| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008441668073611346, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016883336147222692, | |
| "eval_loss": 2.0252552032470703, | |
| "eval_runtime": 147.2209, | |
| "eval_samples_per_second": 67.762, | |
| "eval_steps_per_second": 8.47, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008441668073611346, | |
| "grad_norm": 26.66962242126465, | |
| "learning_rate": 5e-05, | |
| "loss": 8.2084, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016883336147222692, | |
| "grad_norm": 33.646820068359375, | |
| "learning_rate": 0.0001, | |
| "loss": 7.1279, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016883336147222692, | |
| "eval_loss": 1.5629302263259888, | |
| "eval_runtime": 109.6442, | |
| "eval_samples_per_second": 90.985, | |
| "eval_steps_per_second": 11.373, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002532500422083404, | |
| "grad_norm": 16.691024780273438, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.6021, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033766672294445383, | |
| "grad_norm": 25.607318878173828, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.175, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0033766672294445383, | |
| "eval_loss": 1.1118829250335693, | |
| "eval_runtime": 109.7936, | |
| "eval_samples_per_second": 90.861, | |
| "eval_steps_per_second": 11.358, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004220834036805673, | |
| "grad_norm": 25.512271881103516, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.2593, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005065000844166808, | |
| "grad_norm": 18.301593780517578, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7172, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005065000844166808, | |
| "eval_loss": 0.9802479147911072, | |
| "eval_runtime": 110.0082, | |
| "eval_samples_per_second": 90.684, | |
| "eval_steps_per_second": 11.336, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005909167651527942, | |
| "grad_norm": 30.921207427978516, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.4898, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006753334458889077, | |
| "grad_norm": 18.379047393798828, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.8394, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006753334458889077, | |
| "eval_loss": 0.9370124936103821, | |
| "eval_runtime": 110.0748, | |
| "eval_samples_per_second": 90.629, | |
| "eval_steps_per_second": 11.329, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007597501266250211, | |
| "grad_norm": 25.660686492919922, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.5916, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008441668073611346, | |
| "grad_norm": 29.074373245239258, | |
| "learning_rate": 0.0, | |
| "loss": 3.7459, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008441668073611346, | |
| "eval_loss": 0.9260633587837219, | |
| "eval_runtime": 110.0826, | |
| "eval_samples_per_second": 90.623, | |
| "eval_steps_per_second": 11.328, | |
| "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": 6.625091824438477e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |