| { | |
| "best_metric": 3.1342406272888184, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01613228473482557, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006452913893930228, | |
| "grad_norm": 0.5631341934204102, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3164, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006452913893930228, | |
| "eval_loss": 3.6528780460357666, | |
| "eval_runtime": 1.8185, | |
| "eval_samples_per_second": 27.495, | |
| "eval_steps_per_second": 7.149, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012905827787860456, | |
| "grad_norm": 0.7973557710647583, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3274, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0019358741681790683, | |
| "grad_norm": 0.8007791042327881, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.382, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002581165557572091, | |
| "grad_norm": 0.7314369678497314, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.3105, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003226456946965114, | |
| "grad_norm": 0.7187217473983765, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.2995, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0038717483363581366, | |
| "grad_norm": 0.7889419198036194, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.2893, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004517039725751159, | |
| "grad_norm": 0.6888266801834106, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.2479, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005162331115144182, | |
| "grad_norm": 0.764917254447937, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 3.264, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005807622504537205, | |
| "grad_norm": 0.8784753084182739, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 3.4395, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006452913893930228, | |
| "grad_norm": 0.8352928757667542, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 3.5471, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007098205283323251, | |
| "grad_norm": 0.8680716753005981, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.4538, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007743496672716273, | |
| "grad_norm": 1.9051700830459595, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 3.4912, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008388788062109296, | |
| "grad_norm": 2.840733766555786, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.384, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009034079451502319, | |
| "grad_norm": 2.835117816925049, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.3401, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009679370840895343, | |
| "grad_norm": 1.942787528038025, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 3.2027, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010324662230288365, | |
| "grad_norm": 0.9424628615379333, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.1445, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010969953619681387, | |
| "grad_norm": 0.8486276865005493, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.1109, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01161524500907441, | |
| "grad_norm": 1.0867027044296265, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.1341, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012260536398467433, | |
| "grad_norm": 1.185585618019104, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.1287, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012905827787860456, | |
| "grad_norm": 0.5100924372673035, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.1871, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013551119177253478, | |
| "grad_norm": 0.6486760377883911, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.1607, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014196410566646502, | |
| "grad_norm": 0.8669289946556091, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.3634, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014841701956039524, | |
| "grad_norm": 0.8486496210098267, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.4392, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.015486993345432546, | |
| "grad_norm": 1.0553802251815796, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.4503, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01613228473482557, | |
| "grad_norm": 1.206745982170105, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 3.5133, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01613228473482557, | |
| "eval_loss": 3.1342406272888184, | |
| "eval_runtime": 1.1541, | |
| "eval_samples_per_second": 43.326, | |
| "eval_steps_per_second": 11.265, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.114626154561536e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |