| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 245, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 20286.314453125, | |
| "learning_rate": 1.2244897959183673e-06, | |
| "loss": 2.0797, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 21226.833984375, | |
| "learning_rate": 2.4489795918367347e-06, | |
| "loss": 2.0794, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 20473.34375, | |
| "learning_rate": 3.673469387755102e-06, | |
| "loss": 2.0791, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 21295.623046875, | |
| "learning_rate": 4.897959183673469e-06, | |
| "loss": 2.0786, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 22374.26953125, | |
| "learning_rate": 6.122448979591837e-06, | |
| "loss": 2.0775, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 27922.837890625, | |
| "learning_rate": 7.346938775510204e-06, | |
| "loss": 2.0762, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 21962.65625, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 2.0751, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 25949.669921875, | |
| "learning_rate": 9.795918367346939e-06, | |
| "loss": 2.073, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3673469387755102, | |
| "grad_norm": 21337.779296875, | |
| "learning_rate": 1.1020408163265306e-05, | |
| "loss": 2.0711, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 21139.53125, | |
| "learning_rate": 1.2244897959183674e-05, | |
| "loss": 2.068, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4489795918367347, | |
| "grad_norm": 18687.326171875, | |
| "learning_rate": 1.3469387755102042e-05, | |
| "loss": 2.0621, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 23997.892578125, | |
| "learning_rate": 1.4693877551020408e-05, | |
| "loss": 2.0557, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5306122448979592, | |
| "grad_norm": 25094.125, | |
| "learning_rate": 1.5918367346938776e-05, | |
| "loss": 2.0436, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 35127.62890625, | |
| "learning_rate": 1.7142857142857142e-05, | |
| "loss": 2.0313, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 38480.73046875, | |
| "learning_rate": 1.836734693877551e-05, | |
| "loss": 2.0124, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 37025.25390625, | |
| "learning_rate": 1.9591836734693877e-05, | |
| "loss": 1.9832, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6938775510204082, | |
| "grad_norm": 47326.75390625, | |
| "learning_rate": 2.0816326530612247e-05, | |
| "loss": 1.9503, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7346938775510204, | |
| "grad_norm": 44386.79296875, | |
| "learning_rate": 2.2040816326530613e-05, | |
| "loss": 1.9033, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7755102040816326, | |
| "grad_norm": 60427.28515625, | |
| "learning_rate": 2.326530612244898e-05, | |
| "loss": 1.8548, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 60310.234375, | |
| "learning_rate": 2.448979591836735e-05, | |
| "loss": 1.7809, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 73581.171875, | |
| "learning_rate": 2.5714285714285714e-05, | |
| "loss": 1.8435, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8979591836734694, | |
| "grad_norm": 63305.5, | |
| "learning_rate": 2.6938775510204084e-05, | |
| "loss": 1.7222, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9387755102040817, | |
| "grad_norm": 78695.546875, | |
| "learning_rate": 2.816326530612245e-05, | |
| "loss": 1.7823, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": 118529.84375, | |
| "learning_rate": 2.9387755102040816e-05, | |
| "loss": 1.7203, | |
| "step": 240 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2450, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.24301109962752e+18, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |