| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007142857142857143, | |
| "grad_norm": 286.327392578125, | |
| "learning_rate": 0.003333333333333333, | |
| "loss": 27.4831, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03571428571428571, | |
| "grad_norm": 564.7811889648438, | |
| "learning_rate": 0.016666666666666666, | |
| "loss": 180.9505, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 45641.8671875, | |
| "learning_rate": 0.029770992366412213, | |
| "loss": 193.5063, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10714285714285714, | |
| "grad_norm": 1771723.5, | |
| "learning_rate": 0.02862595419847328, | |
| "loss": 376.766, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 286214.5, | |
| "learning_rate": 0.02748091603053435, | |
| "loss": 569.9451, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 1100.7747802734375, | |
| "learning_rate": 0.02633587786259542, | |
| "loss": 615.8839, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": 169022.0, | |
| "learning_rate": 0.025190839694656485, | |
| "loss": 481.0353, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 333.40972900390625, | |
| "learning_rate": 0.024045801526717557, | |
| "loss": 305.1498, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 139948.15625, | |
| "learning_rate": 0.022900763358778626, | |
| "loss": 241.1332, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32142857142857145, | |
| "grad_norm": 1393742.875, | |
| "learning_rate": 0.021755725190839695, | |
| "loss": 207.3882, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 12597.32421875, | |
| "learning_rate": 0.020610687022900764, | |
| "loss": 201.0974, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.39285714285714285, | |
| "grad_norm": 1081976.875, | |
| "learning_rate": 0.01946564885496183, | |
| "loss": 222.2186, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 18104.56640625, | |
| "learning_rate": 0.0183206106870229, | |
| "loss": 254.4615, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4642857142857143, | |
| "grad_norm": 53967.2265625, | |
| "learning_rate": 0.017175572519083967, | |
| "loss": 256.7784, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 36778.24609375, | |
| "learning_rate": 0.01603053435114504, | |
| "loss": 189.0749, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 1759.3746337890625, | |
| "learning_rate": 0.014885496183206106, | |
| "loss": 198.0302, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 2888.434326171875, | |
| "learning_rate": 0.013740458015267175, | |
| "loss": 208.9426, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6071428571428571, | |
| "grad_norm": 3183.7255859375, | |
| "learning_rate": 0.012595419847328242, | |
| "loss": 237.6604, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 295.5591735839844, | |
| "learning_rate": 0.011450381679389313, | |
| "loss": 259.345, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6785714285714286, | |
| "grad_norm": 2817.36083984375, | |
| "learning_rate": 0.010305343511450382, | |
| "loss": 229.8393, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 1439.1002197265625, | |
| "learning_rate": 0.00916030534351145, | |
| "loss": 206.7085, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 2063.854248046875, | |
| "learning_rate": 0.00801526717557252, | |
| "loss": 200.2123, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.7857142857142857, | |
| "grad_norm": 3193.01953125, | |
| "learning_rate": 0.006870229007633588, | |
| "loss": 195.9004, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8214285714285714, | |
| "grad_norm": 1513.8978271484375, | |
| "learning_rate": 0.0057251908396946565, | |
| "loss": 188.8404, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 5677.81494140625, | |
| "learning_rate": 0.004580152671755725, | |
| "loss": 176.7594, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8928571428571429, | |
| "grad_norm": 726.0751953125, | |
| "learning_rate": 0.003435114503816794, | |
| "loss": 167.6159, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9285714285714286, | |
| "grad_norm": 1151.048095703125, | |
| "learning_rate": 0.0022900763358778627, | |
| "loss": 155.8075, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9642857142857143, | |
| "grad_norm": 3488.1396484375, | |
| "learning_rate": 0.0011450381679389313, | |
| "loss": 155.3781, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 718.7391357421875, | |
| "learning_rate": 0.0, | |
| "loss": 149.2635, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 149.4047088623047, | |
| "eval_runtime": 2.8984, | |
| "eval_samples_per_second": 61.413, | |
| "eval_steps_per_second": 1.035, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 140, | |
| "total_flos": 4.2812236905630925e+17, | |
| "train_loss": 249.82138957977295, | |
| "train_runtime": 1603.7748, | |
| "train_samples_per_second": 11.164, | |
| "train_steps_per_second": 0.087 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 140, | |
| "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": 4.2812236905630925e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |