| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.030120481927710843, | |
| "eval_steps": 2, | |
| "global_step": 15, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002008032128514056, | |
| "grad_norm": 0.6553430557250977, | |
| "learning_rate": 2e-05, | |
| "loss": 6.1161, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002008032128514056, | |
| "eval_loss": 1.5243630409240723, | |
| "eval_runtime": 23.5287, | |
| "eval_samples_per_second": 8.925, | |
| "eval_steps_per_second": 4.463, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004016064257028112, | |
| "grad_norm": 1.010875940322876, | |
| "learning_rate": 4e-05, | |
| "loss": 6.2307, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004016064257028112, | |
| "eval_loss": 1.5242719650268555, | |
| "eval_runtime": 23.9427, | |
| "eval_samples_per_second": 8.771, | |
| "eval_steps_per_second": 4.385, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006024096385542169, | |
| "grad_norm": 0.6301004886627197, | |
| "learning_rate": 6e-05, | |
| "loss": 6.3617, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008032128514056224, | |
| "grad_norm": 0.7382184267044067, | |
| "learning_rate": 8e-05, | |
| "loss": 6.217, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008032128514056224, | |
| "eval_loss": 1.5222368240356445, | |
| "eval_runtime": 23.9718, | |
| "eval_samples_per_second": 8.76, | |
| "eval_steps_per_second": 4.38, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010040160642570281, | |
| "grad_norm": 0.6771762371063232, | |
| "learning_rate": 0.0001, | |
| "loss": 5.6022, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012048192771084338, | |
| "grad_norm": 1.1300783157348633, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 6.2136, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012048192771084338, | |
| "eval_loss": 1.5139317512512207, | |
| "eval_runtime": 24.4198, | |
| "eval_samples_per_second": 8.6, | |
| "eval_steps_per_second": 4.3, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014056224899598393, | |
| "grad_norm": 0.7629399299621582, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 5.591, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01606425702811245, | |
| "grad_norm": 0.991378664970398, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 5.6169, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01606425702811245, | |
| "eval_loss": 1.4971964359283447, | |
| "eval_runtime": 24.1606, | |
| "eval_samples_per_second": 8.692, | |
| "eval_steps_per_second": 4.346, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018072289156626505, | |
| "grad_norm": 1.3900601863861084, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 5.0918, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020080321285140562, | |
| "grad_norm": 1.6595548391342163, | |
| "learning_rate": 5e-05, | |
| "loss": 5.4715, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020080321285140562, | |
| "eval_loss": 1.4780693054199219, | |
| "eval_runtime": 24.0817, | |
| "eval_samples_per_second": 8.72, | |
| "eval_steps_per_second": 4.36, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02208835341365462, | |
| "grad_norm": 1.0076066255569458, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 5.7772, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.024096385542168676, | |
| "grad_norm": 1.1053738594055176, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 5.7395, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.024096385542168676, | |
| "eval_loss": 1.465615153312683, | |
| "eval_runtime": 24.3564, | |
| "eval_samples_per_second": 8.622, | |
| "eval_steps_per_second": 4.311, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02610441767068273, | |
| "grad_norm": 1.1769044399261475, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 5.7144, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.028112449799196786, | |
| "grad_norm": 1.0415147542953491, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 5.9251, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.028112449799196786, | |
| "eval_loss": 1.4606515169143677, | |
| "eval_runtime": 24.087, | |
| "eval_samples_per_second": 8.718, | |
| "eval_steps_per_second": 4.359, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.030120481927710843, | |
| "grad_norm": 1.0108901262283325, | |
| "learning_rate": 0.0, | |
| "loss": 6.6035, | |
| "step": 15 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5130560112427008.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |