| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02674392689993314, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008914642299977714, | |
| "eval_loss": 2.851620674133301, | |
| "eval_runtime": 61.6963, | |
| "eval_samples_per_second": 7.667, | |
| "eval_steps_per_second": 3.841, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002674392689993314, | |
| "grad_norm": 3.3117973804473877, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8099, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005348785379986628, | |
| "grad_norm": 3.115156888961792, | |
| "learning_rate": 0.00012, | |
| "loss": 2.6418, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007131713839982171, | |
| "eval_loss": 2.3706119060516357, | |
| "eval_runtime": 62.1771, | |
| "eval_samples_per_second": 7.607, | |
| "eval_steps_per_second": 3.812, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008023178069979943, | |
| "grad_norm": 2.5370635986328125, | |
| "learning_rate": 0.00018, | |
| "loss": 2.5039, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010697570759973256, | |
| "grad_norm": 2.72739577293396, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.338, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01337196344996657, | |
| "grad_norm": 2.532747745513916, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.1035, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014263427679964342, | |
| "eval_loss": 1.9922682046890259, | |
| "eval_runtime": 62.2375, | |
| "eval_samples_per_second": 7.6, | |
| "eval_steps_per_second": 3.808, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.016046356139959885, | |
| "grad_norm": 2.4762778282165527, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.9376, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0187207488299532, | |
| "grad_norm": 2.475957155227661, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.9267, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.021395141519946512, | |
| "grad_norm": 2.125596761703491, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.813, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.021395141519946512, | |
| "eval_loss": 1.8673545122146606, | |
| "eval_runtime": 62.3393, | |
| "eval_samples_per_second": 7.588, | |
| "eval_steps_per_second": 3.802, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.024069534209939826, | |
| "grad_norm": 2.2016642093658447, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.8512, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02674392689993314, | |
| "grad_norm": 4.105894565582275, | |
| "learning_rate": 0.0, | |
| "loss": 1.919, | |
| "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 | |
| } | |