| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005260504570063345, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.7535015233544485e-05, | |
| "eval_loss": 3.3408658504486084, | |
| "eval_runtime": 2045.3867, | |
| "eval_samples_per_second": 11.74, | |
| "eval_steps_per_second": 5.87, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.260504570063345e-05, | |
| "grad_norm": 1.5817010402679443, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4312, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001052100914012669, | |
| "grad_norm": 1.8071105480194092, | |
| "learning_rate": 0.00012, | |
| "loss": 3.2441, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00014028012186835588, | |
| "eval_loss": 2.9393482208251953, | |
| "eval_runtime": 2053.896, | |
| "eval_samples_per_second": 11.691, | |
| "eval_steps_per_second": 5.846, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00015781513710190037, | |
| "grad_norm": 1.914255976676941, | |
| "learning_rate": 0.00018, | |
| "loss": 2.8462, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002104201828025338, | |
| "grad_norm": 1.7149313688278198, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.6854, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00026302522850316724, | |
| "grad_norm": 1.5628223419189453, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.9379, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00028056024373671176, | |
| "eval_loss": 2.7104389667510986, | |
| "eval_runtime": 2054.0791, | |
| "eval_samples_per_second": 11.69, | |
| "eval_steps_per_second": 5.845, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00031563027420380074, | |
| "grad_norm": 1.5255248546600342, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.6268, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0003682353199044342, | |
| "grad_norm": 1.3287110328674316, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.8136, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0004208403656050676, | |
| "grad_norm": 1.2561800479888916, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.6873, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0004208403656050676, | |
| "eval_loss": 2.6514663696289062, | |
| "eval_runtime": 2054.3228, | |
| "eval_samples_per_second": 11.689, | |
| "eval_steps_per_second": 5.845, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00047344541130570105, | |
| "grad_norm": 1.3759137392044067, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.6437, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0005260504570063345, | |
| "grad_norm": 1.3066251277923584, | |
| "learning_rate": 0.0, | |
| "loss": 2.4955, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |