| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003770810158562567, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.541620317125135e-05, | |
| "eval_loss": 2.0435900688171387, | |
| "eval_runtime": 665.4247, | |
| "eval_samples_per_second": 8.392, | |
| "eval_steps_per_second": 4.196, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003770810158562567, | |
| "grad_norm": 2.116191864013672, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0936, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007541620317125134, | |
| "grad_norm": 1.9126191139221191, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8052, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007541620317125134, | |
| "eval_loss": 1.2857778072357178, | |
| "eval_runtime": 669.1514, | |
| "eval_samples_per_second": 8.345, | |
| "eval_steps_per_second": 4.172, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011312430475687702, | |
| "grad_norm": 1.9551734924316406, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9694, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015083240634250269, | |
| "grad_norm": 1.7354230880737305, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015083240634250269, | |
| "eval_loss": 0.6742600798606873, | |
| "eval_runtime": 670.7305, | |
| "eval_samples_per_second": 8.325, | |
| "eval_steps_per_second": 4.163, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018854050792812835, | |
| "grad_norm": 1.9610943794250488, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6783, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022624860951375404, | |
| "grad_norm": 1.485725998878479, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5881, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022624860951375404, | |
| "eval_loss": 0.5489432215690613, | |
| "eval_runtime": 667.7804, | |
| "eval_samples_per_second": 8.362, | |
| "eval_steps_per_second": 4.181, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002639567110993797, | |
| "grad_norm": 1.5018064975738525, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.569, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0030166481268500537, | |
| "grad_norm": 1.476067066192627, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5314, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0030166481268500537, | |
| "eval_loss": 0.5157779455184937, | |
| "eval_runtime": 664.516, | |
| "eval_samples_per_second": 8.403, | |
| "eval_steps_per_second": 4.202, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0033937291427063106, | |
| "grad_norm": 1.6906317472457886, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4455, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003770810158562567, | |
| "grad_norm": 1.3468632698059082, | |
| "learning_rate": 0.0, | |
| "loss": 0.4905, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003770810158562567, | |
| "eval_loss": 0.5104564428329468, | |
| "eval_runtime": 667.6626, | |
| "eval_samples_per_second": 8.364, | |
| "eval_steps_per_second": 4.182, | |
| "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": 1.780205588840448e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |