| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00474293302978562, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.485866059571239e-05, | |
| "eval_loss": 2.1410107612609863, | |
| "eval_runtime": 553.002, | |
| "eval_samples_per_second": 8.027, | |
| "eval_steps_per_second": 4.014, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004742933029785619, | |
| "grad_norm": 0.34695127606391907, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2003, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009485866059571238, | |
| "grad_norm": 0.4375736117362976, | |
| "learning_rate": 0.0001, | |
| "loss": 2.0296, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009485866059571238, | |
| "eval_loss": 2.1128005981445312, | |
| "eval_runtime": 555.0801, | |
| "eval_samples_per_second": 7.997, | |
| "eval_steps_per_second": 3.999, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0014228799089356858, | |
| "grad_norm": 0.6132789850234985, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0717, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0018971732119142477, | |
| "grad_norm": 0.5792968273162842, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.0385, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018971732119142477, | |
| "eval_loss": 2.051406145095825, | |
| "eval_runtime": 556.5739, | |
| "eval_samples_per_second": 7.976, | |
| "eval_steps_per_second": 3.989, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00237146651489281, | |
| "grad_norm": 0.5881865620613098, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0528, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0028457598178713715, | |
| "grad_norm": 0.6386412382125854, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9569, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0028457598178713715, | |
| "eval_loss": 2.0335803031921387, | |
| "eval_runtime": 558.5873, | |
| "eval_samples_per_second": 7.947, | |
| "eval_steps_per_second": 3.974, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0033200531208499337, | |
| "grad_norm": 0.595703125, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.0149, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0037943464238284954, | |
| "grad_norm": 0.618114709854126, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.0647, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0037943464238284954, | |
| "eval_loss": 2.0265140533447266, | |
| "eval_runtime": 558.9904, | |
| "eval_samples_per_second": 7.941, | |
| "eval_steps_per_second": 3.971, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0042686397268070575, | |
| "grad_norm": 0.7434813380241394, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.0384, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00474293302978562, | |
| "grad_norm": 0.7082255482673645, | |
| "learning_rate": 0.0, | |
| "loss": 2.0398, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00474293302978562, | |
| "eval_loss": 2.0250840187072754, | |
| "eval_runtime": 553.8165, | |
| "eval_samples_per_second": 8.015, | |
| "eval_steps_per_second": 4.009, | |
| "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": 1.821820784423731e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |