| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 166, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012048192771084338, | |
| "grad_norm": 5.144875488861497, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 5.2383, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.060240963855421686, | |
| "grad_norm": 4.400640807642775, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 5.1426, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12048192771084337, | |
| "grad_norm": 2.8424185774279995, | |
| "learning_rate": 0.00019990989662046818, | |
| "loss": 4.9195, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18072289156626506, | |
| "grad_norm": 2.1742733252180533, | |
| "learning_rate": 0.0001967732946933499, | |
| "loss": 4.5773, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.24096385542168675, | |
| "grad_norm": 2.0811257888315406, | |
| "learning_rate": 0.00018929258581495685, | |
| "loss": 4.3453, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.30120481927710846, | |
| "grad_norm": 1.3196766642254727, | |
| "learning_rate": 0.00017780357543184397, | |
| "loss": 4.1766, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3614457831325301, | |
| "grad_norm": 1.7074769394742433, | |
| "learning_rate": 0.00016282199972956425, | |
| "loss": 4.0355, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.42168674698795183, | |
| "grad_norm": 1.786794986516103, | |
| "learning_rate": 0.00014502037448176734, | |
| "loss": 3.9418, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4819277108433735, | |
| "grad_norm": 1.712555578478064, | |
| "learning_rate": 0.00012519780613851254, | |
| "loss": 3.8637, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5421686746987951, | |
| "grad_norm": 1.1317257705596584, | |
| "learning_rate": 0.00010424412031961484, | |
| "loss": 3.8164, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6024096385542169, | |
| "grad_norm": 0.8808395413039651, | |
| "learning_rate": 8.309991796781511e-05, | |
| "loss": 3.7855, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6626506024096386, | |
| "grad_norm": 0.9070705182297121, | |
| "learning_rate": 6.271435222196916e-05, | |
| "loss": 3.7594, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.7228915662650602, | |
| "grad_norm": 0.800430133148163, | |
| "learning_rate": 4.4002521386240466e-05, | |
| "loss": 3.723, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7831325301204819, | |
| "grad_norm": 0.9084524552496485, | |
| "learning_rate": 2.7804390604547557e-05, | |
| "loss": 3.7258, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8433734939759037, | |
| "grad_norm": 0.7470706061804011, | |
| "learning_rate": 1.4847086226668872e-05, | |
| "loss": 3.6902, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9036144578313253, | |
| "grad_norm": 0.697773024233771, | |
| "learning_rate": 5.71225545389158e-06, | |
| "loss": 3.691, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.963855421686747, | |
| "grad_norm": 0.70777044124217, | |
| "learning_rate": 8.099564741123166e-07, | |
| "loss": 3.6707, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5120481927710844, | |
| "grad_norm": 1.03125, | |
| "learning_rate": 2.3529411764705884e-05, | |
| "loss": 3.6468, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5421686746987951, | |
| "grad_norm": 0.89453125, | |
| "learning_rate": 8.23529411764706e-05, | |
| "loss": 3.6491, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.572289156626506, | |
| "grad_norm": 1.0703125, | |
| "learning_rate": 0.0001411764705882353, | |
| "loss": 3.6893, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6024096385542169, | |
| "grad_norm": 1.0625, | |
| "learning_rate": 0.0002, | |
| "loss": 3.6404, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6325301204819277, | |
| "grad_norm": 0.92578125, | |
| "learning_rate": 0.00019944481853548335, | |
| "loss": 3.6761, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6626506024096386, | |
| "grad_norm": 0.94140625, | |
| "learning_rate": 0.00019778543867110426, | |
| "loss": 3.6328, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6927710843373494, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 0.00019504028554572864, | |
| "loss": 3.6478, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7228915662650602, | |
| "grad_norm": 1.0703125, | |
| "learning_rate": 0.00019123984032200586, | |
| "loss": 3.6035, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7530120481927711, | |
| "grad_norm": 0.87890625, | |
| "learning_rate": 0.00018642630173483832, | |
| "loss": 3.6189, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7831325301204819, | |
| "grad_norm": 0.88671875, | |
| "learning_rate": 0.00018065311753227273, | |
| "loss": 3.6364, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8132530120481928, | |
| "grad_norm": 0.96484375, | |
| "learning_rate": 0.00017398439101151905, | |
| "loss": 3.6213, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8433734939759037, | |
| "grad_norm": 0.90625, | |
| "learning_rate": 0.0001664941692397025, | |
| "loss": 3.558, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8734939759036144, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 0.00015826562086267956, | |
| "loss": 3.5992, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.9036144578313253, | |
| "grad_norm": 0.84765625, | |
| "learning_rate": 0.00014939011263122634, | |
| "loss": 3.5675, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9337349397590361, | |
| "grad_norm": 0.78515625, | |
| "learning_rate": 0.00013996619489850822, | |
| "loss": 3.5625, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.963855421686747, | |
| "grad_norm": 0.84765625, | |
| "learning_rate": 0.0001300985073534919, | |
| "loss": 3.5525, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9939759036144579, | |
| "grad_norm": 0.890625, | |
| "learning_rate": 0.00011989661714062999, | |
| "loss": 3.5954, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 166, | |
| "total_flos": 2783887138750464.0, | |
| "train_loss": 0.0, | |
| "train_runtime": 3.0865, | |
| "train_samples_per_second": 3442.1, | |
| "train_steps_per_second": 53.783 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 166, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2783887138750464.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |