| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.022997316979685704, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007665772326561902, | |
| "eval_loss": 1.4402562379837036, | |
| "eval_runtime": 111.3354, | |
| "eval_samples_per_second": 4.94, | |
| "eval_steps_per_second": 2.47, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022997316979685703, | |
| "grad_norm": 2.2092761993408203, | |
| "learning_rate": 6e-05, | |
| "loss": 5.8138, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0045994633959371405, | |
| "grad_norm": 1.861556887626648, | |
| "learning_rate": 0.00012, | |
| "loss": 5.6808, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006132617861249521, | |
| "eval_loss": 1.2501766681671143, | |
| "eval_runtime": 112.2324, | |
| "eval_samples_per_second": 4.901, | |
| "eval_steps_per_second": 2.45, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006899195093905711, | |
| "grad_norm": 2.0317749977111816, | |
| "learning_rate": 0.00018, | |
| "loss": 5.2817, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009198926791874281, | |
| "grad_norm": 2.100029706954956, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 4.5409, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011498658489842852, | |
| "grad_norm": 1.713498830795288, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 4.2998, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012265235722499043, | |
| "eval_loss": 0.9625716805458069, | |
| "eval_runtime": 111.8928, | |
| "eval_samples_per_second": 4.915, | |
| "eval_steps_per_second": 2.458, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013798390187811422, | |
| "grad_norm": 1.6698487997055054, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 3.8355, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01609812188577999, | |
| "grad_norm": 1.566597819328308, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 3.709, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018397853583748562, | |
| "grad_norm": 1.4933898448944092, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 3.6925, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.018397853583748562, | |
| "eval_loss": 0.8878971934318542, | |
| "eval_runtime": 111.8602, | |
| "eval_samples_per_second": 4.917, | |
| "eval_steps_per_second": 2.458, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020697585281717133, | |
| "grad_norm": 1.413949966430664, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 3.4661, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.022997316979685704, | |
| "grad_norm": 1.453066110610962, | |
| "learning_rate": 0.0, | |
| "loss": 3.5221, | |
| "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": 5526274525102080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |