| { | |
| "best_metric": 11.5, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.010111734668082309, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002022346933616462, | |
| "grad_norm": 4.2358762584626675e-05, | |
| "learning_rate": 2e-05, | |
| "loss": 46.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002022346933616462, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 27.4401, | |
| "eval_samples_per_second": 303.498, | |
| "eval_steps_per_second": 37.937, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004044693867232924, | |
| "grad_norm": 6.443895836127922e-05, | |
| "learning_rate": 4e-05, | |
| "loss": 46.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006067040800849386, | |
| "grad_norm": 6.794629734940827e-05, | |
| "learning_rate": 6e-05, | |
| "loss": 46.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008089387734465848, | |
| "grad_norm": 3.1927360396366566e-05, | |
| "learning_rate": 8e-05, | |
| "loss": 46.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001011173466808231, | |
| "grad_norm": 3.5578777897171676e-05, | |
| "learning_rate": 0.0001, | |
| "loss": 46.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0012134081601698772, | |
| "grad_norm": 4.199743125354871e-05, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 46.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014156428535315234, | |
| "grad_norm": 4.674758747569285e-05, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 46.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0016178775468931696, | |
| "grad_norm": 4.5814202167093754e-05, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 46.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018201122402548156, | |
| "grad_norm": 6.019407737767324e-05, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 46.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002022346933616462, | |
| "grad_norm": 5.581518053077161e-05, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 46.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002224581626978108, | |
| "grad_norm": 4.392482151160948e-05, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 46.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0024268163203397543, | |
| "grad_norm": 4.266178802936338e-05, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 46.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0026290510137014006, | |
| "grad_norm": 5.492364289239049e-05, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 46.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002831285707063047, | |
| "grad_norm": 4.168040322838351e-05, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 46.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003033520400424693, | |
| "grad_norm": 7.527901470893994e-05, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 46.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0032357550937863393, | |
| "grad_norm": 8.684495696797967e-05, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 46.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003437989787147985, | |
| "grad_norm": 5.6331173254875466e-05, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 46.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0036402244805096313, | |
| "grad_norm": 0.00010844603093573824, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 46.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0038424591738712775, | |
| "grad_norm": 4.5255659642862156e-05, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 46.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004044693867232924, | |
| "grad_norm": 7.285013271030039e-05, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 46.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00424692856059457, | |
| "grad_norm": 0.00018613284919410944, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 46.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.004449163253956216, | |
| "grad_norm": 5.612182940240018e-05, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 46.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004651397947317862, | |
| "grad_norm": 0.00031355692772194743, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 46.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004853632640679509, | |
| "grad_norm": 9.290708840126172e-05, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 46.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0050558673340411545, | |
| "grad_norm": 0.00017926632426679134, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 46.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0050558673340411545, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 27.5611, | |
| "eval_samples_per_second": 302.166, | |
| "eval_steps_per_second": 37.771, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005258102027402801, | |
| "grad_norm": 0.00018002571596298367, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 46.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.005460336720764447, | |
| "grad_norm": 0.0002462012926116586, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 46.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.005662571414126094, | |
| "grad_norm": 0.00029739696765318513, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 46.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005864806107487739, | |
| "grad_norm": 0.0003964843926951289, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 46.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.006067040800849386, | |
| "grad_norm": 0.0004054371966049075, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 46.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006269275494211032, | |
| "grad_norm": 0.00019075242744293064, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 46.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0064715101875726785, | |
| "grad_norm": 0.0004364342021290213, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 46.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.006673744880934324, | |
| "grad_norm": 0.0003642778901848942, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 46.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00687597957429597, | |
| "grad_norm": 0.00036662680213339627, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 46.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.007078214267657617, | |
| "grad_norm": 0.0002541069407016039, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 46.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0072804489610192626, | |
| "grad_norm": 0.0003552269481588155, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 46.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.007482683654380909, | |
| "grad_norm": 0.0002922409912571311, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 46.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.007684918347742555, | |
| "grad_norm": 0.000310244329739362, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 46.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0078871530411042, | |
| "grad_norm": 0.0001724491303320974, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 46.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.008089387734465847, | |
| "grad_norm": 7.884677324909717e-05, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 46.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008291622427827494, | |
| "grad_norm": 7.308423664653674e-05, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 46.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.00849385712118914, | |
| "grad_norm": 0.00012783825513906777, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 46.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.008696091814550786, | |
| "grad_norm": 0.00034225135459564626, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 46.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.008898326507912432, | |
| "grad_norm": 0.0005108854384161532, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 46.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.009100561201274079, | |
| "grad_norm": 0.0004680280981119722, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 46.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009302795894635724, | |
| "grad_norm": 0.0004146777791902423, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 46.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.00950503058799737, | |
| "grad_norm": 0.0003186096728313714, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 46.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.009707265281359017, | |
| "grad_norm": 0.0003894997644238174, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 46.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.009909499974720664, | |
| "grad_norm": 0.00041468587005510926, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 46.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.010111734668082309, | |
| "grad_norm": 0.0004269829369150102, | |
| "learning_rate": 0.0, | |
| "loss": 46.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.010111734668082309, | |
| "eval_loss": 11.5, | |
| "eval_runtime": 27.5269, | |
| "eval_samples_per_second": 302.54, | |
| "eval_steps_per_second": 37.818, | |
| "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": 6371395436544.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |