| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05383580080753701, | |
| "eval_steps": 4, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026917900403768506, | |
| "grad_norm": 2.0982859134674072, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7376, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026917900403768506, | |
| "eval_loss": 0.7193137407302856, | |
| "eval_runtime": 10.1138, | |
| "eval_samples_per_second": 7.811, | |
| "eval_steps_per_second": 7.811, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005383580080753701, | |
| "grad_norm": 2.031587839126587, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7275, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008075370121130552, | |
| "grad_norm": 2.1216890811920166, | |
| "learning_rate": 6e-05, | |
| "loss": 0.6912, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010767160161507403, | |
| "grad_norm": 1.755471110343933, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6835, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010767160161507403, | |
| "eval_loss": 0.6272252202033997, | |
| "eval_runtime": 10.0256, | |
| "eval_samples_per_second": 7.88, | |
| "eval_steps_per_second": 7.88, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013458950201884253, | |
| "grad_norm": 1.9561946392059326, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7364, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016150740242261104, | |
| "grad_norm": 1.8313077688217163, | |
| "learning_rate": 0.00012, | |
| "loss": 0.6385, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018842530282637954, | |
| "grad_norm": 1.4374486207962036, | |
| "learning_rate": 0.00014, | |
| "loss": 0.4741, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.021534320323014805, | |
| "grad_norm": 1.279863715171814, | |
| "learning_rate": 0.00016, | |
| "loss": 0.3742, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.021534320323014805, | |
| "eval_loss": 0.3805864155292511, | |
| "eval_runtime": 10.1128, | |
| "eval_samples_per_second": 7.812, | |
| "eval_steps_per_second": 7.812, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024226110363391656, | |
| "grad_norm": 1.7297841310501099, | |
| "learning_rate": 0.00018, | |
| "loss": 0.3654, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026917900403768506, | |
| "grad_norm": 1.6552913188934326, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3738, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029609690444145357, | |
| "grad_norm": 1.50761079788208, | |
| "learning_rate": 0.0001996917333733128, | |
| "loss": 0.4244, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03230148048452221, | |
| "grad_norm": 1.431064248085022, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 0.2788, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03230148048452221, | |
| "eval_loss": 0.32530486583709717, | |
| "eval_runtime": 10.0708, | |
| "eval_samples_per_second": 7.844, | |
| "eval_steps_per_second": 7.844, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.034993270524899055, | |
| "grad_norm": 1.4582064151763916, | |
| "learning_rate": 0.00019723699203976766, | |
| "loss": 0.3575, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03768506056527591, | |
| "grad_norm": 1.6408145427703857, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.4609, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.040376850605652756, | |
| "grad_norm": 1.7364938259124756, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.4607, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04306864064602961, | |
| "grad_norm": 2.5827343463897705, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 0.5915, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04306864064602961, | |
| "eval_loss": 0.29014351963996887, | |
| "eval_runtime": 10.1162, | |
| "eval_samples_per_second": 7.809, | |
| "eval_steps_per_second": 7.809, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04576043068640646, | |
| "grad_norm": 1.0929858684539795, | |
| "learning_rate": 0.00018526401643540922, | |
| "loss": 0.2242, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04845222072678331, | |
| "grad_norm": 1.4121438264846802, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.2983, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05114401076716016, | |
| "grad_norm": 0.9734262824058533, | |
| "learning_rate": 0.0001760405965600031, | |
| "loss": 0.3084, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05383580080753701, | |
| "grad_norm": 0.9649080038070679, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.2583, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05383580080753701, | |
| "eval_loss": 0.28261926770210266, | |
| "eval_runtime": 10.3045, | |
| "eval_samples_per_second": 7.667, | |
| "eval_steps_per_second": 7.667, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8068024208719872.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |