| { | |
| "best_metric": 0.1386825442314148, | |
| "best_model_checkpoint": "saves/Gemma-7B/lora/train_1/checkpoint-70", | |
| "epoch": 2.918918918918919, | |
| "eval_steps": 10, | |
| "global_step": 81, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.36036036036036034, | |
| "grad_norm": 39.81270980834961, | |
| "learning_rate": 2.888585953903336e-05, | |
| "loss": 8.8326, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.36036036036036034, | |
| "eval_loss": 2.50767183303833, | |
| "eval_runtime": 57.5911, | |
| "eval_samples_per_second": 25.421, | |
| "eval_steps_per_second": 3.178, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7207207207207207, | |
| "grad_norm": 4.2045698165893555, | |
| "learning_rate": 2.570894601836849e-05, | |
| "loss": 1.0933, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7207207207207207, | |
| "eval_loss": 0.2859745919704437, | |
| "eval_runtime": 57.6461, | |
| "eval_samples_per_second": 25.396, | |
| "eval_steps_per_second": 3.175, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "grad_norm": 1.2538220882415771, | |
| "learning_rate": 2.0941196490587352e-05, | |
| "loss": 0.1736, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0810810810810811, | |
| "eval_loss": 0.15085211396217346, | |
| "eval_runtime": 57.5905, | |
| "eval_samples_per_second": 25.421, | |
| "eval_steps_per_second": 3.178, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.4414414414414414, | |
| "grad_norm": 0.8226311802864075, | |
| "learning_rate": 1.5290869976577365e-05, | |
| "loss": 0.1398, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.4414414414414414, | |
| "eval_loss": 0.13882194459438324, | |
| "eval_runtime": 57.5631, | |
| "eval_samples_per_second": 25.433, | |
| "eval_steps_per_second": 3.179, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8018018018018018, | |
| "grad_norm": 0.37431085109710693, | |
| "learning_rate": 9.597334127929346e-06, | |
| "loss": 0.1378, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8018018018018018, | |
| "eval_loss": 0.140076145529747, | |
| "eval_runtime": 57.58, | |
| "eval_samples_per_second": 25.426, | |
| "eval_steps_per_second": 3.178, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.1621621621621623, | |
| "grad_norm": 0.8156893849372864, | |
| "learning_rate": 4.706375431968998e-06, | |
| "loss": 0.1393, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.1621621621621623, | |
| "eval_loss": 0.14055073261260986, | |
| "eval_runtime": 57.5678, | |
| "eval_samples_per_second": 25.431, | |
| "eval_steps_per_second": 3.179, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.5225225225225225, | |
| "grad_norm": 0.37961214780807495, | |
| "learning_rate": 1.3445558855078017e-06, | |
| "loss": 0.1354, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.5225225225225225, | |
| "eval_loss": 0.1386825442314148, | |
| "eval_runtime": 57.5753, | |
| "eval_samples_per_second": 25.428, | |
| "eval_steps_per_second": 3.178, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8828828828828827, | |
| "grad_norm": 0.4499067962169647, | |
| "learning_rate": 1.1280712436549379e-08, | |
| "loss": 0.135, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.8828828828828827, | |
| "eval_loss": 0.13870705664157867, | |
| "eval_runtime": 57.6227, | |
| "eval_samples_per_second": 25.407, | |
| "eval_steps_per_second": 3.176, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.918918918918919, | |
| "step": 81, | |
| "total_flos": 1.2063913869213696e+17, | |
| "train_loss": 1.3333390743276219, | |
| "train_runtime": 2755.6111, | |
| "train_samples_per_second": 7.732, | |
| "train_steps_per_second": 0.029 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 81, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2063913869213696e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |