| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003926573083341513, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003926573083341514, | |
| "grad_norm": 1.0043013095855713, | |
| "learning_rate": 2e-05, | |
| "loss": 44.4968, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003926573083341514, | |
| "eval_loss": 11.118735313415527, | |
| "eval_runtime": 5.6811, | |
| "eval_samples_per_second": 188.873, | |
| "eval_steps_per_second": 94.525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007853146166683027, | |
| "grad_norm": 1.038082480430603, | |
| "learning_rate": 4e-05, | |
| "loss": 44.4785, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001177971925002454, | |
| "grad_norm": 1.251917839050293, | |
| "learning_rate": 6e-05, | |
| "loss": 44.4567, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001177971925002454, | |
| "eval_loss": 11.118449211120605, | |
| "eval_runtime": 5.0189, | |
| "eval_samples_per_second": 213.792, | |
| "eval_steps_per_second": 106.996, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015706292333366055, | |
| "grad_norm": 1.4662525653839111, | |
| "learning_rate": 8e-05, | |
| "loss": 44.4384, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0019632865416707567, | |
| "grad_norm": 0.8915764093399048, | |
| "learning_rate": 0.0001, | |
| "loss": 44.4569, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002355943850004908, | |
| "grad_norm": 0.9424355626106262, | |
| "learning_rate": 0.00012, | |
| "loss": 44.4515, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002355943850004908, | |
| "eval_loss": 11.115720748901367, | |
| "eval_runtime": 5.1321, | |
| "eval_samples_per_second": 209.076, | |
| "eval_steps_per_second": 104.635, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0027486011583390596, | |
| "grad_norm": 1.0006824731826782, | |
| "learning_rate": 0.00014, | |
| "loss": 44.4647, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003141258466673211, | |
| "grad_norm": 0.7817240953445435, | |
| "learning_rate": 0.00016, | |
| "loss": 44.4589, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0035339157750073624, | |
| "grad_norm": 1.1782363653182983, | |
| "learning_rate": 0.00018, | |
| "loss": 44.4546, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0035339157750073624, | |
| "eval_loss": 11.110819816589355, | |
| "eval_runtime": 5.1587, | |
| "eval_samples_per_second": 207.997, | |
| "eval_steps_per_second": 104.095, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003926573083341513, | |
| "grad_norm": 1.0923489332199097, | |
| "learning_rate": 0.0002, | |
| "loss": 44.4483, | |
| "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": 96448020480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |