| { | |
| "best_metric": 11.932692527770996, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.17271157167530224, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0034542314335060447, | |
| "grad_norm": 0.04175278916954994, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9399, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034542314335060447, | |
| "eval_loss": 11.940598487854004, | |
| "eval_runtime": 8.5028, | |
| "eval_samples_per_second": 229.453, | |
| "eval_steps_per_second": 28.696, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0069084628670120895, | |
| "grad_norm": 0.04260191321372986, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9395, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010362694300518135, | |
| "grad_norm": 0.04679454118013382, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9407, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013816925734024179, | |
| "grad_norm": 0.04993719235062599, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9391, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.017271157167530225, | |
| "grad_norm": 0.05013435333967209, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9399, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02072538860103627, | |
| "grad_norm": 0.06913993507623672, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.9367, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.024179620034542316, | |
| "grad_norm": 0.07582654058933258, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9384, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.027633851468048358, | |
| "grad_norm": 0.07948369532823563, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9411, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.031088082901554404, | |
| "grad_norm": 0.08457164466381073, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.939, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03454231433506045, | |
| "grad_norm": 0.09221560508012772, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9394, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.037996545768566495, | |
| "grad_norm": 0.09865477681159973, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9381, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04145077720207254, | |
| "grad_norm": 0.1040349081158638, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9369, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.044905008635578586, | |
| "grad_norm": 0.06590238213539124, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9372, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04835924006908463, | |
| "grad_norm": 0.05209377408027649, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9386, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05181347150259067, | |
| "grad_norm": 0.06293608248233795, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9372, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.055267702936096716, | |
| "grad_norm": 0.06793326884508133, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9402, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05872193436960276, | |
| "grad_norm": 0.07311394810676575, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9388, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06217616580310881, | |
| "grad_norm": 0.08118285238742828, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9378, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06563039723661486, | |
| "grad_norm": 0.09678582102060318, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.9348, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0690846286701209, | |
| "grad_norm": 0.10049033910036087, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9381, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07253886010362694, | |
| "grad_norm": 0.1105872094631195, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.937, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07599309153713299, | |
| "grad_norm": 0.11385960131883621, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9332, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07944732297063903, | |
| "grad_norm": 0.12892016768455505, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9336, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08290155440414508, | |
| "grad_norm": 0.12460300326347351, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.9342, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08635578583765112, | |
| "grad_norm": 0.14798326790332794, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.9328, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08635578583765112, | |
| "eval_loss": 11.935075759887695, | |
| "eval_runtime": 8.4955, | |
| "eval_samples_per_second": 229.652, | |
| "eval_steps_per_second": 28.721, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08981001727115717, | |
| "grad_norm": 0.06985343992710114, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9375, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09326424870466321, | |
| "grad_norm": 0.06996572017669678, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.934, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09671848013816926, | |
| "grad_norm": 0.08063080906867981, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.9362, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1001727115716753, | |
| "grad_norm": 0.09464134275913239, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.9325, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10362694300518134, | |
| "grad_norm": 0.10078255087137222, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.9353, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1070811744386874, | |
| "grad_norm": 0.11674533039331436, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.9342, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11053540587219343, | |
| "grad_norm": 0.12914171814918518, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9355, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11398963730569948, | |
| "grad_norm": 0.1331762671470642, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.9333, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11744386873920552, | |
| "grad_norm": 0.1348942667245865, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.9311, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12089810017271158, | |
| "grad_norm": 0.13685396313667297, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.9319, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12435233160621761, | |
| "grad_norm": 0.14600132405757904, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.9309, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12780656303972365, | |
| "grad_norm": 0.16344575583934784, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.9316, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.13126079447322972, | |
| "grad_norm": 0.10145840793848038, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9345, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13471502590673576, | |
| "grad_norm": 0.08084696531295776, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.9366, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1381692573402418, | |
| "grad_norm": 0.08430986106395721, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.9352, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14162348877374784, | |
| "grad_norm": 0.0992431789636612, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.9346, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.14507772020725387, | |
| "grad_norm": 0.10876741260290146, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.9335, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.14853195164075994, | |
| "grad_norm": 0.11824341118335724, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.9327, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.15198618307426598, | |
| "grad_norm": 0.12585586309432983, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9324, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.15544041450777202, | |
| "grad_norm": 0.14251390099525452, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.9351, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15889464594127806, | |
| "grad_norm": 0.13823118805885315, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.9348, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.16234887737478412, | |
| "grad_norm": 0.14277690649032593, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.9315, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.16580310880829016, | |
| "grad_norm": 0.1486414670944214, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.9307, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1692573402417962, | |
| "grad_norm": 0.1497362107038498, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.9301, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.17271157167530224, | |
| "grad_norm": 0.16538454592227936, | |
| "learning_rate": 0.0, | |
| "loss": 11.9283, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17271157167530224, | |
| "eval_loss": 11.932692527770996, | |
| "eval_runtime": 8.6042, | |
| "eval_samples_per_second": 226.749, | |
| "eval_steps_per_second": 28.358, | |
| "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": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1042494259200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |