| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002931304870363042, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.8626097407260844e-05, | |
| "eval_loss": 0.7561618089675903, | |
| "eval_runtime": 547.616, | |
| "eval_samples_per_second": 13.115, | |
| "eval_steps_per_second": 6.558, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002931304870363042, | |
| "grad_norm": 0.796758770942688, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7901, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005862609740726084, | |
| "grad_norm": 1.1202898025512695, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7311, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005862609740726084, | |
| "eval_loss": 0.6243858933448792, | |
| "eval_runtime": 557.4416, | |
| "eval_samples_per_second": 12.884, | |
| "eval_steps_per_second": 6.442, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008793914611089126, | |
| "grad_norm": 0.3528475761413574, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5036, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011725219481452168, | |
| "grad_norm": 0.40145859122276306, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.516, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011725219481452168, | |
| "eval_loss": 0.4801919460296631, | |
| "eval_runtime": 557.7337, | |
| "eval_samples_per_second": 12.877, | |
| "eval_steps_per_second": 6.439, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001465652435181521, | |
| "grad_norm": 0.44575509428977966, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4756, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0017587829222178253, | |
| "grad_norm": 0.5272068381309509, | |
| "learning_rate": 5e-05, | |
| "loss": 0.46, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0017587829222178253, | |
| "eval_loss": 0.4582103490829468, | |
| "eval_runtime": 558.4346, | |
| "eval_samples_per_second": 12.861, | |
| "eval_steps_per_second": 6.43, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0020519134092541295, | |
| "grad_norm": 0.32150745391845703, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.431, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0023450438962904336, | |
| "grad_norm": 0.38870739936828613, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4092, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0023450438962904336, | |
| "eval_loss": 0.4501087963581085, | |
| "eval_runtime": 557.0, | |
| "eval_samples_per_second": 12.894, | |
| "eval_steps_per_second": 6.447, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002638174383326738, | |
| "grad_norm": 0.44614657759666443, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4634, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002931304870363042, | |
| "grad_norm": 0.36046040058135986, | |
| "learning_rate": 0.0, | |
| "loss": 0.4351, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002931304870363042, | |
| "eval_loss": 0.4485422670841217, | |
| "eval_runtime": 557.2954, | |
| "eval_samples_per_second": 12.887, | |
| "eval_steps_per_second": 6.444, | |
| "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": 8143746210201600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |