| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.4129793510324484, |
| "eval_steps": 50, |
| "global_step": 120, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.11799410029498525, |
| "grad_norm": 0.20195358991622925, |
| "learning_rate": 0.0003, |
| "loss": 1.9738, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.2359882005899705, |
| "grad_norm": 0.1426803171634674, |
| "learning_rate": 0.0002963855421686747, |
| "loss": 1.5063, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.35398230088495575, |
| "grad_norm": 0.15137845277786255, |
| "learning_rate": 0.0002927710843373494, |
| "loss": 1.3522, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.471976401179941, |
| "grad_norm": 0.14357119798660278, |
| "learning_rate": 0.0002891566265060241, |
| "loss": 1.2434, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5899705014749262, |
| "grad_norm": 0.13860304653644562, |
| "learning_rate": 0.00028554216867469873, |
| "loss": 1.1816, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.5899705014749262, |
| "eval_loss": 1.159853458404541, |
| "eval_runtime": 18.5086, |
| "eval_samples_per_second": 8.861, |
| "eval_steps_per_second": 0.756, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.7079646017699115, |
| "grad_norm": 0.13697050511837006, |
| "learning_rate": 0.0002819277108433735, |
| "loss": 1.1465, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.8259587020648967, |
| "grad_norm": 0.12234006822109222, |
| "learning_rate": 0.0002783132530120482, |
| "loss": 1.1006, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.943952802359882, |
| "grad_norm": 0.1310320794582367, |
| "learning_rate": 0.00027469879518072284, |
| "loss": 1.0819, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.0589970501474926, |
| "grad_norm": 0.12331829220056534, |
| "learning_rate": 0.0002710843373493976, |
| "loss": 1.044, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.176991150442478, |
| "grad_norm": 0.11900211870670319, |
| "learning_rate": 0.00026746987951807225, |
| "loss": 1.0244, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.176991150442478, |
| "eval_loss": 1.0301724672317505, |
| "eval_runtime": 18.427, |
| "eval_samples_per_second": 8.9, |
| "eval_steps_per_second": 0.76, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.294985250737463, |
| "grad_norm": 0.13372938334941864, |
| "learning_rate": 0.00026385542168674695, |
| "loss": 1.0084, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.4129793510324484, |
| "grad_norm": 0.12052427977323532, |
| "learning_rate": 0.00026024096385542165, |
| "loss": 0.9994, |
| "step": 120 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 840, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 120, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.0204428618912236e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
