| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005049187501577872, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.683062500525957e-05, | |
| "eval_loss": 3.985291004180908, | |
| "eval_runtime": 3226.9267, | |
| "eval_samples_per_second": 7.753, | |
| "eval_steps_per_second": 3.876, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.049187501577871e-05, | |
| "grad_norm": 4.857234954833984, | |
| "learning_rate": 6e-05, | |
| "loss": 3.8005, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010098375003155742, | |
| "grad_norm": 3.308483600616455, | |
| "learning_rate": 0.00012, | |
| "loss": 3.3817, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00013464500004207655, | |
| "eval_loss": 3.4002809524536133, | |
| "eval_runtime": 3248.2918, | |
| "eval_samples_per_second": 7.702, | |
| "eval_steps_per_second": 3.851, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00015147562504733614, | |
| "grad_norm": 3.129868745803833, | |
| "learning_rate": 0.00018, | |
| "loss": 2.803, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00020196750006311483, | |
| "grad_norm": 3.431424617767334, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.9995, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0002524593750788936, | |
| "grad_norm": 4.4516777992248535, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.5562, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002692900000841531, | |
| "eval_loss": 2.6974403858184814, | |
| "eval_runtime": 3245.9239, | |
| "eval_samples_per_second": 7.708, | |
| "eval_steps_per_second": 3.854, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0003029512500946723, | |
| "grad_norm": 4.282509803771973, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.5551, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00035344312511045097, | |
| "grad_norm": 3.7091686725616455, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.244, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00040393500012622966, | |
| "grad_norm": 4.029706954956055, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.5597, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00040393500012622966, | |
| "eval_loss": 2.5306174755096436, | |
| "eval_runtime": 3247.4102, | |
| "eval_samples_per_second": 7.704, | |
| "eval_steps_per_second": 3.852, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0004544268751420084, | |
| "grad_norm": 4.2530412673950195, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.5887, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0005049187501577872, | |
| "grad_norm": 3.34025502204895, | |
| "learning_rate": 0.0, | |
| "loss": 2.0085, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1313781074296832e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |