| { |
| "best_metric": 0.564608097076416, |
| "best_model_checkpoint": "./beans_outputs/checkpoint-51", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 51, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5882352941176471, |
| "grad_norm": 1.342671275138855, |
| "learning_rate": 1.607843137254902e-05, |
| "loss": 0.9886, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.924812030075188, |
| "eval_loss": 0.7758036851882935, |
| "eval_runtime": 13.3932, |
| "eval_samples_per_second": 9.93, |
| "eval_steps_per_second": 0.224, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.1764705882352942, |
| "grad_norm": 1.2002716064453125, |
| "learning_rate": 1.215686274509804e-05, |
| "loss": 0.8266, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.7647058823529411, |
| "grad_norm": 1.1757010221481323, |
| "learning_rate": 8.23529411764706e-06, |
| "loss": 0.7226, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9548872180451128, |
| "eval_loss": 0.6197953820228577, |
| "eval_runtime": 12.3405, |
| "eval_samples_per_second": 10.778, |
| "eval_steps_per_second": 0.243, |
| "step": 34 |
| }, |
| { |
| "epoch": 2.3529411764705883, |
| "grad_norm": 1.2492908239364624, |
| "learning_rate": 4.313725490196079e-06, |
| "loss": 0.6423, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.9411764705882355, |
| "grad_norm": 1.134194254875183, |
| "learning_rate": 3.921568627450981e-07, |
| "loss": 0.6041, |
| "step": 50 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9699248120300752, |
| "eval_loss": 0.564608097076416, |
| "eval_runtime": 12.5805, |
| "eval_samples_per_second": 10.572, |
| "eval_steps_per_second": 0.238, |
| "step": 51 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 51, |
| "total_flos": 2.4038230623573197e+17, |
| "train_loss": 0.7542588278359058, |
| "train_runtime": 427.2792, |
| "train_samples_per_second": 7.26, |
| "train_steps_per_second": 0.119 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 51, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 2.4038230623573197e+17, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
