| { |
| "best_global_step": 300, |
| "best_metric": 0.3165888488292694, |
| "best_model_checkpoint": "/workspace/anchor/olmo-compassion-web-s2/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": 1.163063645362854, |
| "learning_rate": 1.7021276595744682e-05, |
| "loss": 1.1207, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.010692328254477412, |
| "grad_norm": 1.4067025184631348, |
| "learning_rate": 3.829787234042553e-05, |
| "loss": 0.9711, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.01603849238171612, |
| "grad_norm": 0.8022639155387878, |
| "learning_rate": 5.9574468085106384e-05, |
| "loss": 0.8716, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.021384656508954825, |
| "grad_norm": 1.227128267288208, |
| "learning_rate": 8.085106382978723e-05, |
| "loss": 0.6679, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.02673082063619353, |
| "grad_norm": 1.3577823638916016, |
| "learning_rate": 0.00010212765957446809, |
| "loss": 0.6026, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.03207698476343224, |
| "grad_norm": 1.6052050590515137, |
| "learning_rate": 0.00012340425531914893, |
| "loss": 0.7036, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.03742314889067094, |
| "grad_norm": 1.4057849645614624, |
| "learning_rate": 0.0001446808510638298, |
| "loss": 0.5792, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.04276931301790965, |
| "grad_norm": 1.3657870292663574, |
| "learning_rate": 0.00016595744680851065, |
| "loss": 0.5134, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.048115477145148355, |
| "grad_norm": 1.0391675233840942, |
| "learning_rate": 0.0001872340425531915, |
| "loss": 0.5381, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.05346164127238706, |
| "grad_norm": 0.9683766961097717, |
| "learning_rate": 0.00019999750239122662, |
| "loss": 0.5001, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.05346164127238706, |
| "eval_loss": 0.4231555461883545, |
| "eval_runtime": 166.2485, |
| "eval_samples_per_second": 2.31, |
| "eval_steps_per_second": 1.155, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.05880780539962577, |
| "grad_norm": 1.1648342609405518, |
| "learning_rate": 0.0001999694057253083, |
| "loss": 0.6182, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.06415396952686447, |
| "grad_norm": 1.2007864713668823, |
| "learning_rate": 0.00019991009918336413, |
| "loss": 0.4698, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.06950013365410318, |
| "grad_norm": 0.8219057321548462, |
| "learning_rate": 0.00019981960128055687, |
| "loss": 0.3948, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.07484629778134189, |
| "grad_norm": 0.9363082647323608, |
| "learning_rate": 0.0001996979402698136, |
| "loss": 0.5086, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.08019246190858059, |
| "grad_norm": 0.6071483492851257, |
| "learning_rate": 0.00019954515413300516, |
| "loss": 0.4872, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.0855386260358193, |
| "grad_norm": 0.6483224034309387, |
| "learning_rate": 0.00019936129056908865, |
| "loss": 0.6249, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.090884790163058, |
| "grad_norm": 0.6583413481712341, |
| "learning_rate": 0.00019914640697921585, |
| "loss": 0.4704, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.09623095429029671, |
| "grad_norm": 0.5416878461837769, |
| "learning_rate": 0.00019890057044881306, |
| "loss": 0.5516, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.10157711841753542, |
| "grad_norm": 0.656437873840332, |
| "learning_rate": 0.0001986238577266374, |
| "loss": 0.4088, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.10692328254477412, |
| "grad_norm": 0.6249133944511414, |
| "learning_rate": 0.00019831635520081625, |
| "loss": 0.4826, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.10692328254477412, |
| "eval_loss": 0.3424660265445709, |
| "eval_runtime": 64.3443, |
| "eval_samples_per_second": 5.968, |
| "eval_steps_per_second": 2.984, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.11226944667201283, |
| "grad_norm": 0.601626455783844, |
| "learning_rate": 0.00019797815887187726, |
| "loss": 0.4567, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.11761561079925154, |
| "grad_norm": 0.4807310104370117, |
| "learning_rate": 0.00019760937432277786, |
| "loss": 0.4607, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.12296177492649024, |
| "grad_norm": 0.5414025783538818, |
| "learning_rate": 0.0001972101166859425, |
| "loss": 0.5798, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.12830793905372895, |
| "grad_norm": 0.46784576773643494, |
| "learning_rate": 0.0001967805106073192, |
| "loss": 0.3468, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.13365410318096765, |
| "grad_norm": 0.5162056088447571, |
| "learning_rate": 0.00019632069020746572, |
| "loss": 0.4652, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.13900026730820636, |
| "grad_norm": 0.6472817063331604, |
| "learning_rate": 0.00019583079903967785, |
| "loss": 0.5919, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.14434643143544507, |
| "grad_norm": 0.692052960395813, |
| "learning_rate": 0.000195310990045173, |
| "loss": 0.5115, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.14969259556268377, |
| "grad_norm": 0.44978657364845276, |
| "learning_rate": 0.0001947614255053428, |
| "loss": 0.3182, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.15503875968992248, |
| "grad_norm": 0.5151785016059875, |
| "learning_rate": 0.00019418227699108956, |
| "loss": 0.4794, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.16038492381716118, |
| "grad_norm": 0.5038560628890991, |
| "learning_rate": 0.00019357372530926322, |
| "loss": 0.5511, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.16038492381716118, |
| "eval_loss": 0.33385396003723145, |
| "eval_runtime": 64.3938, |
| "eval_samples_per_second": 5.963, |
| "eval_steps_per_second": 2.982, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.1657310879443999, |
| "grad_norm": 0.5619863867759705, |
| "learning_rate": 0.00019293596044621416, |
| "loss": 0.4903, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.1710772520716386, |
| "grad_norm": 0.6460179090499878, |
| "learning_rate": 0.00019226918150848068, |
| "loss": 0.4651, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.1764234161988773, |
| "grad_norm": 0.6186167597770691, |
| "learning_rate": 0.00019157359666062903, |
| "loss": 0.466, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.181769580326116, |
| "grad_norm": 0.5170834064483643, |
| "learning_rate": 0.00019084942306026568, |
| "loss": 0.4862, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.18711574445335472, |
| "grad_norm": 0.5558421611785889, |
| "learning_rate": 0.0001900968867902419, |
| "loss": 0.56, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.19246190858059342, |
| "grad_norm": 0.5665396451950073, |
| "learning_rate": 0.00018931622278807212, |
| "loss": 0.5789, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.19780807270783213, |
| "grad_norm": 0.6116076707839966, |
| "learning_rate": 0.00018850767477258753, |
| "loss": 0.2663, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.20315423683507083, |
| "grad_norm": 0.5950028300285339, |
| "learning_rate": 0.00018767149516784874, |
| "loss": 0.4403, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.20850040096230954, |
| "grad_norm": 0.5122601985931396, |
| "learning_rate": 0.00018680794502434018, |
| "loss": 0.3972, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.21384656508954825, |
| "grad_norm": 0.5357354283332825, |
| "learning_rate": 0.00018591729393747187, |
| "loss": 0.4764, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.21384656508954825, |
| "eval_loss": 0.3293338119983673, |
| "eval_runtime": 64.3912, |
| "eval_samples_per_second": 5.964, |
| "eval_steps_per_second": 2.982, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.21919272921678695, |
| "grad_norm": 0.5082443952560425, |
| "learning_rate": 0.0001849998199634131, |
| "loss": 0.5307, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.22453889334402566, |
| "grad_norm": 0.5360233783721924, |
| "learning_rate": 0.00018405580953228493, |
| "loss": 0.419, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.22988505747126436, |
| "grad_norm": 0.41893500089645386, |
| "learning_rate": 0.00018308555735873844, |
| "loss": 0.3601, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.23523122159850307, |
| "grad_norm": 0.6814525723457336, |
| "learning_rate": 0.0001820893663499464, |
| "loss": 0.5563, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.24057738572574178, |
| "grad_norm": 0.4897703528404236, |
| "learning_rate": 0.00018106754751103735, |
| "loss": 0.4657, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.24592354985298048, |
| "grad_norm": 0.4542348384857178, |
| "learning_rate": 0.00018002041984800174, |
| "loss": 0.417, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.2512697139802192, |
| "grad_norm": 0.47860705852508545, |
| "learning_rate": 0.00017894831026809985, |
| "loss": 0.4546, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.2566158781074579, |
| "grad_norm": 0.6006109714508057, |
| "learning_rate": 0.00017785155347780352, |
| "loss": 0.4021, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.2619620422346966, |
| "grad_norm": 0.6438106298446655, |
| "learning_rate": 0.00017673049187830252, |
| "loss": 0.4151, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.2673082063619353, |
| "grad_norm": 0.6574239730834961, |
| "learning_rate": 0.00017558547545860868, |
| "loss": 0.5328, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2673082063619353, |
| "eval_loss": 0.3203986585140228, |
| "eval_runtime": 64.4396, |
| "eval_samples_per_second": 5.959, |
| "eval_steps_per_second": 2.98, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.272654370489174, |
| "grad_norm": 0.5759228467941284, |
| "learning_rate": 0.0001744168616862918, |
| "loss": 0.3799, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.2780005346164127, |
| "grad_norm": 0.6944848895072937, |
| "learning_rate": 0.00017322501539587988, |
| "loss": 0.4535, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.2833466987436514, |
| "grad_norm": 0.5996747016906738, |
| "learning_rate": 0.00017201030867496005, |
| "loss": 0.4694, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.28869286287089013, |
| "grad_norm": 0.42816469073295593, |
| "learning_rate": 0.00017077312074801498, |
| "loss": 0.3768, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.29403902699812884, |
| "grad_norm": 0.5391706228256226, |
| "learning_rate": 0.00016951383785803115, |
| "loss": 0.2878, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.29938519112536754, |
| "grad_norm": 0.8284974098205566, |
| "learning_rate": 0.00016823285314591593, |
| "loss": 0.5322, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.30473135525260625, |
| "grad_norm": 0.42258185148239136, |
| "learning_rate": 0.00016693056652776126, |
| "loss": 0.4177, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.31007751937984496, |
| "grad_norm": 0.6932430267333984, |
| "learning_rate": 0.00016560738456999232, |
| "loss": 0.5879, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.31542368350708366, |
| "grad_norm": 0.5092376470565796, |
| "learning_rate": 0.00016426372036243945, |
| "loss": 0.4069, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.32076984763432237, |
| "grad_norm": 0.5992222428321838, |
| "learning_rate": 0.00016289999338937427, |
| "loss": 0.4777, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.32076984763432237, |
| "eval_loss": 0.3165888488292694, |
| "eval_runtime": 64.5744, |
| "eval_samples_per_second": 5.947, |
| "eval_steps_per_second": 2.973, |
| "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 |
| } |
|
|
