| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005709120319710738, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001903040106570246, | |
| "eval_loss": 6.338423728942871, | |
| "eval_runtime": 50.9352, | |
| "eval_samples_per_second": 43.447, | |
| "eval_steps_per_second": 21.733, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005709120319710738, | |
| "grad_norm": 26.756820678710938, | |
| "learning_rate": 6e-05, | |
| "loss": 6.6032, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011418240639421476, | |
| "grad_norm": 24.603538513183594, | |
| "learning_rate": 0.00012, | |
| "loss": 5.7403, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015224320852561968, | |
| "eval_loss": 5.388502597808838, | |
| "eval_runtime": 50.759, | |
| "eval_samples_per_second": 43.598, | |
| "eval_steps_per_second": 21.809, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0017127360959132215, | |
| "grad_norm": 5.607676029205322, | |
| "learning_rate": 0.00018, | |
| "loss": 5.2884, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0022836481278842953, | |
| "grad_norm": 7.313529014587402, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 4.8237, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002854560159855369, | |
| "grad_norm": 7.197733402252197, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 4.9716, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0030448641705123937, | |
| "eval_loss": 4.382098197937012, | |
| "eval_runtime": 50.0157, | |
| "eval_samples_per_second": 44.246, | |
| "eval_steps_per_second": 22.133, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003425472191826443, | |
| "grad_norm": 4.23797607421875, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.5092, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0039963842237975165, | |
| "grad_norm": 10.855512619018555, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 4.3654, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0045672962557685905, | |
| "grad_norm": 3.5917742252349854, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 3.9673, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0045672962557685905, | |
| "eval_loss": 3.9958908557891846, | |
| "eval_runtime": 51.1395, | |
| "eval_samples_per_second": 43.274, | |
| "eval_steps_per_second": 21.647, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005138208287739664, | |
| "grad_norm": 4.35882043838501, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 3.8858, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005709120319710738, | |
| "grad_norm": 2.9137649536132812, | |
| "learning_rate": 0.0, | |
| "loss": 3.7191, | |
| "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": 1544053158051840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |