| { | |
| "best_metric": 0.5707394480705261, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.05370569280343716, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010741138560687433, | |
| "grad_norm": 1.300419807434082, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6542, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010741138560687433, | |
| "eval_loss": 2.067019462585449, | |
| "eval_runtime": 253.6367, | |
| "eval_samples_per_second": 1.546, | |
| "eval_steps_per_second": 0.773, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021482277121374865, | |
| "grad_norm": 1.5085821151733398, | |
| "learning_rate": 0.0002, | |
| "loss": 3.5856, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00322234156820623, | |
| "grad_norm": 4.469718933105469, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 4.6187, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004296455424274973, | |
| "grad_norm": 3.348555088043213, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 4.2747, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0053705692803437165, | |
| "grad_norm": 5.730258941650391, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 3.7536, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00644468313641246, | |
| "grad_norm": 5.00005578994751, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 3.574, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007518796992481203, | |
| "grad_norm": 5.454052925109863, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 3.3832, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "grad_norm": 3.948171854019165, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 2.9389, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00966702470461869, | |
| "grad_norm": 3.8745367527008057, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 2.6021, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010741138560687433, | |
| "grad_norm": 6.631568908691406, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 2.42, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011815252416756176, | |
| "grad_norm": 3.7132058143615723, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 2.8465, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "grad_norm": 3.5346767902374268, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 2.2022, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013963480128893663, | |
| "grad_norm": 3.1227457523345947, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 2.2492, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015037593984962405, | |
| "grad_norm": 2.1377246379852295, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.1818, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01611170784103115, | |
| "grad_norm": 1.9351719617843628, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 1.5732, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "grad_norm": 2.7266533374786377, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 1.8584, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.018259935553168637, | |
| "grad_norm": 2.3338723182678223, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 1.66, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01933404940923738, | |
| "grad_norm": 3.5971460342407227, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 2.2369, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 1.9934290647506714, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 1.9199, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.021482277121374866, | |
| "grad_norm": 2.5816171169281006, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 1.8563, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022556390977443608, | |
| "grad_norm": 2.795732259750366, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 2.0038, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.023630504833512353, | |
| "grad_norm": 2.574127674102783, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 2.1637, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.024704618689581095, | |
| "grad_norm": 3.4169461727142334, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 2.9757, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "grad_norm": 2.764451742172241, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 1.8735, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02685284640171858, | |
| "grad_norm": 3.691221237182617, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 2.1683, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02685284640171858, | |
| "eval_loss": 0.6165056824684143, | |
| "eval_runtime": 254.8895, | |
| "eval_samples_per_second": 1.538, | |
| "eval_steps_per_second": 0.769, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027926960257787327, | |
| "grad_norm": 3.5959391593933105, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7773, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02900107411385607, | |
| "grad_norm": 3.213015079498291, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 2.4237, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03007518796992481, | |
| "grad_norm": 3.6218926906585693, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 2.8496, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.031149301825993556, | |
| "grad_norm": 3.0756144523620605, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 1.9848, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0322234156820623, | |
| "grad_norm": 3.864434003829956, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 3.1022, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03329752953813104, | |
| "grad_norm": 3.296337842941284, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 2.2655, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.034371643394199784, | |
| "grad_norm": 3.269047498703003, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 2.284, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03544575725026853, | |
| "grad_norm": 3.5344269275665283, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 1.8864, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.036519871106337275, | |
| "grad_norm": 4.668367385864258, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 2.3255, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03759398496240601, | |
| "grad_norm": 4.970749855041504, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 2.8352, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03866809881847476, | |
| "grad_norm": 3.3336353302001953, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 2.0678, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0397422126745435, | |
| "grad_norm": 3.146103620529175, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 1.6564, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 4.855753421783447, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 2.3859, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04189044038668099, | |
| "grad_norm": 4.550353050231934, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 2.1639, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04296455424274973, | |
| "grad_norm": 7.876417636871338, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 2.2466, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04403866809881848, | |
| "grad_norm": 4.67519474029541, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 1.9059, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.045112781954887216, | |
| "grad_norm": 5.316860675811768, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 2.3931, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04618689581095596, | |
| "grad_norm": 4.196220874786377, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 2.2159, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.047261009667024706, | |
| "grad_norm": 4.706377029418945, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 2.0003, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04833512352309345, | |
| "grad_norm": 5.4141154289245605, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 2.9123, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04940923737916219, | |
| "grad_norm": 6.08075475692749, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 2.6994, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.050483351235230935, | |
| "grad_norm": 4.99581241607666, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 3.621, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05155746509129968, | |
| "grad_norm": 7.598954677581787, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 2.4808, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 6.14135217666626, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 2.6089, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05370569280343716, | |
| "grad_norm": 9.300232887268066, | |
| "learning_rate": 0.0, | |
| "loss": 1.8088, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05370569280343716, | |
| "eval_loss": 0.5707394480705261, | |
| "eval_runtime": 255.0357, | |
| "eval_samples_per_second": 1.537, | |
| "eval_steps_per_second": 0.769, | |
| "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": 6.53464644354048e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |