| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.00041734485205124997, |
| "eval_steps": 500, |
| "global_step": 30, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.3911495068374998e-05, |
| "grad_norm": 68.36048889160156, |
| "learning_rate": 0.0, |
| "loss": 18.5386, |
| "step": 1 |
| }, |
| { |
| "epoch": 2.7822990136749997e-05, |
| "grad_norm": 71.29923248291016, |
| "learning_rate": 4e-05, |
| "loss": 17.6841, |
| "step": 2 |
| }, |
| { |
| "epoch": 4.1734485205125e-05, |
| "grad_norm": 75.4001693725586, |
| "learning_rate": 8e-05, |
| "loss": 19.0986, |
| "step": 3 |
| }, |
| { |
| "epoch": 5.5645980273499994e-05, |
| "grad_norm": 74.53475189208984, |
| "learning_rate": 0.00012, |
| "loss": 17.6713, |
| "step": 4 |
| }, |
| { |
| "epoch": 6.955747534187499e-05, |
| "grad_norm": 62.05671691894531, |
| "learning_rate": 0.00016, |
| "loss": 14.1331, |
| "step": 5 |
| }, |
| { |
| "epoch": 8.346897041025e-05, |
| "grad_norm": 64.3744888305664, |
| "learning_rate": 0.0002, |
| "loss": 10.9915, |
| "step": 6 |
| }, |
| { |
| "epoch": 9.738046547862498e-05, |
| "grad_norm": 79.88032531738281, |
| "learning_rate": 0.000192, |
| "loss": 6.3303, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.00011129196054699999, |
| "grad_norm": 33.379764556884766, |
| "learning_rate": 0.00018400000000000003, |
| "loss": 2.7904, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.000125203455615375, |
| "grad_norm": 15.933351516723633, |
| "learning_rate": 0.00017600000000000002, |
| "loss": 1.9766, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.00013911495068374998, |
| "grad_norm": 4.526773929595947, |
| "learning_rate": 0.000168, |
| "loss": 0.9661, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.00015302644575212497, |
| "grad_norm": 1.9286530017852783, |
| "learning_rate": 0.00016, |
| "loss": 0.7805, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.0001669379408205, |
| "grad_norm": 1.0767860412597656, |
| "learning_rate": 0.000152, |
| "loss": 0.9457, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.00018084943588887498, |
| "grad_norm": 0.9176913499832153, |
| "learning_rate": 0.000144, |
| "loss": 0.6094, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.00019476093095724997, |
| "grad_norm": 0.8865966200828552, |
| "learning_rate": 0.00013600000000000003, |
| "loss": 0.5635, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.00020867242602562499, |
| "grad_norm": 0.8140920400619507, |
| "learning_rate": 0.00012800000000000002, |
| "loss": 0.6797, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.00022258392109399998, |
| "grad_norm": 1.4326921701431274, |
| "learning_rate": 0.00012, |
| "loss": 0.8631, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.00023649541616237497, |
| "grad_norm": 0.8285752534866333, |
| "learning_rate": 0.00011200000000000001, |
| "loss": 0.5675, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.00025040691123075, |
| "grad_norm": 1.2299859523773193, |
| "learning_rate": 0.00010400000000000001, |
| "loss": 1.1321, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.00026431840629912497, |
| "grad_norm": 0.9245197176933289, |
| "learning_rate": 9.6e-05, |
| "loss": 1.0017, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.00027822990136749996, |
| "grad_norm": 1.1311694383621216, |
| "learning_rate": 8.800000000000001e-05, |
| "loss": 0.9173, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.00029214139643587495, |
| "grad_norm": 1.061496615409851, |
| "learning_rate": 8e-05, |
| "loss": 0.696, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.00030605289150424994, |
| "grad_norm": 0.5580381155014038, |
| "learning_rate": 7.2e-05, |
| "loss": 0.3912, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.000319964386572625, |
| "grad_norm": 0.6166224479675293, |
| "learning_rate": 6.400000000000001e-05, |
| "loss": 0.6241, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.000333875881641, |
| "grad_norm": 0.590518593788147, |
| "learning_rate": 5.6000000000000006e-05, |
| "loss": 0.602, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.00034778737670937497, |
| "grad_norm": 0.6541720032691956, |
| "learning_rate": 4.8e-05, |
| "loss": 0.6138, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.00036169887177774996, |
| "grad_norm": 0.5166042447090149, |
| "learning_rate": 4e-05, |
| "loss": 0.4645, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.00037561036684612495, |
| "grad_norm": 0.6018291711807251, |
| "learning_rate": 3.2000000000000005e-05, |
| "loss": 0.5399, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.00038952186191449994, |
| "grad_norm": 0.8229033350944519, |
| "learning_rate": 2.4e-05, |
| "loss": 0.7849, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.0004034333569828749, |
| "grad_norm": 0.8277194499969482, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 1.1107, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.00041734485205124997, |
| "grad_norm": 0.5916028022766113, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.5184, |
| "step": 30 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 30, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 7059632839676928.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
