| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.42316314450517617, | |
| "eval_steps": 500, | |
| "global_step": 10500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020150625928817913, | |
| "grad_norm": 1.1627434492111206, | |
| "learning_rate": 1.0072522159548751e-05, | |
| "loss": 0.6529, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.04030125185763583, | |
| "grad_norm": 1.1110010147094727, | |
| "learning_rate": 2.0145044319097503e-05, | |
| "loss": 0.6192, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.060451877786453743, | |
| "grad_norm": 0.8589074611663818, | |
| "learning_rate": 3.0217566478646254e-05, | |
| "loss": 0.5975, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.08060250371527165, | |
| "grad_norm": 0.9587840437889099, | |
| "learning_rate": 4.0290088638195005e-05, | |
| "loss": 0.5769, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.10075312964408957, | |
| "grad_norm": 0.8058000206947327, | |
| "learning_rate": 4.9959697281805565e-05, | |
| "loss": 0.5703, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.12090375557290749, | |
| "grad_norm": 0.7425491809844971, | |
| "learning_rate": 4.8840177331960056e-05, | |
| "loss": 0.5645, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.1410543815017254, | |
| "grad_norm": 0.7902853488922119, | |
| "learning_rate": 4.7720657382114555e-05, | |
| "loss": 0.5477, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.1612050074305433, | |
| "grad_norm": 0.7411909699440002, | |
| "learning_rate": 4.6601137432269046e-05, | |
| "loss": 0.5451, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.18135563335936122, | |
| "grad_norm": 0.7251479625701904, | |
| "learning_rate": 4.548161748242354e-05, | |
| "loss": 0.5372, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.20150625928817914, | |
| "grad_norm": 0.7090137600898743, | |
| "learning_rate": 4.4362097532578036e-05, | |
| "loss": 0.5366, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.22165688521699706, | |
| "grad_norm": 0.5888206362724304, | |
| "learning_rate": 4.324257758273253e-05, | |
| "loss": 0.5289, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.24180751114581497, | |
| "grad_norm": 0.5961526036262512, | |
| "learning_rate": 4.212305763288702e-05, | |
| "loss": 0.5286, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.2619581370746329, | |
| "grad_norm": 0.676559567451477, | |
| "learning_rate": 4.1003537683041517e-05, | |
| "loss": 0.5263, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.2821087630034508, | |
| "grad_norm": 0.5270068645477295, | |
| "learning_rate": 3.988401773319601e-05, | |
| "loss": 0.5221, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.3022593889322687, | |
| "grad_norm": 0.6866596937179565, | |
| "learning_rate": 3.87644977833505e-05, | |
| "loss": 0.517, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.3224100148610866, | |
| "grad_norm": 0.6050545573234558, | |
| "learning_rate": 3.7644977833505e-05, | |
| "loss": 0.5183, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.34256064078990456, | |
| "grad_norm": 0.5003291368484497, | |
| "learning_rate": 3.652545788365949e-05, | |
| "loss": 0.5097, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.36271126671872245, | |
| "grad_norm": 0.5456134676933289, | |
| "learning_rate": 3.540593793381398e-05, | |
| "loss": 0.5072, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.3828618926475404, | |
| "grad_norm": 0.6824153661727905, | |
| "learning_rate": 3.428641798396848e-05, | |
| "loss": 0.5048, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.4030125185763583, | |
| "grad_norm": 0.5959055423736572, | |
| "learning_rate": 3.316689803412297e-05, | |
| "loss": 0.5021, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.42316314450517617, | |
| "grad_norm": 0.5629556775093079, | |
| "learning_rate": 3.204737808427746e-05, | |
| "loss": 0.5001, | |
| "step": 10500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 24813, | |
| "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": 1.677250108543338e+19, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |