| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008398068444257821, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000839806844425782, | |
| "grad_norm": 0.6686991453170776, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9571, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000839806844425782, | |
| "eval_loss": 0.9189421534538269, | |
| "eval_runtime": 31.43, | |
| "eval_samples_per_second": 15.972, | |
| "eval_steps_per_second": 7.986, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001679613688851564, | |
| "grad_norm": 0.7383980751037598, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9637, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0025194205332773464, | |
| "grad_norm": 0.691645622253418, | |
| "learning_rate": 6e-05, | |
| "loss": 0.915, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025194205332773464, | |
| "eval_loss": 0.9044798612594604, | |
| "eval_runtime": 31.4757, | |
| "eval_samples_per_second": 15.949, | |
| "eval_steps_per_second": 7.974, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003359227377703128, | |
| "grad_norm": 0.6957189440727234, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9805, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004199034222128911, | |
| "grad_norm": 0.7422357797622681, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8764, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005038841066554693, | |
| "grad_norm": 0.6519572138786316, | |
| "learning_rate": 0.00012, | |
| "loss": 0.8963, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005038841066554693, | |
| "eval_loss": 0.7828396558761597, | |
| "eval_runtime": 31.5287, | |
| "eval_samples_per_second": 15.922, | |
| "eval_steps_per_second": 7.961, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005878647910980474, | |
| "grad_norm": 0.6797656416893005, | |
| "learning_rate": 0.00014, | |
| "loss": 0.7593, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006718454755406256, | |
| "grad_norm": 0.7729480862617493, | |
| "learning_rate": 0.00016, | |
| "loss": 0.7399, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007558261599832038, | |
| "grad_norm": 0.8539050817489624, | |
| "learning_rate": 0.00018, | |
| "loss": 0.6934, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007558261599832038, | |
| "eval_loss": 0.6700757741928101, | |
| "eval_runtime": 31.4993, | |
| "eval_samples_per_second": 15.937, | |
| "eval_steps_per_second": 7.968, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008398068444257821, | |
| "grad_norm": 0.9188011288642883, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6829, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3822182832537600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |