| { |
| "best_metric": 0.736162006855011, |
| "best_model_checkpoint": "/content/drive/MyDrive/Fine-Tuned_Model3/checkpoint-120", |
| "epoch": 30.0, |
| "eval_steps": 20, |
| "global_step": 120, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 5.0, |
| "learning_rate": 6.25e-05, |
| "loss": 3.2255, |
| "step": 20 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.512, |
| "eval_f1": 0.30833289169267614, |
| "eval_loss": 1.9573944807052612, |
| "eval_runtime": 43.495, |
| "eval_samples_per_second": 2.874, |
| "eval_steps_per_second": 0.368, |
| "step": 20 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 8.535533905932738e-05, |
| "loss": 1.3773, |
| "step": 40 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.584, |
| "eval_f1": 0.46169772256728775, |
| "eval_loss": 0.8853923678398132, |
| "eval_runtime": 43.5002, |
| "eval_samples_per_second": 2.874, |
| "eval_steps_per_second": 0.368, |
| "step": 40 |
| }, |
| { |
| "epoch": 15.0, |
| "learning_rate": 3.8060233744356633e-06, |
| "loss": 0.869, |
| "step": 60 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_accuracy": 0.608, |
| "eval_f1": 0.4795432331237958, |
| "eval_loss": 0.7879514098167419, |
| "eval_runtime": 43.7619, |
| "eval_samples_per_second": 2.856, |
| "eval_steps_per_second": 0.366, |
| "step": 60 |
| }, |
| { |
| "epoch": 20.0, |
| "learning_rate": 4.999999999999999e-05, |
| "loss": 0.7966, |
| "step": 80 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_accuracy": 0.6, |
| "eval_f1": 0.4846140574401444, |
| "eval_loss": 0.7732068300247192, |
| "eval_runtime": 43.5459, |
| "eval_samples_per_second": 2.871, |
| "eval_steps_per_second": 0.367, |
| "step": 80 |
| }, |
| { |
| "epoch": 25.0, |
| "learning_rate": 9.619397662556435e-05, |
| "loss": 0.8458, |
| "step": 100 |
| }, |
| { |
| "epoch": 25.0, |
| "eval_accuracy": 0.576, |
| "eval_f1": 0.4111637823594345, |
| "eval_loss": 0.7794835567474365, |
| "eval_runtime": 43.6082, |
| "eval_samples_per_second": 2.866, |
| "eval_steps_per_second": 0.367, |
| "step": 100 |
| }, |
| { |
| "epoch": 30.0, |
| "learning_rate": 1.4644660940672666e-05, |
| "loss": 0.8135, |
| "step": 120 |
| }, |
| { |
| "epoch": 30.0, |
| "eval_accuracy": 0.608, |
| "eval_f1": 0.5096170704866357, |
| "eval_loss": 0.736162006855011, |
| "eval_runtime": 43.4882, |
| "eval_samples_per_second": 2.874, |
| "eval_steps_per_second": 0.368, |
| "step": 120 |
| }, |
| { |
| "epoch": 30.0, |
| "step": 120, |
| "total_flos": 2.907095595264e+17, |
| "train_loss": 1.321283253033956, |
| "train_runtime": 2416.2795, |
| "train_samples_per_second": 1.552, |
| "train_steps_per_second": 0.05 |
| } |
| ], |
| "logging_steps": 20, |
| "max_steps": 120, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 30, |
| "save_steps": 20, |
| "total_flos": 2.907095595264e+17, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
