| { | |
| "best_metric": 0.9016749262809753, | |
| "best_model_checkpoint": "Llama-3.1-8B-medquad-V1/checkpoint-120", | |
| "epoch": 1.988950276243094, | |
| "eval_steps": 10, | |
| "global_step": 120, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16574585635359115, | |
| "grad_norm": 0.45320844650268555, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3598, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16574585635359115, | |
| "eval_loss": 1.150091528892517, | |
| "eval_runtime": 262.9709, | |
| "eval_samples_per_second": 5.503, | |
| "eval_steps_per_second": 0.688, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3314917127071823, | |
| "grad_norm": 0.2883709669113159, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0759, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3314917127071823, | |
| "eval_loss": 1.0142412185668945, | |
| "eval_runtime": 262.9361, | |
| "eval_samples_per_second": 5.503, | |
| "eval_steps_per_second": 0.688, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4972375690607735, | |
| "grad_norm": 0.594289243221283, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0658, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4972375690607735, | |
| "eval_loss": 0.9933609366416931, | |
| "eval_runtime": 263.0573, | |
| "eval_samples_per_second": 5.501, | |
| "eval_steps_per_second": 0.688, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6629834254143646, | |
| "grad_norm": 0.20665977895259857, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0488, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6629834254143646, | |
| "eval_loss": 0.9609452486038208, | |
| "eval_runtime": 263.0813, | |
| "eval_samples_per_second": 5.5, | |
| "eval_steps_per_second": 0.688, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8287292817679558, | |
| "grad_norm": 0.21681097149848938, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9015, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8287292817679558, | |
| "eval_loss": 0.9510175585746765, | |
| "eval_runtime": 263.0103, | |
| "eval_samples_per_second": 5.502, | |
| "eval_steps_per_second": 0.688, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.994475138121547, | |
| "grad_norm": 0.41058990359306335, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0082, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.994475138121547, | |
| "eval_loss": 0.9378434419631958, | |
| "eval_runtime": 263.0681, | |
| "eval_samples_per_second": 5.5, | |
| "eval_steps_per_second": 0.688, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.160220994475138, | |
| "grad_norm": 0.1634252816438675, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9717, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.160220994475138, | |
| "eval_loss": 0.9255585074424744, | |
| "eval_runtime": 262.87, | |
| "eval_samples_per_second": 5.505, | |
| "eval_steps_per_second": 0.689, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.3259668508287292, | |
| "grad_norm": 0.170590341091156, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8399, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3259668508287292, | |
| "eval_loss": 0.924992024898529, | |
| "eval_runtime": 263.1411, | |
| "eval_samples_per_second": 5.499, | |
| "eval_steps_per_second": 0.688, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.4917127071823204, | |
| "grad_norm": 0.34625816345214844, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9485, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.4917127071823204, | |
| "eval_loss": 0.9176306128501892, | |
| "eval_runtime": 262.9978, | |
| "eval_samples_per_second": 5.502, | |
| "eval_steps_per_second": 0.688, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6574585635359116, | |
| "grad_norm": 0.1708645522594452, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9363, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6574585635359116, | |
| "eval_loss": 0.910330057144165, | |
| "eval_runtime": 263.1053, | |
| "eval_samples_per_second": 5.5, | |
| "eval_steps_per_second": 0.688, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.8232044198895028, | |
| "grad_norm": 0.16559375822544098, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8485, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.8232044198895028, | |
| "eval_loss": 0.9077811241149902, | |
| "eval_runtime": 262.9968, | |
| "eval_samples_per_second": 5.502, | |
| "eval_steps_per_second": 0.688, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.988950276243094, | |
| "grad_norm": 0.3019842505455017, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9398, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.988950276243094, | |
| "eval_loss": 0.9016749262809753, | |
| "eval_runtime": 263.1028, | |
| "eval_samples_per_second": 5.5, | |
| "eval_steps_per_second": 0.688, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.988950276243094, | |
| "step": 120, | |
| "total_flos": 2.1394363129941197e+17, | |
| "train_loss": 0.9953938881556194, | |
| "train_runtime": 10885.5423, | |
| "train_samples_per_second": 7.444, | |
| "train_steps_per_second": 0.039 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 420, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 5 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1394363129941197e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |