| { | |
| "best_metric": 0.6085440516471863, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6914433880726015, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013828867761452032, | |
| "grad_norm": 19.45879364013672, | |
| "learning_rate": 5e-05, | |
| "loss": 9.4334, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013828867761452032, | |
| "eval_loss": 13.031184196472168, | |
| "eval_runtime": 2.0482, | |
| "eval_samples_per_second": 24.411, | |
| "eval_steps_per_second": 6.347, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027657735522904063, | |
| "grad_norm": 26.073572158813477, | |
| "learning_rate": 0.0001, | |
| "loss": 11.5136, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04148660328435609, | |
| "grad_norm": 26.8472900390625, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.522, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.055315471045808126, | |
| "grad_norm": 22.755924224853516, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 7.9491, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06914433880726016, | |
| "grad_norm": 15.595483779907227, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 5.5744, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08297320656871218, | |
| "grad_norm": 9.190838813781738, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.6789, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.09680207433016422, | |
| "grad_norm": 8.115129470825195, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.419, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11063094209161625, | |
| "grad_norm": 6.998908996582031, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.8091, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12445980985306827, | |
| "grad_norm": 12.257213592529297, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.5854, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13828867761452032, | |
| "grad_norm": 7.180285453796387, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.1056, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15211754537597233, | |
| "grad_norm": 5.567869663238525, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.9129, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.16594641313742436, | |
| "grad_norm": 6.853220462799072, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.9943, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1797752808988764, | |
| "grad_norm": 9.853415489196777, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.356, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.19360414866032843, | |
| "grad_norm": 7.0330610275268555, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.8573, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.20743301642178047, | |
| "grad_norm": 4.917099475860596, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.8123, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2212618841832325, | |
| "grad_norm": 3.9539589881896973, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.7671, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.23509075194468454, | |
| "grad_norm": 3.8756351470947266, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.7778, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.24891961970613655, | |
| "grad_norm": 2.0061542987823486, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.5251, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2627484874675886, | |
| "grad_norm": 3.0238029956817627, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.6715, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.27657735522904064, | |
| "grad_norm": 2.458611249923706, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.6011, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2904062229904927, | |
| "grad_norm": 3.516721725463867, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.7158, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.30423509075194466, | |
| "grad_norm": 3.330580949783325, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.6801, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3180639585133967, | |
| "grad_norm": 4.436331748962402, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.6519, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.33189282627484873, | |
| "grad_norm": 2.7713534832000732, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.5614, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.34572169403630076, | |
| "grad_norm": 3.136500358581543, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.8205, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.34572169403630076, | |
| "eval_loss": 0.7706587910652161, | |
| "eval_runtime": 2.0716, | |
| "eval_samples_per_second": 24.136, | |
| "eval_steps_per_second": 6.275, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3595505617977528, | |
| "grad_norm": 4.098012924194336, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.6486, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.37337942955920483, | |
| "grad_norm": 1.8370767831802368, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.5103, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.38720829732065687, | |
| "grad_norm": 2.5867722034454346, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.5091, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4010371650821089, | |
| "grad_norm": 4.111291885375977, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.7217, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.41486603284356094, | |
| "grad_norm": 3.1537652015686035, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.6047, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.428694900605013, | |
| "grad_norm": 2.0026071071624756, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.4514, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.442523768366465, | |
| "grad_norm": 1.9003419876098633, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.5366, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.45635263612791704, | |
| "grad_norm": 1.8137303590774536, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.4817, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4701815038893691, | |
| "grad_norm": 1.5047740936279297, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.4376, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4840103716508211, | |
| "grad_norm": 1.2853477001190186, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.4678, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4978392394122731, | |
| "grad_norm": 1.4708086252212524, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.4805, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5116681071737251, | |
| "grad_norm": 2.1151070594787598, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.6592, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5254969749351772, | |
| "grad_norm": 1.9331130981445312, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.5447, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5393258426966292, | |
| "grad_norm": 3.0865390300750732, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4057, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5531547104580813, | |
| "grad_norm": 2.0977120399475098, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.4851, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5669835782195333, | |
| "grad_norm": 2.0266997814178467, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.5072, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5808124459809854, | |
| "grad_norm": 2.711892604827881, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4954, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5946413137424373, | |
| "grad_norm": 2.093878984451294, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.5194, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6084701815038893, | |
| "grad_norm": 1.8590729236602783, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.4422, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6222990492653414, | |
| "grad_norm": 1.5098389387130737, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.4165, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6361279170267934, | |
| "grad_norm": 1.8109772205352783, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.4278, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6499567847882455, | |
| "grad_norm": 1.3001216650009155, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.3659, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6637856525496975, | |
| "grad_norm": 2.071249008178711, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.5591, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6776145203111495, | |
| "grad_norm": 1.9663314819335938, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.4666, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6914433880726015, | |
| "grad_norm": 2.350602388381958, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7485, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6914433880726015, | |
| "eval_loss": 0.6085440516471863, | |
| "eval_runtime": 2.0865, | |
| "eval_samples_per_second": 23.963, | |
| "eval_steps_per_second": 6.23, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |