| { | |
| "best_metric": 1.4513202905654907, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0020567667626491155, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.227067050596462e-05, | |
| "grad_norm": 3.947374105453491, | |
| "learning_rate": 2e-05, | |
| "loss": 5.6138, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.227067050596462e-05, | |
| "eval_loss": 1.5118179321289062, | |
| "eval_runtime": 990.3773, | |
| "eval_samples_per_second": 5.168, | |
| "eval_steps_per_second": 2.584, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016454134101192923, | |
| "grad_norm": 5.0255255699157715, | |
| "learning_rate": 4e-05, | |
| "loss": 7.0739, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00024681201151789385, | |
| "grad_norm": 2.599471092224121, | |
| "learning_rate": 6e-05, | |
| "loss": 6.2316, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00032908268202385847, | |
| "grad_norm": 3.12210750579834, | |
| "learning_rate": 8e-05, | |
| "loss": 5.6966, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00041135335252982314, | |
| "grad_norm": 2.7087185382843018, | |
| "learning_rate": 0.0001, | |
| "loss": 6.3187, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00041135335252982314, | |
| "eval_loss": 1.4958966970443726, | |
| "eval_runtime": 945.0184, | |
| "eval_samples_per_second": 5.416, | |
| "eval_steps_per_second": 2.708, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004936240230357877, | |
| "grad_norm": 2.585333824157715, | |
| "learning_rate": 0.00012, | |
| "loss": 6.3612, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005758946935417523, | |
| "grad_norm": 2.1012344360351562, | |
| "learning_rate": 0.00014, | |
| "loss": 6.218, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006581653640477169, | |
| "grad_norm": 3.0408711433410645, | |
| "learning_rate": 0.00016, | |
| "loss": 6.6268, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007404360345536817, | |
| "grad_norm": 2.718195915222168, | |
| "learning_rate": 0.00018, | |
| "loss": 5.8723, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008227067050596463, | |
| "grad_norm": 3.4171600341796875, | |
| "learning_rate": 0.0002, | |
| "loss": 6.7864, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008227067050596463, | |
| "eval_loss": 1.4742869138717651, | |
| "eval_runtime": 974.0111, | |
| "eval_samples_per_second": 5.255, | |
| "eval_steps_per_second": 2.627, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009049773755656109, | |
| "grad_norm": 3.754530668258667, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 6.7109, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0009872480460715754, | |
| "grad_norm": 2.7262985706329346, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 6.0774, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0010695187165775401, | |
| "grad_norm": 2.529963254928589, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 5.9247, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0011517893870835046, | |
| "grad_norm": 3.371697425842285, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 6.4366, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0012340600575894694, | |
| "grad_norm": 3.3902432918548584, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.9649, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0012340600575894694, | |
| "eval_loss": 1.4562937021255493, | |
| "eval_runtime": 946.1588, | |
| "eval_samples_per_second": 5.409, | |
| "eval_steps_per_second": 2.705, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013163307280954339, | |
| "grad_norm": 2.6186981201171875, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 5.7222, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0013986013986013986, | |
| "grad_norm": 2.9605960845947266, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 5.6037, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0014808720691073633, | |
| "grad_norm": 2.3991353511810303, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 5.9318, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0015631427396133278, | |
| "grad_norm": 1.7448457479476929, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 5.5354, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0016454134101192926, | |
| "grad_norm": 3.0942559242248535, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 5.8968, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016454134101192926, | |
| "eval_loss": 1.45272696018219, | |
| "eval_runtime": 953.2521, | |
| "eval_samples_per_second": 5.369, | |
| "eval_steps_per_second": 2.684, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001727684080625257, | |
| "grad_norm": 3.263594150543213, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 7.3905, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018099547511312218, | |
| "grad_norm": 2.3657073974609375, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 5.9281, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0018922254216371863, | |
| "grad_norm": 2.6124701499938965, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 6.014, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.001974496092143151, | |
| "grad_norm": 2.2480545043945312, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 5.6176, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0020567667626491155, | |
| "grad_norm": 3.322998046875, | |
| "learning_rate": 0.0, | |
| "loss": 5.9863, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0020567667626491155, | |
| "eval_loss": 1.4513202905654907, | |
| "eval_runtime": 946.2132, | |
| "eval_samples_per_second": 5.409, | |
| "eval_steps_per_second": 2.704, | |
| "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": 1000864902807552.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |