| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.806579693703914, | |
| "eval_steps": 500, | |
| "global_step": 12000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.28360748723766305, | |
| "grad_norm": 4.999021530151367, | |
| "learning_rate": 1.971639251276234e-05, | |
| "loss": 6.7525, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5672149744753261, | |
| "grad_norm": 8.877035140991211, | |
| "learning_rate": 1.9432785025524678e-05, | |
| "loss": 4.8633, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.8508224617129893, | |
| "grad_norm": 5.504563808441162, | |
| "learning_rate": 1.9149177538287012e-05, | |
| "loss": 4.7848, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_runtime": 39.1159, | |
| "eval_samples_per_second": 5.011, | |
| "eval_steps_per_second": 5.011, | |
| "step": 1763 | |
| }, | |
| { | |
| "epoch": 1.1344299489506522, | |
| "grad_norm": 4.3093953132629395, | |
| "learning_rate": 1.886557005104935e-05, | |
| "loss": 4.7304, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.4180374361883152, | |
| "grad_norm": 8.88564395904541, | |
| "learning_rate": 1.8581962563811688e-05, | |
| "loss": 4.7621, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.7016449234259783, | |
| "grad_norm": 4.924105644226074, | |
| "learning_rate": 1.8298355076574022e-05, | |
| "loss": 4.7163, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.9852524106636416, | |
| "grad_norm": 5.222480773925781, | |
| "learning_rate": 1.801474758933636e-05, | |
| "loss": 4.6234, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_runtime": 40.3571, | |
| "eval_samples_per_second": 4.857, | |
| "eval_steps_per_second": 4.857, | |
| "step": 3526 | |
| }, | |
| { | |
| "epoch": 2.2688598979013044, | |
| "grad_norm": 4.8733978271484375, | |
| "learning_rate": 1.7731140102098695e-05, | |
| "loss": 4.7049, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.552467385138968, | |
| "grad_norm": 5.571890830993652, | |
| "learning_rate": 1.7447532614861033e-05, | |
| "loss": 4.5987, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.8360748723766305, | |
| "grad_norm": 5.371450424194336, | |
| "learning_rate": 1.716392512762337e-05, | |
| "loss": 4.6503, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_runtime": 36.7471, | |
| "eval_samples_per_second": 5.334, | |
| "eval_steps_per_second": 5.334, | |
| "step": 5289 | |
| }, | |
| { | |
| "epoch": 3.119682359614294, | |
| "grad_norm": 6.941244602203369, | |
| "learning_rate": 1.688031764038571e-05, | |
| "loss": 4.7147, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 3.403289846851957, | |
| "grad_norm": 7.103884220123291, | |
| "learning_rate": 1.6596710153148043e-05, | |
| "loss": 4.6078, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.68689733408962, | |
| "grad_norm": 6.286114692687988, | |
| "learning_rate": 1.631310266591038e-05, | |
| "loss": 4.6098, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.970504821327283, | |
| "grad_norm": 11.397751808166504, | |
| "learning_rate": 1.602949517867272e-05, | |
| "loss": 4.583, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_runtime": 39.4552, | |
| "eval_samples_per_second": 4.968, | |
| "eval_steps_per_second": 4.968, | |
| "step": 7052 | |
| }, | |
| { | |
| "epoch": 4.254112308564946, | |
| "grad_norm": 6.588546276092529, | |
| "learning_rate": 1.5745887691435057e-05, | |
| "loss": 4.6439, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 4.537719795802609, | |
| "grad_norm": 6.508044719696045, | |
| "learning_rate": 1.546228020419739e-05, | |
| "loss": 4.5772, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.821327283040272, | |
| "grad_norm": 13.856376647949219, | |
| "learning_rate": 1.5178672716959728e-05, | |
| "loss": 4.5647, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_runtime": 37.0746, | |
| "eval_samples_per_second": 5.287, | |
| "eval_steps_per_second": 5.287, | |
| "step": 8815 | |
| }, | |
| { | |
| "epoch": 5.104934770277936, | |
| "grad_norm": 11.172317504882812, | |
| "learning_rate": 1.4895065229722066e-05, | |
| "loss": 4.6058, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 5.388542257515598, | |
| "grad_norm": 9.843143463134766, | |
| "learning_rate": 1.4611457742484402e-05, | |
| "loss": 4.5818, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 5.672149744753262, | |
| "grad_norm": 6.524191856384277, | |
| "learning_rate": 1.432785025524674e-05, | |
| "loss": 4.5783, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 5.955757231990924, | |
| "grad_norm": 13.230880737304688, | |
| "learning_rate": 1.4044242768009078e-05, | |
| "loss": 4.527, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_runtime": 39.9935, | |
| "eval_samples_per_second": 4.901, | |
| "eval_steps_per_second": 4.901, | |
| "step": 10578 | |
| }, | |
| { | |
| "epoch": 6.239364719228588, | |
| "grad_norm": 10.95142936706543, | |
| "learning_rate": 1.3760635280771412e-05, | |
| "loss": 4.5873, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 6.5229722064662505, | |
| "grad_norm": 7.862865924835205, | |
| "learning_rate": 1.347702779353375e-05, | |
| "loss": 4.5154, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 6.806579693703914, | |
| "grad_norm": 7.10567045211792, | |
| "learning_rate": 1.3193420306296087e-05, | |
| "loss": 4.5425, | |
| "step": 12000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 35260, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.43730149801984e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |