| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "eval_steps": 500, |
| "global_step": 50, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2, |
| "grad_norm": 0.23638540506362915, |
| "learning_rate": 1e-05, |
| "loss": 0.03748631849884987, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.24871790409088135, |
| "learning_rate": 9.800000000000001e-06, |
| "loss": 0.02071208506822586, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 0.659176766872406, |
| "learning_rate": 9.600000000000001e-06, |
| "loss": 0.08492697030305862, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.5017268061637878, |
| "learning_rate": 9.4e-06, |
| "loss": 0.06373442709445953, |
| "step": 4 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.5318911671638489, |
| "learning_rate": 9.200000000000002e-06, |
| "loss": 0.0942009761929512, |
| "step": 5 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 0.2209520936012268, |
| "learning_rate": 9e-06, |
| "loss": 0.019313231110572815, |
| "step": 6 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 0.501861572265625, |
| "learning_rate": 8.8e-06, |
| "loss": 0.060948677361011505, |
| "step": 7 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 0.5123077630996704, |
| "learning_rate": 8.6e-06, |
| "loss": 0.07889888435602188, |
| "step": 8 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 0.30701160430908203, |
| "learning_rate": 8.400000000000001e-06, |
| "loss": 0.047030009329319, |
| "step": 9 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.470781147480011, |
| "learning_rate": 8.2e-06, |
| "loss": 0.07686996459960938, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.2, |
| "grad_norm": 0.19430357217788696, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.0327804833650589, |
| "step": 11 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 0.5163173079490662, |
| "learning_rate": 7.800000000000002e-06, |
| "loss": 0.0699235051870346, |
| "step": 12 |
| }, |
| { |
| "epoch": 2.6, |
| "grad_norm": 0.43405282497406006, |
| "learning_rate": 7.600000000000001e-06, |
| "loss": 0.058998964726924896, |
| "step": 13 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 0.16127917170524597, |
| "learning_rate": 7.4e-06, |
| "loss": 0.020424678921699524, |
| "step": 14 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.5113937258720398, |
| "learning_rate": 7.2000000000000005e-06, |
| "loss": 0.0865558534860611, |
| "step": 15 |
| }, |
| { |
| "epoch": 3.2, |
| "grad_norm": 0.26205581426620483, |
| "learning_rate": 7e-06, |
| "loss": 0.043833862990140915, |
| "step": 16 |
| }, |
| { |
| "epoch": 3.4, |
| "grad_norm": 0.7279136776924133, |
| "learning_rate": 6.800000000000001e-06, |
| "loss": 0.12289629876613617, |
| "step": 17 |
| }, |
| { |
| "epoch": 3.6, |
| "grad_norm": 0.36075446009635925, |
| "learning_rate": 6.600000000000001e-06, |
| "loss": 0.04190639778971672, |
| "step": 18 |
| }, |
| { |
| "epoch": 3.8, |
| "grad_norm": 0.21748273074626923, |
| "learning_rate": 6.4000000000000006e-06, |
| "loss": 0.028236374258995056, |
| "step": 19 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.11316434293985367, |
| "learning_rate": 6.200000000000001e-06, |
| "loss": 0.02187465876340866, |
| "step": 20 |
| }, |
| { |
| "epoch": 4.2, |
| "grad_norm": 0.46911606192588806, |
| "learning_rate": 6e-06, |
| "loss": 0.07013603299856186, |
| "step": 21 |
| }, |
| { |
| "epoch": 4.4, |
| "grad_norm": 0.5346769094467163, |
| "learning_rate": 5.8e-06, |
| "loss": 0.06986264884471893, |
| "step": 22 |
| }, |
| { |
| "epoch": 4.6, |
| "grad_norm": 0.18702906370162964, |
| "learning_rate": 5.600000000000001e-06, |
| "loss": 0.02777681313455105, |
| "step": 23 |
| }, |
| { |
| "epoch": 4.8, |
| "grad_norm": 0.34534305334091187, |
| "learning_rate": 5.400000000000001e-06, |
| "loss": 0.03661029785871506, |
| "step": 24 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.26124849915504456, |
| "learning_rate": 5.2e-06, |
| "loss": 0.044447772204875946, |
| "step": 25 |
| }, |
| { |
| "epoch": 5.2, |
| "grad_norm": 0.7143075466156006, |
| "learning_rate": 5e-06, |
| "loss": 0.08767477422952652, |
| "step": 26 |
| }, |
| { |
| "epoch": 5.4, |
| "grad_norm": 0.4375913441181183, |
| "learning_rate": 4.800000000000001e-06, |
| "loss": 0.06535093486309052, |
| "step": 27 |
| }, |
| { |
| "epoch": 5.6, |
| "grad_norm": 0.16346432268619537, |
| "learning_rate": 4.600000000000001e-06, |
| "loss": 0.023847032338380814, |
| "step": 28 |
| }, |
| { |
| "epoch": 5.8, |
| "grad_norm": 0.250222384929657, |
| "learning_rate": 4.4e-06, |
| "loss": 0.043669044971466064, |
| "step": 29 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.1317228376865387, |
| "learning_rate": 4.2000000000000004e-06, |
| "loss": 0.021536512300372124, |
| "step": 30 |
| }, |
| { |
| "epoch": 6.2, |
| "grad_norm": 0.1009778305888176, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.015370301902294159, |
| "step": 31 |
| }, |
| { |
| "epoch": 6.4, |
| "grad_norm": 0.6650776863098145, |
| "learning_rate": 3.8000000000000005e-06, |
| "loss": 0.11082910001277924, |
| "step": 32 |
| }, |
| { |
| "epoch": 6.6, |
| "grad_norm": 0.3372114896774292, |
| "learning_rate": 3.6000000000000003e-06, |
| "loss": 0.0402531735599041, |
| "step": 33 |
| }, |
| { |
| "epoch": 6.8, |
| "grad_norm": 0.1697712540626526, |
| "learning_rate": 3.4000000000000005e-06, |
| "loss": 0.02657049335539341, |
| "step": 34 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.24037496745586395, |
| "learning_rate": 3.2000000000000003e-06, |
| "loss": 0.042785875499248505, |
| "step": 35 |
| }, |
| { |
| "epoch": 7.2, |
| "grad_norm": 0.5006395578384399, |
| "learning_rate": 3e-06, |
| "loss": 0.07394951581954956, |
| "step": 36 |
| }, |
| { |
| "epoch": 7.4, |
| "grad_norm": 0.46958982944488525, |
| "learning_rate": 2.8000000000000003e-06, |
| "loss": 0.06693384796380997, |
| "step": 37 |
| }, |
| { |
| "epoch": 7.6, |
| "grad_norm": 0.21251286566257477, |
| "learning_rate": 2.6e-06, |
| "loss": 0.03206902742385864, |
| "step": 38 |
| }, |
| { |
| "epoch": 7.8, |
| "grad_norm": 0.09421742707490921, |
| "learning_rate": 2.4000000000000003e-06, |
| "loss": 0.015086423605680466, |
| "step": 39 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.3681463897228241, |
| "learning_rate": 2.2e-06, |
| "loss": 0.044432226568460464, |
| "step": 40 |
| }, |
| { |
| "epoch": 8.2, |
| "grad_norm": 0.11850324273109436, |
| "learning_rate": 2.0000000000000003e-06, |
| "loss": 0.018159169703722, |
| "step": 41 |
| }, |
| { |
| "epoch": 8.4, |
| "grad_norm": 0.4186587929725647, |
| "learning_rate": 1.8000000000000001e-06, |
| "loss": 0.07121849060058594, |
| "step": 42 |
| }, |
| { |
| "epoch": 8.6, |
| "grad_norm": 0.3460211157798767, |
| "learning_rate": 1.6000000000000001e-06, |
| "loss": 0.03904581442475319, |
| "step": 43 |
| }, |
| { |
| "epoch": 8.8, |
| "grad_norm": 0.4996100962162018, |
| "learning_rate": 1.4000000000000001e-06, |
| "loss": 0.05915703624486923, |
| "step": 44 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.23112986981868744, |
| "learning_rate": 1.2000000000000002e-06, |
| "loss": 0.0419197604060173, |
| "step": 45 |
| }, |
| { |
| "epoch": 9.2, |
| "grad_norm": 0.17390993237495422, |
| "learning_rate": 1.0000000000000002e-06, |
| "loss": 0.02823176607489586, |
| "step": 46 |
| }, |
| { |
| "epoch": 9.4, |
| "grad_norm": 0.5298067927360535, |
| "learning_rate": 8.000000000000001e-07, |
| "loss": 0.07540108263492584, |
| "step": 47 |
| }, |
| { |
| "epoch": 9.6, |
| "grad_norm": 0.34885483980178833, |
| "learning_rate": 6.000000000000001e-07, |
| "loss": 0.03874276578426361, |
| "step": 48 |
| }, |
| { |
| "epoch": 9.8, |
| "grad_norm": 0.16484539210796356, |
| "learning_rate": 4.0000000000000003e-07, |
| "loss": 0.025954462587833405, |
| "step": 49 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.39541739225387573, |
| "learning_rate": 2.0000000000000002e-07, |
| "loss": 0.05980378016829491, |
| "step": 50 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 50, |
| "total_flos": 4.094261748301824e+17, |
| "train_loss": 0.0505675720050931, |
| "train_runtime": 75.7009, |
| "train_samples_per_second": 1.321, |
| "train_steps_per_second": 0.66 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 50, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "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": 4.094261748301824e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
