| { | |
| "best_metric": 2.192828893661499, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.06180469715698393, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002472187886279357, | |
| "grad_norm": 3.027806520462036, | |
| "learning_rate": 2e-05, | |
| "loss": 3.2903, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002472187886279357, | |
| "eval_loss": 3.3662045001983643, | |
| "eval_runtime": 39.5364, | |
| "eval_samples_per_second": 4.325, | |
| "eval_steps_per_second": 2.175, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004944375772558714, | |
| "grad_norm": 3.298875570297241, | |
| "learning_rate": 4e-05, | |
| "loss": 2.9307, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007416563658838072, | |
| "grad_norm": 5.236861228942871, | |
| "learning_rate": 6e-05, | |
| "loss": 3.5628, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009888751545117428, | |
| "grad_norm": 2.9144644737243652, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8374, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012360939431396786, | |
| "grad_norm": 3.148221731185913, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7625, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012360939431396786, | |
| "eval_loss": 3.0952134132385254, | |
| "eval_runtime": 40.936, | |
| "eval_samples_per_second": 4.177, | |
| "eval_steps_per_second": 2.101, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014833127317676144, | |
| "grad_norm": 3.250784158706665, | |
| "learning_rate": 0.00012, | |
| "loss": 2.8753, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0173053152039555, | |
| "grad_norm": 2.7544045448303223, | |
| "learning_rate": 0.00014, | |
| "loss": 2.7558, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019777503090234856, | |
| "grad_norm": 3.0907797813415527, | |
| "learning_rate": 0.00016, | |
| "loss": 2.6975, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022249690976514216, | |
| "grad_norm": 4.045582294464111, | |
| "learning_rate": 0.00018, | |
| "loss": 2.5026, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024721878862793572, | |
| "grad_norm": 5.466610431671143, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6372, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024721878862793572, | |
| "eval_loss": 2.473076343536377, | |
| "eval_runtime": 42.2937, | |
| "eval_samples_per_second": 4.043, | |
| "eval_steps_per_second": 2.033, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027194066749072928, | |
| "grad_norm": 2.8220388889312744, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.414, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.029666254635352288, | |
| "grad_norm": 2.93212890625, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.1275, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.032138442521631644, | |
| "grad_norm": 4.090857982635498, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 2.749, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.034610630407911, | |
| "grad_norm": 3.273655414581299, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.0628, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.037082818294190356, | |
| "grad_norm": 2.5305113792419434, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.3392, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.037082818294190356, | |
| "eval_loss": 2.295578718185425, | |
| "eval_runtime": 44.7285, | |
| "eval_samples_per_second": 3.823, | |
| "eval_steps_per_second": 1.923, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03955500618046971, | |
| "grad_norm": 2.3927266597747803, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.1773, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.042027194066749075, | |
| "grad_norm": 3.170795202255249, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 2.3366, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04449938195302843, | |
| "grad_norm": 3.0512592792510986, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 2.4167, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04697156983930779, | |
| "grad_norm": 2.5195651054382324, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.9421, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.049443757725587144, | |
| "grad_norm": 1.8259810209274292, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.9974, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.049443757725587144, | |
| "eval_loss": 2.213010311126709, | |
| "eval_runtime": 41.4947, | |
| "eval_samples_per_second": 4.121, | |
| "eval_steps_per_second": 2.073, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0519159456118665, | |
| "grad_norm": 2.4947733879089355, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 2.2319, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.054388133498145856, | |
| "grad_norm": 2.533128023147583, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.3865, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05686032138442522, | |
| "grad_norm": 2.4493701457977295, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 2.252, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.059332509270704575, | |
| "grad_norm": 1.7773404121398926, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.9413, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06180469715698393, | |
| "grad_norm": 2.166700601577759, | |
| "learning_rate": 0.0, | |
| "loss": 2.3894, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06180469715698393, | |
| "eval_loss": 2.192828893661499, | |
| "eval_runtime": 41.0714, | |
| "eval_samples_per_second": 4.163, | |
| "eval_steps_per_second": 2.094, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1480670324981760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |