| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009771891479887818, | |
| "eval_steps": 500, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003257297159962606, | |
| "grad_norm": 2.2308592796325684, | |
| "learning_rate": 4.99853416853153e-05, | |
| "loss": 1.4483, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0006514594319925212, | |
| "grad_norm": 2.3997225761413574, | |
| "learning_rate": 4.996905466899897e-05, | |
| "loss": 1.3276, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0009771891479887819, | |
| "grad_norm": 1.4687339067459106, | |
| "learning_rate": 4.995276765268264e-05, | |
| "loss": 1.3394, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.0013029188639850425, | |
| "grad_norm": 0.6583470702171326, | |
| "learning_rate": 4.993648063636631e-05, | |
| "loss": 1.3245, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.0016286485799813031, | |
| "grad_norm": 1.6252340078353882, | |
| "learning_rate": 4.992019362004997e-05, | |
| "loss": 1.3249, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.0019543782959775637, | |
| "grad_norm": 2.0806777477264404, | |
| "learning_rate": 4.9903906603733634e-05, | |
| "loss": 1.32, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.002280108011973824, | |
| "grad_norm": 1.376539707183838, | |
| "learning_rate": 4.988761958741731e-05, | |
| "loss": 1.3133, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.002605837727970085, | |
| "grad_norm": 2.234644889831543, | |
| "learning_rate": 4.987133257110097e-05, | |
| "loss": 1.3179, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.0029315674439663454, | |
| "grad_norm": 1.4599684476852417, | |
| "learning_rate": 4.985504555478464e-05, | |
| "loss": 1.3097, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.0032572971599626062, | |
| "grad_norm": 1.7078094482421875, | |
| "learning_rate": 4.9838758538468304e-05, | |
| "loss": 1.3083, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.0035830268759588666, | |
| "grad_norm": 0.6953567266464233, | |
| "learning_rate": 4.9822471522151976e-05, | |
| "loss": 1.3075, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.0039087565919551275, | |
| "grad_norm": 1.225602626800537, | |
| "learning_rate": 4.980618450583564e-05, | |
| "loss": 1.3054, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.004234486307951388, | |
| "grad_norm": 1.3010519742965698, | |
| "learning_rate": 4.978989748951931e-05, | |
| "loss": 1.3066, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.004560216023947648, | |
| "grad_norm": 0.6475724577903748, | |
| "learning_rate": 4.9773610473202974e-05, | |
| "loss": 1.3109, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.004885945739943909, | |
| "grad_norm": 1.046614646911621, | |
| "learning_rate": 4.975732345688664e-05, | |
| "loss": 1.3074, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.00521167545594017, | |
| "grad_norm": 1.113573670387268, | |
| "learning_rate": 4.974103644057031e-05, | |
| "loss": 1.3083, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.005537405171936431, | |
| "grad_norm": 1.4273550510406494, | |
| "learning_rate": 4.972474942425398e-05, | |
| "loss": 1.3018, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.005863134887932691, | |
| "grad_norm": 0.5519908666610718, | |
| "learning_rate": 4.970846240793764e-05, | |
| "loss": 1.2945, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.006188864603928952, | |
| "grad_norm": 0.6653416156768799, | |
| "learning_rate": 4.969217539162131e-05, | |
| "loss": 1.3004, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.0065145943199252125, | |
| "grad_norm": 0.732170581817627, | |
| "learning_rate": 4.9675888375304975e-05, | |
| "loss": 1.3014, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.006840324035921473, | |
| "grad_norm": 0.405608594417572, | |
| "learning_rate": 4.965960135898865e-05, | |
| "loss": 1.2939, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.007166053751917733, | |
| "grad_norm": 0.9849847555160522, | |
| "learning_rate": 4.9643314342672306e-05, | |
| "loss": 1.2922, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.007491783467913994, | |
| "grad_norm": 0.7152832746505737, | |
| "learning_rate": 4.962702732635598e-05, | |
| "loss": 1.2905, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.007817513183910255, | |
| "grad_norm": 1.1164734363555908, | |
| "learning_rate": 4.9610740310039644e-05, | |
| "loss": 1.3024, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.008143242899906516, | |
| "grad_norm": 0.574243426322937, | |
| "learning_rate": 4.959445329372332e-05, | |
| "loss": 1.2944, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.008468972615902777, | |
| "grad_norm": 0.6976324319839478, | |
| "learning_rate": 4.9578166277406976e-05, | |
| "loss": 1.2939, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.008794702331899037, | |
| "grad_norm": 0.4648737609386444, | |
| "learning_rate": 4.956187926109064e-05, | |
| "loss": 1.2841, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.009120432047895297, | |
| "grad_norm": 1.189271092414856, | |
| "learning_rate": 4.9545592244774314e-05, | |
| "loss": 1.294, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.009446161763891557, | |
| "grad_norm": 0.6437670588493347, | |
| "learning_rate": 4.952930522845798e-05, | |
| "loss": 1.2882, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.009771891479887818, | |
| "grad_norm": 1.591304898262024, | |
| "learning_rate": 4.9513018212141646e-05, | |
| "loss": 1.2805, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 307003, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 4.4578841296896e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |