| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.030134096730450505, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006026819346090101, | |
| "eval_loss": 5.079477310180664, | |
| "eval_runtime": 24.8869, | |
| "eval_samples_per_second": 28.087, | |
| "eval_steps_per_second": 14.064, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0030134096730450506, | |
| "grad_norm": 1.770930290222168, | |
| "learning_rate": 5e-05, | |
| "loss": 4.6092, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006026819346090101, | |
| "grad_norm": 3.8804337978363037, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7694, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006026819346090101, | |
| "eval_loss": 4.817326068878174, | |
| "eval_runtime": 23.2427, | |
| "eval_samples_per_second": 30.074, | |
| "eval_steps_per_second": 15.058, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009040229019135152, | |
| "grad_norm": 3.369185447692871, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.6366, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012053638692180202, | |
| "grad_norm": 3.6224210262298584, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.8207, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.012053638692180202, | |
| "eval_loss": 4.2354631423950195, | |
| "eval_runtime": 23.18, | |
| "eval_samples_per_second": 30.155, | |
| "eval_steps_per_second": 15.099, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015067048365225252, | |
| "grad_norm": 5.666136264801025, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.943, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018080458038270304, | |
| "grad_norm": 3.962995767593384, | |
| "learning_rate": 5e-05, | |
| "loss": 4.1967, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.018080458038270304, | |
| "eval_loss": 3.9847233295440674, | |
| "eval_runtime": 23.2257, | |
| "eval_samples_per_second": 30.096, | |
| "eval_steps_per_second": 15.07, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021093867711315353, | |
| "grad_norm": 3.604246139526367, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.792, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.024107277384360404, | |
| "grad_norm": 3.8603432178497314, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.9186, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.024107277384360404, | |
| "eval_loss": 3.8864994049072266, | |
| "eval_runtime": 23.2913, | |
| "eval_samples_per_second": 30.011, | |
| "eval_steps_per_second": 15.027, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.027120687057405453, | |
| "grad_norm": 4.722931861877441, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.991, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.030134096730450505, | |
| "grad_norm": 3.504997730255127, | |
| "learning_rate": 0.0, | |
| "loss": 3.7988, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.030134096730450505, | |
| "eval_loss": 3.8751306533813477, | |
| "eval_runtime": 23.4525, | |
| "eval_samples_per_second": 29.805, | |
| "eval_steps_per_second": 14.924, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 447416773115904.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |