| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.01870732391731363, |
| "eval_steps": 200, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0023384154896642037, |
| "grad_norm": 1.9981695413589478, |
| "learning_rate": 4.4859813084112145e-06, |
| "loss": 0.47716766357421875, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.004676830979328407, |
| "grad_norm": 1.9483280181884766, |
| "learning_rate": 9.158878504672897e-06, |
| "loss": 0.4592530059814453, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0070152464689926105, |
| "grad_norm": 2.1290855407714844, |
| "learning_rate": 1.3831775700934579e-05, |
| "loss": 0.394501838684082, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.009353661958656815, |
| "grad_norm": 2.8394205570220947, |
| "learning_rate": 1.8504672897196264e-05, |
| "loss": 0.3752219009399414, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.011692077448321018, |
| "grad_norm": 2.5833706855773926, |
| "learning_rate": 2.3177570093457944e-05, |
| "loss": 0.40475303649902344, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.014030492937985221, |
| "grad_norm": 2.622011661529541, |
| "learning_rate": 2.7850467289719627e-05, |
| "loss": 0.45625301361083986, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.016368908427649424, |
| "grad_norm": 2.9406535625457764, |
| "learning_rate": 3.2523364485981314e-05, |
| "loss": 0.34918937683105467, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.01870732391731363, |
| "grad_norm": 3.8391785621643066, |
| "learning_rate": 3.7196261682242994e-05, |
| "loss": 0.41711517333984377, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.01870732391731363, |
| "eval_pairs_with_negatives_loss": 0.3914637565612793, |
| "eval_pairs_with_negatives_runtime": 44.0353, |
| "eval_pairs_with_negatives_samples_per_second": 28.523, |
| "eval_pairs_with_negatives_steps_per_second": 3.565, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.01870732391731363, |
| "eval_positives_loss": 0.1480681300163269, |
| "eval_positives_runtime": 51.7193, |
| "eval_positives_samples_per_second": 42.537, |
| "eval_positives_steps_per_second": 5.317, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 10691, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
