| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012776287210936502, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00025552574421873004, | |
| "eval_loss": 0.44080615043640137, | |
| "eval_runtime": 163.4805, | |
| "eval_samples_per_second": 10.081, | |
| "eval_steps_per_second": 5.04, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012776287210936501, | |
| "grad_norm": 0.6050224304199219, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3806, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025552574421873002, | |
| "grad_norm": 0.3790658712387085, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3812, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025552574421873002, | |
| "eval_loss": 0.36030489206314087, | |
| "eval_runtime": 168.9311, | |
| "eval_samples_per_second": 9.755, | |
| "eval_steps_per_second": 4.878, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0038328861632809506, | |
| "grad_norm": 0.6246739029884338, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.2917, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0051105148843746005, | |
| "grad_norm": 0.3205125331878662, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.2045, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0051105148843746005, | |
| "eval_loss": 0.18292254209518433, | |
| "eval_runtime": 213.9892, | |
| "eval_samples_per_second": 7.701, | |
| "eval_steps_per_second": 3.851, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006388143605468251, | |
| "grad_norm": 0.29717549681663513, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1541, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007665772326561901, | |
| "grad_norm": 0.2781718969345093, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1247, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007665772326561901, | |
| "eval_loss": 0.13439211249351501, | |
| "eval_runtime": 227.907, | |
| "eval_samples_per_second": 7.231, | |
| "eval_steps_per_second": 3.616, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008943401047655552, | |
| "grad_norm": 0.28511881828308105, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0939, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010221029768749201, | |
| "grad_norm": 0.2863682508468628, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.138, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010221029768749201, | |
| "eval_loss": 0.124103844165802, | |
| "eval_runtime": 228.0539, | |
| "eval_samples_per_second": 7.226, | |
| "eval_steps_per_second": 3.613, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011498658489842852, | |
| "grad_norm": 0.2913203537464142, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1075, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012776287210936502, | |
| "grad_norm": 0.26606062054634094, | |
| "learning_rate": 0.0, | |
| "loss": 0.1025, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012776287210936502, | |
| "eval_loss": 0.1226755753159523, | |
| "eval_runtime": 227.985, | |
| "eval_samples_per_second": 7.229, | |
| "eval_steps_per_second": 3.614, | |
| "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": 2237073293574144.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |