| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3629764065335753, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007259528130671506, | |
| "eval_loss": 2.36360764503479, | |
| "eval_runtime": 2.1308, | |
| "eval_samples_per_second": 108.877, | |
| "eval_steps_per_second": 13.61, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.036297640653357534, | |
| "grad_norm": 7.917306900024414, | |
| "learning_rate": 5e-05, | |
| "loss": 9.7342, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07259528130671507, | |
| "grad_norm": 11.976446151733398, | |
| "learning_rate": 0.0001, | |
| "loss": 9.4831, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07259528130671507, | |
| "eval_loss": 1.717249870300293, | |
| "eval_runtime": 2.1803, | |
| "eval_samples_per_second": 106.407, | |
| "eval_steps_per_second": 13.301, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1088929219600726, | |
| "grad_norm": 6.565160751342773, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.5041, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14519056261343014, | |
| "grad_norm": 3.8733808994293213, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.5637, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14519056261343014, | |
| "eval_loss": 1.0715842247009277, | |
| "eval_runtime": 2.1777, | |
| "eval_samples_per_second": 106.537, | |
| "eval_steps_per_second": 13.317, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18148820326678766, | |
| "grad_norm": 2.763819456100464, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.3577, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2177858439201452, | |
| "grad_norm": 4.010653495788574, | |
| "learning_rate": 5e-05, | |
| "loss": 4.3569, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2177858439201452, | |
| "eval_loss": 0.9906569123268127, | |
| "eval_runtime": 2.2155, | |
| "eval_samples_per_second": 104.718, | |
| "eval_steps_per_second": 13.09, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2540834845735027, | |
| "grad_norm": 3.135490894317627, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.309, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.29038112522686027, | |
| "grad_norm": 2.5858254432678223, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.4672, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.29038112522686027, | |
| "eval_loss": 0.9652195572853088, | |
| "eval_runtime": 2.2359, | |
| "eval_samples_per_second": 103.761, | |
| "eval_steps_per_second": 12.97, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32667876588021777, | |
| "grad_norm": 2.5173561573028564, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.9447, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3629764065335753, | |
| "grad_norm": 3.130607843399048, | |
| "learning_rate": 0.0, | |
| "loss": 3.7905, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3629764065335753, | |
| "eval_loss": 0.9589429497718811, | |
| "eval_runtime": 2.1778, | |
| "eval_samples_per_second": 106.528, | |
| "eval_steps_per_second": 13.316, | |
| "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": 1.916227713970995e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |