| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011779950524207798, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00023559901048415596, | |
| "eval_loss": 10.376893043518066, | |
| "eval_runtime": 10.972, | |
| "eval_samples_per_second": 162.96, | |
| "eval_steps_per_second": 81.48, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011779950524207798, | |
| "grad_norm": 0.3874177634716034, | |
| "learning_rate": 5e-05, | |
| "loss": 41.5082, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0023559901048415596, | |
| "grad_norm": 0.3574215769767761, | |
| "learning_rate": 0.0001, | |
| "loss": 41.4991, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0023559901048415596, | |
| "eval_loss": 10.376096725463867, | |
| "eval_runtime": 11.0366, | |
| "eval_samples_per_second": 162.007, | |
| "eval_steps_per_second": 81.003, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0035339851572623393, | |
| "grad_norm": 0.427160382270813, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 41.4984, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004711980209683119, | |
| "grad_norm": 0.43340450525283813, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 41.5071, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004711980209683119, | |
| "eval_loss": 10.37428092956543, | |
| "eval_runtime": 11.1192, | |
| "eval_samples_per_second": 160.803, | |
| "eval_steps_per_second": 80.401, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005889975262103899, | |
| "grad_norm": 0.39236587285995483, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 41.493, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007067970314524679, | |
| "grad_norm": 0.47753089666366577, | |
| "learning_rate": 5e-05, | |
| "loss": 41.493, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007067970314524679, | |
| "eval_loss": 10.372749328613281, | |
| "eval_runtime": 11.1057, | |
| "eval_samples_per_second": 160.999, | |
| "eval_steps_per_second": 80.499, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00824596536694546, | |
| "grad_norm": 0.4785812497138977, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 41.4795, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009423960419366238, | |
| "grad_norm": 0.4244927763938904, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 41.5, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.009423960419366238, | |
| "eval_loss": 10.371926307678223, | |
| "eval_runtime": 11.2431, | |
| "eval_samples_per_second": 159.031, | |
| "eval_steps_per_second": 79.515, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010601955471787019, | |
| "grad_norm": 0.5031403303146362, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 41.4935, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011779950524207798, | |
| "grad_norm": 0.4761594533920288, | |
| "learning_rate": 0.0, | |
| "loss": 41.4824, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.011779950524207798, | |
| "eval_loss": 10.371774673461914, | |
| "eval_runtime": 11.0171, | |
| "eval_samples_per_second": 162.293, | |
| "eval_steps_per_second": 81.147, | |
| "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": 2566481510400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |