| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04095004095004095, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "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 | |
| }, | |
| { | |
| "epoch": 0.021294021294021293, | |
| "grad_norm": 9.622883796691895, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7396, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.022113022113022112, | |
| "grad_norm": 6.45455265045166, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 1.3214, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02293202293202293, | |
| "grad_norm": 4.9485321044921875, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.8279, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02375102375102375, | |
| "grad_norm": 9.586699485778809, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 1.581, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02457002457002457, | |
| "grad_norm": 7.429810047149658, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 1.0575, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025389025389025387, | |
| "grad_norm": 6.126893043518066, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 1.1027, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02620802620802621, | |
| "grad_norm": 6.2424092292785645, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 1.2761, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02702702702702703, | |
| "grad_norm": 6.50886869430542, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 1.0928, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.027846027846027847, | |
| "grad_norm": 7.481552600860596, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.4276, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.028665028665028666, | |
| "grad_norm": 6.688877582550049, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 1.1327, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.029484029484029485, | |
| "grad_norm": 5.75411319732666, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.994, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.030303030303030304, | |
| "grad_norm": 6.614503860473633, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 1.3631, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.031122031122031123, | |
| "grad_norm": 6.146459102630615, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.9955, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03194103194103194, | |
| "grad_norm": 7.359333038330078, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 1.2426, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03276003276003276, | |
| "grad_norm": 5.484676837921143, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 1.0349, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03357903357903358, | |
| "grad_norm": 8.491670608520508, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 1.2368, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0343980343980344, | |
| "grad_norm": 6.154683589935303, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 1.1268, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03521703521703522, | |
| "grad_norm": 7.551387786865234, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 1.458, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.036036036036036036, | |
| "grad_norm": 7.239658832550049, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 1.2141, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.036855036855036855, | |
| "grad_norm": 6.411778926849365, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 1.2161, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03767403767403767, | |
| "grad_norm": 5.392111778259277, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.6257, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03849303849303849, | |
| "grad_norm": 6.593170166015625, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 1.2943, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03931203931203931, | |
| "grad_norm": 7.4250969886779785, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 1.063, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04013104013104013, | |
| "grad_norm": 6.657473087310791, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 1.0355, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04095004095004095, | |
| "grad_norm": 7.4479475021362305, | |
| "learning_rate": 0.0, | |
| "loss": 1.4415, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.02936877203456e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |