| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.11154489682097044, |
| "eval_steps": 100, |
| "global_step": 50, |
| "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 |
| } |
| ], |
| "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": 805387198366656.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
