| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006418450906873626, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.139483635624542e-05, | |
| "eval_loss": 3.725355863571167, | |
| "eval_runtime": 2541.9047, | |
| "eval_samples_per_second": 7.743, | |
| "eval_steps_per_second": 3.872, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.418450906873626e-05, | |
| "grad_norm": 3.953409194946289, | |
| "learning_rate": 3e-05, | |
| "loss": 3.7594, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001283690181374725, | |
| "grad_norm": 3.3203933238983154, | |
| "learning_rate": 6e-05, | |
| "loss": 3.7394, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00017115869084996337, | |
| "eval_loss": 2.99819016456604, | |
| "eval_runtime": 2550.9541, | |
| "eval_samples_per_second": 7.715, | |
| "eval_steps_per_second": 3.858, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001925535272062088, | |
| "grad_norm": 2.904099702835083, | |
| "learning_rate": 9e-05, | |
| "loss": 3.2948, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000256738036274945, | |
| "grad_norm": 3.060228109359741, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.7908, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0003209225453436813, | |
| "grad_norm": 3.075441837310791, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.3934, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00034231738169992673, | |
| "eval_loss": 2.2090160846710205, | |
| "eval_runtime": 2548.8684, | |
| "eval_samples_per_second": 7.721, | |
| "eval_steps_per_second": 3.861, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0003851070544124176, | |
| "grad_norm": 2.209512710571289, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.286, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0004492915634811538, | |
| "grad_norm": 2.8848774433135986, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 2.1907, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00051347607254989, | |
| "grad_norm": 2.1118345260620117, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 2.0544, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00051347607254989, | |
| "eval_loss": 2.096832275390625, | |
| "eval_runtime": 2546.8778, | |
| "eval_samples_per_second": 7.728, | |
| "eval_steps_per_second": 3.864, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0005776605816186263, | |
| "grad_norm": 2.1737489700317383, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 2.0826, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0006418450906873626, | |
| "grad_norm": 2.259516954421997, | |
| "learning_rate": 0.0, | |
| "loss": 1.9007, | |
| "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": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |