| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.8237082066869301, | |
| "eval_steps": 500, | |
| "global_step": 4800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.037993920972644375, | |
| "grad_norm": 0.5791582465171814, | |
| "learning_rate": 0.0004952982522796353, | |
| "loss": 1.9579, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07598784194528875, | |
| "grad_norm": 0.578816831111908, | |
| "learning_rate": 0.0004905490121580547, | |
| "loss": 1.5938, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11398176291793313, | |
| "grad_norm": 0.7128555774688721, | |
| "learning_rate": 0.00048579977203647417, | |
| "loss": 1.6012, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1519756838905775, | |
| "grad_norm": 0.5568099021911621, | |
| "learning_rate": 0.0004810505319148936, | |
| "loss": 1.6271, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1899696048632219, | |
| "grad_norm": 0.5209512114524841, | |
| "learning_rate": 0.0004763012917933131, | |
| "loss": 1.5465, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.22796352583586627, | |
| "grad_norm": 0.739372968673706, | |
| "learning_rate": 0.00047155205167173257, | |
| "loss": 1.5851, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.26595744680851063, | |
| "grad_norm": 0.48252037167549133, | |
| "learning_rate": 0.000466802811550152, | |
| "loss": 1.5936, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.303951367781155, | |
| "grad_norm": 0.5574118494987488, | |
| "learning_rate": 0.0004620535714285715, | |
| "loss": 1.547, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.34194528875379937, | |
| "grad_norm": 0.4584231674671173, | |
| "learning_rate": 0.0004573043313069909, | |
| "loss": 1.5526, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.3799392097264438, | |
| "grad_norm": 0.5431011319160461, | |
| "learning_rate": 0.00045255509118541034, | |
| "loss": 1.5691, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.41793313069908816, | |
| "grad_norm": 0.5586347579956055, | |
| "learning_rate": 0.00044780585106382983, | |
| "loss": 1.5839, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.45592705167173253, | |
| "grad_norm": 0.4354408085346222, | |
| "learning_rate": 0.00044305661094224926, | |
| "loss": 1.55, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.4939209726443769, | |
| "grad_norm": 0.5265607237815857, | |
| "learning_rate": 0.0004383073708206687, | |
| "loss": 1.5339, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "grad_norm": 0.4391303062438965, | |
| "learning_rate": 0.0004335581306990882, | |
| "loss": 1.5296, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.5699088145896657, | |
| "grad_norm": 0.7169055342674255, | |
| "learning_rate": 0.0004288088905775076, | |
| "loss": 1.5336, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.60790273556231, | |
| "grad_norm": 0.5826978087425232, | |
| "learning_rate": 0.00042405965045592704, | |
| "loss": 1.5803, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.6458966565349544, | |
| "grad_norm": 0.6483295559883118, | |
| "learning_rate": 0.0004193104103343465, | |
| "loss": 1.5538, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.6838905775075987, | |
| "grad_norm": 0.4572024941444397, | |
| "learning_rate": 0.00041456117021276595, | |
| "loss": 1.5207, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.7218844984802432, | |
| "grad_norm": 0.509039580821991, | |
| "learning_rate": 0.0004098119300911854, | |
| "loss": 1.535, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.7598784194528876, | |
| "grad_norm": 0.45722949504852295, | |
| "learning_rate": 0.00040506268996960487, | |
| "loss": 1.5684, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7978723404255319, | |
| "grad_norm": 0.4910150170326233, | |
| "learning_rate": 0.0004003134498480243, | |
| "loss": 1.581, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.8358662613981763, | |
| "grad_norm": 0.4546220600605011, | |
| "learning_rate": 0.0003955642097264438, | |
| "loss": 1.5244, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.8738601823708206, | |
| "grad_norm": 0.5551008582115173, | |
| "learning_rate": 0.0003908149696048632, | |
| "loss": 1.5148, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.9118541033434651, | |
| "grad_norm": 0.5794001817703247, | |
| "learning_rate": 0.00038606572948328264, | |
| "loss": 1.5236, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.9498480243161094, | |
| "grad_norm": 0.4178274869918823, | |
| "learning_rate": 0.0003813164893617022, | |
| "loss": 1.4909, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.9878419452887538, | |
| "grad_norm": 0.4754296541213989, | |
| "learning_rate": 0.0003765672492401216, | |
| "loss": 1.5292, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.0258358662613982, | |
| "grad_norm": 0.6230200529098511, | |
| "learning_rate": 0.00037181800911854104, | |
| "loss": 1.3509, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "grad_norm": 0.6134634017944336, | |
| "learning_rate": 0.00036706876899696053, | |
| "loss": 1.2918, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.1018237082066868, | |
| "grad_norm": 0.41924381256103516, | |
| "learning_rate": 0.00036231952887537996, | |
| "loss": 1.2676, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.1398176291793314, | |
| "grad_norm": 0.43015140295028687, | |
| "learning_rate": 0.0003575702887537994, | |
| "loss": 1.3059, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.1778115501519757, | |
| "grad_norm": 0.4945460855960846, | |
| "learning_rate": 0.0003528210486322189, | |
| "loss": 1.2662, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.21580547112462, | |
| "grad_norm": 0.529432475566864, | |
| "learning_rate": 0.0003480718085106383, | |
| "loss": 1.3159, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.2537993920972643, | |
| "grad_norm": 0.4257758557796478, | |
| "learning_rate": 0.00034332256838905773, | |
| "loss": 1.332, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.2917933130699089, | |
| "grad_norm": 0.5150781869888306, | |
| "learning_rate": 0.0003385733282674772, | |
| "loss": 1.3296, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.3297872340425532, | |
| "grad_norm": 0.6550915241241455, | |
| "learning_rate": 0.00033382408814589665, | |
| "loss": 1.3199, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.3677811550151975, | |
| "grad_norm": 0.5338163375854492, | |
| "learning_rate": 0.00032907484802431613, | |
| "loss": 1.3259, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.405775075987842, | |
| "grad_norm": 0.47377586364746094, | |
| "learning_rate": 0.00032432560790273556, | |
| "loss": 1.3242, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.4437689969604863, | |
| "grad_norm": 0.5152885317802429, | |
| "learning_rate": 0.000319576367781155, | |
| "loss": 1.3159, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.4817629179331306, | |
| "grad_norm": 0.539071261882782, | |
| "learning_rate": 0.0003148271276595745, | |
| "loss": 1.2949, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.5197568389057752, | |
| "grad_norm": 0.48675107955932617, | |
| "learning_rate": 0.0003100778875379939, | |
| "loss": 1.3048, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.5577507598784195, | |
| "grad_norm": 0.49419140815734863, | |
| "learning_rate": 0.00030532864741641334, | |
| "loss": 1.3517, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "grad_norm": 0.5641041398048401, | |
| "learning_rate": 0.0003005794072948328, | |
| "loss": 1.3546, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.6337386018237083, | |
| "grad_norm": 0.5435624122619629, | |
| "learning_rate": 0.0002958301671732523, | |
| "loss": 1.3001, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.6717325227963524, | |
| "grad_norm": 0.5236312747001648, | |
| "learning_rate": 0.00029108092705167174, | |
| "loss": 1.3159, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.709726443768997, | |
| "grad_norm": 0.5345861315727234, | |
| "learning_rate": 0.0002863316869300912, | |
| "loss": 1.3137, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.7477203647416415, | |
| "grad_norm": 0.6117902994155884, | |
| "learning_rate": 0.00028158244680851066, | |
| "loss": 1.3116, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.7857142857142856, | |
| "grad_norm": 0.45284005999565125, | |
| "learning_rate": 0.0002768332066869301, | |
| "loss": 1.3079, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.8237082066869301, | |
| "grad_norm": 0.46459677815437317, | |
| "learning_rate": 0.00027208396656534957, | |
| "loss": 1.3346, | |
| "step": 4800 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 10528, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 300, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.7625268731904e+16, | |
| "train_batch_size": 15, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |