| { | |
| "best_metric": 11.938733100891113, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.21668472372697725, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00866738894907909, | |
| "grad_norm": 0.014205647632479668, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 11.9344, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00866738894907909, | |
| "eval_loss": 11.943220138549805, | |
| "eval_runtime": 0.2668, | |
| "eval_samples_per_second": 187.436, | |
| "eval_steps_per_second": 48.733, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01733477789815818, | |
| "grad_norm": 0.021280059590935707, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 11.9345, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02600216684723727, | |
| "grad_norm": 0.026625456288456917, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9361, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03466955579631636, | |
| "grad_norm": 0.031291306018829346, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 11.9349, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04333694474539545, | |
| "grad_norm": 0.036243926733732224, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 11.9361, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05200433369447454, | |
| "grad_norm": 0.04476647451519966, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9369, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06067172264355363, | |
| "grad_norm": 0.05329675227403641, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 11.9366, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06933911159263272, | |
| "grad_norm": 0.05616913363337517, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 11.9381, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0780065005417118, | |
| "grad_norm": 0.06590206176042557, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.9394, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0866738894907909, | |
| "grad_norm": 0.08881666511297226, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 11.9406, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09534127843986999, | |
| "grad_norm": 0.11582574248313904, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 11.9429, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10400866738894908, | |
| "grad_norm": 0.15351854264736176, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.9471, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": 0.02668151818215847, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 11.9345, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12134344528710726, | |
| "grad_norm": 0.022617211565375328, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 11.9325, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13001083423618634, | |
| "grad_norm": 0.027192845940589905, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.9352, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13867822318526543, | |
| "grad_norm": 0.03240914270281792, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 11.9353, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.14734561213434452, | |
| "grad_norm": 0.042475830763578415, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 11.935, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1560130010834236, | |
| "grad_norm": 0.049555882811546326, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.9354, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1646803900325027, | |
| "grad_norm": 0.053182654082775116, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 11.935, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1733477789815818, | |
| "grad_norm": 0.06439302861690521, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 11.936, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1820151679306609, | |
| "grad_norm": 0.07124801725149155, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.9372, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19068255687973998, | |
| "grad_norm": 0.09465167671442032, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 11.9363, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19934994582881907, | |
| "grad_norm": 0.12675674259662628, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 11.9384, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20801733477789816, | |
| "grad_norm": 0.16636888682842255, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.9427, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21668472372697725, | |
| "grad_norm": 0.2566799223423004, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 11.9439, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.21668472372697725, | |
| "eval_loss": 11.938733100891113, | |
| "eval_runtime": 0.2609, | |
| "eval_samples_per_second": 191.665, | |
| "eval_steps_per_second": 49.833, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 522713137152.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |