| { | |
| "best_metric": 1.129067301750183, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5610098176718092, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011220196353436185, | |
| "grad_norm": 88.7046127319336, | |
| "learning_rate": 5e-05, | |
| "loss": 7.5505, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011220196353436185, | |
| "eval_loss": 7.712277412414551, | |
| "eval_runtime": 40.8743, | |
| "eval_samples_per_second": 14.704, | |
| "eval_steps_per_second": 1.859, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02244039270687237, | |
| "grad_norm": 86.15890502929688, | |
| "learning_rate": 0.0001, | |
| "loss": 7.5103, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.033660589060308554, | |
| "grad_norm": 77.88780212402344, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.3948, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04488078541374474, | |
| "grad_norm": 86.77691650390625, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.3639, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.056100981767180924, | |
| "grad_norm": 93.0388412475586, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.8274, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06732117812061711, | |
| "grad_norm": 90.54244995117188, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.6161, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0785413744740533, | |
| "grad_norm": 72.11747741699219, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.5886, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08976157082748948, | |
| "grad_norm": 39.879398345947266, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.8196, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10098176718092566, | |
| "grad_norm": 34.943485260009766, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.5364, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11220196353436185, | |
| "grad_norm": 29.057737350463867, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.36, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12342215988779803, | |
| "grad_norm": 23.04311752319336, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.2703, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13464235624123422, | |
| "grad_norm": 18.392635345458984, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2251, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1458625525946704, | |
| "grad_norm": 7.056333065032959, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.1468, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1570827489481066, | |
| "grad_norm": 10.856261253356934, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.165, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16830294530154277, | |
| "grad_norm": 9.134137153625488, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.1652, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17952314165497896, | |
| "grad_norm": 16.10779571533203, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.1788, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.19074333800841514, | |
| "grad_norm": 18.05542755126953, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.1929, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.20196353436185133, | |
| "grad_norm": 12.648049354553223, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1706, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2131837307152875, | |
| "grad_norm": 8.945832252502441, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1571, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2244039270687237, | |
| "grad_norm": 10.021390914916992, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1729, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23562412342215988, | |
| "grad_norm": 8.964709281921387, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.1638, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24684431977559607, | |
| "grad_norm": 7.527612686157227, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.1355, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 6.7927069664001465, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.1351, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.26928471248246844, | |
| "grad_norm": 7.700843334197998, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1265, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2805049088359046, | |
| "grad_norm": 6.00221061706543, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.0921, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2805049088359046, | |
| "eval_loss": 1.1426749229431152, | |
| "eval_runtime": 40.8704, | |
| "eval_samples_per_second": 14.705, | |
| "eval_steps_per_second": 1.86, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2917251051893408, | |
| "grad_norm": 6.840883255004883, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1596, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.302945301542777, | |
| "grad_norm": 11.515652656555176, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.1579, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3141654978962132, | |
| "grad_norm": 9.219208717346191, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.1314, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.32538569424964936, | |
| "grad_norm": 6.959238052368164, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.1417, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.33660589060308554, | |
| "grad_norm": 9.272762298583984, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.165, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 5.884149074554443, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1467, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3590462833099579, | |
| "grad_norm": 7.155044078826904, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1392, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3702664796633941, | |
| "grad_norm": 7.817929744720459, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.1468, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3814866760168303, | |
| "grad_norm": 5.918971538543701, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.1328, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.39270687237026647, | |
| "grad_norm": 5.975762844085693, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.1179, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.40392706872370265, | |
| "grad_norm": 6.991667747497559, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1391, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.41514726507713884, | |
| "grad_norm": 6.5501322746276855, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.0932, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.426367461430575, | |
| "grad_norm": 7.059451580047607, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1087, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4375876577840112, | |
| "grad_norm": 6.76327657699585, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.1367, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4488078541374474, | |
| "grad_norm": 5.15268611907959, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.1455, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4600280504908836, | |
| "grad_norm": 7.797684669494629, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.1518, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.47124824684431976, | |
| "grad_norm": 6.6517205238342285, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.1512, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.48246844319775595, | |
| "grad_norm": 4.980301380157471, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.1459, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.49368863955119213, | |
| "grad_norm": 5.792754173278809, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.148, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5049088359046283, | |
| "grad_norm": 4.484447956085205, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.1291, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 6.743837833404541, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.1486, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5273492286115007, | |
| "grad_norm": 6.317599296569824, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.1474, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5385694249649369, | |
| "grad_norm": 6.558826446533203, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.137, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5497896213183731, | |
| "grad_norm": 5.561692237854004, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.126, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5610098176718092, | |
| "grad_norm": 6.571597099304199, | |
| "learning_rate": 0.0, | |
| "loss": 0.9847, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5610098176718092, | |
| "eval_loss": 1.129067301750183, | |
| "eval_runtime": 40.8822, | |
| "eval_samples_per_second": 14.701, | |
| "eval_steps_per_second": 1.859, | |
| "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": 1.0205748533395456e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |