| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06105006105006105, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001221001221001221, | |
| "eval_loss": 11.934243202209473, | |
| "eval_runtime": 5.9922, | |
| "eval_samples_per_second": 57.575, | |
| "eval_steps_per_second": 28.871, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006105006105006105, | |
| "grad_norm": 0.010467967949807644, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9338, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01221001221001221, | |
| "grad_norm": 0.012429132126271725, | |
| "learning_rate": 0.0001, | |
| "loss": 11.934, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01221001221001221, | |
| "eval_loss": 11.934219360351562, | |
| "eval_runtime": 6.086, | |
| "eval_samples_per_second": 56.688, | |
| "eval_steps_per_second": 28.426, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018315018315018316, | |
| "grad_norm": 0.010163530707359314, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9346, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02442002442002442, | |
| "grad_norm": 0.010413922369480133, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9359, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02442002442002442, | |
| "eval_loss": 11.934165954589844, | |
| "eval_runtime": 5.9793, | |
| "eval_samples_per_second": 57.699, | |
| "eval_steps_per_second": 28.933, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.030525030525030524, | |
| "grad_norm": 0.010765035636723042, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.933, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03663003663003663, | |
| "grad_norm": 0.017171213403344154, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9326, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03663003663003663, | |
| "eval_loss": 11.934120178222656, | |
| "eval_runtime": 6.1064, | |
| "eval_samples_per_second": 56.498, | |
| "eval_steps_per_second": 28.331, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.042735042735042736, | |
| "grad_norm": 0.009910144843161106, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9316, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04884004884004884, | |
| "grad_norm": 0.014119105413556099, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9326, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04884004884004884, | |
| "eval_loss": 11.934100151062012, | |
| "eval_runtime": 6.0973, | |
| "eval_samples_per_second": 56.582, | |
| "eval_steps_per_second": 28.373, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.054945054945054944, | |
| "grad_norm": 0.00930514745414257, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9322, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06105006105006105, | |
| "grad_norm": 0.010311778634786606, | |
| "learning_rate": 0.0, | |
| "loss": 11.9343, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06105006105006105, | |
| "eval_loss": 11.934097290039062, | |
| "eval_runtime": 6.0342, | |
| "eval_samples_per_second": 57.174, | |
| "eval_steps_per_second": 28.67, | |
| "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": 5908070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |