| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0019666843668259683, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.933368733651936e-05, | |
| "eval_loss": 11.096795082092285, | |
| "eval_runtime": 46.8316, | |
| "eval_samples_per_second": 228.585, | |
| "eval_steps_per_second": 114.303, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019666843668259682, | |
| "grad_norm": 1.5377999544143677, | |
| "learning_rate": 5e-05, | |
| "loss": 44.3816, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00039333687336519363, | |
| "grad_norm": 1.4307451248168945, | |
| "learning_rate": 0.0001, | |
| "loss": 44.3909, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00039333687336519363, | |
| "eval_loss": 11.09162712097168, | |
| "eval_runtime": 45.6691, | |
| "eval_samples_per_second": 234.404, | |
| "eval_steps_per_second": 117.213, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005900053100477904, | |
| "grad_norm": 1.1491507291793823, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 44.3578, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007866737467303873, | |
| "grad_norm": 1.6496262550354004, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 44.3452, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0007866737467303873, | |
| "eval_loss": 11.082364082336426, | |
| "eval_runtime": 46.2125, | |
| "eval_samples_per_second": 231.647, | |
| "eval_steps_per_second": 115.835, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009833421834129841, | |
| "grad_norm": 1.3222088813781738, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 44.3251, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0011800106200955808, | |
| "grad_norm": 1.2229790687561035, | |
| "learning_rate": 5e-05, | |
| "loss": 44.3031, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0011800106200955808, | |
| "eval_loss": 11.074202537536621, | |
| "eval_runtime": 46.147, | |
| "eval_samples_per_second": 231.976, | |
| "eval_steps_per_second": 115.999, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0013766790567781777, | |
| "grad_norm": 1.6104438304901123, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 44.2844, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0015733474934607745, | |
| "grad_norm": 1.5601561069488525, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 44.2775, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0015733474934607745, | |
| "eval_loss": 11.069042205810547, | |
| "eval_runtime": 46.0948, | |
| "eval_samples_per_second": 232.239, | |
| "eval_steps_per_second": 116.13, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0017700159301433714, | |
| "grad_norm": 1.4664158821105957, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 44.2782, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0019666843668259683, | |
| "grad_norm": 1.510535717010498, | |
| "learning_rate": 0.0, | |
| "loss": 44.2712, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0019666843668259683, | |
| "eval_loss": 11.06863021850586, | |
| "eval_runtime": 46.0285, | |
| "eval_samples_per_second": 232.573, | |
| "eval_steps_per_second": 116.297, | |
| "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": 37729075200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |