 7.41887283560448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |