| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 626, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1597444089456869, |
| "grad_norm": 3.102206230163574, |
| "learning_rate": 2.4000000000000003e-06, |
| "loss": 0.8333, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3194888178913738, |
| "grad_norm": 2.281259298324585, |
| "learning_rate": 4.9000000000000005e-06, |
| "loss": 0.5443, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4792332268370607, |
| "grad_norm": 3.091155767440796, |
| "learning_rate": 7.4e-06, |
| "loss": 0.3887, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.6389776357827476, |
| "grad_norm": 2.561985969543457, |
| "learning_rate": 9.9e-06, |
| "loss": 0.292, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.7987220447284346, |
| "grad_norm": 3.2992053031921387, |
| "learning_rate": 8.87323943661972e-06, |
| "loss": 0.228, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.9584664536741214, |
| "grad_norm": 5.076635837554932, |
| "learning_rate": 7.699530516431926e-06, |
| "loss": 0.2053, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.1182108626198084, |
| "grad_norm": 2.2927370071411133, |
| "learning_rate": 6.525821596244132e-06, |
| "loss": 0.1873, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.2779552715654952, |
| "grad_norm": 2.024038314819336, |
| "learning_rate": 5.352112676056338e-06, |
| "loss": 0.1636, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.4376996805111821, |
| "grad_norm": 6.6107401847839355, |
| "learning_rate": 4.178403755868545e-06, |
| "loss": 0.152, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.5974440894568689, |
| "grad_norm": 1.735270619392395, |
| "learning_rate": 3.0046948356807513e-06, |
| "loss": 0.1634, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.7571884984025559, |
| "grad_norm": 1.976096749305725, |
| "learning_rate": 1.8309859154929579e-06, |
| "loss": 0.1567, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.9169329073482428, |
| "grad_norm": 1.8631360530853271, |
| "learning_rate": 6.572769953051644e-07, |
| "loss": 0.1537, |
| "step": 600 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 626, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 1306507376640000.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
