| { | |
| "best_metric": 1.5645349025726318, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5194805194805194, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01038961038961039, | |
| "grad_norm": 31.575532913208008, | |
| "learning_rate": 1e-05, | |
| "loss": 8.1047, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01038961038961039, | |
| "eval_loss": 3.256531238555908, | |
| "eval_runtime": 17.4231, | |
| "eval_samples_per_second": 9.298, | |
| "eval_steps_per_second": 2.353, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02077922077922078, | |
| "grad_norm": 28.155101776123047, | |
| "learning_rate": 2e-05, | |
| "loss": 7.7535, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03116883116883117, | |
| "grad_norm": 29.722841262817383, | |
| "learning_rate": 3e-05, | |
| "loss": 7.0905, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04155844155844156, | |
| "grad_norm": 24.271745681762695, | |
| "learning_rate": 4e-05, | |
| "loss": 6.9458, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05194805194805195, | |
| "grad_norm": 15.081071853637695, | |
| "learning_rate": 5e-05, | |
| "loss": 6.2569, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06233766233766234, | |
| "grad_norm": 17.337806701660156, | |
| "learning_rate": 6e-05, | |
| "loss": 5.5676, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07272727272727272, | |
| "grad_norm": 14.162841796875, | |
| "learning_rate": 7e-05, | |
| "loss": 5.6366, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08311688311688312, | |
| "grad_norm": 12.245787620544434, | |
| "learning_rate": 8e-05, | |
| "loss": 4.3564, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09350649350649351, | |
| "grad_norm": 13.69145679473877, | |
| "learning_rate": 9e-05, | |
| "loss": 4.0589, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1038961038961039, | |
| "grad_norm": 13.597987174987793, | |
| "learning_rate": 0.0001, | |
| "loss": 8.1335, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11428571428571428, | |
| "grad_norm": 14.616402626037598, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 9.6304, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.12467532467532468, | |
| "grad_norm": 11.459513664245605, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 9.9764, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.13506493506493505, | |
| "grad_norm": 12.888184547424316, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 10.047, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.14545454545454545, | |
| "grad_norm": 13.779420852661133, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 9.0076, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.15584415584415584, | |
| "grad_norm": 12.598060607910156, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 9.4718, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16623376623376623, | |
| "grad_norm": 16.062429428100586, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 8.831, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.17662337662337663, | |
| "grad_norm": 14.329278945922852, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 8.3048, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.18701298701298702, | |
| "grad_norm": 15.02530288696289, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 7.8693, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1974025974025974, | |
| "grad_norm": 12.204208374023438, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 7.4351, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2077922077922078, | |
| "grad_norm": 14.54892349243164, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 7.2178, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21818181818181817, | |
| "grad_norm": 17.59307861328125, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 8.6468, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 17.434343338012695, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 8.8287, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.23896103896103896, | |
| "grad_norm": 18.935226440429688, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 9.2807, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.24935064935064935, | |
| "grad_norm": 22.874101638793945, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 9.694, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": 53.946224212646484, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 9.9461, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2701298701298701, | |
| "grad_norm": 29.029720306396484, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 7.0315, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2805194805194805, | |
| "grad_norm": 18.960189819335938, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 4.5629, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2909090909090909, | |
| "grad_norm": 9.779653549194336, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 3.24, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3012987012987013, | |
| "grad_norm": 8.916206359863281, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.8276, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3116883116883117, | |
| "grad_norm": 9.138333320617676, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 3.5757, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3220779220779221, | |
| "grad_norm": 7.929874897003174, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 2.7643, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.33246753246753247, | |
| "grad_norm": 9.097893714904785, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 3.2975, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.34285714285714286, | |
| "grad_norm": 7.803646087646484, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 3.9145, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.35324675324675325, | |
| "grad_norm": 7.991164207458496, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 4.3464, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 8.554464340209961, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 8.5205, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.37402597402597404, | |
| "grad_norm": 9.929701805114746, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 8.237, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.38441558441558443, | |
| "grad_norm": 8.353158950805664, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 8.1351, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3948051948051948, | |
| "grad_norm": 8.773914337158203, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 7.4218, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4051948051948052, | |
| "grad_norm": 11.468509674072266, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 8.0759, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4155844155844156, | |
| "grad_norm": 10.545614242553711, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 6.6658, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.42597402597402595, | |
| "grad_norm": 11.069193840026855, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 7.5761, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.43636363636363634, | |
| "grad_norm": 13.026829719543457, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 7.7726, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.44675324675324674, | |
| "grad_norm": 11.747293472290039, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 6.9672, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 12.037382125854492, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 7.141, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4675324675324675, | |
| "grad_norm": 11.983041763305664, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 7.0005, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4779220779220779, | |
| "grad_norm": 12.65049934387207, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 7.4668, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4883116883116883, | |
| "grad_norm": 13.043449401855469, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 8.2192, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4987012987012987, | |
| "grad_norm": 17.99029541015625, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 8.188, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.509090909090909, | |
| "grad_norm": 21.040903091430664, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 5.0701, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "grad_norm": 14.175978660583496, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 4.6808, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "eval_loss": 1.5645349025726318, | |
| "eval_runtime": 17.6797, | |
| "eval_samples_per_second": 9.163, | |
| "eval_steps_per_second": 2.319, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 1.16045503266816e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |