| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.22308979364194087, |
| "eval_steps": 100, |
| "global_step": 100, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.022308979364194088, |
| "grad_norm": 3.6059792041778564, |
| "learning_rate": 0.00019999016517595753, |
| "loss": 3.6749305725097656, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.044617958728388175, |
| "grad_norm": 1.686761498451233, |
| "learning_rate": 0.00019987954562051725, |
| "loss": 0.9972598075866699, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06692693809258227, |
| "grad_norm": 1.0181570053100586, |
| "learning_rate": 0.00019964614941176195, |
| "loss": 0.7280679225921631, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.08923591745677635, |
| "grad_norm": 0.9052721261978149, |
| "learning_rate": 0.00019929026345133122, |
| "loss": 0.6308993339538574, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.11154489682097044, |
| "grad_norm": 0.8318365812301636, |
| "learning_rate": 0.00019881232521105089, |
| "loss": 0.6105688571929931, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.13385387618516453, |
| "grad_norm": 0.9255080223083496, |
| "learning_rate": 0.00019821292219517192, |
| "loss": 0.5463937282562256, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.1561628555493586, |
| "grad_norm": 0.8712772727012634, |
| "learning_rate": 0.00019749279121818235, |
| "loss": 0.513142728805542, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.1784718349135527, |
| "grad_norm": 0.6806803941726685, |
| "learning_rate": 0.00019665281749908033, |
| "loss": 0.45452089309692384, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.2007808142777468, |
| "grad_norm": 0.8569662570953369, |
| "learning_rate": 0.0001956940335732209, |
| "loss": 0.4099240303039551, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.22308979364194087, |
| "grad_norm": 0.5690306425094604, |
| "learning_rate": 0.00019461761802307495, |
| "loss": 0.4181380748748779, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.22308979364194087, |
| "eval_loss": 7.142496585845947, |
| "eval_runtime": 196.0856, |
| "eval_samples_per_second": 2.3, |
| "eval_steps_per_second": 2.3, |
| "step": 100 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 898, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1609636050452544.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
