| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3000.0, | |
| "eval_steps": 500, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 100.0, | |
| "grad_norm": 0.06228038668632507, | |
| "learning_rate": 0.00019946308119914323, | |
| "loss": 0.5217, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 200.0, | |
| "grad_norm": 0.02468216046690941, | |
| "learning_rate": 0.00019783647889781136, | |
| "loss": 0.0023, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 300.0, | |
| "grad_norm": 0.0070268092676997185, | |
| "learning_rate": 0.00019513795966007562, | |
| "loss": 0.0006, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 400.0, | |
| "grad_norm": 0.00667573232203722, | |
| "learning_rate": 0.00019139708902740613, | |
| "loss": 0.0004, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 500.0, | |
| "grad_norm": 0.005153825972229242, | |
| "learning_rate": 0.00018665485276128188, | |
| "loss": 0.0002, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 600.0, | |
| "grad_norm": 0.004352587275207043, | |
| "learning_rate": 0.00018096320779461132, | |
| "loss": 0.0002, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 700.0, | |
| "grad_norm": 0.0017930130707100034, | |
| "learning_rate": 0.00017438451298070252, | |
| "loss": 0.0001, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 800.0, | |
| "grad_norm": 0.0013685841113328934, | |
| "learning_rate": 0.0001669908458766171, | |
| "loss": 0.0001, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 900.0, | |
| "grad_norm": 0.003938326612114906, | |
| "learning_rate": 0.0001588632130463717, | |
| "loss": 0.0002, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1000.0, | |
| "grad_norm": 0.008353661745786667, | |
| "learning_rate": 0.000150090662536071, | |
| "loss": 0.0083, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1100.0, | |
| "grad_norm": 0.0031552647706121206, | |
| "learning_rate": 0.00014086490747363493, | |
| "loss": 0.0008, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1200.0, | |
| "grad_norm": 0.0014439212391152978, | |
| "learning_rate": 0.0001312003296688415, | |
| "loss": 0.0032, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1300.0, | |
| "grad_norm": 0.0022927618119865656, | |
| "learning_rate": 0.00012109836010773424, | |
| "loss": 0.0073, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1400.0, | |
| "grad_norm": 0.0016441670013591647, | |
| "learning_rate": 0.00011076523249817094, | |
| "loss": 0.0001, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1500.0, | |
| "grad_norm": 0.0006704287370666862, | |
| "learning_rate": 0.00010031415874858797, | |
| "loss": 0.0001, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1600.0, | |
| "grad_norm": 0.0009293225011788309, | |
| "learning_rate": 8.985964301001353e-05, | |
| "loss": 0.0001, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1700.0, | |
| "grad_norm": 0.0012109966482967138, | |
| "learning_rate": 7.951622714462746e-05, | |
| "loss": 0.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1800.0, | |
| "grad_norm": 0.0008299258770421147, | |
| "learning_rate": 6.939723578114993e-05, | |
| "loss": 0.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1900.0, | |
| "grad_norm": 0.0008420582162216306, | |
| "learning_rate": 5.961353470649426e-05, | |
| "loss": 0.0, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2000.0, | |
| "grad_norm": 0.0005832781316712499, | |
| "learning_rate": 5.0272316197005396e-05, | |
| "loss": 0.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2100.0, | |
| "grad_norm": 0.00045646895887330174, | |
| "learning_rate": 4.1475924597449024e-05, | |
| "loss": 0.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2200.0, | |
| "grad_norm": 0.0006278394139371812, | |
| "learning_rate": 3.3320735014953076e-05, | |
| "loss": 0.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2300.0, | |
| "grad_norm": 0.0005234285490587354, | |
| "learning_rate": 2.5896097413166564e-05, | |
| "loss": 0.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2400.0, | |
| "grad_norm": 0.0005604827310889959, | |
| "learning_rate": 1.928335767535997e-05, | |
| "loss": 0.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2500.0, | |
| "grad_norm": 0.0004753954126499593, | |
| "learning_rate": 1.3554966361905464e-05, | |
| "loss": 0.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2600.0, | |
| "grad_norm": 0.00042428780579939485, | |
| "learning_rate": 8.77368492677616e-06, | |
| "loss": 0.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2700.0, | |
| "grad_norm": 0.00040628627175465226, | |
| "learning_rate": 4.991898089922819e-06, | |
| "loss": 0.0, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2800.0, | |
| "grad_norm": 0.0004407366504892707, | |
| "learning_rate": 2.2510398993198067e-06, | |
| "loss": 0.0, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2900.0, | |
| "grad_norm": 0.0009461056906729937, | |
| "learning_rate": 5.811397708647803e-07, | |
| "loss": 0.0, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 3000.0, | |
| "grad_norm": 0.0005067897727712989, | |
| "learning_rate": 4.934798141786879e-10, | |
| "loss": 0.0, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3000, | |
| "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": 589966765056000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |