| { |
| "best_metric": 1.9378653764724731, |
| "best_model_checkpoint": "./output/training_results/C020_Meta-Llama-3-8B_pretrain_20240726_033210/checkpoint-32778", |
| "epoch": 4.0, |
| "eval_steps": 3642, |
| "global_step": 36412, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00010985389432055367, |
| "grad_norm": 0.0, |
| "learning_rate": 0.0, |
| "loss": 2.0915, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.20004394155772823, |
| "grad_norm": 1.880800447163735, |
| "learning_rate": 1.9904796777737092e-06, |
| "loss": 2.0663, |
| "step": 1821 |
| }, |
| { |
| "epoch": 0.40008788311545646, |
| "grad_norm": 1.91582729652135, |
| "learning_rate": 2.239936089625888e-06, |
| "loss": 2.007, |
| "step": 3642 |
| }, |
| { |
| "epoch": 0.40008788311545646, |
| "eval_loss": 1.9830611944198608, |
| "eval_runtime": 322.5516, |
| "eval_samples_per_second": 200.684, |
| "eval_steps_per_second": 1.569, |
| "step": 3642 |
| }, |
| { |
| "epoch": 0.6001318246731847, |
| "grad_norm": 1.8799884350488187, |
| "learning_rate": 1.2178786981582618e-06, |
| "loss": 1.9789, |
| "step": 5463 |
| }, |
| { |
| "epoch": 0.8001757662309129, |
| "grad_norm": 2.167713398694089, |
| "learning_rate": 6.502057578924368e-07, |
| "loss": 1.9635, |
| "step": 7284 |
| }, |
| { |
| "epoch": 0.8001757662309129, |
| "eval_loss": 1.9486902952194214, |
| "eval_runtime": 315.8318, |
| "eval_samples_per_second": 204.954, |
| "eval_steps_per_second": 1.602, |
| "step": 7284 |
| }, |
| { |
| "epoch": 1.000219707788641, |
| "grad_norm": 1.9185025050401976, |
| "learning_rate": 3.4539250265217177e-07, |
| "loss": 1.9518, |
| "step": 9105 |
| }, |
| { |
| "epoch": 1.2002636493463694, |
| "grad_norm": 1.8537277337784435, |
| "learning_rate": 1.8838570953925226e-07, |
| "loss": 1.8917, |
| "step": 10926 |
| }, |
| { |
| "epoch": 1.2002636493463694, |
| "eval_loss": 1.9423131942749023, |
| "eval_runtime": 315.8691, |
| "eval_samples_per_second": 204.93, |
| "eval_steps_per_second": 1.602, |
| "step": 10926 |
| }, |
| { |
| "epoch": 1.4003075909040976, |
| "grad_norm": 1.8472997131423734, |
| "learning_rate": 1.113186862393777e-07, |
| "loss": 1.8886, |
| "step": 12747 |
| }, |
| { |
| "epoch": 1.6003515324618258, |
| "grad_norm": 1.895662682121472, |
| "learning_rate": 7.547123756350748e-08, |
| "loss": 1.8884, |
| "step": 14568 |
| }, |
| { |
| "epoch": 1.6003515324618258, |
| "eval_loss": 1.9401631355285645, |
| "eval_runtime": 315.8338, |
| "eval_samples_per_second": 204.953, |
| "eval_steps_per_second": 1.602, |
| "step": 14568 |
| }, |
| { |
| "epoch": 1.800395474019554, |
| "grad_norm": 1.8596122602328744, |
| "learning_rate": 5.97978448731285e-08, |
| "loss": 1.891, |
| "step": 16389 |
| }, |
| { |
| "epoch": 2.000439415577282, |
| "grad_norm": 1.752487380981475, |
| "learning_rate": 5.343917594361068e-08, |
| "loss": 1.8872, |
| "step": 18210 |
| }, |
| { |
| "epoch": 2.000439415577282, |
| "eval_loss": 1.9390411376953125, |
| "eval_runtime": 316.1594, |
| "eval_samples_per_second": 204.742, |
| "eval_steps_per_second": 1.6, |
| "step": 18210 |
| }, |
| { |
| "epoch": 2.2004833571350106, |
| "grad_norm": 1.8941258580557327, |
| "learning_rate": 5.108265610728981e-08, |
| "loss": 1.8788, |
| "step": 20031 |
| }, |
| { |
| "epoch": 2.400527298692739, |
| "grad_norm": 1.8532314600998243, |
| "learning_rate": 5.0297076317689476e-08, |
| "loss": 1.8811, |
| "step": 21852 |
| }, |
| { |
| "epoch": 2.400527298692739, |
| "eval_loss": 1.9393320083618164, |
| "eval_runtime": 316.5674, |
| "eval_samples_per_second": 204.478, |
| "eval_steps_per_second": 1.598, |
| "step": 21852 |
| }, |
| { |
| "epoch": 2.600571240250467, |
| "grad_norm": 1.856636820022415, |
| "learning_rate": 5.006877574024932e-08, |
| "loss": 1.8807, |
| "step": 23673 |
| }, |
| { |
| "epoch": 2.8006151818081952, |
| "grad_norm": 1.8975919928137213, |
| "learning_rate": 5.001268969632882e-08, |
| "loss": 1.8782, |
| "step": 25494 |
| }, |
| { |
| "epoch": 2.8006151818081952, |
| "eval_loss": 1.938640832901001, |
| "eval_runtime": 316.1355, |
| "eval_samples_per_second": 204.757, |
| "eval_steps_per_second": 1.601, |
| "step": 25494 |
| }, |
| { |
| "epoch": 3.0006591233659234, |
| "grad_norm": 1.8638851197626498, |
| "learning_rate": 5.000172130703981e-08, |
| "loss": 1.8764, |
| "step": 27315 |
| }, |
| { |
| "epoch": 3.2007030649236516, |
| "grad_norm": 1.9182088121869934, |
| "learning_rate": 5.000014937976813e-08, |
| "loss": 1.8742, |
| "step": 29136 |
| }, |
| { |
| "epoch": 3.2007030649236516, |
| "eval_loss": 1.9384987354278564, |
| "eval_runtime": 316.0484, |
| "eval_samples_per_second": 204.814, |
| "eval_steps_per_second": 1.601, |
| "step": 29136 |
| }, |
| { |
| "epoch": 3.40074700648138, |
| "grad_norm": 1.9601402086429087, |
| "learning_rate": 5.000000644319432e-08, |
| "loss": 1.8775, |
| "step": 30957 |
| }, |
| { |
| "epoch": 3.600790948039108, |
| "grad_norm": 1.8139760695838174, |
| "learning_rate": 5.000000007721787e-08, |
| "loss": 1.8756, |
| "step": 32778 |
| }, |
| { |
| "epoch": 3.600790948039108, |
| "eval_loss": 1.9378653764724731, |
| "eval_runtime": 316.2121, |
| "eval_samples_per_second": 204.708, |
| "eval_steps_per_second": 1.6, |
| "step": 32778 |
| }, |
| { |
| "epoch": 3.8008348895968362, |
| "grad_norm": 1.9502862375669288, |
| "learning_rate": 5.000000000004247e-08, |
| "loss": 1.871, |
| "step": 34599 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 36412, |
| "total_flos": 3807150279229440.0, |
| "train_loss": 1.9091134535458327, |
| "train_runtime": 51834.1311, |
| "train_samples_per_second": 44.957, |
| "train_steps_per_second": 0.702 |
| } |
| ], |
| "logging_steps": 1821, |
| "max_steps": 36412, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 3642, |
| "total_flos": 3807150279229440.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
