| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003470715835140998, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.470715835140998e-05, | |
| "grad_norm": 6.89044713973999, | |
| "learning_rate": 2e-05, | |
| "loss": 6.754, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.470715835140998e-05, | |
| "eval_loss": 1.308242917060852, | |
| "eval_runtime": 322.0408, | |
| "eval_samples_per_second": 37.672, | |
| "eval_steps_per_second": 18.836, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.941431670281996e-05, | |
| "grad_norm": 2.492136001586914, | |
| "learning_rate": 4e-05, | |
| "loss": 5.6375, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010412147505422994, | |
| "grad_norm": 2.607607364654541, | |
| "learning_rate": 6e-05, | |
| "loss": 5.0086, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010412147505422994, | |
| "eval_loss": 1.3050315380096436, | |
| "eval_runtime": 319.8943, | |
| "eval_samples_per_second": 37.925, | |
| "eval_steps_per_second": 18.963, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013882863340563992, | |
| "grad_norm": 2.1943202018737793, | |
| "learning_rate": 8e-05, | |
| "loss": 5.1899, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001735357917570499, | |
| "grad_norm": 5.0044145584106445, | |
| "learning_rate": 0.0001, | |
| "loss": 7.0007, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00020824295010845987, | |
| "grad_norm": 2.0717947483062744, | |
| "learning_rate": 0.00012, | |
| "loss": 4.5291, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00020824295010845987, | |
| "eval_loss": 1.281042456626892, | |
| "eval_runtime": 321.7797, | |
| "eval_samples_per_second": 37.703, | |
| "eval_steps_per_second": 18.851, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00024295010845986985, | |
| "grad_norm": 2.251619338989258, | |
| "learning_rate": 0.00014, | |
| "loss": 4.9577, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00027765726681127983, | |
| "grad_norm": 2.264468193054199, | |
| "learning_rate": 0.00016, | |
| "loss": 4.5139, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0003123644251626898, | |
| "grad_norm": 4.589754104614258, | |
| "learning_rate": 0.00018, | |
| "loss": 5.1324, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003123644251626898, | |
| "eval_loss": 1.2194496393203735, | |
| "eval_runtime": 324.2447, | |
| "eval_samples_per_second": 37.416, | |
| "eval_steps_per_second": 18.708, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003470715835140998, | |
| "grad_norm": 3.1652841567993164, | |
| "learning_rate": 0.0002, | |
| "loss": 5.1345, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1110013850419200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |