| { | |
| "best_metric": 7.063704490661621, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.12886597938144329, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002577319587628866, | |
| "grad_norm": 8.84896469116211, | |
| "learning_rate": 5e-05, | |
| "loss": 8.769, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002577319587628866, | |
| "eval_loss": 7.704258441925049, | |
| "eval_runtime": 13.4583, | |
| "eval_samples_per_second": 194.229, | |
| "eval_steps_per_second": 24.297, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005154639175257732, | |
| "grad_norm": 5.125444412231445, | |
| "learning_rate": 0.0001, | |
| "loss": 8.594, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007731958762886598, | |
| "grad_norm": 4.254770755767822, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 8.2293, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010309278350515464, | |
| "grad_norm": 3.761096239089966, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 8.3432, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01288659793814433, | |
| "grad_norm": 2.6418516635894775, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 7.6389, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015463917525773196, | |
| "grad_norm": 2.60322642326355, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 7.5408, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01804123711340206, | |
| "grad_norm": 2.4060311317443848, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 7.5405, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020618556701030927, | |
| "grad_norm": 2.1694252490997314, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 7.2925, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023195876288659795, | |
| "grad_norm": 1.9732533693313599, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 7.2964, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02577319587628866, | |
| "grad_norm": 1.90111243724823, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.9977, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.028350515463917526, | |
| "grad_norm": 1.7233860492706299, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 7.0945, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.030927835051546393, | |
| "grad_norm": 1.980125069618225, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 7.056, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03350515463917526, | |
| "grad_norm": 3.8307547569274902, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 7.6226, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03608247422680412, | |
| "grad_norm": 4.206315994262695, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 7.7023, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03865979381443299, | |
| "grad_norm": 2.2115254402160645, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 7.7303, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.041237113402061855, | |
| "grad_norm": 1.6303458213806152, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 7.5333, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04381443298969072, | |
| "grad_norm": 1.4174168109893799, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 7.4892, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04639175257731959, | |
| "grad_norm": 1.1928077936172485, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 7.4843, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04896907216494845, | |
| "grad_norm": 1.2452458143234253, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 7.3061, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05154639175257732, | |
| "grad_norm": 1.2192394733428955, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 7.1825, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05412371134020619, | |
| "grad_norm": 1.2151198387145996, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 7.0109, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05670103092783505, | |
| "grad_norm": 1.2521761655807495, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 6.8825, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.059278350515463915, | |
| "grad_norm": 1.183918833732605, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 6.9443, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.061855670103092786, | |
| "grad_norm": 1.1090588569641113, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 6.9259, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06443298969072164, | |
| "grad_norm": 1.5472322702407837, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 6.5826, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06443298969072164, | |
| "eval_loss": 7.122404098510742, | |
| "eval_runtime": 13.3389, | |
| "eval_samples_per_second": 195.968, | |
| "eval_steps_per_second": 24.515, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06701030927835051, | |
| "grad_norm": 2.843515634536743, | |
| "learning_rate": 5e-05, | |
| "loss": 7.2493, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06958762886597938, | |
| "grad_norm": 1.6025389432907104, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 7.8308, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07216494845360824, | |
| "grad_norm": 1.3303579092025757, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 7.5161, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07474226804123711, | |
| "grad_norm": 1.0986202955245972, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 7.4137, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07731958762886598, | |
| "grad_norm": 0.9372117519378662, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 7.3211, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07989690721649484, | |
| "grad_norm": 1.0359989404678345, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 7.4251, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08247422680412371, | |
| "grad_norm": 1.050330400466919, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.9601, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08505154639175258, | |
| "grad_norm": 1.0149939060211182, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 7.0997, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08762886597938144, | |
| "grad_norm": 0.8797879815101624, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 6.8525, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09020618556701031, | |
| "grad_norm": 0.9121543169021606, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 6.8513, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09278350515463918, | |
| "grad_norm": 0.9668096303939819, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 6.7363, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09536082474226804, | |
| "grad_norm": 1.13383150100708, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 6.6522, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0979381443298969, | |
| "grad_norm": 1.455060601234436, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 7.743, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10051546391752578, | |
| "grad_norm": 1.4939161539077759, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 7.6736, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10309278350515463, | |
| "grad_norm": 1.1243243217468262, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 7.5141, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1056701030927835, | |
| "grad_norm": 1.0334477424621582, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 7.4467, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10824742268041238, | |
| "grad_norm": 0.850965142250061, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 7.4166, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11082474226804123, | |
| "grad_norm": 0.9271207451820374, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 7.2256, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1134020618556701, | |
| "grad_norm": 0.924728512763977, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 7.1742, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11597938144329897, | |
| "grad_norm": 0.8596798777580261, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 7.0014, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11855670103092783, | |
| "grad_norm": 0.9014486074447632, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 6.9507, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1211340206185567, | |
| "grad_norm": 0.8988224267959595, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 6.8728, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12371134020618557, | |
| "grad_norm": 0.8983946442604065, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 6.6614, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12628865979381443, | |
| "grad_norm": 0.9872623085975647, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 6.8147, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12886597938144329, | |
| "grad_norm": 1.2063250541687012, | |
| "learning_rate": 0.0, | |
| "loss": 6.6433, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12886597938144329, | |
| "eval_loss": 7.063704490661621, | |
| "eval_runtime": 13.226, | |
| "eval_samples_per_second": 197.64, | |
| "eval_steps_per_second": 24.724, | |
| "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": 239916767772672.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |