| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04070832485243232, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008141664970486464, | |
| "eval_loss": 2.4700965881347656, | |
| "eval_runtime": 52.4183, | |
| "eval_samples_per_second": 9.882, | |
| "eval_steps_per_second": 4.941, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004070832485243233, | |
| "grad_norm": 0.37725594639778137, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1874, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008141664970486465, | |
| "grad_norm": 0.75648033618927, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4084, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008141664970486465, | |
| "eval_loss": 2.3090720176696777, | |
| "eval_runtime": 54.9027, | |
| "eval_samples_per_second": 9.435, | |
| "eval_steps_per_second": 4.717, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012212497455729696, | |
| "grad_norm": 0.6268041729927063, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2516, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01628332994097293, | |
| "grad_norm": 0.6889188885688782, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7638, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01628332994097293, | |
| "eval_loss": 1.7881678342819214, | |
| "eval_runtime": 55.6645, | |
| "eval_samples_per_second": 9.306, | |
| "eval_steps_per_second": 4.653, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02035416242621616, | |
| "grad_norm": 1.2505710124969482, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6658, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.024424994911459393, | |
| "grad_norm": 0.7620664834976196, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4841, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.024424994911459393, | |
| "eval_loss": 1.4007254838943481, | |
| "eval_runtime": 55.7229, | |
| "eval_samples_per_second": 9.296, | |
| "eval_steps_per_second": 4.648, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.028495827396702627, | |
| "grad_norm": 0.7537080645561218, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2442, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03256665988194586, | |
| "grad_norm": 0.7182632684707642, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2216, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03256665988194586, | |
| "eval_loss": 1.2438228130340576, | |
| "eval_runtime": 55.7606, | |
| "eval_samples_per_second": 9.29, | |
| "eval_steps_per_second": 4.645, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03663749236718909, | |
| "grad_norm": 0.7580611705780029, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.188, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04070832485243232, | |
| "grad_norm": 0.7346731424331665, | |
| "learning_rate": 0.0, | |
| "loss": 1.1845, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04070832485243232, | |
| "eval_loss": 1.2215094566345215, | |
| "eval_runtime": 55.8373, | |
| "eval_samples_per_second": 9.277, | |
| "eval_steps_per_second": 4.638, | |
| "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": 1.023798677078016e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |