| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020191822311963654, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004038364462392731, | |
| "eval_loss": 2.2638325691223145, | |
| "eval_runtime": 72.2429, | |
| "eval_samples_per_second": 14.437, | |
| "eval_steps_per_second": 7.226, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020191822311963654, | |
| "grad_norm": 1.711580753326416, | |
| "learning_rate": 5e-05, | |
| "loss": 8.8889, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004038364462392731, | |
| "grad_norm": 3.8859548568725586, | |
| "learning_rate": 0.0001, | |
| "loss": 8.6508, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004038364462392731, | |
| "eval_loss": 2.084975481033325, | |
| "eval_runtime": 72.1737, | |
| "eval_samples_per_second": 14.451, | |
| "eval_steps_per_second": 7.233, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006057546693589096, | |
| "grad_norm": 2.641202688217163, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 7.3139, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008076728924785462, | |
| "grad_norm": 3.002156972885132, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.6485, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008076728924785462, | |
| "eval_loss": 1.2097488641738892, | |
| "eval_runtime": 72.1762, | |
| "eval_samples_per_second": 14.451, | |
| "eval_steps_per_second": 7.232, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010095911155981827, | |
| "grad_norm": 2.1998674869537354, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.8394, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012115093387178193, | |
| "grad_norm": 2.629648208618164, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0821, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012115093387178193, | |
| "eval_loss": 0.9872159957885742, | |
| "eval_runtime": 72.8771, | |
| "eval_samples_per_second": 14.312, | |
| "eval_steps_per_second": 7.163, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014134275618374558, | |
| "grad_norm": 2.2382519245147705, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.0689, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.016153457849570924, | |
| "grad_norm": 2.6332736015319824, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.6059, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.016153457849570924, | |
| "eval_loss": 0.9159337282180786, | |
| "eval_runtime": 72.2562, | |
| "eval_samples_per_second": 14.435, | |
| "eval_steps_per_second": 7.224, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01817264008076729, | |
| "grad_norm": 1.8842055797576904, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.7696, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.020191822311963654, | |
| "grad_norm": 1.6226767301559448, | |
| "learning_rate": 0.0, | |
| "loss": 3.3385, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.020191822311963654, | |
| "eval_loss": 0.9051779508590698, | |
| "eval_runtime": 72.2214, | |
| "eval_samples_per_second": 14.442, | |
| "eval_steps_per_second": 7.228, | |
| "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": 8143746210201600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |