| { | |
| "best_metric": 0.26686012744903564, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7733204446592556, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015466408893185114, | |
| "grad_norm": 0.34002751111984253, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.4411, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015466408893185114, | |
| "eval_loss": 1.1426082849502563, | |
| "eval_runtime": 7.1707, | |
| "eval_samples_per_second": 6.973, | |
| "eval_steps_per_second": 6.973, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.030932817786370227, | |
| "grad_norm": 0.4139275550842285, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.4555, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04639922667955534, | |
| "grad_norm": 0.481924831867218, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.424, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.061865635572740454, | |
| "grad_norm": 0.4299992322921753, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.3855, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07733204446592556, | |
| "grad_norm": 0.42819246649742126, | |
| "learning_rate": 0.00015, | |
| "loss": 0.4611, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09279845335911067, | |
| "grad_norm": 0.9149371385574341, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 0.7301, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1082648622522958, | |
| "grad_norm": 1.1431907415390015, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 0.7905, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.12373127114548091, | |
| "grad_norm": 1.802942156791687, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 0.6581, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13919768003866603, | |
| "grad_norm": 2.6315770149230957, | |
| "learning_rate": 0.00027, | |
| "loss": 0.6625, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15466408893185113, | |
| "grad_norm": 1.5995557308197021, | |
| "learning_rate": 0.0003, | |
| "loss": 0.5518, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17013049782503625, | |
| "grad_norm": 1.1412254571914673, | |
| "learning_rate": 0.00029994859874633357, | |
| "loss": 0.4248, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.18559690671822135, | |
| "grad_norm": 1.1108283996582031, | |
| "learning_rate": 0.000299794430213186, | |
| "loss": 0.4044, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.20106331561140647, | |
| "grad_norm": 1.4058749675750732, | |
| "learning_rate": 0.00029953760005996916, | |
| "loss": 0.4258, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2165297245045916, | |
| "grad_norm": 0.8541085124015808, | |
| "learning_rate": 0.00029917828430524096, | |
| "loss": 0.419, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2319961333977767, | |
| "grad_norm": 0.7577608823776245, | |
| "learning_rate": 0.00029871672920607153, | |
| "loss": 0.4055, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.24746254229096182, | |
| "grad_norm": 0.8010592460632324, | |
| "learning_rate": 0.00029815325108927063, | |
| "loss": 0.4587, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.26292895118414694, | |
| "grad_norm": 2.178513526916504, | |
| "learning_rate": 0.00029748823613459316, | |
| "loss": 0.3844, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.27839536007733207, | |
| "grad_norm": 1.049085021018982, | |
| "learning_rate": 0.0002967221401100708, | |
| "loss": 0.3085, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.29386176897051713, | |
| "grad_norm": 0.2664034962654114, | |
| "learning_rate": 0.0002958554880596515, | |
| "loss": 0.2314, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.30932817786370226, | |
| "grad_norm": 0.9501022696495056, | |
| "learning_rate": 0.0002948888739433602, | |
| "loss": 0.2162, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3247945867568874, | |
| "grad_norm": 0.29297515749931335, | |
| "learning_rate": 0.00029382296023022894, | |
| "loss": 0.1734, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3402609956500725, | |
| "grad_norm": 0.29325342178344727, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 0.2472, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.35572740454325763, | |
| "grad_norm": 0.7397837042808533, | |
| "learning_rate": 0.00029139622366382674, | |
| "loss": 0.3872, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3711938134364427, | |
| "grad_norm": 0.5978482365608215, | |
| "learning_rate": 0.00029003706397458023, | |
| "loss": 0.3756, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3866602223296278, | |
| "grad_norm": 0.8143917918205261, | |
| "learning_rate": 0.000288581929876693, | |
| "loss": 0.3305, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3866602223296278, | |
| "eval_loss": 0.2919376492500305, | |
| "eval_runtime": 7.3131, | |
| "eval_samples_per_second": 6.837, | |
| "eval_steps_per_second": 6.837, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.40212663122281295, | |
| "grad_norm": 0.5971204042434692, | |
| "learning_rate": 0.0002870318186463901, | |
| "loss": 0.329, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.41759304011599807, | |
| "grad_norm": 0.5656357407569885, | |
| "learning_rate": 0.0002853877926524791, | |
| "loss": 0.2991, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4330594490091832, | |
| "grad_norm": 0.9046909809112549, | |
| "learning_rate": 0.00028365097862825513, | |
| "loss": 0.3522, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4485258579023683, | |
| "grad_norm": 1.8343451023101807, | |
| "learning_rate": 0.00028182256689929475, | |
| "loss": 0.3253, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4639922667955534, | |
| "grad_norm": 1.3387500047683716, | |
| "learning_rate": 0.0002799038105676658, | |
| "loss": 0.3363, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4794586756887385, | |
| "grad_norm": 0.7546955943107605, | |
| "learning_rate": 0.0002778960246531138, | |
| "loss": 0.3319, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.49492508458192364, | |
| "grad_norm": 0.5383890271186829, | |
| "learning_rate": 0.0002758005851918136, | |
| "loss": 0.4198, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5103914934751087, | |
| "grad_norm": 2.9426941871643066, | |
| "learning_rate": 0.0002736189282933023, | |
| "loss": 0.3846, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5258579023682939, | |
| "grad_norm": 1.3911627531051636, | |
| "learning_rate": 0.0002713525491562421, | |
| "loss": 0.2681, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.541324311261479, | |
| "grad_norm": 0.33964619040489197, | |
| "learning_rate": 0.00026900300104368524, | |
| "loss": 0.2078, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5567907201546641, | |
| "grad_norm": 0.6098275780677795, | |
| "learning_rate": 0.0002665718942185456, | |
| "loss": 0.2027, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5722571290478492, | |
| "grad_norm": 0.5025777816772461, | |
| "learning_rate": 0.00026406089484000466, | |
| "loss": 0.206, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5877235379410343, | |
| "grad_norm": 0.4298511743545532, | |
| "learning_rate": 0.00026147172382160914, | |
| "loss": 0.2803, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6031899468342194, | |
| "grad_norm": 0.9432958364486694, | |
| "learning_rate": 0.00025880615565184313, | |
| "loss": 0.3849, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6186563557274045, | |
| "grad_norm": 0.6062995791435242, | |
| "learning_rate": 0.00025606601717798207, | |
| "loss": 0.3508, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6341227646205897, | |
| "grad_norm": 0.5804493427276611, | |
| "learning_rate": 0.0002532531863540631, | |
| "loss": 0.3212, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6495891735137748, | |
| "grad_norm": 0.5816200375556946, | |
| "learning_rate": 0.0002503695909538287, | |
| "loss": 0.2876, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6650555824069598, | |
| "grad_norm": 0.4420316219329834, | |
| "learning_rate": 0.0002474172072495275, | |
| "loss": 0.3054, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.680521991300145, | |
| "grad_norm": 0.45776253938674927, | |
| "learning_rate": 0.0002443980586574756, | |
| "loss": 0.279, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6959884001933301, | |
| "grad_norm": 0.7748484015464783, | |
| "learning_rate": 0.00024131421435130807, | |
| "loss": 0.2875, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7114548090865153, | |
| "grad_norm": 0.5803005695343018, | |
| "learning_rate": 0.00023816778784387094, | |
| "loss": 0.3088, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7269212179797003, | |
| "grad_norm": 1.1293902397155762, | |
| "learning_rate": 0.0002349609355387249, | |
| "loss": 0.3188, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7423876268728854, | |
| "grad_norm": 1.2384657859802246, | |
| "learning_rate": 0.00023169585525225405, | |
| "loss": 0.4065, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7578540357660706, | |
| "grad_norm": 1.8807259798049927, | |
| "learning_rate": 0.0002283747847073923, | |
| "loss": 0.2961, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7733204446592556, | |
| "grad_norm": 0.7909408211708069, | |
| "learning_rate": 0.000225, | |
| "loss": 0.2371, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7733204446592556, | |
| "eval_loss": 0.26686012744903564, | |
| "eval_runtime": 7.3174, | |
| "eval_samples_per_second": 6.833, | |
| "eval_steps_per_second": 6.833, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 130, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.89733217355694e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |