| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.932862190812721, | |
| "eval_steps": 500, | |
| "global_step": 105, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1413427561837456, | |
| "grad_norm": 10.981925964355469, | |
| "learning_rate": 4.972077065562821e-05, | |
| "loss": 4.3219, | |
| "num_input_tokens_seen": 89360, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2826855123674912, | |
| "grad_norm": 19.007112503051758, | |
| "learning_rate": 4.888932014465352e-05, | |
| "loss": 2.7795, | |
| "num_input_tokens_seen": 173680, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.42402826855123676, | |
| "grad_norm": 48.207359313964844, | |
| "learning_rate": 4.783863644106502e-05, | |
| "loss": 3.1788, | |
| "num_input_tokens_seen": 256320, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5653710247349824, | |
| "grad_norm": 21.095312118530273, | |
| "learning_rate": 4.606802396635098e-05, | |
| "loss": 2.8887, | |
| "num_input_tokens_seen": 354080, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7067137809187279, | |
| "grad_norm": 28.128597259521484, | |
| "learning_rate": 4.382678665009028e-05, | |
| "loss": 2.5454, | |
| "num_input_tokens_seen": 445120, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8480565371024735, | |
| "grad_norm": 20.008413314819336, | |
| "learning_rate": 4.116499003039499e-05, | |
| "loss": 2.201, | |
| "num_input_tokens_seen": 536160, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9893992932862191, | |
| "grad_norm": 14.743931770324707, | |
| "learning_rate": 3.814209424526262e-05, | |
| "loss": 1.3345, | |
| "num_input_tokens_seen": 622160, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1130742049469964, | |
| "grad_norm": 8.293540000915527, | |
| "learning_rate": 3.4825625791348096e-05, | |
| "loss": 0.9507, | |
| "num_input_tokens_seen": 702992, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.254416961130742, | |
| "grad_norm": 17.665626525878906, | |
| "learning_rate": 3.1289669093612714e-05, | |
| "loss": 0.6257, | |
| "num_input_tokens_seen": 795712, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.3957597173144876, | |
| "grad_norm": 33.63065719604492, | |
| "learning_rate": 2.761321158169134e-05, | |
| "loss": 1.9766, | |
| "num_input_tokens_seen": 880032, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5371024734982333, | |
| "grad_norm": 23.377574920654297, | |
| "learning_rate": 2.3878379241237136e-05, | |
| "loss": 1.0377, | |
| "num_input_tokens_seen": 969392, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.6784452296819787, | |
| "grad_norm": 55.45833969116211, | |
| "learning_rate": 2.0168602055111173e-05, | |
| "loss": 1.5486, | |
| "num_input_tokens_seen": 1058752, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.8197879858657244, | |
| "grad_norm": 48.33625411987305, | |
| "learning_rate": 1.6566750315429254e-05, | |
| "loss": 0.7542, | |
| "num_input_tokens_seen": 1143072, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.96113074204947, | |
| "grad_norm": 33.805084228515625, | |
| "learning_rate": 1.3153283438175034e-05, | |
| "loss": 0.7561, | |
| "num_input_tokens_seen": 1234112, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.0848056537102475, | |
| "grad_norm": 40.988277435302734, | |
| "learning_rate": 1.0004452632802158e-05, | |
| "loss": 0.73, | |
| "num_input_tokens_seen": 1303184, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.2261484098939928, | |
| "grad_norm": 8.889869689941406, | |
| "learning_rate": 7.190597576216385e-06, | |
| "loss": 0.5124, | |
| "num_input_tokens_seen": 1385824, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.3674911660777385, | |
| "grad_norm": 17.493833541870117, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 0.7801, | |
| "num_input_tokens_seen": 1476864, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 2.508833922261484, | |
| "grad_norm": 16.65656280517578, | |
| "learning_rate": 2.8103552748861476e-06, | |
| "loss": 0.3849, | |
| "num_input_tokens_seen": 1569584, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.65017667844523, | |
| "grad_norm": 21.752721786499023, | |
| "learning_rate": 1.3418154050208936e-06, | |
| "loss": 0.4539, | |
| "num_input_tokens_seen": 1657264, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.791519434628975, | |
| "grad_norm": 18.232982635498047, | |
| "learning_rate": 4.0176028503425835e-07, | |
| "loss": 1.1474, | |
| "num_input_tokens_seen": 1746624, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.932862190812721, | |
| "grad_norm": 17.093202590942383, | |
| "learning_rate": 1.1189192912416934e-08, | |
| "loss": 0.7139, | |
| "num_input_tokens_seen": 1841024, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.932862190812721, | |
| "num_input_tokens_seen": 1841024, | |
| "step": 105, | |
| "total_flos": 7451631889809408.0, | |
| "train_loss": 1.5058091197695052, | |
| "train_runtime": 2933.1034, | |
| "train_samples_per_second": 0.578, | |
| "train_steps_per_second": 0.036 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 105, | |
| "num_input_tokens_seen": 1841024, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7451631889809408.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |