| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 26.666666666666668, | |
| "eval_steps": 500, | |
| "global_step": 90, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 1.0835238695144653, | |
| "learning_rate": 0.00019555555555555556, | |
| "loss": 9.4668, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 1.3387597799301147, | |
| "learning_rate": 0.00019111111111111114, | |
| "loss": 9.0964, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 2.4566526412963867, | |
| "learning_rate": 0.0001866666666666667, | |
| "loss": 8.5058, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 1.337947964668274, | |
| "learning_rate": 0.00018222222222222224, | |
| "loss": 7.8295, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.9213329553604126, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 7.55, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.8294873237609863, | |
| "learning_rate": 0.00017333333333333334, | |
| "loss": 7.4103, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 1.0435646772384644, | |
| "learning_rate": 0.00016888888888888889, | |
| "loss": 7.3669, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 2.152470111846924, | |
| "learning_rate": 0.00016444444444444444, | |
| "loss": 7.3731, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.6850627064704895, | |
| "learning_rate": 0.00016, | |
| "loss": 7.3274, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 5.925925925925926, | |
| "grad_norm": 0.9927621483802795, | |
| "learning_rate": 0.00015555555555555556, | |
| "loss": 7.2687, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 6.518518518518518, | |
| "grad_norm": 0.6255151629447937, | |
| "learning_rate": 0.0001511111111111111, | |
| "loss": 7.2457, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 7.111111111111111, | |
| "grad_norm": 0.4171934425830841, | |
| "learning_rate": 0.00014666666666666666, | |
| "loss": 7.265, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 7.703703703703704, | |
| "grad_norm": 0.7594227194786072, | |
| "learning_rate": 0.00014222222222222224, | |
| "loss": 7.2059, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 8.296296296296296, | |
| "grad_norm": 0.6241652965545654, | |
| "learning_rate": 0.0001377777777777778, | |
| "loss": 7.2223, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": 0.6361931562423706, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 7.1813, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 9.481481481481481, | |
| "grad_norm": 0.40144020318984985, | |
| "learning_rate": 0.00012888888888888892, | |
| "loss": 7.1944, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 10.074074074074074, | |
| "grad_norm": 0.8601672053337097, | |
| "learning_rate": 0.00012444444444444444, | |
| "loss": 7.191, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 10.666666666666666, | |
| "grad_norm": 0.47764790058135986, | |
| "learning_rate": 0.00012, | |
| "loss": 7.1806, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 11.25925925925926, | |
| "grad_norm": 0.6741082072257996, | |
| "learning_rate": 0.00011555555555555555, | |
| "loss": 7.1588, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 11.851851851851851, | |
| "grad_norm": 0.320622056722641, | |
| "learning_rate": 0.00011111111111111112, | |
| "loss": 7.1678, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 12.444444444444445, | |
| "grad_norm": 0.41680437326431274, | |
| "learning_rate": 0.00010666666666666667, | |
| "loss": 7.1937, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 13.037037037037036, | |
| "grad_norm": 0.5265238285064697, | |
| "learning_rate": 0.00010222222222222222, | |
| "loss": 7.1729, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 13.62962962962963, | |
| "grad_norm": 0.2438785880804062, | |
| "learning_rate": 9.777777777777778e-05, | |
| "loss": 7.1447, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 14.222222222222221, | |
| "grad_norm": 0.2717892527580261, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 7.1401, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 14.814814814814815, | |
| "grad_norm": 0.27455106377601624, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 7.1263, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 15.407407407407407, | |
| "grad_norm": 0.32036423683166504, | |
| "learning_rate": 8.444444444444444e-05, | |
| "loss": 7.1606, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 0.3542112708091736, | |
| "learning_rate": 8e-05, | |
| "loss": 7.1612, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 16.59259259259259, | |
| "grad_norm": 0.2720729112625122, | |
| "learning_rate": 7.555555555555556e-05, | |
| "loss": 7.157, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 17.185185185185187, | |
| "grad_norm": 0.4563415050506592, | |
| "learning_rate": 7.111111111111112e-05, | |
| "loss": 7.1165, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "grad_norm": 0.3706892430782318, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 7.1504, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 18.37037037037037, | |
| "grad_norm": 0.4367642402648926, | |
| "learning_rate": 6.222222222222222e-05, | |
| "loss": 7.1585, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 18.962962962962962, | |
| "grad_norm": 0.35599270462989807, | |
| "learning_rate": 5.7777777777777776e-05, | |
| "loss": 7.121, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 19.555555555555557, | |
| "grad_norm": 0.28254929184913635, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 7.1481, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 20.14814814814815, | |
| "grad_norm": 0.3943895399570465, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 7.1082, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 20.74074074074074, | |
| "grad_norm": 0.2905910313129425, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 7.1596, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 21.333333333333332, | |
| "grad_norm": 0.33000853657722473, | |
| "learning_rate": 4e-05, | |
| "loss": 7.1279, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 21.925925925925927, | |
| "grad_norm": 0.30440381169319153, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 7.1007, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 22.51851851851852, | |
| "grad_norm": 0.31049448251724243, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 7.1304, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 23.11111111111111, | |
| "grad_norm": 0.33641088008880615, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 7.1468, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 23.703703703703702, | |
| "grad_norm": 0.5838092565536499, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 7.1533, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 24.296296296296298, | |
| "grad_norm": 0.2617644965648651, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 7.1076, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 24.88888888888889, | |
| "grad_norm": 0.23922277987003326, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 7.1408, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 25.48148148148148, | |
| "grad_norm": 0.28710824251174927, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 7.0894, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 26.074074074074073, | |
| "grad_norm": 0.5698680877685547, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 7.1309, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 0.3135036528110504, | |
| "learning_rate": 0.0, | |
| "loss": 7.1452, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "step": 90, | |
| "total_flos": 410861219852448.0, | |
| "train_loss": 7.326659817165798, | |
| "train_runtime": 2404.3353, | |
| "train_samples_per_second": 0.674, | |
| "train_steps_per_second": 0.037 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 90, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "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": 410861219852448.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |