| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.13531799729364005, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027063599458728013, | |
| "eval_loss": 1.4137221574783325, | |
| "eval_runtime": 7.5249, | |
| "eval_samples_per_second": 20.731, | |
| "eval_steps_per_second": 10.366, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013531799729364006, | |
| "grad_norm": 0.28464218974113464, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4182, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02706359945872801, | |
| "grad_norm": 0.321644127368927, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3545, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02706359945872801, | |
| "eval_loss": 1.3843153715133667, | |
| "eval_runtime": 7.5771, | |
| "eval_samples_per_second": 20.588, | |
| "eval_steps_per_second": 10.294, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04059539918809202, | |
| "grad_norm": 0.4265204966068268, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3519, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05412719891745602, | |
| "grad_norm": 0.5590308904647827, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4073, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05412719891745602, | |
| "eval_loss": 1.296107530593872, | |
| "eval_runtime": 7.5375, | |
| "eval_samples_per_second": 20.696, | |
| "eval_steps_per_second": 10.348, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06765899864682003, | |
| "grad_norm": 0.48316705226898193, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.2226, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08119079837618404, | |
| "grad_norm": 0.4648173153400421, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2654, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08119079837618404, | |
| "eval_loss": 1.2512714862823486, | |
| "eval_runtime": 7.6186, | |
| "eval_samples_per_second": 20.476, | |
| "eval_steps_per_second": 10.238, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09472259810554803, | |
| "grad_norm": 0.5235780477523804, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2409, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10825439783491204, | |
| "grad_norm": 0.5214589834213257, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2773, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10825439783491204, | |
| "eval_loss": 1.2332532405853271, | |
| "eval_runtime": 7.5664, | |
| "eval_samples_per_second": 20.617, | |
| "eval_steps_per_second": 10.309, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12178619756427606, | |
| "grad_norm": 0.5683117508888245, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2716, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13531799729364005, | |
| "grad_norm": 0.47812074422836304, | |
| "learning_rate": 0.0, | |
| "loss": 1.2547, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13531799729364005, | |
| "eval_loss": 1.2298351526260376, | |
| "eval_runtime": 7.5132, | |
| "eval_samples_per_second": 20.763, | |
| "eval_steps_per_second": 10.382, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5432822405529600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |