| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.7611940298507462, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": 0.05495734512805939, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6818, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 0.052561622112989426, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7122, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 0.06833003461360931, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6803, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 0.04182825982570648, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7165, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.04483667016029358, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7222, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 0.06029865890741348, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 1.7201, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.417910447761194, | |
| "grad_norm": 0.0529303252696991, | |
| "learning_rate": 0.0001968583161128631, | |
| "loss": 1.6792, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 0.043452031910419464, | |
| "learning_rate": 0.00019297764858882514, | |
| "loss": 1.7168, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "grad_norm": 0.054760657250881195, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 1.6322, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.030201369896531105, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.6522, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6567164179104478, | |
| "grad_norm": 0.029813148081302643, | |
| "learning_rate": 0.00017289686274214118, | |
| "loss": 1.6651, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 0.03090563230216503, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 1.6628, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7761194029850746, | |
| "grad_norm": 0.029010523110628128, | |
| "learning_rate": 0.00015358267949789966, | |
| "loss": 1.621, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.835820895522388, | |
| "grad_norm": 0.030593572184443474, | |
| "learning_rate": 0.00014257792915650728, | |
| "loss": 1.6541, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8955223880597015, | |
| "grad_norm": 0.03024781309068203, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.6372, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9552238805970149, | |
| "grad_norm": 0.029992835596203804, | |
| "learning_rate": 0.00011873813145857249, | |
| "loss": 1.6062, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0149253731343284, | |
| "grad_norm": 0.02901672199368477, | |
| "learning_rate": 0.00010627905195293135, | |
| "loss": 1.5861, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.044776119402985, | |
| "grad_norm": 0.028797345235943794, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 1.6102, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1044776119402986, | |
| "grad_norm": 0.02690853551030159, | |
| "learning_rate": 8.126186854142752e-05, | |
| "loss": 1.6044, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.164179104477612, | |
| "grad_norm": 0.027849391102790833, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.6151, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2238805970149254, | |
| "grad_norm": 0.027856728062033653, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 1.6182, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2835820895522387, | |
| "grad_norm": 0.02708267979323864, | |
| "learning_rate": 4.6417320502100316e-05, | |
| "loss": 1.5595, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3432835820895521, | |
| "grad_norm": 0.025661876425147057, | |
| "learning_rate": 3.6257601025131026e-05, | |
| "loss": 1.6033, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.4029850746268657, | |
| "grad_norm": 0.027525661513209343, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 1.5768, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.462686567164179, | |
| "grad_norm": 0.028624940663576126, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.6284, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.5223880597014925, | |
| "grad_norm": 0.02710120566189289, | |
| "learning_rate": 1.2369331995613665e-05, | |
| "loss": 1.5989, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.582089552238806, | |
| "grad_norm": 0.027335483580827713, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 1.5608, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.6417910447761193, | |
| "grad_norm": 0.02575034461915493, | |
| "learning_rate": 3.1416838871368924e-06, | |
| "loss": 1.5661, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.7014925373134329, | |
| "grad_norm": 0.025826627388596535, | |
| "learning_rate": 7.885298685522235e-07, | |
| "loss": 1.5514, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7611940298507462, | |
| "grad_norm": 0.02626100741326809, | |
| "learning_rate": 0.0, | |
| "loss": 1.5588, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5777468946317312e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |