| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0966183574879227, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001932367149758454, | |
| "eval_loss": 0.19060376286506653, | |
| "eval_runtime": 115.54, | |
| "eval_samples_per_second": 7.547, | |
| "eval_steps_per_second": 0.943, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005797101449275362, | |
| "grad_norm": 0.9495611190795898, | |
| "learning_rate": 3e-05, | |
| "loss": 0.17, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00966183574879227, | |
| "eval_loss": 0.1351812481880188, | |
| "eval_runtime": 116.6752, | |
| "eval_samples_per_second": 7.474, | |
| "eval_steps_per_second": 0.934, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011594202898550725, | |
| "grad_norm": 0.9149388670921326, | |
| "learning_rate": 6e-05, | |
| "loss": 0.1441, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017391304347826087, | |
| "grad_norm": 0.5411681532859802, | |
| "learning_rate": 9e-05, | |
| "loss": 0.1328, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01932367149758454, | |
| "eval_loss": 0.11909719556570053, | |
| "eval_runtime": 116.6714, | |
| "eval_samples_per_second": 7.474, | |
| "eval_steps_per_second": 0.934, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02318840579710145, | |
| "grad_norm": 0.4105644226074219, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.1287, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.028985507246376812, | |
| "grad_norm": 0.45149490237236023, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.125, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.028985507246376812, | |
| "eval_loss": 0.11515907943248749, | |
| "eval_runtime": 116.6908, | |
| "eval_samples_per_second": 7.473, | |
| "eval_steps_per_second": 0.934, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.034782608695652174, | |
| "grad_norm": 0.4921862483024597, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.1103, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03864734299516908, | |
| "eval_loss": 0.11116211861371994, | |
| "eval_runtime": 116.7218, | |
| "eval_samples_per_second": 7.471, | |
| "eval_steps_per_second": 0.934, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04057971014492753, | |
| "grad_norm": 0.47375577688217163, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.1083, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0463768115942029, | |
| "grad_norm": 0.4400457441806793, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.1057, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04830917874396135, | |
| "eval_loss": 0.10784460604190826, | |
| "eval_runtime": 116.7599, | |
| "eval_samples_per_second": 7.468, | |
| "eval_steps_per_second": 0.934, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05217391304347826, | |
| "grad_norm": 0.38069862127304077, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.1235, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.057971014492753624, | |
| "grad_norm": 0.3471054136753082, | |
| "learning_rate": 5e-05, | |
| "loss": 0.094, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.057971014492753624, | |
| "eval_loss": 0.10548962652683258, | |
| "eval_runtime": 116.7489, | |
| "eval_samples_per_second": 7.469, | |
| "eval_steps_per_second": 0.934, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06376811594202898, | |
| "grad_norm": 0.4750822186470032, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.1154, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06763285024154589, | |
| "eval_loss": 0.10251878947019577, | |
| "eval_runtime": 116.6949, | |
| "eval_samples_per_second": 7.472, | |
| "eval_steps_per_second": 0.934, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06956521739130435, | |
| "grad_norm": 0.42566755414009094, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.1062, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07536231884057971, | |
| "grad_norm": 0.3791707158088684, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.0931, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07729468599033816, | |
| "eval_loss": 0.10088106989860535, | |
| "eval_runtime": 116.6822, | |
| "eval_samples_per_second": 7.473, | |
| "eval_steps_per_second": 0.934, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08115942028985507, | |
| "grad_norm": 0.373145192861557, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.1072, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": 0.3523075580596924, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1039, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08695652173913043, | |
| "eval_loss": 0.09994707256555557, | |
| "eval_runtime": 116.7859, | |
| "eval_samples_per_second": 7.467, | |
| "eval_steps_per_second": 0.933, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0927536231884058, | |
| "grad_norm": 0.39486297965049744, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.11, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0966183574879227, | |
| "eval_loss": 0.09973125904798508, | |
| "eval_runtime": 116.6819, | |
| "eval_samples_per_second": 7.473, | |
| "eval_steps_per_second": 0.934, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2986314239718195e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |