| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0020140175622331427, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.028035124466285e-05, | |
| "eval_loss": 1.3375216722488403, | |
| "eval_runtime": 835.7879, | |
| "eval_samples_per_second": 12.508, | |
| "eval_steps_per_second": 6.254, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020140175622331428, | |
| "grad_norm": 2.134361982345581, | |
| "learning_rate": 5e-05, | |
| "loss": 1.218, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00040280351244662856, | |
| "grad_norm": 2.4398152828216553, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1661, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00040280351244662856, | |
| "eval_loss": 0.8356062769889832, | |
| "eval_runtime": 835.3909, | |
| "eval_samples_per_second": 12.514, | |
| "eval_steps_per_second": 6.257, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006042052686699428, | |
| "grad_norm": 2.973989486694336, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6552, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008056070248932571, | |
| "grad_norm": 2.6805059909820557, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3329, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008056070248932571, | |
| "eval_loss": 0.26544415950775146, | |
| "eval_runtime": 839.614, | |
| "eval_samples_per_second": 12.451, | |
| "eval_steps_per_second": 6.225, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010070087811165714, | |
| "grad_norm": 2.0367231369018555, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2225, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0012084105373398855, | |
| "grad_norm": 2.0526347160339355, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1694, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0012084105373398855, | |
| "eval_loss": 0.14396847784519196, | |
| "eval_runtime": 839.3229, | |
| "eval_samples_per_second": 12.455, | |
| "eval_steps_per_second": 6.228, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0014098122935631999, | |
| "grad_norm": 2.1771583557128906, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1454, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0016112140497865142, | |
| "grad_norm": 2.3186516761779785, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1262, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0016112140497865142, | |
| "eval_loss": 0.11483553051948547, | |
| "eval_runtime": 841.3258, | |
| "eval_samples_per_second": 12.426, | |
| "eval_steps_per_second": 6.213, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0018126158060098284, | |
| "grad_norm": 1.910662293434143, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1299, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0020140175622331427, | |
| "grad_norm": 1.3861061334609985, | |
| "learning_rate": 0.0, | |
| "loss": 0.0962, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0020140175622331427, | |
| "eval_loss": 0.10776723176240921, | |
| "eval_runtime": 839.7271, | |
| "eval_samples_per_second": 12.449, | |
| "eval_steps_per_second": 6.225, | |
| "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": 9555457081344000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |