| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08880994671403197, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017761989342806395, | |
| "eval_loss": 10.375921249389648, | |
| "eval_runtime": 1.1462, | |
| "eval_samples_per_second": 207.638, | |
| "eval_steps_per_second": 103.819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008880994671403197, | |
| "grad_norm": 0.04732152819633484, | |
| "learning_rate": 5e-05, | |
| "loss": 10.38, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.017761989342806393, | |
| "grad_norm": 0.03675731271505356, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3764, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017761989342806393, | |
| "eval_loss": 10.375849723815918, | |
| "eval_runtime": 1.1333, | |
| "eval_samples_per_second": 210.002, | |
| "eval_steps_per_second": 105.001, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02664298401420959, | |
| "grad_norm": 0.054118264466524124, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3796, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.035523978685612786, | |
| "grad_norm": 0.052961334586143494, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3793, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.035523978685612786, | |
| "eval_loss": 10.375701904296875, | |
| "eval_runtime": 1.157, | |
| "eval_samples_per_second": 205.713, | |
| "eval_steps_per_second": 102.856, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04440497335701599, | |
| "grad_norm": 0.04892309010028839, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3723, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05328596802841918, | |
| "grad_norm": 0.04572363942861557, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3777, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05328596802841918, | |
| "eval_loss": 10.375574111938477, | |
| "eval_runtime": 1.2336, | |
| "eval_samples_per_second": 192.927, | |
| "eval_steps_per_second": 96.464, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06216696269982238, | |
| "grad_norm": 0.056839704513549805, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3748, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07104795737122557, | |
| "grad_norm": 0.05530121922492981, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3747, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07104795737122557, | |
| "eval_loss": 10.37551498413086, | |
| "eval_runtime": 1.2478, | |
| "eval_samples_per_second": 190.729, | |
| "eval_steps_per_second": 95.364, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07992895204262877, | |
| "grad_norm": 0.05178322643041611, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.364, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08880994671403197, | |
| "grad_norm": 0.05107550323009491, | |
| "learning_rate": 0.0, | |
| "loss": 10.3756, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08880994671403197, | |
| "eval_loss": 10.375503540039062, | |
| "eval_runtime": 1.2205, | |
| "eval_samples_per_second": 195.007, | |
| "eval_steps_per_second": 97.503, | |
| "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": 646545408000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |