| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03537944454272068, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007075888908544136, | |
| "eval_loss": 10.552796363830566, | |
| "eval_runtime": 47.6423, | |
| "eval_samples_per_second": 12.489, | |
| "eval_steps_per_second": 6.255, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0035379444542720678, | |
| "grad_norm": 26.04566192626953, | |
| "learning_rate": 5e-05, | |
| "loss": 10.6868, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0070758889085441356, | |
| "grad_norm": 25.12905502319336, | |
| "learning_rate": 0.0001, | |
| "loss": 7.7325, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0070758889085441356, | |
| "eval_loss": 4.372666835784912, | |
| "eval_runtime": 47.9791, | |
| "eval_samples_per_second": 12.401, | |
| "eval_steps_per_second": 6.211, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010613833362816204, | |
| "grad_norm": 26.672901153564453, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.7413, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014151777817088271, | |
| "grad_norm": 11.739270210266113, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4716, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014151777817088271, | |
| "eval_loss": 0.4289584755897522, | |
| "eval_runtime": 47.8845, | |
| "eval_samples_per_second": 12.426, | |
| "eval_steps_per_second": 6.223, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01768972227136034, | |
| "grad_norm": 5.6261467933654785, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3967, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.021227666725632408, | |
| "grad_norm": 7.217609405517578, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2675, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.021227666725632408, | |
| "eval_loss": 0.19041143357753754, | |
| "eval_runtime": 47.9386, | |
| "eval_samples_per_second": 12.412, | |
| "eval_steps_per_second": 6.216, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.024765611179904477, | |
| "grad_norm": 2.8961856365203857, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2384, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.028303555634176542, | |
| "grad_norm": 12.801621437072754, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2437, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028303555634176542, | |
| "eval_loss": 0.1584031879901886, | |
| "eval_runtime": 48.0401, | |
| "eval_samples_per_second": 12.385, | |
| "eval_steps_per_second": 6.203, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03184150008844861, | |
| "grad_norm": 5.449904441833496, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1927, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03537944454272068, | |
| "grad_norm": 7.277150630950928, | |
| "learning_rate": 0.0, | |
| "loss": 0.2981, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03537944454272068, | |
| "eval_loss": 0.13875603675842285, | |
| "eval_runtime": 47.7713, | |
| "eval_samples_per_second": 12.455, | |
| "eval_steps_per_second": 6.238, | |
| "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": 9555457081344000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |