| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9994772608468374, |
| "eval_steps": 500, |
| "global_step": 239, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04181913225300575, |
| "grad_norm": 0.8873776197433472, |
| "learning_rate": 2e-05, |
| "loss": 1.8208, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0836382645060115, |
| "grad_norm": 0.5825883150100708, |
| "learning_rate": 4e-05, |
| "loss": 1.7048, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.12545739675901724, |
| "grad_norm": 0.24893978238105774, |
| "learning_rate": 6e-05, |
| "loss": 1.4799, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.167276529012023, |
| "grad_norm": 0.2235335111618042, |
| "learning_rate": 8e-05, |
| "loss": 1.3812, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.20909566126502874, |
| "grad_norm": 0.18197111785411835, |
| "learning_rate": 0.0001, |
| "loss": 1.2497, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2509147935180345, |
| "grad_norm": 0.1728171855211258, |
| "learning_rate": 0.00012, |
| "loss": 1.1161, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.29273392577104024, |
| "grad_norm": 0.1883663833141327, |
| "learning_rate": 0.00014, |
| "loss": 1.0589, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.334553058024046, |
| "grad_norm": 0.19224515557289124, |
| "learning_rate": 0.00016, |
| "loss": 0.9908, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.37637219027705177, |
| "grad_norm": 0.20248346030712128, |
| "learning_rate": 0.00018, |
| "loss": 0.9601, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.4181913225300575, |
| "grad_norm": 0.2133675217628479, |
| "learning_rate": 0.0002, |
| "loss": 0.9457, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.46001045478306324, |
| "grad_norm": 0.2351628541946411, |
| "learning_rate": 0.00019965482753212156, |
| "loss": 0.8952, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.501829587036069, |
| "grad_norm": 0.22406116127967834, |
| "learning_rate": 0.00019862169300913785, |
| "loss": 0.8748, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5436487192890748, |
| "grad_norm": 0.2309526801109314, |
| "learning_rate": 0.0001969077286229078, |
| "loss": 0.9075, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.5854678515420805, |
| "grad_norm": 0.25324976444244385, |
| "learning_rate": 0.00019452476663977248, |
| "loss": 0.8719, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.6272869837950863, |
| "grad_norm": 0.22996799647808075, |
| "learning_rate": 0.00019148925771710347, |
| "loss": 0.8529, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.669106116048092, |
| "grad_norm": 0.23832310736179352, |
| "learning_rate": 0.00018782215733702286, |
| "loss": 0.8631, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.7109252483010977, |
| "grad_norm": 0.23019501566886902, |
| "learning_rate": 0.00018354878114129367, |
| "loss": 0.8408, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.7527443805541035, |
| "grad_norm": 0.26359736919403076, |
| "learning_rate": 0.0001786986301660689, |
| "loss": 0.835, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.7945635128071092, |
| "grad_norm": 0.24976789951324463, |
| "learning_rate": 0.00017330518718298264, |
| "loss": 0.8232, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.836382645060115, |
| "grad_norm": 0.26566267013549805, |
| "learning_rate": 0.00016740568555253155, |
| "loss": 0.8125, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.8782017773131208, |
| "grad_norm": 0.24996772408485413, |
| "learning_rate": 0.00016104085218545633, |
| "loss": 0.8277, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.9200209095661265, |
| "grad_norm": 0.22901593148708344, |
| "learning_rate": 0.00015425462638657595, |
| "loss": 0.8178, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.9618400418191323, |
| "grad_norm": 0.25155940651893616, |
| "learning_rate": 0.00014709385652202203, |
| "loss": 0.7874, |
| "step": 230 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 478, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.32804778098688e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
