| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014138272303124559, | |
| "eval_steps": 500, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005655308921249824, | |
| "grad_norm": 9.447598457336426, | |
| "learning_rate": 0.0001, | |
| "loss": 7.5877, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011310617842499647, | |
| "grad_norm": 12.224023818969727, | |
| "learning_rate": 0.0002, | |
| "loss": 7.4966, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001696592676374947, | |
| "grad_norm": 8.18627643585205, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 6.524, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0022621235684999294, | |
| "grad_norm": 9.624427795410156, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 4.5356, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0028276544606249117, | |
| "grad_norm": 8.553901672363281, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 4.2528, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003393185352749894, | |
| "grad_norm": 5.756651401519775, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 4.1727, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003958716244874877, | |
| "grad_norm": 2.862290143966675, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 4.1679, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004524247136999859, | |
| "grad_norm": 1.6996726989746094, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 4.1149, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005089778029124841, | |
| "grad_norm": 2.1115152835845947, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 3.8839, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005655308921249823, | |
| "grad_norm": 1.4950510263442993, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 4.0708, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006220839813374806, | |
| "grad_norm": 3.2026827335357666, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 4.2101, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006786370705499788, | |
| "grad_norm": 1.4218138456344604, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 4.0784, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00735190159762477, | |
| "grad_norm": 2.44765043258667, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 4.079, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.007917432489749753, | |
| "grad_norm": 1.5132642984390259, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 4.1191, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.008482963381874735, | |
| "grad_norm": 1.7532415390014648, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 3.9846, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009048494273999718, | |
| "grad_norm": 1.528114914894104, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 4.0772, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.009614025166124699, | |
| "grad_norm": 1.0905526876449585, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 4.1484, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.010179556058249682, | |
| "grad_norm": 1.0690267086029053, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 4.01, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010745086950374664, | |
| "grad_norm": 0.7005692720413208, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 3.9638, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.011310617842499647, | |
| "grad_norm": 0.8180456757545471, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 4.0638, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011876148734624628, | |
| "grad_norm": 0.7685333490371704, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 4.0947, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.012441679626749611, | |
| "grad_norm": 0.8267884850502014, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 4.1512, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.013007210518874594, | |
| "grad_norm": 0.80919349193573, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 4.0781, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.013572741410999576, | |
| "grad_norm": 0.862808108329773, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 4.0492, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.014138272303124559, | |
| "grad_norm": 1.0544193983078003, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 3.9988, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.11806271012864e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |