| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.008624035186063559, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00017248070372127117, |
| "eval_loss": 6.329273700714111, |
| "eval_runtime": 37.2306, |
| "eval_samples_per_second": 65.591, |
| "eval_steps_per_second": 32.796, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0008624035186063559, |
| "grad_norm": 2.544393539428711, |
| "learning_rate": 5e-05, |
| "loss": 6.2995, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0017248070372127117, |
| "grad_norm": 2.786011219024658, |
| "learning_rate": 0.0001, |
| "loss": 6.2716, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0017248070372127117, |
| "eval_loss": 6.270487308502197, |
| "eval_runtime": 38.5696, |
| "eval_samples_per_second": 63.314, |
| "eval_steps_per_second": 31.657, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.002587210555819068, |
| "grad_norm": 3.6353487968444824, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 6.0843, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0034496140744254234, |
| "grad_norm": 2.0951130390167236, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 5.8982, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0034496140744254234, |
| "eval_loss": 5.9787092208862305, |
| "eval_runtime": 37.6929, |
| "eval_samples_per_second": 64.787, |
| "eval_steps_per_second": 32.393, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0043120175930317795, |
| "grad_norm": 3.2061691284179688, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 6.0776, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.005174421111638136, |
| "grad_norm": 2.500523328781128, |
| "learning_rate": 5e-05, |
| "loss": 5.8464, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.005174421111638136, |
| "eval_loss": 5.717452049255371, |
| "eval_runtime": 39.253, |
| "eval_samples_per_second": 62.212, |
| "eval_steps_per_second": 31.106, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.006036824630244492, |
| "grad_norm": 1.5522089004516602, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 5.6319, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.006899228148850847, |
| "grad_norm": 1.5637425184249878, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 5.5491, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.006899228148850847, |
| "eval_loss": 5.575439929962158, |
| "eval_runtime": 37.6254, |
| "eval_samples_per_second": 64.903, |
| "eval_steps_per_second": 32.451, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.007761631667457203, |
| "grad_norm": 1.783243179321289, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 5.4637, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.008624035186063559, |
| "grad_norm": 2.0012452602386475, |
| "learning_rate": 0.0, |
| "loss": 5.6158, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.008624035186063559, |
| "eval_loss": 5.548293113708496, |
| "eval_runtime": 37.6341, |
| "eval_samples_per_second": 64.888, |
| "eval_steps_per_second": 32.444, |
| "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": 171463252377600.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
