| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.045238633793259445, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009047726758651889, | |
| "eval_loss": 2.064779758453369, | |
| "eval_runtime": 26.5978, | |
| "eval_samples_per_second": 17.52, | |
| "eval_steps_per_second": 8.76, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004523863379325944, | |
| "grad_norm": 0.862048327922821, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9389, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009047726758651889, | |
| "grad_norm": 1.0893000364303589, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1701, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009047726758651889, | |
| "eval_loss": 1.9893431663513184, | |
| "eval_runtime": 26.6634, | |
| "eval_samples_per_second": 17.477, | |
| "eval_steps_per_second": 8.739, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013571590137977834, | |
| "grad_norm": 1.2828798294067383, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.7962, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018095453517303777, | |
| "grad_norm": 1.6727559566497803, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8921, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.018095453517303777, | |
| "eval_loss": 1.8502036333084106, | |
| "eval_runtime": 26.7351, | |
| "eval_samples_per_second": 17.43, | |
| "eval_steps_per_second": 8.715, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022619316896629722, | |
| "grad_norm": 2.150460958480835, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.7503, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027143180275955667, | |
| "grad_norm": 1.8646595478057861, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8562, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027143180275955667, | |
| "eval_loss": 1.7833797931671143, | |
| "eval_runtime": 26.9697, | |
| "eval_samples_per_second": 17.279, | |
| "eval_steps_per_second": 8.639, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03166704365528161, | |
| "grad_norm": 1.6002821922302246, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.7892, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.036190907034607554, | |
| "grad_norm": 1.73232901096344, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7725, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.036190907034607554, | |
| "eval_loss": 1.7645617723464966, | |
| "eval_runtime": 26.8966, | |
| "eval_samples_per_second": 17.326, | |
| "eval_steps_per_second": 8.663, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.040714770413933496, | |
| "grad_norm": 1.872810959815979, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7943, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.045238633793259445, | |
| "grad_norm": 1.9267327785491943, | |
| "learning_rate": 0.0, | |
| "loss": 1.7084, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.045238633793259445, | |
| "eval_loss": 1.7611631155014038, | |
| "eval_runtime": 26.8268, | |
| "eval_samples_per_second": 17.371, | |
| "eval_steps_per_second": 8.685, | |
| "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": 5322281299476480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |