| { | |
| "best_metric": 0.410976380109787, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.004951261024292124, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00019805044097168497, | |
| "grad_norm": 0.3693576455116272, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4965, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00019805044097168497, | |
| "eval_loss": 1.5097695589065552, | |
| "eval_runtime": 3.0017, | |
| "eval_samples_per_second": 16.657, | |
| "eval_steps_per_second": 4.331, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00039610088194336993, | |
| "grad_norm": 0.5695458650588989, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7833, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000594151322915055, | |
| "grad_norm": 0.538998544216156, | |
| "learning_rate": 9.958086757163489e-05, | |
| "loss": 0.8395, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007922017638867399, | |
| "grad_norm": 0.48934289813041687, | |
| "learning_rate": 9.833127793065098e-05, | |
| "loss": 0.8156, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000990252204858425, | |
| "grad_norm": 0.5884993672370911, | |
| "learning_rate": 9.627450856774539e-05, | |
| "loss": 0.7746, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00118830264583011, | |
| "grad_norm": 0.942425012588501, | |
| "learning_rate": 9.3448873204592e-05, | |
| "loss": 0.7724, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013863530868017948, | |
| "grad_norm": 1.2021466493606567, | |
| "learning_rate": 8.990700808169889e-05, | |
| "loss": 0.7622, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0015844035277734797, | |
| "grad_norm": 1.1035913228988647, | |
| "learning_rate": 8.571489144483944e-05, | |
| "loss": 0.8172, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0017824539687451648, | |
| "grad_norm": 1.4270416498184204, | |
| "learning_rate": 8.095061449516903e-05, | |
| "loss": 0.7218, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00198050440971685, | |
| "grad_norm": 1.638703465461731, | |
| "learning_rate": 7.570292669790186e-05, | |
| "loss": 0.7281, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002178554850688535, | |
| "grad_norm": 1.686064600944519, | |
| "learning_rate": 7.006958254769438e-05, | |
| "loss": 0.8658, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00237660529166022, | |
| "grad_norm": 2.808910369873047, | |
| "learning_rate": 6.415552058736854e-05, | |
| "loss": 1.0043, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0025746557326319047, | |
| "grad_norm": 4.342678070068359, | |
| "learning_rate": 5.80709086014102e-05, | |
| "loss": 0.4586, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0027727061736035896, | |
| "grad_norm": 3.246701955795288, | |
| "learning_rate": 5.192909139858981e-05, | |
| "loss": 0.5144, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0029707566145752745, | |
| "grad_norm": 1.3120652437210083, | |
| "learning_rate": 4.584447941263149e-05, | |
| "loss": 0.5208, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0031688070555469594, | |
| "grad_norm": 1.1554656028747559, | |
| "learning_rate": 3.9930417452305626e-05, | |
| "loss": 0.5637, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003366857496518645, | |
| "grad_norm": 0.8644917607307434, | |
| "learning_rate": 3.4297073302098156e-05, | |
| "loss": 0.4661, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0035649079374903297, | |
| "grad_norm": 1.2488857507705688, | |
| "learning_rate": 2.9049385504830985e-05, | |
| "loss": 0.4439, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0037629583784620146, | |
| "grad_norm": 2.353053331375122, | |
| "learning_rate": 2.4285108555160577e-05, | |
| "loss": 0.4638, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0039610088194337, | |
| "grad_norm": 2.4651124477386475, | |
| "learning_rate": 2.0092991918301108e-05, | |
| "loss": 0.4453, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004159059260405384, | |
| "grad_norm": 2.5981829166412354, | |
| "learning_rate": 1.6551126795408016e-05, | |
| "loss": 0.5069, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00435710970137707, | |
| "grad_norm": 1.784904956817627, | |
| "learning_rate": 1.3725491432254624e-05, | |
| "loss": 0.5401, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004555160142348754, | |
| "grad_norm": 0.9995982646942139, | |
| "learning_rate": 1.1668722069349041e-05, | |
| "loss": 0.5714, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00475321058332044, | |
| "grad_norm": 1.417913556098938, | |
| "learning_rate": 1.0419132428365116e-05, | |
| "loss": 0.7382, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004951261024292124, | |
| "grad_norm": 3.399224042892456, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8122, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004951261024292124, | |
| "eval_loss": 0.410976380109787, | |
| "eval_runtime": 3.0576, | |
| "eval_samples_per_second": 16.353, | |
| "eval_steps_per_second": 4.252, | |
| "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": 2.6634211685721702e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |