| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0015710096355257646, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.236698785085882e-05, | |
| "eval_loss": 0.9385595321655273, | |
| "eval_runtime": 1322.2075, | |
| "eval_samples_per_second": 6.081, | |
| "eval_steps_per_second": 3.041, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015710096355257646, | |
| "grad_norm": 0.23999691009521484, | |
| "learning_rate": 6e-05, | |
| "loss": 0.8098, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003142019271051529, | |
| "grad_norm": 0.3056129813194275, | |
| "learning_rate": 0.00012, | |
| "loss": 0.8653, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00041893590280687055, | |
| "eval_loss": 0.917888343334198, | |
| "eval_runtime": 1327.2388, | |
| "eval_samples_per_second": 6.058, | |
| "eval_steps_per_second": 3.03, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00047130289065772937, | |
| "grad_norm": 0.43505358695983887, | |
| "learning_rate": 0.00018, | |
| "loss": 0.8328, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006284038542103058, | |
| "grad_norm": 0.3369526267051697, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.9986, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0007855048177628823, | |
| "grad_norm": 0.3511159121990204, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.9991, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008378718056137411, | |
| "eval_loss": 0.8831256031990051, | |
| "eval_runtime": 1327.855, | |
| "eval_samples_per_second": 6.056, | |
| "eval_steps_per_second": 3.028, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0009426057813154587, | |
| "grad_norm": 0.3320366442203522, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.9714, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0010997067448680353, | |
| "grad_norm": 0.2684893310070038, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.7822, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0012568077084206116, | |
| "grad_norm": 0.34340476989746094, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.9724, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0012568077084206116, | |
| "eval_loss": 0.8722042441368103, | |
| "eval_runtime": 1327.6431, | |
| "eval_samples_per_second": 6.057, | |
| "eval_steps_per_second": 3.029, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0014139086719731882, | |
| "grad_norm": 0.26883986592292786, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.9491, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0015710096355257646, | |
| "grad_norm": 0.2960861921310425, | |
| "learning_rate": 0.0, | |
| "loss": 0.8432, | |
| "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": 2.160746713369805e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |