| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0351123595505618, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007022471910112359, | |
| "eval_loss": 11.740757942199707, | |
| "eval_runtime": 6.2147, | |
| "eval_samples_per_second": 96.545, | |
| "eval_steps_per_second": 48.273, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0035112359550561797, | |
| "grad_norm": 0.17098312079906464, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7564, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007022471910112359, | |
| "grad_norm": 0.2087431102991104, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7573, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007022471910112359, | |
| "eval_loss": 11.739577293395996, | |
| "eval_runtime": 6.371, | |
| "eval_samples_per_second": 94.176, | |
| "eval_steps_per_second": 47.088, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010533707865168539, | |
| "grad_norm": 0.15307602286338806, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.7499, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014044943820224719, | |
| "grad_norm": 0.16069342195987701, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.7419, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014044943820224719, | |
| "eval_loss": 11.736796379089355, | |
| "eval_runtime": 6.2966, | |
| "eval_samples_per_second": 95.29, | |
| "eval_steps_per_second": 47.645, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0175561797752809, | |
| "grad_norm": 0.18296130001544952, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.7451, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.021067415730337078, | |
| "grad_norm": 0.2008729875087738, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7372, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021067415730337078, | |
| "eval_loss": 11.734527587890625, | |
| "eval_runtime": 7.1879, | |
| "eval_samples_per_second": 83.474, | |
| "eval_steps_per_second": 41.737, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02457865168539326, | |
| "grad_norm": 0.26322323083877563, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.7447, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.028089887640449437, | |
| "grad_norm": 0.18757085502147675, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.7128, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028089887640449437, | |
| "eval_loss": 11.733393669128418, | |
| "eval_runtime": 6.0275, | |
| "eval_samples_per_second": 99.544, | |
| "eval_steps_per_second": 49.772, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03160112359550562, | |
| "grad_norm": 0.19444578886032104, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.7489, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0351123595505618, | |
| "grad_norm": 0.2428700029850006, | |
| "learning_rate": 0.0, | |
| "loss": 11.7347, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0351123595505618, | |
| "eval_loss": 11.733201026916504, | |
| "eval_runtime": 6.0062, | |
| "eval_samples_per_second": 99.896, | |
| "eval_steps_per_second": 49.948, | |
| "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": 2577100603392.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |