| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012686330478908976, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004228776826302992, | |
| "eval_loss": 1.7915385961532593, | |
| "eval_runtime": 87.7121, | |
| "eval_samples_per_second": 11.355, | |
| "eval_steps_per_second": 5.678, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012686330478908975, | |
| "grad_norm": 0.7311314940452576, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7856, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002537266095781795, | |
| "grad_norm": 0.8283582925796509, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8386, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0033830214610423934, | |
| "eval_loss": 1.6457921266555786, | |
| "eval_runtime": 86.6816, | |
| "eval_samples_per_second": 11.49, | |
| "eval_steps_per_second": 5.745, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003805899143672693, | |
| "grad_norm": 0.7579265832901001, | |
| "learning_rate": 0.00018, | |
| "loss": 1.559, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00507453219156359, | |
| "grad_norm": 1.1918922662734985, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.7637, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006343165239454488, | |
| "grad_norm": 0.7861229777336121, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.458, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006766042922084787, | |
| "eval_loss": 1.489386796951294, | |
| "eval_runtime": 86.7212, | |
| "eval_samples_per_second": 11.485, | |
| "eval_steps_per_second": 5.743, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007611798287345386, | |
| "grad_norm": 0.9497506022453308, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.5591, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008880431335236283, | |
| "grad_norm": 0.9134187698364258, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.4547, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01014906438312718, | |
| "grad_norm": 0.9056223034858704, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.4131, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01014906438312718, | |
| "eval_loss": 1.4413870573043823, | |
| "eval_runtime": 86.9195, | |
| "eval_samples_per_second": 11.459, | |
| "eval_steps_per_second": 5.729, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011417697431018078, | |
| "grad_norm": 0.7665942311286926, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.3923, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012686330478908976, | |
| "grad_norm": 1.1542731523513794, | |
| "learning_rate": 0.0, | |
| "loss": 1.5591, | |
| "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": 1.578362204061696e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |