| { | |
| "best_metric": 1.9785971641540527, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.013889130019618397, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00027778260039236795, | |
| "grad_norm": 11.772335052490234, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 33.1371, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027778260039236795, | |
| "eval_loss": 2.143366813659668, | |
| "eval_runtime": 2204.6716, | |
| "eval_samples_per_second": 11.0, | |
| "eval_steps_per_second": 1.375, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005555652007847359, | |
| "grad_norm": 10.740192413330078, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 31.1104, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008333478011771037, | |
| "grad_norm": 8.600647926330566, | |
| "learning_rate": 1.5e-06, | |
| "loss": 29.9754, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011111304015694718, | |
| "grad_norm": 10.105558395385742, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 29.1562, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013889130019618396, | |
| "grad_norm": 12.394813537597656, | |
| "learning_rate": 2.5e-06, | |
| "loss": 31.1149, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016666956023542075, | |
| "grad_norm": 12.586294174194336, | |
| "learning_rate": 3e-06, | |
| "loss": 31.1174, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019444782027465755, | |
| "grad_norm": 10.115208625793457, | |
| "learning_rate": 3.5e-06, | |
| "loss": 30.822, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022222608031389436, | |
| "grad_norm": 9.80542278289795, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 31.9496, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002500043403531311, | |
| "grad_norm": 15.492188453674316, | |
| "learning_rate": 4.5e-06, | |
| "loss": 30.6914, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0027778260039236793, | |
| "grad_norm": 14.333991050720215, | |
| "learning_rate": 5e-06, | |
| "loss": 31.0897, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0030556086043160473, | |
| "grad_norm": 13.288778305053711, | |
| "learning_rate": 4.99847706754774e-06, | |
| "loss": 32.038, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003333391204708415, | |
| "grad_norm": 10.738077163696289, | |
| "learning_rate": 4.993910125649561e-06, | |
| "loss": 31.5108, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003611173805100783, | |
| "grad_norm": 11.2579345703125, | |
| "learning_rate": 4.986304738420684e-06, | |
| "loss": 32.6261, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003888956405493151, | |
| "grad_norm": 10.858186721801758, | |
| "learning_rate": 4.975670171853926e-06, | |
| "loss": 32.1063, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004166739005885519, | |
| "grad_norm": 12.74929428100586, | |
| "learning_rate": 4.962019382530521e-06, | |
| "loss": 32.9972, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004444521606277887, | |
| "grad_norm": 12.187442779541016, | |
| "learning_rate": 4.9453690018345144e-06, | |
| "loss": 33.676, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004722304206670255, | |
| "grad_norm": 11.097588539123535, | |
| "learning_rate": 4.925739315689991e-06, | |
| "loss": 31.9569, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005000086807062622, | |
| "grad_norm": 12.763700485229492, | |
| "learning_rate": 4.903154239845798e-06, | |
| "loss": 34.0068, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005277869407454991, | |
| "grad_norm": 12.541844367980957, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 33.3713, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0055556520078473585, | |
| "grad_norm": 13.987171173095703, | |
| "learning_rate": 4.849231551964771e-06, | |
| "loss": 34.36, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005833434608239726, | |
| "grad_norm": 13.892500877380371, | |
| "learning_rate": 4.817959636416969e-06, | |
| "loss": 34.3124, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006111217208632095, | |
| "grad_norm": 14.628053665161133, | |
| "learning_rate": 4.783863644106502e-06, | |
| "loss": 33.545, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006388999809024462, | |
| "grad_norm": 14.313295364379883, | |
| "learning_rate": 4.746985115747918e-06, | |
| "loss": 33.1382, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00666678240941683, | |
| "grad_norm": 15.4104642868042, | |
| "learning_rate": 4.707368982147318e-06, | |
| "loss": 33.9549, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006944565009809198, | |
| "grad_norm": 16.55370330810547, | |
| "learning_rate": 4.665063509461098e-06, | |
| "loss": 32.9898, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007222347610201566, | |
| "grad_norm": 14.391225814819336, | |
| "learning_rate": 4.620120240391065e-06, | |
| "loss": 32.4941, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007500130210593934, | |
| "grad_norm": 16.7861385345459, | |
| "learning_rate": 4.572593931387604e-06, | |
| "loss": 35.6379, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007777912810986302, | |
| "grad_norm": 14.925787925720215, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 32.6469, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00805569541137867, | |
| "grad_norm": 16.225515365600586, | |
| "learning_rate": 4.470026884016805e-06, | |
| "loss": 33.9583, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008333478011771037, | |
| "grad_norm": 16.99432373046875, | |
| "learning_rate": 4.415111107797445e-06, | |
| "loss": 34.1699, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008611260612163406, | |
| "grad_norm": 17.615966796875, | |
| "learning_rate": 4.357862063693486e-06, | |
| "loss": 32.8139, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008889043212555774, | |
| "grad_norm": 22.280908584594727, | |
| "learning_rate": 4.2983495008466285e-06, | |
| "loss": 35.1964, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009166825812948141, | |
| "grad_norm": 18.062667846679688, | |
| "learning_rate": 4.236645926147493e-06, | |
| "loss": 33.659, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00944460841334051, | |
| "grad_norm": 18.6680908203125, | |
| "learning_rate": 4.172826515897146e-06, | |
| "loss": 35.3859, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009722391013732878, | |
| "grad_norm": 17.215133666992188, | |
| "learning_rate": 4.106969024216348e-06, | |
| "loss": 33.7911, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010000173614125245, | |
| "grad_norm": 20.330347061157227, | |
| "learning_rate": 4.039153688314146e-06, | |
| "loss": 35.2101, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010277956214517613, | |
| "grad_norm": 19.99478530883789, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 33.3331, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010555738814909982, | |
| "grad_norm": 19.694744110107422, | |
| "learning_rate": 3.897982258676867e-06, | |
| "loss": 33.9149, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010833521415302349, | |
| "grad_norm": 19.878915786743164, | |
| "learning_rate": 3.824798160583012e-06, | |
| "loss": 33.9199, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011111304015694717, | |
| "grad_norm": 21.502235412597656, | |
| "learning_rate": 3.7500000000000005e-06, | |
| "loss": 33.4184, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011389086616087086, | |
| "grad_norm": 20.41208839416504, | |
| "learning_rate": 3.6736789069647273e-06, | |
| "loss": 35.8002, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011666869216479452, | |
| "grad_norm": 19.16145133972168, | |
| "learning_rate": 3.595927866972694e-06, | |
| "loss": 33.5787, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01194465181687182, | |
| "grad_norm": 19.13408851623535, | |
| "learning_rate": 3.516841607689501e-06, | |
| "loss": 33.0847, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.01222243441726419, | |
| "grad_norm": 19.427921295166016, | |
| "learning_rate": 3.436516483539781e-06, | |
| "loss": 34.2262, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012500217017656556, | |
| "grad_norm": 21.819917678833008, | |
| "learning_rate": 3.3550503583141726e-06, | |
| "loss": 34.3069, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012777999618048924, | |
| "grad_norm": 22.254148483276367, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 35.325, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013055782218441293, | |
| "grad_norm": 26.261808395385742, | |
| "learning_rate": 3.189093389542498e-06, | |
| "loss": 36.7306, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.01333356481883366, | |
| "grad_norm": 25.339427947998047, | |
| "learning_rate": 3.1048047389991693e-06, | |
| "loss": 36.3985, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013611347419226028, | |
| "grad_norm": 37.24362564086914, | |
| "learning_rate": 3.019779227044398e-06, | |
| "loss": 36.1939, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013889130019618397, | |
| "grad_norm": 30.434406280517578, | |
| "learning_rate": 2.9341204441673267e-06, | |
| "loss": 37.8932, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013889130019618397, | |
| "eval_loss": 1.9785971641540527, | |
| "eval_runtime": 2210.751, | |
| "eval_samples_per_second": 10.97, | |
| "eval_steps_per_second": 1.371, | |
| "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": 2.6171259006379622e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |