| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03715170278637771, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001238390092879257, | |
| "eval_loss": 3.5004749298095703, | |
| "eval_runtime": 28.3849, | |
| "eval_samples_per_second": 11.978, | |
| "eval_steps_per_second": 5.989, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0037151702786377707, | |
| "grad_norm": 3.120950937271118, | |
| "learning_rate": 6e-05, | |
| "loss": 3.423, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006191950464396285, | |
| "eval_loss": 2.645940065383911, | |
| "eval_runtime": 28.7175, | |
| "eval_samples_per_second": 11.839, | |
| "eval_steps_per_second": 5.92, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007430340557275541, | |
| "grad_norm": 3.04407000541687, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9764, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011145510835913313, | |
| "grad_norm": 2.6234803199768066, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7183, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01238390092879257, | |
| "eval_loss": 1.169345498085022, | |
| "eval_runtime": 36.3271, | |
| "eval_samples_per_second": 9.359, | |
| "eval_steps_per_second": 4.68, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014860681114551083, | |
| "grad_norm": 2.586092710494995, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.3273, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.018575851393188854, | |
| "grad_norm": 1.8593789339065552, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.126, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018575851393188854, | |
| "eval_loss": 0.9424641132354736, | |
| "eval_runtime": 61.7521, | |
| "eval_samples_per_second": 5.506, | |
| "eval_steps_per_second": 2.753, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.022291021671826627, | |
| "grad_norm": 1.9731193780899048, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.8594, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02476780185758514, | |
| "eval_loss": 0.8208107352256775, | |
| "eval_runtime": 61.9509, | |
| "eval_samples_per_second": 5.488, | |
| "eval_steps_per_second": 2.744, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026006191950464396, | |
| "grad_norm": 1.1178371906280518, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.9378, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029721362229102165, | |
| "grad_norm": 0.7379412651062012, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.8101, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.030959752321981424, | |
| "eval_loss": 0.7880878448486328, | |
| "eval_runtime": 61.9476, | |
| "eval_samples_per_second": 5.489, | |
| "eval_steps_per_second": 2.744, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03343653250773994, | |
| "grad_norm": 0.8323380947113037, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.819, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03715170278637771, | |
| "grad_norm": 0.670154333114624, | |
| "learning_rate": 0.0, | |
| "loss": 0.767, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03715170278637771, | |
| "eval_loss": 0.7814973592758179, | |
| "eval_runtime": 61.7928, | |
| "eval_samples_per_second": 5.502, | |
| "eval_steps_per_second": 2.751, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |