| { |
| "best_metric": 0.2607206702232361, |
| "best_model_checkpoint": "tweet-xlmr-finetuned-toxicity-classification/checkpoint-2008", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 4016, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.24906600249066002, |
| "grad_norm": 22.069509506225586, |
| "learning_rate": 1.9003487792725463e-05, |
| "loss": 0.4381, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.49813200498132004, |
| "grad_norm": 8.925381660461426, |
| "learning_rate": 1.8006975585450922e-05, |
| "loss": 0.3312, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.7471980074719801, |
| "grad_norm": 17.554454803466797, |
| "learning_rate": 1.7010463378176384e-05, |
| "loss": 0.3061, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.9962640099626401, |
| "grad_norm": 13.063820838928223, |
| "learning_rate": 1.6013951170901845e-05, |
| "loss": 0.2846, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.2607206702232361, |
| "eval_runtime": 142.7454, |
| "eval_samples_per_second": 50.012, |
| "eval_steps_per_second": 3.131, |
| "step": 2008 |
| }, |
| { |
| "epoch": 1.2450809464508095, |
| "grad_norm": 22.06833267211914, |
| "learning_rate": 1.5017438963627307e-05, |
| "loss": 0.1974, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.4941469489414696, |
| "grad_norm": 10.912453651428223, |
| "learning_rate": 1.4020926756352765e-05, |
| "loss": 0.2038, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.7432129514321295, |
| "grad_norm": 18.099023818969727, |
| "learning_rate": 1.3024414549078229e-05, |
| "loss": 0.1937, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.9922789539227894, |
| "grad_norm": 8.781684875488281, |
| "learning_rate": 1.2027902341803687e-05, |
| "loss": 0.1929, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.2738674283027649, |
| "eval_runtime": 142.6259, |
| "eval_samples_per_second": 50.054, |
| "eval_steps_per_second": 3.134, |
| "step": 4016 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 10035, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.1972522224674816e+17, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
