| { | |
| "best_metric": 1.2643074989318848, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4429678848283499, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008859357696566999, | |
| "grad_norm": 0.9485101103782654, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.612, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008859357696566999, | |
| "eval_loss": 1.553291916847229, | |
| "eval_runtime": 4.4999, | |
| "eval_samples_per_second": 42.223, | |
| "eval_steps_per_second": 10.667, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017718715393133997, | |
| "grad_norm": 1.1285669803619385, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.6924, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.026578073089700997, | |
| "grad_norm": 1.2248897552490234, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.7535, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.035437430786267994, | |
| "grad_norm": 1.3399925231933594, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.8382, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.044296788482835, | |
| "grad_norm": 1.2440378665924072, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.8152, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.053156146179401995, | |
| "grad_norm": 1.3065143823623657, | |
| "learning_rate": 3e-06, | |
| "loss": 0.8765, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06201550387596899, | |
| "grad_norm": 1.3389146327972412, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.8682, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07087486157253599, | |
| "grad_norm": 1.4991661310195923, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.9377, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07973421926910298, | |
| "grad_norm": 1.5609127283096313, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.9843, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08859357696567, | |
| "grad_norm": 1.606197714805603, | |
| "learning_rate": 5e-06, | |
| "loss": 0.9854, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09745293466223699, | |
| "grad_norm": 1.6176241636276245, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 1.0551, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10631229235880399, | |
| "grad_norm": 1.7782856225967407, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 1.0912, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11517165005537099, | |
| "grad_norm": 1.8382161855697632, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 1.1267, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12403100775193798, | |
| "grad_norm": 1.9208855628967285, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 1.1959, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.132890365448505, | |
| "grad_norm": 1.9712958335876465, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 1.2675, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14174972314507198, | |
| "grad_norm": 2.083667516708374, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 1.2653, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.150609080841639, | |
| "grad_norm": 2.186372756958008, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 1.4033, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15946843853820597, | |
| "grad_norm": 2.37186336517334, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 1.3923, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16832779623477298, | |
| "grad_norm": 2.5746705532073975, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 1.5115, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17718715393134, | |
| "grad_norm": 2.6584019660949707, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 1.5311, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18604651162790697, | |
| "grad_norm": 2.9570505619049072, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 1.7797, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19490586932447398, | |
| "grad_norm": 3.1041574478149414, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 1.8168, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20376522702104097, | |
| "grad_norm": 3.4724597930908203, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 1.9245, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21262458471760798, | |
| "grad_norm": 3.84148907661438, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 2.1395, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.22148394241417496, | |
| "grad_norm": 4.133121013641357, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 2.4366, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.23034330011074197, | |
| "grad_norm": 5.210682392120361, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 2.8673, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23920265780730898, | |
| "grad_norm": 6.036959171295166, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 3.518, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24806201550387597, | |
| "grad_norm": 7.2502217292785645, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 4.8131, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.25692137320044295, | |
| "grad_norm": 0.9300296902656555, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 0.5366, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.26578073089701, | |
| "grad_norm": 1.2756208181381226, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 0.686, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27464008859357697, | |
| "grad_norm": 1.1982041597366333, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 0.6861, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.28349944629014395, | |
| "grad_norm": 1.281528115272522, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 0.6776, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.292358803986711, | |
| "grad_norm": 1.363015055656433, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 0.7314, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.301218161683278, | |
| "grad_norm": 1.3497728109359741, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 0.7302, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.31007751937984496, | |
| "grad_norm": 1.5836461782455444, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 0.8165, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.31893687707641194, | |
| "grad_norm": 1.5133098363876343, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 0.816, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.327796234772979, | |
| "grad_norm": 1.7491017580032349, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 0.901, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.33665559246954596, | |
| "grad_norm": 1.7113882303237915, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 0.8938, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.34551495016611294, | |
| "grad_norm": 1.796938180923462, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 0.9217, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.35437430786268, | |
| "grad_norm": 1.9191011190414429, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 0.9363, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36323366555924697, | |
| "grad_norm": 1.886011004447937, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 0.9239, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "grad_norm": 2.0969114303588867, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 1.0055, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 2.182500123977661, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 1.0549, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.38981173864894797, | |
| "grad_norm": 2.10186767578125, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 1.0984, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.39867109634551495, | |
| "grad_norm": 2.180788516998291, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 1.0864, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.40753045404208194, | |
| "grad_norm": 2.39646053314209, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 1.1876, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.416389811738649, | |
| "grad_norm": 2.6219873428344727, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 1.2726, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.42524916943521596, | |
| "grad_norm": 2.8094468116760254, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 1.281, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.43410852713178294, | |
| "grad_norm": 2.993520975112915, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 1.5087, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4429678848283499, | |
| "grad_norm": 3.10237717628479, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 1.5396, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4429678848283499, | |
| "eval_loss": 1.2643074989318848, | |
| "eval_runtime": 4.1452, | |
| "eval_samples_per_second": 45.836, | |
| "eval_steps_per_second": 11.58, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 9677225695641600.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |