| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014138118542686243, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00036251586006887804, | |
| "eval_loss": 2.9616458415985107, | |
| "eval_runtime": 46.0997, | |
| "eval_samples_per_second": 25.206, | |
| "eval_steps_per_second": 12.603, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018125793003443901, | |
| "grad_norm": 0.7898205518722534, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0092, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036251586006887803, | |
| "grad_norm": 0.6784542202949524, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0097, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0036251586006887803, | |
| "eval_loss": 2.9095137119293213, | |
| "eval_runtime": 44.7952, | |
| "eval_samples_per_second": 25.94, | |
| "eval_steps_per_second": 12.97, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005437737901033171, | |
| "grad_norm": 0.6488664150238037, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.9522, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0072503172013775605, | |
| "grad_norm": 0.592515230178833, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.9618, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0072503172013775605, | |
| "eval_loss": 2.8583121299743652, | |
| "eval_runtime": 44.9692, | |
| "eval_samples_per_second": 25.84, | |
| "eval_steps_per_second": 12.92, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00906289650172195, | |
| "grad_norm": 0.697870135307312, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.8699, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010875475802066341, | |
| "grad_norm": 0.6746653318405151, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9307, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010875475802066341, | |
| "eval_loss": 2.8378565311431885, | |
| "eval_runtime": 44.849, | |
| "eval_samples_per_second": 25.909, | |
| "eval_steps_per_second": 12.955, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012688055102410731, | |
| "grad_norm": 0.6385213732719421, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.8624, | |
| "step": 35 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 678915999006720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |