| { |
| "best_metric": 0.7166203260421753, |
| "best_model_checkpoint": "./fine_tuned_model/checkpoint-60", |
| "epoch": 4.699801192842942, |
| "eval_steps": 5, |
| "global_step": 75, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.31809145129224653, |
| "eval_loss": 0.8427419066429138, |
| "eval_runtime": 3.6217, |
| "eval_samples_per_second": 17.119, |
| "eval_steps_per_second": 17.119, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.6361829025844931, |
| "eval_loss": 0.7870082855224609, |
| "eval_runtime": 3.6306, |
| "eval_samples_per_second": 17.077, |
| "eval_steps_per_second": 17.077, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.9542743538767395, |
| "eval_loss": 0.7365150451660156, |
| "eval_runtime": 3.6293, |
| "eval_samples_per_second": 17.083, |
| "eval_steps_per_second": 17.083, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.2544731610337971, |
| "eval_loss": 0.7298184633255005, |
| "eval_runtime": 3.6552, |
| "eval_samples_per_second": 16.962, |
| "eval_steps_per_second": 16.962, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.5725646123260437, |
| "grad_norm": 1968.0, |
| "learning_rate": 2e-06, |
| "loss": 26.0961, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.5725646123260437, |
| "eval_loss": 0.722483217716217, |
| "eval_runtime": 3.5805, |
| "eval_samples_per_second": 17.316, |
| "eval_steps_per_second": 17.316, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.8906560636182903, |
| "eval_loss": 0.7267560362815857, |
| "eval_runtime": 3.6543, |
| "eval_samples_per_second": 16.966, |
| "eval_steps_per_second": 16.966, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.1908548707753477, |
| "eval_loss": 0.72198885679245, |
| "eval_runtime": 3.6646, |
| "eval_samples_per_second": 16.919, |
| "eval_steps_per_second": 16.919, |
| "step": 35 |
| }, |
| { |
| "epoch": 2.5089463220675943, |
| "eval_loss": 0.7208355069160461, |
| "eval_runtime": 3.6385, |
| "eval_samples_per_second": 17.04, |
| "eval_steps_per_second": 17.04, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.827037773359841, |
| "eval_loss": 0.7194154262542725, |
| "eval_runtime": 3.6704, |
| "eval_samples_per_second": 16.892, |
| "eval_steps_per_second": 16.892, |
| "step": 45 |
| }, |
| { |
| "epoch": 3.1272365805168985, |
| "grad_norm": 1020.0, |
| "learning_rate": 1e-06, |
| "loss": 21.5636, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.1272365805168985, |
| "eval_loss": 0.7177529335021973, |
| "eval_runtime": 3.6163, |
| "eval_samples_per_second": 17.145, |
| "eval_steps_per_second": 17.145, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.445328031809145, |
| "eval_loss": 0.7173358798027039, |
| "eval_runtime": 3.6461, |
| "eval_samples_per_second": 17.004, |
| "eval_steps_per_second": 17.004, |
| "step": 55 |
| }, |
| { |
| "epoch": 3.7634194831013916, |
| "eval_loss": 0.7166203260421753, |
| "eval_runtime": 3.6673, |
| "eval_samples_per_second": 16.906, |
| "eval_steps_per_second": 16.906, |
| "step": 60 |
| }, |
| { |
| "epoch": 4.063618290258449, |
| "eval_loss": 0.7183635234832764, |
| "eval_runtime": 3.6456, |
| "eval_samples_per_second": 17.007, |
| "eval_steps_per_second": 17.007, |
| "step": 65 |
| }, |
| { |
| "epoch": 4.381709741550695, |
| "eval_loss": 0.718068540096283, |
| "eval_runtime": 3.6468, |
| "eval_samples_per_second": 17.001, |
| "eval_steps_per_second": 17.001, |
| "step": 70 |
| }, |
| { |
| "epoch": 4.699801192842942, |
| "grad_norm": 796.0, |
| "learning_rate": 0.0, |
| "loss": 21.5142, |
| "step": 75 |
| }, |
| { |
| "epoch": 4.699801192842942, |
| "eval_loss": 0.718126118183136, |
| "eval_runtime": 3.5679, |
| "eval_samples_per_second": 17.377, |
| "eval_steps_per_second": 17.377, |
| "step": 75 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 75, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.090067860731494e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
