| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.023512814483893724, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00047025628967787447, | |
| "eval_loss": 1.3333030939102173, | |
| "eval_runtime": 72.5334, | |
| "eval_samples_per_second": 49.384, | |
| "eval_steps_per_second": 6.176, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014107688690336232, | |
| "grad_norm": 1.7957247495651245, | |
| "learning_rate": 3e-05, | |
| "loss": 1.3816, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0023512814483893723, | |
| "eval_loss": 1.252621054649353, | |
| "eval_runtime": 72.4361, | |
| "eval_samples_per_second": 49.451, | |
| "eval_steps_per_second": 6.185, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0028215377380672465, | |
| "grad_norm": 0.8181892037391663, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2521, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00423230660710087, | |
| "grad_norm": 0.6588422060012817, | |
| "learning_rate": 9e-05, | |
| "loss": 1.2152, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0047025628967787446, | |
| "eval_loss": 1.1770787239074707, | |
| "eval_runtime": 72.7257, | |
| "eval_samples_per_second": 49.254, | |
| "eval_steps_per_second": 6.16, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005643075476134493, | |
| "grad_norm": 0.6331816911697388, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 1.1578, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007053844345168116, | |
| "grad_norm": 0.5597560405731201, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2228, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007053844345168116, | |
| "eval_loss": 1.157048225402832, | |
| "eval_runtime": 72.6624, | |
| "eval_samples_per_second": 49.296, | |
| "eval_steps_per_second": 6.166, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00846461321420174, | |
| "grad_norm": 0.6084182262420654, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.2561, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009405125793557489, | |
| "eval_loss": 1.14651358127594, | |
| "eval_runtime": 72.6867, | |
| "eval_samples_per_second": 49.28, | |
| "eval_steps_per_second": 6.163, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009875382083235363, | |
| "grad_norm": 0.5509119033813477, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 1.1259, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011286150952268986, | |
| "grad_norm": 0.48853400349617004, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 1.1989, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011756407241946862, | |
| "eval_loss": 1.1405397653579712, | |
| "eval_runtime": 72.6738, | |
| "eval_samples_per_second": 49.289, | |
| "eval_steps_per_second": 6.165, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01269691982130261, | |
| "grad_norm": 0.4752669930458069, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 1.2031, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.014107688690336233, | |
| "grad_norm": 0.48559480905532837, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1301, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014107688690336233, | |
| "eval_loss": 1.1357909440994263, | |
| "eval_runtime": 72.6566, | |
| "eval_samples_per_second": 49.3, | |
| "eval_steps_per_second": 6.166, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015518457559369857, | |
| "grad_norm": 0.41411325335502625, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 1.1651, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.016458970138725604, | |
| "eval_loss": 1.1328095197677612, | |
| "eval_runtime": 72.7319, | |
| "eval_samples_per_second": 49.249, | |
| "eval_steps_per_second": 6.16, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01692922642840348, | |
| "grad_norm": 0.4719478487968445, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 1.1109, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.018339995297437104, | |
| "grad_norm": 0.3741627335548401, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 1.2164, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.018810251587114978, | |
| "eval_loss": 1.1306617259979248, | |
| "eval_runtime": 72.6878, | |
| "eval_samples_per_second": 49.279, | |
| "eval_steps_per_second": 6.163, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.019750764166470727, | |
| "grad_norm": 0.3560473918914795, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.1565, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02116153303550435, | |
| "grad_norm": 0.4546699523925781, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.175, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02116153303550435, | |
| "eval_loss": 1.13008713722229, | |
| "eval_runtime": 72.7277, | |
| "eval_samples_per_second": 49.252, | |
| "eval_steps_per_second": 6.16, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.022572301904537972, | |
| "grad_norm": 0.42464736104011536, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 1.1632, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.023512814483893724, | |
| "eval_loss": 1.129866361618042, | |
| "eval_runtime": 72.7273, | |
| "eval_samples_per_second": 49.252, | |
| "eval_steps_per_second": 6.16, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.06657392623616e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |