| { | |
| "best_metric": 1.733582854270935, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.01994813484939158, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007979253939756633, | |
| "grad_norm": 2.8838422298431396, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5275, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007979253939756633, | |
| "eval_loss": 3.5597481727600098, | |
| "eval_runtime": 78.3765, | |
| "eval_samples_per_second": 6.737, | |
| "eval_steps_per_second": 3.368, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015958507879513266, | |
| "grad_norm": 2.270010471343994, | |
| "learning_rate": 4e-05, | |
| "loss": 3.7981, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0023937761819269898, | |
| "grad_norm": 2.4229674339294434, | |
| "learning_rate": 6e-05, | |
| "loss": 3.5103, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003191701575902653, | |
| "grad_norm": 3.0669827461242676, | |
| "learning_rate": 8e-05, | |
| "loss": 4.3181, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003989626969878316, | |
| "grad_norm": 2.609445333480835, | |
| "learning_rate": 0.0001, | |
| "loss": 3.6593, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003989626969878316, | |
| "eval_loss": 3.453962564468384, | |
| "eval_runtime": 75.987, | |
| "eval_samples_per_second": 6.949, | |
| "eval_steps_per_second": 3.474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0047875523638539795, | |
| "grad_norm": 2.4561522006988525, | |
| "learning_rate": 0.00012, | |
| "loss": 3.4741, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005585477757829643, | |
| "grad_norm": 3.6380248069763184, | |
| "learning_rate": 0.00014, | |
| "loss": 3.6034, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006383403151805306, | |
| "grad_norm": 4.2364888191223145, | |
| "learning_rate": 0.00016, | |
| "loss": 3.1764, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00718132854578097, | |
| "grad_norm": 2.6599268913269043, | |
| "learning_rate": 0.00018, | |
| "loss": 2.7251, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007979253939756632, | |
| "grad_norm": 3.048786163330078, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7599, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007979253939756632, | |
| "eval_loss": 2.513199806213379, | |
| "eval_runtime": 76.0095, | |
| "eval_samples_per_second": 6.946, | |
| "eval_steps_per_second": 3.473, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008777179333732297, | |
| "grad_norm": 3.242194652557373, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 2.6828, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009575104727707959, | |
| "grad_norm": 3.6447784900665283, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 2.4083, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010373030121683623, | |
| "grad_norm": 3.447577476501465, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.7904, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011170955515659286, | |
| "grad_norm": 4.225980758666992, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 2.0227, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011968880909634948, | |
| "grad_norm": 3.9412906169891357, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.0159, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011968880909634948, | |
| "eval_loss": 1.8926352262496948, | |
| "eval_runtime": 76.1619, | |
| "eval_samples_per_second": 6.933, | |
| "eval_steps_per_second": 3.466, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012766806303610613, | |
| "grad_norm": 3.749465227127075, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.0085, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013564731697586275, | |
| "grad_norm": 3.92561936378479, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 1.7099, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01436265709156194, | |
| "grad_norm": 2.869910478591919, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 1.6106, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015160582485537602, | |
| "grad_norm": 2.9856624603271484, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.7619, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015958507879513265, | |
| "grad_norm": 2.9668376445770264, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.4858, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015958507879513265, | |
| "eval_loss": 1.760087490081787, | |
| "eval_runtime": 75.7956, | |
| "eval_samples_per_second": 6.966, | |
| "eval_steps_per_second": 3.483, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016756433273488927, | |
| "grad_norm": 3.524348020553589, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 1.9754, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.017554358667464593, | |
| "grad_norm": 3.734744071960449, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 2.0051, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.018352284061440256, | |
| "grad_norm": 2.849287509918213, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 1.6124, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019150209455415918, | |
| "grad_norm": 3.2284393310546875, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 1.8731, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01994813484939158, | |
| "grad_norm": 2.4725162982940674, | |
| "learning_rate": 0.0, | |
| "loss": 1.4547, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01994813484939158, | |
| "eval_loss": 1.733582854270935, | |
| "eval_runtime": 75.6746, | |
| "eval_samples_per_second": 6.977, | |
| "eval_steps_per_second": 3.489, | |
| "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": 4623910620364800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |