| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6016540317022743, | |
| "eval_steps": 291, | |
| "global_step": 873, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06891798759476224, | |
| "grad_norm": 8.768977165222168, | |
| "learning_rate": 9.88557738007169e-06, | |
| "loss": 0.6099, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13783597518952448, | |
| "grad_norm": 13.488529205322266, | |
| "learning_rate": 9.547546534667266e-06, | |
| "loss": 0.5507, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2005513439007581, | |
| "eval_accuracy": 0.7176081716426815, | |
| "eval_loss": 0.5506236553192139, | |
| "eval_runtime": 1151.562, | |
| "eval_samples_per_second": 72.772, | |
| "eval_steps_per_second": 9.097, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.2067539627842867, | |
| "grad_norm": 11.636795043945312, | |
| "learning_rate": 8.994878055100864e-06, | |
| "loss": 0.5184, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.27567195037904896, | |
| "grad_norm": 14.019742965698242, | |
| "learning_rate": 8.255669894863161e-06, | |
| "loss": 0.5074, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.34458993797381116, | |
| "grad_norm": 32.54533767700195, | |
| "learning_rate": 7.373972308696536e-06, | |
| "loss": 0.4921, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4011026878015162, | |
| "eval_accuracy": 0.7393737619627216, | |
| "eval_loss": 0.5162956714630127, | |
| "eval_runtime": 1152.6745, | |
| "eval_samples_per_second": 72.702, | |
| "eval_steps_per_second": 9.088, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.4135079255685734, | |
| "grad_norm": 40.92453384399414, | |
| "learning_rate": 6.3732141693438686e-06, | |
| "loss": 0.471, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4824259131633356, | |
| "grad_norm": 16.179763793945312, | |
| "learning_rate": 5.3299412488905934e-06, | |
| "loss": 0.4839, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5513439007580979, | |
| "grad_norm": 16.651920318603516, | |
| "learning_rate": 4.250456101466412e-06, | |
| "loss": 0.4727, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6016540317022743, | |
| "eval_accuracy": 0.7367604591775853, | |
| "eval_loss": 0.5193670988082886, | |
| "eval_runtime": 1152.5824, | |
| "eval_samples_per_second": 72.708, | |
| "eval_steps_per_second": 9.089, | |
| "step": 873 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1451, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 291, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |