| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0008794219491880145, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.764784224523189e-05, | |
| "grad_norm": 5.634762287139893, | |
| "learning_rate": 1e-05, | |
| "loss": 3.0597, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.764784224523189e-05, | |
| "eval_loss": 3.2875728607177734, | |
| "eval_runtime": 948.466, | |
| "eval_samples_per_second": 26.25, | |
| "eval_steps_per_second": 13.125, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013529568449046378, | |
| "grad_norm": 5.37744140625, | |
| "learning_rate": 2e-05, | |
| "loss": 3.3157, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00020294352673569564, | |
| "grad_norm": 2.809889078140259, | |
| "learning_rate": 3e-05, | |
| "loss": 3.2284, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00027059136898092756, | |
| "grad_norm": 1.9245902299880981, | |
| "learning_rate": 4e-05, | |
| "loss": 2.5244, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00033823921122615945, | |
| "grad_norm": 1.7348881959915161, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2311, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004058870534713913, | |
| "grad_norm": 1.531990885734558, | |
| "learning_rate": 6e-05, | |
| "loss": 3.0822, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00047353489571662317, | |
| "grad_norm": 1.5458530187606812, | |
| "learning_rate": 7e-05, | |
| "loss": 3.1807, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005411827379618551, | |
| "grad_norm": 1.52450692653656, | |
| "learning_rate": 8e-05, | |
| "loss": 2.732, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.000608830580207087, | |
| "grad_norm": 2.0526621341705322, | |
| "learning_rate": 9e-05, | |
| "loss": 2.5615, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006764784224523189, | |
| "grad_norm": 1.7713125944137573, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4923, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007441262646975507, | |
| "grad_norm": 1.1165575981140137, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 2.8424, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008117741069427826, | |
| "grad_norm": 2.138780355453491, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 2.3238, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0008794219491880145, | |
| "grad_norm": 1.88950777053833, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 2.592, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0008794219491880145, | |
| "eval_loss": 1.9662768840789795, | |
| "eval_runtime": 872.1234, | |
| "eval_samples_per_second": 28.548, | |
| "eval_steps_per_second": 14.274, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3748962364293120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |