| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006816864923821535, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00013633729847643068, | |
| "eval_loss": 1.9493560791015625, | |
| "eval_runtime": 105.7257, | |
| "eval_samples_per_second": 29.217, | |
| "eval_steps_per_second": 14.613, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006816864923821534, | |
| "grad_norm": 0.7078530788421631, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9136, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013633729847643068, | |
| "grad_norm": 0.6613458395004272, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8295, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0013633729847643068, | |
| "eval_loss": 1.932807445526123, | |
| "eval_runtime": 106.4571, | |
| "eval_samples_per_second": 29.016, | |
| "eval_steps_per_second": 14.513, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0020450594771464605, | |
| "grad_norm": 0.9104695320129395, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.8042, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0027267459695286137, | |
| "grad_norm": 0.7825496792793274, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8319, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0027267459695286137, | |
| "eval_loss": 1.8885176181793213, | |
| "eval_runtime": 106.6603, | |
| "eval_samples_per_second": 28.961, | |
| "eval_steps_per_second": 14.485, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0034084324619107673, | |
| "grad_norm": 1.0567548274993896, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.879, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004090118954292921, | |
| "grad_norm": 0.6737384796142578, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8927, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004090118954292921, | |
| "eval_loss": 1.8680771589279175, | |
| "eval_runtime": 106.7241, | |
| "eval_samples_per_second": 28.944, | |
| "eval_steps_per_second": 14.477, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004771805446675074, | |
| "grad_norm": 0.7276881337165833, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.7511, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005453491939057227, | |
| "grad_norm": 0.7873528599739075, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.867, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005453491939057227, | |
| "eval_loss": 1.862397313117981, | |
| "eval_runtime": 106.5274, | |
| "eval_samples_per_second": 28.997, | |
| "eval_steps_per_second": 14.503, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006135178431439381, | |
| "grad_norm": 0.9941609501838684, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.765, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006816864923821535, | |
| "grad_norm": 0.7951815128326416, | |
| "learning_rate": 0.0, | |
| "loss": 1.953, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006816864923821535, | |
| "eval_loss": 1.8610470294952393, | |
| "eval_runtime": 106.8155, | |
| "eval_samples_per_second": 28.919, | |
| "eval_steps_per_second": 14.464, | |
| "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": 2068691432767488.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |