| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.061977068484660676, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012395413696932136, | |
| "eval_loss": 3.160734176635742, | |
| "eval_runtime": 70.7744, | |
| "eval_samples_per_second": 4.804, | |
| "eval_steps_per_second": 2.402, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006197706848466067, | |
| "grad_norm": 1.6868420839309692, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0013, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012395413696932134, | |
| "grad_norm": 1.7511683702468872, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0908, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012395413696932134, | |
| "eval_loss": 2.564448356628418, | |
| "eval_runtime": 71.7863, | |
| "eval_samples_per_second": 4.736, | |
| "eval_steps_per_second": 2.368, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018593120545398203, | |
| "grad_norm": 1.5322659015655518, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2162, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02479082739386427, | |
| "grad_norm": 1.4782131910324097, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7327, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02479082739386427, | |
| "eval_loss": 1.4430201053619385, | |
| "eval_runtime": 71.9238, | |
| "eval_samples_per_second": 4.727, | |
| "eval_steps_per_second": 2.364, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.030988534242330338, | |
| "grad_norm": 1.605191707611084, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2809, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03718624109079641, | |
| "grad_norm": 1.7237857580184937, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2256, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03718624109079641, | |
| "eval_loss": 1.1801698207855225, | |
| "eval_runtime": 71.9099, | |
| "eval_samples_per_second": 4.728, | |
| "eval_steps_per_second": 2.364, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04338394793926247, | |
| "grad_norm": 1.2960554361343384, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0238, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04958165478772854, | |
| "grad_norm": 1.3113014698028564, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0754, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04958165478772854, | |
| "eval_loss": 1.103080153465271, | |
| "eval_runtime": 72.0279, | |
| "eval_samples_per_second": 4.72, | |
| "eval_steps_per_second": 2.36, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05577936163619461, | |
| "grad_norm": 1.3435271978378296, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9994, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.061977068484660676, | |
| "grad_norm": 1.486733317375183, | |
| "learning_rate": 0.0, | |
| "loss": 1.0947, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.061977068484660676, | |
| "eval_loss": 1.0898029804229736, | |
| "eval_runtime": 72.0292, | |
| "eval_samples_per_second": 4.72, | |
| "eval_steps_per_second": 2.36, | |
| "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": 1.6061930309419008e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |