| { |
| "best_metric": 0.8650159744408946, |
| "best_model_checkpoint": "../../modelParams/TrainingArguments_output/checkpoint-352", |
| "epoch": 9.968051118210862, |
| "eval_steps": 500, |
| "global_step": 390, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9968051118210862, |
| "eval_accuracy": 0.6285942492012779, |
| "eval_loss": 0.8213106393814087, |
| "eval_runtime": 33.1234, |
| "eval_samples_per_second": 37.798, |
| "eval_steps_per_second": 4.74, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.9936102236421727, |
| "eval_accuracy": 0.731629392971246, |
| "eval_loss": 0.6166290044784546, |
| "eval_runtime": 33.1358, |
| "eval_samples_per_second": 37.784, |
| "eval_steps_per_second": 4.738, |
| "step": 78 |
| }, |
| { |
| "epoch": 2.9904153354632586, |
| "eval_accuracy": 0.7779552715654952, |
| "eval_loss": 0.5423839688301086, |
| "eval_runtime": 33.1772, |
| "eval_samples_per_second": 37.737, |
| "eval_steps_per_second": 4.732, |
| "step": 117 |
| }, |
| { |
| "epoch": 3.987220447284345, |
| "eval_accuracy": 0.7899361022364217, |
| "eval_loss": 0.5209566354751587, |
| "eval_runtime": 33.2273, |
| "eval_samples_per_second": 37.68, |
| "eval_steps_per_second": 4.725, |
| "step": 156 |
| }, |
| { |
| "epoch": 4.984025559105431, |
| "eval_accuracy": 0.8170926517571885, |
| "eval_loss": 0.4626227915287018, |
| "eval_runtime": 33.1556, |
| "eval_samples_per_second": 37.761, |
| "eval_steps_per_second": 4.735, |
| "step": 195 |
| }, |
| { |
| "epoch": 5.980830670926517, |
| "eval_accuracy": 0.8298722044728435, |
| "eval_loss": 0.45184266567230225, |
| "eval_runtime": 33.1468, |
| "eval_samples_per_second": 37.771, |
| "eval_steps_per_second": 4.737, |
| "step": 234 |
| }, |
| { |
| "epoch": 6.977635782747604, |
| "eval_accuracy": 0.854632587859425, |
| "eval_loss": 0.41386544704437256, |
| "eval_runtime": 33.2519, |
| "eval_samples_per_second": 37.652, |
| "eval_steps_per_second": 4.722, |
| "step": 273 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8554313099041534, |
| "eval_loss": 0.41130325198173523, |
| "eval_runtime": 33.3018, |
| "eval_samples_per_second": 37.596, |
| "eval_steps_per_second": 4.714, |
| "step": 313 |
| }, |
| { |
| "epoch": 8.996805111821086, |
| "eval_accuracy": 0.8650159744408946, |
| "eval_loss": 0.396475613117218, |
| "eval_runtime": 33.2277, |
| "eval_samples_per_second": 37.679, |
| "eval_steps_per_second": 4.725, |
| "step": 352 |
| }, |
| { |
| "epoch": 9.968051118210862, |
| "eval_accuracy": 0.8626198083067093, |
| "eval_loss": 0.4048398733139038, |
| "eval_runtime": 33.3472, |
| "eval_samples_per_second": 37.544, |
| "eval_steps_per_second": 4.708, |
| "step": 390 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 390, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.316604448413917e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
