| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0018196706396142299, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.6393412792284596e-05, | |
| "eval_loss": 0.4564758241176605, | |
| "eval_runtime": 1165.7146, | |
| "eval_samples_per_second": 9.925, | |
| "eval_steps_per_second": 4.963, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000181967063961423, | |
| "grad_norm": 0.4310053884983063, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4241, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000363934127922846, | |
| "grad_norm": 0.34612002968788147, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4417, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000363934127922846, | |
| "eval_loss": 0.3890089988708496, | |
| "eval_runtime": 1168.179, | |
| "eval_samples_per_second": 9.904, | |
| "eval_steps_per_second": 4.952, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005459011918842689, | |
| "grad_norm": 0.3692004084587097, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3391, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000727868255845692, | |
| "grad_norm": 0.4841485321521759, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3235, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000727868255845692, | |
| "eval_loss": 0.33874091506004333, | |
| "eval_runtime": 1166.762, | |
| "eval_samples_per_second": 9.916, | |
| "eval_steps_per_second": 4.958, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009098353198071149, | |
| "grad_norm": 0.41115713119506836, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2833, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010918023837685378, | |
| "grad_norm": 0.4929177463054657, | |
| "learning_rate": 5e-05, | |
| "loss": 0.329, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0010918023837685378, | |
| "eval_loss": 0.32229578495025635, | |
| "eval_runtime": 1169.8281, | |
| "eval_samples_per_second": 9.89, | |
| "eval_steps_per_second": 4.945, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0012737694477299609, | |
| "grad_norm": 0.341118723154068, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.223, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.001455736511691384, | |
| "grad_norm": 0.437232106924057, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3237, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001455736511691384, | |
| "eval_loss": 0.31940722465515137, | |
| "eval_runtime": 1166.033, | |
| "eval_samples_per_second": 9.923, | |
| "eval_steps_per_second": 4.961, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0016377035756528068, | |
| "grad_norm": 0.322145938873291, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2223, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0018196706396142299, | |
| "grad_norm": 0.36519697308540344, | |
| "learning_rate": 0.0, | |
| "loss": 0.2629, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0018196706396142299, | |
| "eval_loss": 0.3180951476097107, | |
| "eval_runtime": 1172.1167, | |
| "eval_samples_per_second": 9.871, | |
| "eval_steps_per_second": 4.936, | |
| "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": 1.479651398516736e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |