| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02321262766945218, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00046425255338904364, | |
| "eval_loss": 4.059295177459717, | |
| "eval_runtime": 20.2414, | |
| "eval_samples_per_second": 44.809, | |
| "eval_steps_per_second": 22.429, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002321262766945218, | |
| "grad_norm": 113.8918228149414, | |
| "learning_rate": 5e-05, | |
| "loss": 18.5564, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004642525533890436, | |
| "grad_norm": 107.09974670410156, | |
| "learning_rate": 0.0001, | |
| "loss": 16.0422, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004642525533890436, | |
| "eval_loss": 3.889435291290283, | |
| "eval_runtime": 18.1949, | |
| "eval_samples_per_second": 49.849, | |
| "eval_steps_per_second": 24.952, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006963788300835654, | |
| "grad_norm": 112.6549072265625, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 14.8815, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009285051067780872, | |
| "grad_norm": 109.76182556152344, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 13.0329, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009285051067780872, | |
| "eval_loss": 3.405557155609131, | |
| "eval_runtime": 18.2908, | |
| "eval_samples_per_second": 49.588, | |
| "eval_steps_per_second": 24.821, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01160631383472609, | |
| "grad_norm": 98.89693450927734, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 12.6359, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013927576601671309, | |
| "grad_norm": 95.26651000976562, | |
| "learning_rate": 5e-05, | |
| "loss": 12.3584, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013927576601671309, | |
| "eval_loss": 3.173269271850586, | |
| "eval_runtime": 18.1951, | |
| "eval_samples_per_second": 49.849, | |
| "eval_steps_per_second": 24.952, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016248839368616527, | |
| "grad_norm": 108.44436645507812, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 12.8901, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.018570102135561744, | |
| "grad_norm": 110.787841796875, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.8677, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018570102135561744, | |
| "eval_loss": 3.076159954071045, | |
| "eval_runtime": 18.4863, | |
| "eval_samples_per_second": 49.063, | |
| "eval_steps_per_second": 24.559, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020891364902506964, | |
| "grad_norm": 124.56420135498047, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 12.2453, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02321262766945218, | |
| "grad_norm": 124.69161224365234, | |
| "learning_rate": 0.0, | |
| "loss": 12.4255, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02321262766945218, | |
| "eval_loss": 3.0605356693267822, | |
| "eval_runtime": 18.4891, | |
| "eval_samples_per_second": 49.056, | |
| "eval_steps_per_second": 24.555, | |
| "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": 440836043046912.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |