| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00487904045537711, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016263468184590365, | |
| "eval_loss": 0.6653284430503845, | |
| "eval_runtime": 336.7786, | |
| "eval_samples_per_second": 7.688, | |
| "eval_steps_per_second": 3.845, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004879040455377109, | |
| "grad_norm": 0.6958808898925781, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8966, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009758080910754218, | |
| "grad_norm": 0.7547984719276428, | |
| "learning_rate": 0.00012, | |
| "loss": 2.6614, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013010774547672292, | |
| "eval_loss": 0.6449689865112305, | |
| "eval_runtime": 337.9054, | |
| "eval_samples_per_second": 7.662, | |
| "eval_steps_per_second": 3.832, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014637121366131327, | |
| "grad_norm": 0.7398614883422852, | |
| "learning_rate": 0.00018, | |
| "loss": 2.532, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0019516161821508437, | |
| "grad_norm": 1.2829382419586182, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.7196, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002439520227688555, | |
| "grad_norm": 0.62413090467453, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.7893, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026021549095344584, | |
| "eval_loss": 0.6180543899536133, | |
| "eval_runtime": 338.4899, | |
| "eval_samples_per_second": 7.649, | |
| "eval_steps_per_second": 3.826, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0029274242732262655, | |
| "grad_norm": 0.5762659311294556, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.1983, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0034153283187639766, | |
| "grad_norm": 0.8231281042098999, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.3862, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0039032323643016873, | |
| "grad_norm": 0.6137740015983582, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.558, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0039032323643016873, | |
| "eval_loss": 0.6066776514053345, | |
| "eval_runtime": 337.8357, | |
| "eval_samples_per_second": 7.663, | |
| "eval_steps_per_second": 3.833, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004391136409839398, | |
| "grad_norm": 0.8133916854858398, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.3135, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00487904045537711, | |
| "grad_norm": 0.6444946527481079, | |
| "learning_rate": 0.0, | |
| "loss": 2.3194, | |
| "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": 2.85652348305408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |