| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03590664272890485, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003590664272890485, | |
| "grad_norm": 2.5617780685424805, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0418, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003590664272890485, | |
| "eval_loss": 3.0280966758728027, | |
| "eval_runtime": 4.0554, | |
| "eval_samples_per_second": 29.097, | |
| "eval_steps_per_second": 14.549, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00718132854578097, | |
| "grad_norm": 2.5941600799560547, | |
| "learning_rate": 4e-05, | |
| "loss": 3.1493, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010771992818671455, | |
| "grad_norm": 2.9957425594329834, | |
| "learning_rate": 6e-05, | |
| "loss": 2.7366, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010771992818671455, | |
| "eval_loss": 2.9922399520874023, | |
| "eval_runtime": 3.529, | |
| "eval_samples_per_second": 33.438, | |
| "eval_steps_per_second": 16.719, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01436265709156194, | |
| "grad_norm": 2.848189353942871, | |
| "learning_rate": 8e-05, | |
| "loss": 3.113, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.017953321364452424, | |
| "grad_norm": 3.064201593399048, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8894, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02154398563734291, | |
| "grad_norm": 3.4115347862243652, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4855, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02154398563734291, | |
| "eval_loss": 2.3920581340789795, | |
| "eval_runtime": 3.4956, | |
| "eval_samples_per_second": 33.757, | |
| "eval_steps_per_second": 16.878, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025134649910233394, | |
| "grad_norm": 3.0992071628570557, | |
| "learning_rate": 0.00014, | |
| "loss": 2.3225, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02872531418312388, | |
| "grad_norm": 2.6027300357818604, | |
| "learning_rate": 0.00016, | |
| "loss": 1.8089, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03231597845601436, | |
| "grad_norm": 2.378600597381592, | |
| "learning_rate": 0.00018, | |
| "loss": 1.5632, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03231597845601436, | |
| "eval_loss": 1.126179575920105, | |
| "eval_runtime": 3.5231, | |
| "eval_samples_per_second": 33.493, | |
| "eval_steps_per_second": 16.747, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03590664272890485, | |
| "grad_norm": 2.6615164279937744, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9871, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1647822923366400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |