| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020537395173712135, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006845798391237378, | |
| "eval_loss": 0.87681645154953, | |
| "eval_runtime": 54.5097, | |
| "eval_samples_per_second": 11.282, | |
| "eval_steps_per_second": 5.65, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020537395173712133, | |
| "grad_norm": 0.5193249583244324, | |
| "learning_rate": 6e-05, | |
| "loss": 0.9895, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004107479034742427, | |
| "grad_norm": 0.5396872162818909, | |
| "learning_rate": 0.00012, | |
| "loss": 0.7803, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005476638712989902, | |
| "eval_loss": 0.7880386114120483, | |
| "eval_runtime": 53.3983, | |
| "eval_samples_per_second": 11.517, | |
| "eval_steps_per_second": 5.768, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00616121855211364, | |
| "grad_norm": 0.7672879695892334, | |
| "learning_rate": 0.00018, | |
| "loss": 0.7291, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008214958069484853, | |
| "grad_norm": 0.9412434697151184, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.7513, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010268697586856067, | |
| "grad_norm": 0.942672610282898, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.7163, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010953277425979804, | |
| "eval_loss": 0.7357094287872314, | |
| "eval_runtime": 53.5798, | |
| "eval_samples_per_second": 11.478, | |
| "eval_steps_per_second": 5.748, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01232243710422728, | |
| "grad_norm": 3.3070077896118164, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.6944, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014376176621598494, | |
| "grad_norm": 0.6650722026824951, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.6943, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016429916138969707, | |
| "grad_norm": 0.8915995359420776, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.6703, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016429916138969707, | |
| "eval_loss": 0.7271555066108704, | |
| "eval_runtime": 53.6434, | |
| "eval_samples_per_second": 11.465, | |
| "eval_steps_per_second": 5.742, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01848365565634092, | |
| "grad_norm": 0.6706926226615906, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.6565, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.020537395173712135, | |
| "grad_norm": 0.47476261854171753, | |
| "learning_rate": 0.0, | |
| "loss": 0.622, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1499252895186944e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |