| { |
| "best_global_step": 100, |
| "best_metric": 0.3424660265445709, |
| "best_model_checkpoint": "/workspace/anchor/olmo-compassion-web-s2/train/checkpoint-100", |
| "epoch": 0.10692328254477412, |
| "eval_steps": 50, |
| "global_step": 100, |
| "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 |
| } |
| ], |
| "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": 2.8103425491183206e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
