| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 137, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0072992700729927005, | |
| "grad_norm": 708.0, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 56.8346, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0364963503649635, | |
| "grad_norm": 368.0, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 45.8547, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.072992700729927, | |
| "grad_norm": 30.875, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 19.792, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.10948905109489052, | |
| "grad_norm": 6.875, | |
| "learning_rate": 0.00019996738360808565, | |
| "loss": 15.0745, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.145985401459854, | |
| "grad_norm": 17.75, | |
| "learning_rate": 0.00019882804237803488, | |
| "loss": 13.3169, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18248175182481752, | |
| "grad_norm": 117.0, | |
| "learning_rate": 0.00019607909582962477, | |
| "loss": 8.4463, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21897810218978103, | |
| "grad_norm": 5.09375, | |
| "learning_rate": 0.0001917653158603628, | |
| "loss": 2.1599, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25547445255474455, | |
| "grad_norm": 3.921875, | |
| "learning_rate": 0.00018595696069872013, | |
| "loss": 1.6643, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.291970802919708, | |
| "grad_norm": 2.21875, | |
| "learning_rate": 0.00017874863061334657, | |
| "loss": 1.4899, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3284671532846715, | |
| "grad_norm": 2.1875, | |
| "learning_rate": 0.00017025772716520323, | |
| "loss": 1.3695, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.36496350364963503, | |
| "grad_norm": 2.0, | |
| "learning_rate": 0.0001606225410966638, | |
| "loss": 1.2794, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.40145985401459855, | |
| "grad_norm": 0.953125, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.2388, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.43795620437956206, | |
| "grad_norm": 3.53125, | |
| "learning_rate": 0.0001385631124488136, | |
| "loss": 1.2269, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4744525547445255, | |
| "grad_norm": 1.453125, | |
| "learning_rate": 0.0001264981502196662, | |
| "loss": 1.1434, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5109489051094891, | |
| "grad_norm": 0.921875, | |
| "learning_rate": 0.00011400161449686293, | |
| "loss": 1.1033, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5474452554744526, | |
| "grad_norm": 1.5703125, | |
| "learning_rate": 0.00010127703547159739, | |
| "loss": 1.0812, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.583941605839416, | |
| "grad_norm": 2.828125, | |
| "learning_rate": 8.853165746015997e-05, | |
| "loss": 1.061, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6204379562043796, | |
| "grad_norm": 7.4375, | |
| "learning_rate": 7.597306353045393e-05, | |
| "loss": 1.0362, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.656934306569343, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 6.380579461128819e-05, | |
| "loss": 1.0233, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6934306569343066, | |
| "grad_norm": 1.296875, | |
| "learning_rate": 5.222801814877369e-05, | |
| "loss": 1.0499, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7299270072992701, | |
| "grad_norm": 1.3125, | |
| "learning_rate": 4.142830056718052e-05, | |
| "loss": 0.995, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7664233576642335, | |
| "grad_norm": 1.015625, | |
| "learning_rate": 3.158253610095697e-05, | |
| "loss": 0.9839, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8029197080291971, | |
| "grad_norm": 0.765625, | |
| "learning_rate": 2.2851082017805703e-05, | |
| "loss": 0.9762, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8394160583941606, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 1.5376146891235598e-05, | |
| "loss": 0.9773, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.8759124087591241, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 9.279474459608805e-06, | |
| "loss": 0.9756, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9124087591240876, | |
| "grad_norm": 0.80859375, | |
| "learning_rate": 4.660360794506946e-06, | |
| "loss": 0.9625, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.948905109489051, | |
| "grad_norm": 0.57421875, | |
| "learning_rate": 1.5940370726542863e-06, | |
| "loss": 0.9625, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9854014598540146, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 1.3044429107700318e-07, | |
| "loss": 0.961, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.341205358505249, | |
| "eval_runtime": 1.0018, | |
| "eval_samples_per_second": 4.991, | |
| "eval_steps_per_second": 1.996, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 137, | |
| "total_flos": 2.0945562398778982e+17, | |
| "train_loss": 4.772963228887015, | |
| "train_runtime": 1080.9502, | |
| "train_samples_per_second": 2.028, | |
| "train_steps_per_second": 0.127 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 137, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.0945562398778982e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |