| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11025358324145534, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002205071664829107, | |
| "eval_loss": 2.177356719970703, | |
| "eval_runtime": 9.5836, | |
| "eval_samples_per_second": 19.93, | |
| "eval_steps_per_second": 10.017, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011025358324145534, | |
| "grad_norm": 3.0545544624328613, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1943, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.022050716648291068, | |
| "grad_norm": 2.2579193115234375, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2168, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022050716648291068, | |
| "eval_loss": 1.7749028205871582, | |
| "eval_runtime": 9.6049, | |
| "eval_samples_per_second": 19.886, | |
| "eval_steps_per_second": 9.995, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03307607497243661, | |
| "grad_norm": 2.798457622528076, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7471, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.044101433296582136, | |
| "grad_norm": 2.5906262397766113, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5741, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.044101433296582136, | |
| "eval_loss": 1.4727933406829834, | |
| "eval_runtime": 9.6402, | |
| "eval_samples_per_second": 19.813, | |
| "eval_steps_per_second": 9.958, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05512679162072767, | |
| "grad_norm": 2.3336644172668457, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.4489, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06615214994487321, | |
| "grad_norm": 2.168654680252075, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4988, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06615214994487321, | |
| "eval_loss": 1.4284926652908325, | |
| "eval_runtime": 9.9918, | |
| "eval_samples_per_second": 19.116, | |
| "eval_steps_per_second": 9.608, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07717750826901874, | |
| "grad_norm": 2.2377634048461914, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3625, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08820286659316427, | |
| "grad_norm": 2.3646817207336426, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.401, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08820286659316427, | |
| "eval_loss": 1.4094713926315308, | |
| "eval_runtime": 9.8204, | |
| "eval_samples_per_second": 19.449, | |
| "eval_steps_per_second": 9.776, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09922822491730982, | |
| "grad_norm": 2.390453577041626, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5494, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11025358324145534, | |
| "grad_norm": 2.1996264457702637, | |
| "learning_rate": 0.0, | |
| "loss": 1.3396, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11025358324145534, | |
| "eval_loss": 1.405466914176941, | |
| "eval_runtime": 9.8045, | |
| "eval_samples_per_second": 19.481, | |
| "eval_steps_per_second": 9.791, | |
| "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": 2500486653542400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |