| { | |
| "best_metric": 0.6138322353363037, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.006159152500615915, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002463661000246366, | |
| "grad_norm": 0.5469629764556885, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9891, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002463661000246366, | |
| "eval_loss": 0.8779290318489075, | |
| "eval_runtime": 313.0811, | |
| "eval_samples_per_second": 5.459, | |
| "eval_steps_per_second": 2.731, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004927322000492732, | |
| "grad_norm": 0.5583520531654358, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5833, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007390983000739098, | |
| "grad_norm": 0.41663986444473267, | |
| "learning_rate": 6e-05, | |
| "loss": 0.5106, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009854644000985464, | |
| "grad_norm": 0.4580349028110504, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7081, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001231830500123183, | |
| "grad_norm": 0.3514888882637024, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4564, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001231830500123183, | |
| "eval_loss": 0.8547623157501221, | |
| "eval_runtime": 311.5363, | |
| "eval_samples_per_second": 5.486, | |
| "eval_steps_per_second": 2.744, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014781966001478197, | |
| "grad_norm": 0.5555539131164551, | |
| "learning_rate": 0.00012, | |
| "loss": 0.6882, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017245627001724563, | |
| "grad_norm": 0.3112781345844269, | |
| "learning_rate": 0.00014, | |
| "loss": 0.3356, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.001970928800197093, | |
| "grad_norm": 0.5190461874008179, | |
| "learning_rate": 0.00016, | |
| "loss": 0.6538, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0022172949002217295, | |
| "grad_norm": 0.4782675504684448, | |
| "learning_rate": 0.00018, | |
| "loss": 1.078, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002463661000246366, | |
| "grad_norm": 0.42852485179901123, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8526, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002463661000246366, | |
| "eval_loss": 0.7292912006378174, | |
| "eval_runtime": 311.1124, | |
| "eval_samples_per_second": 5.493, | |
| "eval_steps_per_second": 2.748, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0027100271002710027, | |
| "grad_norm": 0.4965437054634094, | |
| "learning_rate": 0.00019781476007338058, | |
| "loss": 0.5197, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0029563932002956393, | |
| "grad_norm": 0.6098279356956482, | |
| "learning_rate": 0.0001913545457642601, | |
| "loss": 0.5851, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003202759300320276, | |
| "grad_norm": 0.5826135873794556, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.643, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0034491254003449125, | |
| "grad_norm": 0.4636547565460205, | |
| "learning_rate": 0.00016691306063588583, | |
| "loss": 0.4137, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003695491500369549, | |
| "grad_norm": 0.6051448583602905, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.3466, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003695491500369549, | |
| "eval_loss": 0.6458022594451904, | |
| "eval_runtime": 311.6704, | |
| "eval_samples_per_second": 5.483, | |
| "eval_steps_per_second": 2.743, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003941857600394186, | |
| "grad_norm": 0.5250495672225952, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.6101, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004188223700418822, | |
| "grad_norm": 0.4610646367073059, | |
| "learning_rate": 0.00011045284632676536, | |
| "loss": 0.5967, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004434589800443459, | |
| "grad_norm": 0.4124172627925873, | |
| "learning_rate": 8.954715367323468e-05, | |
| "loss": 0.5159, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004680955900468096, | |
| "grad_norm": 0.3477323651313782, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.4371, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004927322000492732, | |
| "grad_norm": 0.36285078525543213, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.6104, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004927322000492732, | |
| "eval_loss": 0.6183786392211914, | |
| "eval_runtime": 317.4187, | |
| "eval_samples_per_second": 5.384, | |
| "eval_steps_per_second": 2.694, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005173688100517369, | |
| "grad_norm": 0.39517274498939514, | |
| "learning_rate": 3.308693936411421e-05, | |
| "loss": 0.8512, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005420054200542005, | |
| "grad_norm": 0.35510003566741943, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.8077, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005666420300566642, | |
| "grad_norm": 0.23273567855358124, | |
| "learning_rate": 8.645454235739903e-06, | |
| "loss": 0.2846, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005912786400591279, | |
| "grad_norm": 0.38091930747032166, | |
| "learning_rate": 2.1852399266194314e-06, | |
| "loss": 0.8437, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006159152500615915, | |
| "grad_norm": 0.3586118817329407, | |
| "learning_rate": 0.0, | |
| "loss": 0.8139, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006159152500615915, | |
| "eval_loss": 0.6138322353363037, | |
| "eval_runtime": 316.5536, | |
| "eval_samples_per_second": 5.399, | |
| "eval_steps_per_second": 2.701, | |
| "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": 7906887160823808.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |