| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0029996250468691415, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00029996250468691414, | |
| "grad_norm": 0.505634605884552, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3403, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005999250093738283, | |
| "grad_norm": 0.4967665374279022, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3097, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008998875140607424, | |
| "grad_norm": 0.47252127528190613, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3049, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008998875140607424, | |
| "eval_loss": 1.3807117938995361, | |
| "eval_runtime": 121.675, | |
| "eval_samples_per_second": 11.539, | |
| "eval_steps_per_second": 5.769, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011998500187476566, | |
| "grad_norm": 0.4749808609485626, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3186, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014998125234345708, | |
| "grad_norm": 0.5963099598884583, | |
| "learning_rate": 0.0001, | |
| "loss": 1.389, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0017997750281214847, | |
| "grad_norm": 0.5119407773017883, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1688, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017997750281214847, | |
| "eval_loss": 1.3017948865890503, | |
| "eval_runtime": 110.1806, | |
| "eval_samples_per_second": 12.743, | |
| "eval_steps_per_second": 6.371, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002099737532808399, | |
| "grad_norm": 0.6273112297058105, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2812, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002399700037495313, | |
| "grad_norm": 0.6254280209541321, | |
| "learning_rate": 0.00016, | |
| "loss": 1.178, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0026996625421822273, | |
| "grad_norm": 0.5449633002281189, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0342, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0026996625421822273, | |
| "eval_loss": 1.0363199710845947, | |
| "eval_runtime": 96.8589, | |
| "eval_samples_per_second": 14.495, | |
| "eval_steps_per_second": 7.248, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0029996250468691415, | |
| "grad_norm": 0.5097793340682983, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9937, | |
| "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": 3257466271825920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |