| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.6024096385542169, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012048192771084338, | |
| "grad_norm": 9.518840789794922, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0901, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012048192771084338, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.9575, | |
| "eval_samples_per_second": 19.304, | |
| "eval_steps_per_second": 2.417, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.024096385542168676, | |
| "grad_norm": 10.21586799621582, | |
| "learning_rate": 0.0001, | |
| "loss": 3.807, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03614457831325301, | |
| "grad_norm": 7.955934047698975, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.8164, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04819277108433735, | |
| "grad_norm": 5.005773067474365, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.8812, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.060240963855421686, | |
| "grad_norm": 3.6119229793548584, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.432, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07228915662650602, | |
| "grad_norm": 3.380969762802124, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.0891, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08433734939759036, | |
| "grad_norm": 3.353749990463257, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.9375, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0963855421686747, | |
| "grad_norm": 2.2520077228546143, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8165, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10843373493975904, | |
| "grad_norm": 1.9691568613052368, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.7346, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12048192771084337, | |
| "grad_norm": 2.36018443107605, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7562, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13253012048192772, | |
| "grad_norm": 6.809185981750488, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0927, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14457831325301204, | |
| "grad_norm": 7.188030242919922, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8109, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1566265060240964, | |
| "grad_norm": 17.54526710510254, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.836, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1686746987951807, | |
| "grad_norm": 12.532405853271484, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.7006, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.18072289156626506, | |
| "grad_norm": 8.625960350036621, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.3264, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1927710843373494, | |
| "grad_norm": 6.110639572143555, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.1084, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.20481927710843373, | |
| "grad_norm": 3.7198574542999268, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.9261, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.21686746987951808, | |
| "grad_norm": 1.9800914525985718, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7454, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2289156626506024, | |
| "grad_norm": 1.4259741306304932, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7098, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.24096385542168675, | |
| "grad_norm": 1.3230398893356323, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6152, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25301204819277107, | |
| "grad_norm": 1.4084607362747192, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5873, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.26506024096385544, | |
| "grad_norm": 1.6322895288467407, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6166, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.27710843373493976, | |
| "grad_norm": 4.194338798522949, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.973, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2891566265060241, | |
| "grad_norm": 7.518647193908691, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.0908, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.30120481927710846, | |
| "grad_norm": 8.057360649108887, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.0272, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.30120481927710846, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.9315, | |
| "eval_samples_per_second": 19.322, | |
| "eval_steps_per_second": 2.42, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3132530120481928, | |
| "grad_norm": 3.159722089767456, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7818, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3253012048192771, | |
| "grad_norm": 2.7830989360809326, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.7339, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3373493975903614, | |
| "grad_norm": 2.162112236022949, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6881, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3493975903614458, | |
| "grad_norm": 1.7972179651260376, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.6253, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3614457831325301, | |
| "grad_norm": 1.317353367805481, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5675, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.37349397590361444, | |
| "grad_norm": 1.1669085025787354, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5628, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3855421686746988, | |
| "grad_norm": 1.1037367582321167, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5072, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.39759036144578314, | |
| "grad_norm": 1.0369112491607666, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.5365, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.40963855421686746, | |
| "grad_norm": 1.1754462718963623, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4381, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.42168674698795183, | |
| "grad_norm": 1.9122074842453003, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.6633, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.43373493975903615, | |
| "grad_norm": 4.505143165588379, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.9713, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4457831325301205, | |
| "grad_norm": 6.352746486663818, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.9435, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4578313253012048, | |
| "grad_norm": 1.7827593088150024, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6166, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.46987951807228917, | |
| "grad_norm": 1.7395880222320557, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6181, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4819277108433735, | |
| "grad_norm": 1.064204216003418, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5321, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4939759036144578, | |
| "grad_norm": 0.9078404903411865, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4611, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5060240963855421, | |
| "grad_norm": 0.9963672757148743, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5253, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5180722891566265, | |
| "grad_norm": 0.907263994216919, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4595, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5301204819277109, | |
| "grad_norm": 0.938334584236145, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5145, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5421686746987951, | |
| "grad_norm": 0.8603211641311646, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4521, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5542168674698795, | |
| "grad_norm": 0.9404347538948059, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4437, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5662650602409639, | |
| "grad_norm": 1.001924753189087, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.447, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5783132530120482, | |
| "grad_norm": 2.0918359756469727, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7458, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5903614457831325, | |
| "grad_norm": 3.8851842880249023, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.7572, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6024096385542169, | |
| "grad_norm": 5.830325603485107, | |
| "learning_rate": 0.0, | |
| "loss": 0.7994, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6024096385542169, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.9215, | |
| "eval_samples_per_second": 19.328, | |
| "eval_steps_per_second": 2.42, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.631381723512832e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |