| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006579813133307014, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001315962626661403, | |
| "eval_loss": 3.577655076980591, | |
| "eval_runtime": 226.4498, | |
| "eval_samples_per_second": 14.131, | |
| "eval_steps_per_second": 7.066, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006579813133307014, | |
| "grad_norm": 2.4131088256835938, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3284, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013159626266614028, | |
| "grad_norm": 3.137674570083618, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3523, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013159626266614028, | |
| "eval_loss": 3.1352221965789795, | |
| "eval_runtime": 232.2148, | |
| "eval_samples_per_second": 13.78, | |
| "eval_steps_per_second": 6.89, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0019739439399921043, | |
| "grad_norm": 3.401357889175415, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.0719, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026319252533228057, | |
| "grad_norm": 2.3058485984802246, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.3197, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0026319252533228057, | |
| "eval_loss": 2.31852650642395, | |
| "eval_runtime": 232.0096, | |
| "eval_samples_per_second": 13.793, | |
| "eval_steps_per_second": 6.896, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003289906566653507, | |
| "grad_norm": 2.3834540843963623, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.2093, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0039478878799842085, | |
| "grad_norm": 3.427426815032959, | |
| "learning_rate": 5e-05, | |
| "loss": 1.871, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0039478878799842085, | |
| "eval_loss": 2.182154893875122, | |
| "eval_runtime": 233.5298, | |
| "eval_samples_per_second": 13.703, | |
| "eval_steps_per_second": 6.851, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0046058691933149095, | |
| "grad_norm": 2.294675827026367, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.1684, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005263850506645611, | |
| "grad_norm": 2.8732268810272217, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7683, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005263850506645611, | |
| "eval_loss": 2.1445751190185547, | |
| "eval_runtime": 232.7196, | |
| "eval_samples_per_second": 13.75, | |
| "eval_steps_per_second": 6.875, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005921831819976312, | |
| "grad_norm": 3.0339841842651367, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1268, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006579813133307014, | |
| "grad_norm": 3.6315295696258545, | |
| "learning_rate": 0.0, | |
| "loss": 2.0337, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006579813133307014, | |
| "eval_loss": 2.1367852687835693, | |
| "eval_runtime": 232.2652, | |
| "eval_samples_per_second": 13.777, | |
| "eval_steps_per_second": 6.889, | |
| "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": 5931038964449280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |