| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 1000, |
| "global_step": 5515, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00018132366273798732, |
| "grad_norm": 7.9868855476379395, |
| "learning_rate": 0.0, |
| "loss": 3.5226, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.1813236627379873, |
| "grad_norm": 6.11737060546875, |
| "learning_rate": 7.2443799854967376e-06, |
| "loss": 2.9981, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.1813236627379873, |
| "eval_cosine_accuracy": 0.9449994564056396, |
| "eval_loss": 0.5478581190109253, |
| "eval_runtime": 34.6287, |
| "eval_samples_per_second": 274.599, |
| "eval_steps_per_second": 2.166, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.3626473254759746, |
| "grad_norm": 6.67965841293335, |
| "learning_rate": 9.763322644678577e-06, |
| "loss": 2.3124, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.3626473254759746, |
| "eval_cosine_accuracy": 0.9545693397521973, |
| "eval_loss": 0.495151549577713, |
| "eval_runtime": 34.4914, |
| "eval_samples_per_second": 275.692, |
| "eval_steps_per_second": 2.174, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.543970988213962, |
| "grad_norm": 7.58078145980835, |
| "learning_rate": 9.381966712475189e-06, |
| "loss": 1.974, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.543970988213962, |
| "eval_cosine_accuracy": 0.9580397605895996, |
| "eval_loss": 0.4687798023223877, |
| "eval_runtime": 35.422, |
| "eval_samples_per_second": 268.449, |
| "eval_steps_per_second": 2.117, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.7252946509519492, |
| "grad_norm": 11.277643203735352, |
| "learning_rate": 9.000229042601925e-06, |
| "loss": 1.4538, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.7252946509519492, |
| "eval_cosine_accuracy": 0.9532022476196289, |
| "eval_loss": 0.4629732668399811, |
| "eval_runtime": 35.494, |
| "eval_samples_per_second": 267.905, |
| "eval_steps_per_second": 2.113, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.9066183136899365, |
| "grad_norm": 9.13899040222168, |
| "learning_rate": 8.618873110398535e-06, |
| "loss": 1.0996, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.9066183136899365, |
| "eval_cosine_accuracy": 0.9505731463432312, |
| "eval_loss": 0.4556906819343567, |
| "eval_runtime": 35.5731, |
| "eval_samples_per_second": 267.309, |
| "eval_steps_per_second": 2.108, |
| "step": 5000 |
| } |
| ], |
| "logging_steps": 1000, |
| "max_steps": 27575, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "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": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
