| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.0034132605171089685, |
| "eval_steps": 10, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 6.826521034217937e-05, |
| "eval_loss": 3.115783452987671, |
| "eval_runtime": 186.1759, |
| "eval_samples_per_second": 33.13, |
| "eval_steps_per_second": 16.565, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.0003413260517108968, |
| "grad_norm": 2.2947301864624023, |
| "learning_rate": 5e-05, |
| "loss": 2.9986, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0006826521034217937, |
| "grad_norm": 2.5597593784332275, |
| "learning_rate": 0.0001, |
| "loss": 3.0651, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0006826521034217937, |
| "eval_loss": 3.018254518508911, |
| "eval_runtime": 186.6409, |
| "eval_samples_per_second": 33.047, |
| "eval_steps_per_second": 16.524, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.0010239781551326906, |
| "grad_norm": 2.3084704875946045, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 2.8458, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.0013653042068435873, |
| "grad_norm": 2.918429136276245, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 2.5002, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0013653042068435873, |
| "eval_loss": 2.5421009063720703, |
| "eval_runtime": 186.4994, |
| "eval_samples_per_second": 33.073, |
| "eval_steps_per_second": 16.536, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0017066302585544842, |
| "grad_norm": 2.7874643802642822, |
| "learning_rate": 6.91341716182545e-05, |
| "loss": 2.5545, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.002047956310265381, |
| "grad_norm": 2.591674327850342, |
| "learning_rate": 5e-05, |
| "loss": 2.2392, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.002047956310265381, |
| "eval_loss": 2.4233028888702393, |
| "eval_runtime": 186.4659, |
| "eval_samples_per_second": 33.078, |
| "eval_steps_per_second": 16.539, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.002389282361976278, |
| "grad_norm": 2.8810315132141113, |
| "learning_rate": 3.086582838174551e-05, |
| "loss": 2.0842, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.0027306084136871746, |
| "grad_norm": 3.684279441833496, |
| "learning_rate": 1.4644660940672627e-05, |
| "loss": 2.4791, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0027306084136871746, |
| "eval_loss": 2.390902280807495, |
| "eval_runtime": 186.2961, |
| "eval_samples_per_second": 33.109, |
| "eval_steps_per_second": 16.554, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.0030719344653980713, |
| "grad_norm": 3.342024087905884, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 2.3955, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.0034132605171089685, |
| "grad_norm": 3.112165927886963, |
| "learning_rate": 0.0, |
| "loss": 2.4418, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0034132605171089685, |
| "eval_loss": 2.384955406188965, |
| "eval_runtime": 186.5009, |
| "eval_samples_per_second": 33.072, |
| "eval_steps_per_second": 16.536, |
| "step": 50 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 13, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1278959891251200.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
