| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.875, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09375, | |
| "grad_norm": 5.066744327545166, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.5625, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 4.701694965362549, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.5852, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.28125, | |
| "grad_norm": 4.087770938873291, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5712, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 2.5721685886383057, | |
| "learning_rate": 9.966191788709716e-06, | |
| "loss": 0.5382, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.46875, | |
| "grad_norm": 2.3166298866271973, | |
| "learning_rate": 9.86522435289912e-06, | |
| "loss": 0.4693, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5625, | |
| "grad_norm": 2.036036491394043, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.423, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.65625, | |
| "grad_norm": 1.758629560470581, | |
| "learning_rate": 9.468163201617063e-06, | |
| "loss": 0.4039, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 1.4806989431381226, | |
| "learning_rate": 9.177439057064684e-06, | |
| "loss": 0.3673, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.84375, | |
| "grad_norm": 1.3439924716949463, | |
| "learning_rate": 8.83022221559489e-06, | |
| "loss": 0.3763, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 1.2895797491073608, | |
| "learning_rate": 8.43120818934367e-06, | |
| "loss": 0.3948, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0625, | |
| "grad_norm": 2.114377975463867, | |
| "learning_rate": 7.985792958513932e-06, | |
| "loss": 0.56, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.15625, | |
| "grad_norm": 1.0501552820205688, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.3337, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.9907200336456299, | |
| "learning_rate": 6.980398830195785e-06, | |
| "loss": 0.3273, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.34375, | |
| "grad_norm": 0.9435698390007019, | |
| "learning_rate": 6.434016163555452e-06, | |
| "loss": 0.3234, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4375, | |
| "grad_norm": 0.9575456380844116, | |
| "learning_rate": 5.8682408883346535e-06, | |
| "loss": 0.2844, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.53125, | |
| "grad_norm": 0.9119848012924194, | |
| "learning_rate": 5.290724144552379e-06, | |
| "loss": 0.3171, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.625, | |
| "grad_norm": 0.667569637298584, | |
| "learning_rate": 4.7092758554476215e-06, | |
| "loss": 0.2731, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.71875, | |
| "grad_norm": 0.842898964881897, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.2861, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8125, | |
| "grad_norm": 0.6838074922561646, | |
| "learning_rate": 3.5659838364445505e-06, | |
| "loss": 0.2572, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.90625, | |
| "grad_norm": 0.7853348851203918, | |
| "learning_rate": 3.019601169804216e-06, | |
| "loss": 0.2949, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.03125, | |
| "grad_norm": 1.4814157485961914, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 0.4905, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.125, | |
| "grad_norm": 0.7601101398468018, | |
| "learning_rate": 2.0142070414860704e-06, | |
| "loss": 0.2487, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.21875, | |
| "grad_norm": 0.7554824352264404, | |
| "learning_rate": 1.5687918106563326e-06, | |
| "loss": 0.2562, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.3125, | |
| "grad_norm": 0.6123334765434265, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 0.2216, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.40625, | |
| "grad_norm": 0.6512125730514526, | |
| "learning_rate": 8.225609429353187e-07, | |
| "loss": 0.244, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 0.6529915928840637, | |
| "learning_rate": 5.318367983829393e-07, | |
| "loss": 0.2334, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.59375, | |
| "grad_norm": 0.5994971394538879, | |
| "learning_rate": 3.015368960704584e-07, | |
| "loss": 0.2174, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.6875, | |
| "grad_norm": 0.6502348780632019, | |
| "learning_rate": 1.3477564710088097e-07, | |
| "loss": 0.2514, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.78125, | |
| "grad_norm": 0.6495589017868042, | |
| "learning_rate": 3.3808211290284886e-08, | |
| "loss": 0.2288, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.875, | |
| "grad_norm": 0.5587441325187683, | |
| "learning_rate": 0.0, | |
| "loss": 0.2172, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.875, | |
| "step": 30, | |
| "total_flos": 5486752841728.0, | |
| "train_loss": 0.3519415785868963, | |
| "train_runtime": 307.1116, | |
| "train_samples_per_second": 9.768, | |
| "train_steps_per_second": 0.098 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 5486752841728.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |