| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.17301038062283736, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00865051903114187, | |
| "grad_norm": 0.653178334236145, | |
| "learning_rate": 5.142857142857143e-05, | |
| "loss": 2.462, | |
| "mean_token_accuracy": 0.5231182813644409, | |
| "num_tokens": 20480.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01730103806228374, | |
| "grad_norm": 0.4405156075954437, | |
| "learning_rate": 0.00010857142857142856, | |
| "loss": 2.0497, | |
| "mean_token_accuracy": 0.5873411521315575, | |
| "num_tokens": 40960.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025951557093425604, | |
| "grad_norm": 0.6160047054290771, | |
| "learning_rate": 0.00016571428571428575, | |
| "loss": 1.9284, | |
| "mean_token_accuracy": 0.6067448765039444, | |
| "num_tokens": 61440.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03460207612456748, | |
| "grad_norm": 0.4909583330154419, | |
| "learning_rate": 0.00019999371690018224, | |
| "loss": 1.7739, | |
| "mean_token_accuracy": 0.6309384137392045, | |
| "num_tokens": 81920.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04325259515570934, | |
| "grad_norm": 0.4441400170326233, | |
| "learning_rate": 0.00019992304109437157, | |
| "loss": 1.9242, | |
| "mean_token_accuracy": 0.6014662817120552, | |
| "num_tokens": 102400.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05190311418685121, | |
| "grad_norm": 0.5243574976921082, | |
| "learning_rate": 0.00019977389129787062, | |
| "loss": 1.8928, | |
| "mean_token_accuracy": 0.6027370542287827, | |
| "num_tokens": 122880.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06055363321799308, | |
| "grad_norm": 0.3737685978412628, | |
| "learning_rate": 0.00019954638464462175, | |
| "loss": 1.8107, | |
| "mean_token_accuracy": 0.6185728281736373, | |
| "num_tokens": 143360.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06920415224913495, | |
| "grad_norm": 0.5457460284233093, | |
| "learning_rate": 0.00019924069980567822, | |
| "loss": 1.7227, | |
| "mean_token_accuracy": 0.6354838699102402, | |
| "num_tokens": 163840.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07785467128027682, | |
| "grad_norm": 0.41756778955459595, | |
| "learning_rate": 0.00019885707684888566, | |
| "loss": 1.7249, | |
| "mean_token_accuracy": 0.6385141760110855, | |
| "num_tokens": 184320.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08650519031141868, | |
| "grad_norm": 0.39207473397254944, | |
| "learning_rate": 0.00019839581705034624, | |
| "loss": 1.6423, | |
| "mean_token_accuracy": 0.6423753708600998, | |
| "num_tokens": 204800.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09515570934256055, | |
| "grad_norm": 0.46543020009994507, | |
| "learning_rate": 0.00019785728265781324, | |
| "loss": 1.5637, | |
| "mean_token_accuracy": 0.6588465303182602, | |
| "num_tokens": 225280.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.10380622837370242, | |
| "grad_norm": 0.4604319930076599, | |
| "learning_rate": 0.0001972418966062018, | |
| "loss": 1.5936, | |
| "mean_token_accuracy": 0.6586021468043327, | |
| "num_tokens": 245760.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.11245674740484429, | |
| "grad_norm": 0.34409117698669434, | |
| "learning_rate": 0.0001965501421854394, | |
| "loss": 1.7365, | |
| "mean_token_accuracy": 0.6300097703933716, | |
| "num_tokens": 266240.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.12110726643598616, | |
| "grad_norm": 0.46972155570983887, | |
| "learning_rate": 0.0001957825626609169, | |
| "loss": 1.6823, | |
| "mean_token_accuracy": 0.6419354841113091, | |
| "num_tokens": 286720.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.12975778546712802, | |
| "grad_norm": 0.45500946044921875, | |
| "learning_rate": 0.00019493976084683813, | |
| "loss": 1.4338, | |
| "mean_token_accuracy": 0.6832355856895447, | |
| "num_tokens": 307200.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1384083044982699, | |
| "grad_norm": 0.4167431890964508, | |
| "learning_rate": 0.0001940223986328032, | |
| "loss": 1.7327, | |
| "mean_token_accuracy": 0.6318181827664375, | |
| "num_tokens": 327680.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.14705882352941177, | |
| "grad_norm": 0.43620193004608154, | |
| "learning_rate": 0.00019303119646399728, | |
| "loss": 1.5997, | |
| "mean_token_accuracy": 0.6583577707409859, | |
| "num_tokens": 348160.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.15570934256055363, | |
| "grad_norm": 0.48302027583122253, | |
| "learning_rate": 0.00019196693277539307, | |
| "loss": 1.79, | |
| "mean_token_accuracy": 0.617741933465004, | |
| "num_tokens": 368640.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1643598615916955, | |
| "grad_norm": 0.49784767627716064, | |
| "learning_rate": 0.00019083044338041134, | |
| "loss": 1.5624, | |
| "mean_token_accuracy": 0.6568426251411438, | |
| "num_tokens": 389120.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.17301038062283736, | |
| "grad_norm": 0.3815184235572815, | |
| "learning_rate": 0.00018962262081451966, | |
| "loss": 1.5723, | |
| "mean_token_accuracy": 0.6639296174049377, | |
| "num_tokens": 409600.0, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1156, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6987107323084800.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |