| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 50, |
| "global_step": 60, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.016701461377870562, |
| "grad_norm": 4.485437870025635, |
| "learning_rate": 0.0, |
| "loss": 2.8465373516082764, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.08350730688935282, |
| "grad_norm": 3.0602867603302, |
| "learning_rate": 9.992407582166581e-05, |
| "loss": 2.294060707092285, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.16701461377870563, |
| "grad_norm": 0.8693507313728333, |
| "learning_rate": 9.729086208503174e-05, |
| "loss": 1.2953631401062011, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.25052192066805845, |
| "grad_norm": 0.7621045708656311, |
| "learning_rate": 9.108889076126226e-05, |
| "loss": 0.8703152656555175, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.33402922755741127, |
| "grad_norm": 0.6791566014289856, |
| "learning_rate": 8.178618741049842e-05, |
| "loss": 0.6290188312530518, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.4175365344467641, |
| "grad_norm": 0.6321083307266235, |
| "learning_rate": 7.008477123264848e-05, |
| "loss": 0.46433124542236326, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.5010438413361169, |
| "grad_norm": 0.49947911500930786, |
| "learning_rate": 5.686767789092041e-05, |
| "loss": 0.33226304054260253, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5845511482254697, |
| "grad_norm": 0.7511892914772034, |
| "learning_rate": 4.3132322109079596e-05, |
| "loss": 0.4396816730499268, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.6680584551148225, |
| "grad_norm": 0.5519866347312927, |
| "learning_rate": 2.991522876735154e-05, |
| "loss": 0.36175758838653566, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.7515657620041754, |
| "grad_norm": 0.36559605598449707, |
| "learning_rate": 1.821381258950161e-05, |
| "loss": 0.26281235218048093, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.8350730688935282, |
| "grad_norm": 0.6063154339790344, |
| "learning_rate": 8.911109238737747e-06, |
| "loss": 0.3335791826248169, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8350730688935282, |
| "eval_loss": 0.5060427784919739, |
| "eval_runtime": 23.6562, |
| "eval_samples_per_second": 5.157, |
| "eval_steps_per_second": 5.157, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.918580375782881, |
| "grad_norm": 0.6971960663795471, |
| "learning_rate": 2.7091379149682685e-06, |
| "loss": 0.32030749320983887, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.6506057977676392, |
| "learning_rate": 7.59241783341913e-08, |
| "loss": 0.32254273891448976, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.5009067058563232, |
| "eval_runtime": 21.0472, |
| "eval_samples_per_second": 5.797, |
| "eval_steps_per_second": 5.797, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 60, |
| "total_flos": 8434343709060096.0, |
| "train_loss": 0.6697107156117758, |
| "train_runtime": 651.199, |
| "train_samples_per_second": 1.471, |
| "train_steps_per_second": 0.092 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.5009067058563232, |
| "eval_runtime": 23.6746, |
| "eval_samples_per_second": 5.153, |
| "eval_steps_per_second": 5.153, |
| "step": 60 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 60, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 8434343709060096.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
