| { |
| "best_global_step": 100, |
| "best_metric": 0.34459128975868225, |
| "best_model_checkpoint": "/workspace/anchor/olmo-compassion-web-s1/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": 1.1645939350128174, |
| "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 |
| } |
| ], |
| "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 |
| } |
|
|
