| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.9961315280464218, |
| "eval_steps": 500, |
| "global_step": 258, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07736943907156674, |
| "grad_norm": 0.7897351384162903, |
| "learning_rate": 2e-05, |
| "loss": 1.7966, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.15473887814313347, |
| "grad_norm": 0.546701192855835, |
| "learning_rate": 4e-05, |
| "loss": 1.6821, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.23210831721470018, |
| "grad_norm": 0.24719476699829102, |
| "learning_rate": 6e-05, |
| "loss": 1.4684, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.30947775628626695, |
| "grad_norm": 0.19408376514911652, |
| "learning_rate": 8e-05, |
| "loss": 1.3593, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.38684719535783363, |
| "grad_norm": 0.18511685729026794, |
| "learning_rate": 0.0001, |
| "loss": 1.2809, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.46421663442940037, |
| "grad_norm": 0.18041056394577026, |
| "learning_rate": 0.00012, |
| "loss": 1.1822, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.5415860735009671, |
| "grad_norm": 0.18419483304023743, |
| "learning_rate": 0.00014, |
| "loss": 1.0731, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.6189555125725339, |
| "grad_norm": 0.22910986840724945, |
| "learning_rate": 0.00016, |
| "loss": 1.0346, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.6963249516441006, |
| "grad_norm": 0.20705537497997284, |
| "learning_rate": 0.00018, |
| "loss": 0.983, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.7736943907156673, |
| "grad_norm": 0.22625038027763367, |
| "learning_rate": 0.0002, |
| "loss": 0.9447, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.851063829787234, |
| "grad_norm": 0.23730379343032837, |
| "learning_rate": 0.00019802973668046363, |
| "loss": 0.9222, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.9284332688588007, |
| "grad_norm": 0.20882545411586761, |
| "learning_rate": 0.00019219658547282067, |
| "loss": 0.9112, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.0058027079303675, |
| "grad_norm": 0.240465447306633, |
| "learning_rate": 0.00018273040325430574, |
| "loss": 0.903, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.0831721470019342, |
| "grad_norm": 0.2476571947336197, |
| "learning_rate": 0.00017000420745694254, |
| "loss": 0.8574, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.1605415860735009, |
| "grad_norm": 0.22345130145549774, |
| "learning_rate": 0.00015451947721626676, |
| "loss": 0.8703, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.2379110251450678, |
| "grad_norm": 0.23553310334682465, |
| "learning_rate": 0.00013688639245240078, |
| "loss": 0.8414, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.3152804642166345, |
| "grad_norm": 0.2857750952243805, |
| "learning_rate": 0.00011779978956775506, |
| "loss": 0.8407, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.3926499032882012, |
| "grad_norm": 0.24604524672031403, |
| "learning_rate": 9.801178123349298e-05, |
| "loss": 0.8429, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.4700193423597678, |
| "grad_norm": 0.2211475670337677, |
| "learning_rate": 7.83021191893682e-05, |
| "loss": 0.8352, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.5473887814313345, |
| "grad_norm": 0.23726575076580048, |
| "learning_rate": 5.9447467918700614e-05, |
| "loss": 0.819, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.6247582205029012, |
| "grad_norm": 0.2289407104253769, |
| "learning_rate": 4.219079997751515e-05, |
| "loss": 0.8318, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.702127659574468, |
| "grad_norm": 0.24488922953605652, |
| "learning_rate": 2.7212118963050592e-05, |
| "loss": 0.8544, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.7794970986460348, |
| "grad_norm": 0.2198326289653778, |
| "learning_rate": 1.5101663790863596e-05, |
| "loss": 0.8344, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.8568665377176017, |
| "grad_norm": 0.23588140308856964, |
| "learning_rate": 6.336650173127223e-06, |
| "loss": 0.859, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.9342359767891684, |
| "grad_norm": 0.22782348096370697, |
| "learning_rate": 1.2624658063666639e-06, |
| "loss": 0.7938, |
| "step": 250 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 258, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.590811292060877e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
