| { | |
| "best_metric": 0.9541823863983154, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.010930753675465924, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021861507350931847, | |
| "grad_norm": 16.41507339477539, | |
| "learning_rate": 2e-05, | |
| "loss": 7.5287, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021861507350931847, | |
| "eval_loss": 2.686614751815796, | |
| "eval_runtime": 565.8801, | |
| "eval_samples_per_second": 13.614, | |
| "eval_steps_per_second": 1.702, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00043723014701863694, | |
| "grad_norm": 17.904094696044922, | |
| "learning_rate": 4e-05, | |
| "loss": 7.593, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006558452205279554, | |
| "grad_norm": 12.485776901245117, | |
| "learning_rate": 6e-05, | |
| "loss": 7.2943, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008744602940372739, | |
| "grad_norm": 12.988239288330078, | |
| "learning_rate": 8e-05, | |
| "loss": 6.6725, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0010930753675465923, | |
| "grad_norm": 10.89429759979248, | |
| "learning_rate": 0.0001, | |
| "loss": 6.5304, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013116904410559109, | |
| "grad_norm": 9.193744659423828, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 5.9895, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015303055145652292, | |
| "grad_norm": 9.274890899658203, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 5.8249, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0017489205880745478, | |
| "grad_norm": 7.4982757568359375, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 5.6199, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001967535661583866, | |
| "grad_norm": 8.323856353759766, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 5.688, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0021861507350931847, | |
| "grad_norm": 7.066643714904785, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 5.6599, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002404765808602503, | |
| "grad_norm": 5.9596967697143555, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 5.3799, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0026233808821118218, | |
| "grad_norm": 6.757927417755127, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 5.6411, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00284199595562114, | |
| "grad_norm": 6.3292646408081055, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 5.3375, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0030606110291304584, | |
| "grad_norm": 6.017701625823975, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 5.3429, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003279226102639777, | |
| "grad_norm": 6.756369590759277, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 5.2225, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0034978411761490955, | |
| "grad_norm": 6.3840556144714355, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 4.9592, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003716456249658414, | |
| "grad_norm": 6.946917533874512, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 4.8436, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003935071323167732, | |
| "grad_norm": 6.3738017082214355, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 4.9505, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004153686396677051, | |
| "grad_norm": 6.2189812660217285, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 4.8429, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004372301470186369, | |
| "grad_norm": 6.281938552856445, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.9461, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004590916543695688, | |
| "grad_norm": 6.083291530609131, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 4.8348, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004809531617205006, | |
| "grad_norm": 6.0507378578186035, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 4.8981, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005028146690714325, | |
| "grad_norm": 6.219107151031494, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 4.7594, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0052467617642236435, | |
| "grad_norm": 5.713433742523193, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 4.8685, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005465376837732962, | |
| "grad_norm": 6.037445068359375, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 4.6413, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005465376837732962, | |
| "eval_loss": 0.9541823863983154, | |
| "eval_runtime": 571.4514, | |
| "eval_samples_per_second": 13.481, | |
| "eval_steps_per_second": 1.685, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00568399191124228, | |
| "grad_norm": 5.85664176940918, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 4.9116, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005902606984751598, | |
| "grad_norm": 5.565213203430176, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 4.7688, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006121222058260917, | |
| "grad_norm": 5.267945289611816, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 4.3886, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.006339837131770235, | |
| "grad_norm": 5.487580299377441, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 4.937, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006558452205279554, | |
| "grad_norm": 5.872722625732422, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 4.5749, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0067770672787888725, | |
| "grad_norm": 5.429628849029541, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 4.0589, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.006995682352298191, | |
| "grad_norm": 6.078123092651367, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 4.3092, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00721429742580751, | |
| "grad_norm": 6.005480766296387, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 4.3421, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.007432912499316828, | |
| "grad_norm": 6.326774597167969, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 4.169, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007651527572826147, | |
| "grad_norm": 8.954018592834473, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.4574, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007870142646335464, | |
| "grad_norm": 12.161307334899902, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.1153, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.008088757719844783, | |
| "grad_norm": 10.752105712890625, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.0455, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.008307372793354102, | |
| "grad_norm": 9.942269325256348, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.9616, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00852598786686342, | |
| "grad_norm": 9.08958625793457, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 1.0565, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.008744602940372739, | |
| "grad_norm": 9.308728218078613, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.0039, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008963218013882057, | |
| "grad_norm": 8.348808288574219, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.9989, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.009181833087391376, | |
| "grad_norm": 6.326083660125732, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.9553, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.009400448160900694, | |
| "grad_norm": 7.869330406188965, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.0569, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.009619063234410013, | |
| "grad_norm": 10.216377258300781, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 1.0558, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.009837678307919331, | |
| "grad_norm": 11.092399597167969, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.9817, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01005629338142865, | |
| "grad_norm": 8.00503921508789, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.0639, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.010274908454937969, | |
| "grad_norm": 6.840457916259766, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.8486, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.010493523528447287, | |
| "grad_norm": 6.971992492675781, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.884, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.010712138601956606, | |
| "grad_norm": 10.650803565979004, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.8533, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.010930753675465924, | |
| "grad_norm": 8.342534065246582, | |
| "learning_rate": 0.0, | |
| "loss": 0.8778, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010930753675465924, | |
| "eval_loss": 0.9805046319961548, | |
| "eval_runtime": 571.055, | |
| "eval_samples_per_second": 13.491, | |
| "eval_steps_per_second": 1.686, | |
| "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": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.11922310751191e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |