| { | |
| "best_metric": 0.1358620524406433, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.26498840675720436, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010599536270288175, | |
| "grad_norm": 0.9020842909812927, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5214, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010599536270288175, | |
| "eval_loss": 1.1881606578826904, | |
| "eval_runtime": 12.2335, | |
| "eval_samples_per_second": 4.087, | |
| "eval_steps_per_second": 4.087, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02119907254057635, | |
| "grad_norm": 0.8387324810028076, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5454, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03179860881086453, | |
| "grad_norm": 0.8732652068138123, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.4911, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0423981450811527, | |
| "grad_norm": 0.7336243987083435, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.3444, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.052997681351440874, | |
| "grad_norm": 1.0660020112991333, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.3295, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06359721762172905, | |
| "grad_norm": 1.1278345584869385, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.3247, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07419675389201723, | |
| "grad_norm": 1.028996229171753, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.2397, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0847962901623054, | |
| "grad_norm": 0.8584328889846802, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.1836, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09539582643259358, | |
| "grad_norm": 1.0757900476455688, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.2406, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10599536270288175, | |
| "grad_norm": 0.8207722902297974, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.1764, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11659489897316992, | |
| "grad_norm": 0.690769612789154, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.1927, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1271944352434581, | |
| "grad_norm": 0.795420229434967, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 0.1635, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.13779397151374628, | |
| "grad_norm": 0.7445429563522339, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.1299, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.14839350778403446, | |
| "grad_norm": 0.7692167162895203, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.147, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.15899304405432263, | |
| "grad_norm": 0.8508386015892029, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.194, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1695925803246108, | |
| "grad_norm": 0.7124083638191223, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.0985, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18019211659489898, | |
| "grad_norm": 0.7584179043769836, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.18, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19079165286518715, | |
| "grad_norm": 0.7822820544242859, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.2019, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.20139118913547532, | |
| "grad_norm": 0.6126951575279236, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.1246, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2119907254057635, | |
| "grad_norm": 0.7897605299949646, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.154, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22259026167605167, | |
| "grad_norm": 0.7112305164337158, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.1545, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.23318979794633984, | |
| "grad_norm": 0.5926163196563721, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.1246, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.24378933421662802, | |
| "grad_norm": 1.038179636001587, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.1869, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2543888704869162, | |
| "grad_norm": 0.4667412042617798, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 0.0979, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.26498840675720436, | |
| "grad_norm": 0.4274519681930542, | |
| "learning_rate": 1e-05, | |
| "loss": 0.1046, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.26498840675720436, | |
| "eval_loss": 0.1358620524406433, | |
| "eval_runtime": 12.4386, | |
| "eval_samples_per_second": 4.02, | |
| "eval_steps_per_second": 4.02, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.46010452164608e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |