| { | |
| "best_metric": 0.738952100276947, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.443768996960486, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0486322188449848, | |
| "grad_norm": 122.75741577148438, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2344, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0486322188449848, | |
| "eval_loss": 5.1622395515441895, | |
| "eval_runtime": 3.688, | |
| "eval_samples_per_second": 37.69, | |
| "eval_steps_per_second": 4.881, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0972644376899696, | |
| "grad_norm": 69.6625747680664, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1183, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1458966565349544, | |
| "grad_norm": 94.78073120117188, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.9245, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1945288753799392, | |
| "grad_norm": 109.74983978271484, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.4097, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.24316109422492402, | |
| "grad_norm": 123.89290618896484, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 5.9994, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2917933130699088, | |
| "grad_norm": 58.025917053222656, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.7611, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": 58.173011779785156, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.4281, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3890577507598784, | |
| "grad_norm": 61.43299865722656, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3761, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4376899696048632, | |
| "grad_norm": 86.56910705566406, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.6181, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.48632218844984804, | |
| "grad_norm": 123.04452514648438, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.0133, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5349544072948328, | |
| "grad_norm": 64.24591064453125, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0057, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5835866261398176, | |
| "grad_norm": 50.80318832397461, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.7955, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6322188449848024, | |
| "grad_norm": 103.4283447265625, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5451, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": 101.22402954101562, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5553, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.729483282674772, | |
| "grad_norm": 70.3960189819336, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5866, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7781155015197568, | |
| "grad_norm": 107.30152130126953, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.894, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8267477203647416, | |
| "grad_norm": 185.14161682128906, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.0501, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8753799392097265, | |
| "grad_norm": 63.85137176513672, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1898, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9240121580547113, | |
| "grad_norm": 68.57901763916016, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1855, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9726443768996961, | |
| "grad_norm": 81.24263000488281, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1483, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.027355623100304, | |
| "grad_norm": 39.203556060791016, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6328, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0759878419452888, | |
| "grad_norm": 54.474021911621094, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.6113, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.1246200607902737, | |
| "grad_norm": 46.96053695678711, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.7844, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.1732522796352582, | |
| "grad_norm": 56.810081481933594, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1084, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.221884498480243, | |
| "grad_norm": 121.81807708740234, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.0985, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.221884498480243, | |
| "eval_loss": 0.9295913577079773, | |
| "eval_runtime": 3.6736, | |
| "eval_samples_per_second": 37.837, | |
| "eval_steps_per_second": 4.9, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2705167173252279, | |
| "grad_norm": 57.16689682006836, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8051, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.3191489361702127, | |
| "grad_norm": 32.02121353149414, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4653, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.3677811550151975, | |
| "grad_norm": 48.5133056640625, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.825, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.4164133738601823, | |
| "grad_norm": 66.22747039794922, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.856, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.465045592705167, | |
| "grad_norm": 65.52440643310547, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.9969, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.513677811550152, | |
| "grad_norm": 52.595699310302734, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7564, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.5623100303951367, | |
| "grad_norm": 56.82194519042969, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5235, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.6109422492401215, | |
| "grad_norm": 49.04568862915039, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.7778, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.6595744680851063, | |
| "grad_norm": 61.08024978637695, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8873, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.7082066869300911, | |
| "grad_norm": 59.74906921386719, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.772, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.756838905775076, | |
| "grad_norm": 39.438392639160156, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.8044, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.8054711246200608, | |
| "grad_norm": 44.79551696777344, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5302, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.8541033434650456, | |
| "grad_norm": 41.50120162963867, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6659, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.9027355623100304, | |
| "grad_norm": 92.41071319580078, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8416, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.9513677811550152, | |
| "grad_norm": 57.740657806396484, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.7625, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.0060790273556233, | |
| "grad_norm": 37.433349609375, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.7985, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.054711246200608, | |
| "grad_norm": 32.22288513183594, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5062, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.103343465045593, | |
| "grad_norm": 32.619056701660156, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.558, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.1519756838905777, | |
| "grad_norm": 35.74100112915039, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7794, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.2006079027355625, | |
| "grad_norm": 38.613834381103516, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7587, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.2492401215805473, | |
| "grad_norm": 43.844451904296875, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.8223, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.297872340425532, | |
| "grad_norm": 27.004453659057617, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4098, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.3465045592705165, | |
| "grad_norm": 28.623008728027344, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5683, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.3951367781155017, | |
| "grad_norm": 36.22129821777344, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.8083, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.443768996960486, | |
| "grad_norm": 42.232688903808594, | |
| "learning_rate": 0.0, | |
| "loss": 0.9155, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.443768996960486, | |
| "eval_loss": 0.738952100276947, | |
| "eval_runtime": 3.6618, | |
| "eval_samples_per_second": 37.96, | |
| "eval_steps_per_second": 4.916, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 9.70274988097536e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |