| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 35, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05714285714285714, | |
| "grad_norm": 1.4009249776551385, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.5021, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 1.3172016334722576, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.5031, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.17142857142857143, | |
| "grad_norm": 1.9178512673599353, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5062, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 0.6793089435343439, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.3354, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 1.0867703547107586, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.3295, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 1.1377175787228226, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2839, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.8623901226975293, | |
| "learning_rate": 3.9951281005196486e-05, | |
| "loss": 0.2441, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 0.8780874884244323, | |
| "learning_rate": 3.980536137483141e-05, | |
| "loss": 0.1846, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5142857142857142, | |
| "grad_norm": 1.036351588780494, | |
| "learning_rate": 3.9562952014676116e-05, | |
| "loss": 0.1988, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.9238302281565456, | |
| "learning_rate": 3.922523391876638e-05, | |
| "loss": 0.1253, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6285714285714286, | |
| "grad_norm": 0.745481755876343, | |
| "learning_rate": 3.879385241571817e-05, | |
| "loss": 0.1447, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 0.4692969825008956, | |
| "learning_rate": 3.827090915285202e-05, | |
| "loss": 0.134, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7428571428571429, | |
| "grad_norm": 0.3469413634561151, | |
| "learning_rate": 3.7658951857178544e-05, | |
| "loss": 0.1054, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.3346780699651986, | |
| "learning_rate": 3.696096192312852e-05, | |
| "loss": 0.1333, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.3533757350439061, | |
| "learning_rate": 3.6180339887498953e-05, | |
| "loss": 0.1203, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 0.44957677742996416, | |
| "learning_rate": 3.532088886237956e-05, | |
| "loss": 0.1085, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9714285714285714, | |
| "grad_norm": 0.1976618462257492, | |
| "learning_rate": 3.438679600677303e-05, | |
| "loss": 0.0992, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0285714285714285, | |
| "grad_norm": 0.31193519474612263, | |
| "learning_rate": 3.3382612127177166e-05, | |
| "loss": 0.1184, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0857142857142856, | |
| "grad_norm": 0.22230886552354823, | |
| "learning_rate": 3.2313229506513167e-05, | |
| "loss": 0.084, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.5273052165547153, | |
| "learning_rate": 3.1183858069414936e-05, | |
| "loss": 0.0695, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 0.23099852286167058, | |
| "learning_rate": 3.0000000000000004e-05, | |
| "loss": 0.0727, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2571428571428571, | |
| "grad_norm": 0.15466036793183785, | |
| "learning_rate": 2.876742293578155e-05, | |
| "loss": 0.0726, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3142857142857143, | |
| "grad_norm": 0.19431796186289696, | |
| "learning_rate": 2.7492131868318247e-05, | |
| "loss": 0.066, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3714285714285714, | |
| "grad_norm": 0.16481956416422497, | |
| "learning_rate": 2.618033988749895e-05, | |
| "loss": 0.0607, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.15633451614042126, | |
| "learning_rate": 2.4838437911993355e-05, | |
| "loss": 0.062, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4857142857142858, | |
| "grad_norm": 0.13455769043413274, | |
| "learning_rate": 2.3472963553338614e-05, | |
| "loss": 0.0624, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5428571428571427, | |
| "grad_norm": 0.1652523888771218, | |
| "learning_rate": 2.209056926535307e-05, | |
| "loss": 0.0638, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.14446078065937673, | |
| "learning_rate": 2.0697989934050025e-05, | |
| "loss": 0.0664, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.657142857142857, | |
| "grad_norm": 0.16157608324940975, | |
| "learning_rate": 1.930201006594999e-05, | |
| "loss": 0.0612, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.1323142346848781, | |
| "learning_rate": 1.7909430734646936e-05, | |
| "loss": 0.0581, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7714285714285714, | |
| "grad_norm": 0.12523507914355167, | |
| "learning_rate": 1.6527036446661396e-05, | |
| "loss": 0.0563, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8285714285714287, | |
| "grad_norm": 0.12146649654970151, | |
| "learning_rate": 1.5161562088006649e-05, | |
| "loss": 0.0563, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8857142857142857, | |
| "grad_norm": 0.13345706731310938, | |
| "learning_rate": 1.3819660112501054e-05, | |
| "loss": 0.0562, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9428571428571428, | |
| "grad_norm": 0.7649272056527538, | |
| "learning_rate": 1.250786813168176e-05, | |
| "loss": 0.065, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.30935655233065706, | |
| "learning_rate": 1.123257706421845e-05, | |
| "loss": 0.0614, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 51, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 36435683966976.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |