| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020475020475020474, | |
| "eval_steps": 500, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000819000819000819, | |
| "grad_norm": 90.93321228027344, | |
| "learning_rate": 0.0001, | |
| "loss": 7.2571, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001638001638001638, | |
| "grad_norm": 100.0165786743164, | |
| "learning_rate": 0.0002, | |
| "loss": 7.7208, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002457002457002457, | |
| "grad_norm": 29.802927017211914, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 6.3071, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003276003276003276, | |
| "grad_norm": 20.66453742980957, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 4.4939, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004095004095004095, | |
| "grad_norm": 11.550251960754395, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 3.1308, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004914004914004914, | |
| "grad_norm": 12.07933521270752, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 2.5729, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005733005733005733, | |
| "grad_norm": 13.511775970458984, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 2.7139, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006552006552006552, | |
| "grad_norm": 19.122846603393555, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 2.5717, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007371007371007371, | |
| "grad_norm": 12.280449867248535, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 2.5866, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00819000819000819, | |
| "grad_norm": 11.710186004638672, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.2255, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009009009009009009, | |
| "grad_norm": 11.945186614990234, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 2.5426, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009828009828009828, | |
| "grad_norm": 9.754225730895996, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 1.8538, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010647010647010647, | |
| "grad_norm": 7.58078670501709, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 1.9307, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011466011466011465, | |
| "grad_norm": 12.604692459106445, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.9668, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012285012285012284, | |
| "grad_norm": 10.3529634475708, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 1.9298, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013104013104013105, | |
| "grad_norm": 6.979626655578613, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.6039, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013923013923013924, | |
| "grad_norm": 9.227945327758789, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 2.2052, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014742014742014743, | |
| "grad_norm": 7.513698577880859, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.0041, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015561015561015561, | |
| "grad_norm": 7.088660717010498, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 1.8504, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01638001638001638, | |
| "grad_norm": 6.470543384552002, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 1.4294, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0171990171990172, | |
| "grad_norm": 7.033813953399658, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 1.2088, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018018018018018018, | |
| "grad_norm": 5.362617015838623, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 1.1229, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.018837018837018837, | |
| "grad_norm": 6.344296932220459, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 1.4339, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019656019656019656, | |
| "grad_norm": 7.917414665222168, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 1.3725, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020475020475020474, | |
| "grad_norm": 10.315130233764648, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 1.6188, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5146843860172800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |