| { |
| "best_global_step": 300, |
| "best_metric": 0.31583279371261597, |
| "best_model_checkpoint": "/workspace/anchor/olmo-compassion-web-s1/train/checkpoint-300", |
| "epoch": 0.32076984763432237, |
| "eval_steps": 50, |
| "global_step": 300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005346164127238706, |
| "grad_norm": 1.1645939350128174, |
| "learning_rate": 1.7021276595744682e-05, |
| "loss": 1.1232, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.010692328254477412, |
| "grad_norm": 1.3829007148742676, |
| "learning_rate": 3.829787234042553e-05, |
| "loss": 0.9721, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.01603849238171612, |
| "grad_norm": 0.8153295516967773, |
| "learning_rate": 5.9574468085106384e-05, |
| "loss": 0.8705, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.021384656508954825, |
| "grad_norm": 1.2247178554534912, |
| "learning_rate": 8.085106382978723e-05, |
| "loss": 0.67, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.02673082063619353, |
| "grad_norm": 1.347228765487671, |
| "learning_rate": 0.00010212765957446809, |
| "loss": 0.602, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.03207698476343224, |
| "grad_norm": 1.6137101650238037, |
| "learning_rate": 0.00012340425531914893, |
| "loss": 0.7035, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.03742314889067094, |
| "grad_norm": 1.3968698978424072, |
| "learning_rate": 0.0001446808510638298, |
| "loss": 0.579, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.04276931301790965, |
| "grad_norm": 1.3459135293960571, |
| "learning_rate": 0.00016595744680851065, |
| "loss": 0.5141, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.048115477145148355, |
| "grad_norm": 1.031345248222351, |
| "learning_rate": 0.0001872340425531915, |
| "loss": 0.5381, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.05346164127238706, |
| "grad_norm": 0.9651093482971191, |
| "learning_rate": 0.00019999750239122662, |
| "loss": 0.4995, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.05346164127238706, |
| "eval_loss": 0.42345890402793884, |
| "eval_runtime": 186.6803, |
| "eval_samples_per_second": 2.057, |
| "eval_steps_per_second": 1.028, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.05880780539962577, |
| "grad_norm": 1.1626384258270264, |
| "learning_rate": 0.0001999694057253083, |
| "loss": 0.6163, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.06415396952686447, |
| "grad_norm": 1.2009462118148804, |
| "learning_rate": 0.00019991009918336413, |
| "loss": 0.4706, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.06950013365410318, |
| "grad_norm": 0.8203537464141846, |
| "learning_rate": 0.00019981960128055687, |
| "loss": 0.3928, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.07484629778134189, |
| "grad_norm": 0.929426372051239, |
| "learning_rate": 0.0001996979402698136, |
| "loss": 0.5088, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.08019246190858059, |
| "grad_norm": 0.6230363249778748, |
| "learning_rate": 0.00019954515413300516, |
| "loss": 0.4882, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.0855386260358193, |
| "grad_norm": 0.6558757424354553, |
| "learning_rate": 0.00019936129056908865, |
| "loss": 0.6257, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.090884790163058, |
| "grad_norm": 0.6614608764648438, |
| "learning_rate": 0.00019914640697921585, |
| "loss": 0.4705, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.09623095429029671, |
| "grad_norm": 0.5442381501197815, |
| "learning_rate": 0.00019890057044881306, |
| "loss": 0.5511, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.10157711841753542, |
| "grad_norm": 0.6569603681564331, |
| "learning_rate": 0.0001986238577266374, |
| "loss": 0.4093, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.10692328254477412, |
| "grad_norm": 0.6291093826293945, |
| "learning_rate": 0.00019831635520081625, |
| "loss": 0.4826, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.10692328254477412, |
| "eval_loss": 0.34459128975868225, |
| "eval_runtime": 177.4646, |
| "eval_samples_per_second": 2.164, |
| "eval_steps_per_second": 1.082, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.11226944667201283, |
| "grad_norm": 0.5983524918556213, |
| "learning_rate": 0.00019797815887187726, |
| "loss": 0.4564, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.11761561079925154, |
| "grad_norm": 0.4736156761646271, |
| "learning_rate": 0.00019760937432277786, |
| "loss": 0.4606, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.12296177492649024, |
| "grad_norm": 0.5432220697402954, |
| "learning_rate": 0.0001972101166859425, |
| "loss": 0.5781, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.12830793905372895, |
| "grad_norm": 0.4643593728542328, |
| "learning_rate": 0.0001967805106073192, |
| "loss": 0.3453, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.13365410318096765, |
| "grad_norm": 0.5142726302146912, |
| "learning_rate": 0.00019632069020746572, |
| "loss": 0.4645, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.13900026730820636, |
| "grad_norm": 0.643227219581604, |
| "learning_rate": 0.00019583079903967785, |
| "loss": 0.5923, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.14434643143544507, |
| "grad_norm": 0.6978284120559692, |
| "learning_rate": 0.000195310990045173, |
| "loss": 0.512, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.14969259556268377, |
| "grad_norm": 0.4549601674079895, |
| "learning_rate": 0.0001947614255053428, |
| "loss": 0.3192, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.15503875968992248, |
| "grad_norm": 0.5181184411048889, |
| "learning_rate": 0.00019418227699108956, |
| "loss": 0.4764, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.16038492381716118, |
| "grad_norm": 0.5102682113647461, |
| "learning_rate": 0.00019357372530926322, |
| "loss": 0.5491, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.16038492381716118, |
| "eval_loss": 0.33368751406669617, |
| "eval_runtime": 180.2964, |
| "eval_samples_per_second": 2.13, |
| "eval_steps_per_second": 1.065, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.1657310879443999, |
| "grad_norm": 0.5677078366279602, |
| "learning_rate": 0.00019293596044621416, |
| "loss": 0.4879, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.1710772520716386, |
| "grad_norm": 0.617725670337677, |
| "learning_rate": 0.00019226918150848068, |
| "loss": 0.464, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.1764234161988773, |
| "grad_norm": 0.6151540279388428, |
| "learning_rate": 0.00019157359666062903, |
| "loss": 0.4658, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.181769580326116, |
| "grad_norm": 0.5095035433769226, |
| "learning_rate": 0.00019084942306026568, |
| "loss": 0.4824, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.18711574445335472, |
| "grad_norm": 0.5511929392814636, |
| "learning_rate": 0.0001900968867902419, |
| "loss": 0.5601, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.19246190858059342, |
| "grad_norm": 0.5659646391868591, |
| "learning_rate": 0.00018931622278807212, |
| "loss": 0.5773, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.19780807270783213, |
| "grad_norm": 0.6110894680023193, |
| "learning_rate": 0.00018850767477258753, |
| "loss": 0.2625, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.20315423683507083, |
| "grad_norm": 0.6004645824432373, |
| "learning_rate": 0.00018767149516784874, |
| "loss": 0.4398, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.20850040096230954, |
| "grad_norm": 0.5135135650634766, |
| "learning_rate": 0.00018680794502434018, |
| "loss": 0.3974, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.21384656508954825, |
| "grad_norm": 0.5316192507743835, |
| "learning_rate": 0.00018591729393747187, |
| "loss": 0.4736, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.21384656508954825, |
| "eval_loss": 0.3293432295322418, |
| "eval_runtime": 180.4048, |
| "eval_samples_per_second": 2.129, |
| "eval_steps_per_second": 1.064, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.21919272921678695, |
| "grad_norm": 0.5164016485214233, |
| "learning_rate": 0.0001849998199634131, |
| "loss": 0.5304, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.22453889334402566, |
| "grad_norm": 0.5472038388252258, |
| "learning_rate": 0.00018405580953228493, |
| "loss": 0.4185, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.22988505747126436, |
| "grad_norm": 0.42310619354248047, |
| "learning_rate": 0.00018308555735873844, |
| "loss": 0.3606, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.23523122159850307, |
| "grad_norm": 0.6889364719390869, |
| "learning_rate": 0.0001820893663499464, |
| "loss": 0.5575, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.24057738572574178, |
| "grad_norm": 0.4923793375492096, |
| "learning_rate": 0.00018106754751103735, |
| "loss": 0.4651, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.24592354985298048, |
| "grad_norm": 0.452239066362381, |
| "learning_rate": 0.00018002041984800174, |
| "loss": 0.4167, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.2512697139802192, |
| "grad_norm": 0.48884373903274536, |
| "learning_rate": 0.00017894831026809985, |
| "loss": 0.4553, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.2566158781074579, |
| "grad_norm": 0.601999044418335, |
| "learning_rate": 0.00017785155347780352, |
| "loss": 0.4032, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.2619620422346966, |
| "grad_norm": 0.649223268032074, |
| "learning_rate": 0.00017673049187830252, |
| "loss": 0.4139, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.2673082063619353, |
| "grad_norm": 0.6594939231872559, |
| "learning_rate": 0.00017558547545860868, |
| "loss": 0.5335, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2673082063619353, |
| "eval_loss": 0.3202017843723297, |
| "eval_runtime": 182.3055, |
| "eval_samples_per_second": 2.106, |
| "eval_steps_per_second": 1.053, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.272654370489174, |
| "grad_norm": 0.5863476395606995, |
| "learning_rate": 0.0001744168616862918, |
| "loss": 0.3789, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.2780005346164127, |
| "grad_norm": 0.6436650156974792, |
| "learning_rate": 0.00017322501539587988, |
| "loss": 0.4536, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.2833466987436514, |
| "grad_norm": 0.593532145023346, |
| "learning_rate": 0.00017201030867496005, |
| "loss": 0.4684, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.28869286287089013, |
| "grad_norm": 0.43021059036254883, |
| "learning_rate": 0.00017077312074801498, |
| "loss": 0.3755, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.29403902699812884, |
| "grad_norm": 0.5383488535881042, |
| "learning_rate": 0.00016951383785803115, |
| "loss": 0.2876, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.29938519112536754, |
| "grad_norm": 0.8212202191352844, |
| "learning_rate": 0.00016823285314591593, |
| "loss": 0.5294, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.30473135525260625, |
| "grad_norm": 0.4218836724758148, |
| "learning_rate": 0.00016693056652776126, |
| "loss": 0.4148, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.31007751937984496, |
| "grad_norm": 0.6949548125267029, |
| "learning_rate": 0.00016560738456999232, |
| "loss": 0.5895, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.31542368350708366, |
| "grad_norm": 0.5097229480743408, |
| "learning_rate": 0.00016426372036243945, |
| "loss": 0.4069, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.32076984763432237, |
| "grad_norm": 0.6012580990791321, |
| "learning_rate": 0.00016289999338937427, |
| "loss": 0.4793, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.32076984763432237, |
| "eval_loss": 0.31583279371261597, |
| "eval_runtime": 181.4225, |
| "eval_samples_per_second": 2.117, |
| "eval_steps_per_second": 1.058, |
| "step": 300 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 936, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8.165295431271383e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
