| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9955555555555555, | |
| "eval_steps": 100, | |
| "global_step": 168, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02962962962962963, | |
| "grad_norm": 3.2346072118607885, | |
| "learning_rate": 5.882352941176471e-06, | |
| "loss": 1.0169, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05925925925925926, | |
| "grad_norm": 2.1264769797556, | |
| "learning_rate": 1.1764705882352942e-05, | |
| "loss": 0.8756, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 1.4231223829611963, | |
| "learning_rate": 1.7647058823529414e-05, | |
| "loss": 0.7716, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 1.0239519248217772, | |
| "learning_rate": 1.9980527694749952e-05, | |
| "loss": 0.733, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.7202299506697141, | |
| "learning_rate": 1.986180478852149e-05, | |
| "loss": 0.7059, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.5695527206070538, | |
| "learning_rate": 1.963645895935632e-05, | |
| "loss": 0.6695, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2074074074074074, | |
| "grad_norm": 0.6039878702944135, | |
| "learning_rate": 1.930692657985482e-05, | |
| "loss": 0.6779, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.5093109436831765, | |
| "learning_rate": 1.887677045685188e-05, | |
| "loss": 0.6563, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 0.6018876927034159, | |
| "learning_rate": 1.8350641311400813e-05, | |
| "loss": 0.6597, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.5268268034517721, | |
| "learning_rate": 1.773422749654988e-05, | |
| "loss": 0.6483, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32592592592592595, | |
| "grad_norm": 0.5861151838314477, | |
| "learning_rate": 1.7034193496547903e-05, | |
| "loss": 0.649, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.4503680956414544, | |
| "learning_rate": 1.6258107872407376e-05, | |
| "loss": 0.6319, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3851851851851852, | |
| "grad_norm": 0.5307966629696642, | |
| "learning_rate": 1.5414361432856475e-05, | |
| "loss": 0.631, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4148148148148148, | |
| "grad_norm": 0.5782202441621853, | |
| "learning_rate": 1.4512076515391375e-05, | |
| "loss": 0.6328, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.48265196188960013, | |
| "learning_rate": 1.356100835825547e-05, | |
| "loss": 0.6254, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.4813265336090251, | |
| "learning_rate": 1.257143962968246e-05, | |
| "loss": 0.6175, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5037037037037037, | |
| "grad_norm": 0.4515213148563428, | |
| "learning_rate": 1.155406925472205e-05, | |
| "loss": 0.6298, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.44644143858157415, | |
| "learning_rate": 1.0519896741619803e-05, | |
| "loss": 0.6215, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.562962962962963, | |
| "grad_norm": 0.4691339692298715, | |
| "learning_rate": 9.480103258380198e-06, | |
| "loss": 0.6245, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.4311309942505263, | |
| "learning_rate": 8.445930745277953e-06, | |
| "loss": 0.6157, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "eval_loss": 0.6399185061454773, | |
| "eval_runtime": 2.407, | |
| "eval_samples_per_second": 52.763, | |
| "eval_steps_per_second": 1.662, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 0.42038278194306516, | |
| "learning_rate": 7.428560370317542e-06, | |
| "loss": 0.6167, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.6518518518518519, | |
| "grad_norm": 0.478843319690418, | |
| "learning_rate": 6.438991641744531e-06, | |
| "loss": 0.6219, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6814814814814815, | |
| "grad_norm": 0.4347536528553071, | |
| "learning_rate": 5.487923484608629e-06, | |
| "loss": 0.6041, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.3769111515881631, | |
| "learning_rate": 4.5856385671435285e-06, | |
| "loss": 0.5991, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 0.4099151217963583, | |
| "learning_rate": 3.7418921275926245e-06, | |
| "loss": 0.5976, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7703703703703704, | |
| "grad_norm": 0.36781593886520214, | |
| "learning_rate": 2.965806503452098e-06, | |
| "loss": 0.6132, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.3627464720674499, | |
| "learning_rate": 2.265772503450122e-06, | |
| "loss": 0.6104, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.3608772496918306, | |
| "learning_rate": 1.6493586885991908e-06, | |
| "loss": 0.606, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8592592592592593, | |
| "grad_norm": 0.34531094549512426, | |
| "learning_rate": 1.1232295431481222e-06, | |
| "loss": 0.6084, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.3242007784943698, | |
| "learning_rate": 6.930734201451817e-07, | |
| "loss": 0.6146, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9185185185185185, | |
| "grad_norm": 0.3386165753528116, | |
| "learning_rate": 3.635410406436857e-07, | |
| "loss": 0.6066, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.32706837162712976, | |
| "learning_rate": 1.3819521147851122e-07, | |
| "loss": 0.6098, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 0.3256703232456208, | |
| "learning_rate": 1.947230525005006e-08, | |
| "loss": 0.6117, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.9955555555555555, | |
| "step": 168, | |
| "total_flos": 175887366488064.0, | |
| "train_loss": 0.6538166212184089, | |
| "train_runtime": 1597.3219, | |
| "train_samples_per_second": 13.504, | |
| "train_steps_per_second": 0.105 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 168, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 175887366488064.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |