| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04106143817687215, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020530719088436073, | |
| "eval_loss": 1.3546793460845947, | |
| "eval_runtime": 87.8517, | |
| "eval_samples_per_second": 23.346, | |
| "eval_steps_per_second": 11.679, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002053071908843607, | |
| "grad_norm": 1.1122969388961792, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1488, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004106143817687214, | |
| "grad_norm": 0.7866343259811401, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.5164, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006159215726530822, | |
| "grad_norm": 0.9349194765090942, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.3543, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008212287635374429, | |
| "grad_norm": 0.6453638076782227, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.3246, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010265359544218037, | |
| "grad_norm": 0.4768398702144623, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.3237, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010265359544218037, | |
| "eval_loss": 0.3221627175807953, | |
| "eval_runtime": 86.3643, | |
| "eval_samples_per_second": 23.748, | |
| "eval_steps_per_second": 11.88, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012318431453061643, | |
| "grad_norm": 0.49055156111717224, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 0.3168, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.014371503361905251, | |
| "grad_norm": 0.5417104363441467, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.3073, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.016424575270748858, | |
| "grad_norm": 0.681601345539093, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.3046, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.018477647179592466, | |
| "grad_norm": 0.581589937210083, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 0.3075, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.020530719088436074, | |
| "grad_norm": 0.5185021758079529, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.295, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.020530719088436074, | |
| "eval_loss": 0.2953387498855591, | |
| "eval_runtime": 86.335, | |
| "eval_samples_per_second": 23.756, | |
| "eval_steps_per_second": 11.884, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02258379099727968, | |
| "grad_norm": 0.6514111161231995, | |
| "learning_rate": 9.174206545276677e-05, | |
| "loss": 0.3086, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.024636862906123286, | |
| "grad_norm": 0.5423412322998047, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 0.2823, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.026689934814966895, | |
| "grad_norm": 0.43237441778182983, | |
| "learning_rate": 5.983045753470308e-05, | |
| "loss": 0.2855, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.028743006723810503, | |
| "grad_norm": 0.508624792098999, | |
| "learning_rate": 4.530518418775733e-05, | |
| "loss": 0.2724, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.030796078632654107, | |
| "grad_norm": 0.3984101712703705, | |
| "learning_rate": 3.227184283742591e-05, | |
| "loss": 0.2764, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.030796078632654107, | |
| "eval_loss": 0.28801968693733215, | |
| "eval_runtime": 86.3387, | |
| "eval_samples_per_second": 23.755, | |
| "eval_steps_per_second": 11.883, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.032849150541497715, | |
| "grad_norm": 0.4992406666278839, | |
| "learning_rate": 2.1085949060360654e-05, | |
| "loss": 0.2794, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03490222245034132, | |
| "grad_norm": 0.438711017370224, | |
| "learning_rate": 1.2052624879351104e-05, | |
| "loss": 0.2507, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03695529435918493, | |
| "grad_norm": 0.4992602467536926, | |
| "learning_rate": 5.418275829936537e-06, | |
| "loss": 0.2777, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03900836626802854, | |
| "grad_norm": 0.4569292366504669, | |
| "learning_rate": 1.3638696597277679e-06, | |
| "loss": 0.2744, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.04106143817687215, | |
| "grad_norm": 0.49360865354537964, | |
| "learning_rate": 0.0, | |
| "loss": 0.297, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04106143817687215, | |
| "eval_loss": 0.28519004583358765, | |
| "eval_runtime": 86.3294, | |
| "eval_samples_per_second": 23.758, | |
| "eval_steps_per_second": 11.885, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.51479053795328e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |