| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18298261665141813, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036596523330283625, | |
| "eval_loss": 6.844988822937012, | |
| "eval_runtime": 6.9069, | |
| "eval_samples_per_second": 16.65, | |
| "eval_steps_per_second": 8.397, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018298261665141813, | |
| "grad_norm": 11.751487731933594, | |
| "learning_rate": 5e-05, | |
| "loss": 6.8396, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.036596523330283626, | |
| "grad_norm": 8.099217414855957, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2657, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.036596523330283626, | |
| "eval_loss": 1.4936703443527222, | |
| "eval_runtime": 6.9534, | |
| "eval_samples_per_second": 16.539, | |
| "eval_steps_per_second": 8.341, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05489478499542543, | |
| "grad_norm": 2.1512739658355713, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9735, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07319304666056725, | |
| "grad_norm": 1.4982128143310547, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6925, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07319304666056725, | |
| "eval_loss": 0.7363909482955933, | |
| "eval_runtime": 6.9844, | |
| "eval_samples_per_second": 16.465, | |
| "eval_steps_per_second": 8.304, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09149130832570906, | |
| "grad_norm": 0.9344391822814941, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7451, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10978956999085086, | |
| "grad_norm": 1.2351694107055664, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6899, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10978956999085086, | |
| "eval_loss": 0.6869314908981323, | |
| "eval_runtime": 7.1682, | |
| "eval_samples_per_second": 16.043, | |
| "eval_steps_per_second": 8.091, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1280878316559927, | |
| "grad_norm": 1.4144127368927002, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6356, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1463860933211345, | |
| "grad_norm": 1.1237945556640625, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.631, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1463860933211345, | |
| "eval_loss": 0.6841559410095215, | |
| "eval_runtime": 7.1948, | |
| "eval_samples_per_second": 15.984, | |
| "eval_steps_per_second": 8.061, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16468435498627632, | |
| "grad_norm": 0.3947688043117523, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6806, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18298261665141813, | |
| "grad_norm": 1.5522825717926025, | |
| "learning_rate": 0.0, | |
| "loss": 0.7376, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18298261665141813, | |
| "eval_loss": 0.6734411120414734, | |
| "eval_runtime": 7.0017, | |
| "eval_samples_per_second": 16.425, | |
| "eval_steps_per_second": 8.284, | |
| "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": 8239114616832000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |