| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.44776119402985076, | |
| "eval_steps": 9, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005970149253731343, | |
| "grad_norm": 1.2009718418121338, | |
| "learning_rate": 1e-05, | |
| "loss": 7.1874, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005970149253731343, | |
| "eval_loss": 3.6131668090820312, | |
| "eval_runtime": 43.8864, | |
| "eval_samples_per_second": 3.213, | |
| "eval_steps_per_second": 0.41, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011940298507462687, | |
| "grad_norm": 1.276452660560608, | |
| "learning_rate": 2e-05, | |
| "loss": 7.3753, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01791044776119403, | |
| "grad_norm": 1.169365406036377, | |
| "learning_rate": 3e-05, | |
| "loss": 7.1167, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.023880597014925373, | |
| "grad_norm": 1.4007748365402222, | |
| "learning_rate": 4e-05, | |
| "loss": 7.2851, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.029850746268656716, | |
| "grad_norm": 1.4416389465332031, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9871, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03582089552238806, | |
| "grad_norm": 1.5692150592803955, | |
| "learning_rate": 6e-05, | |
| "loss": 7.028, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.041791044776119404, | |
| "grad_norm": 1.3784325122833252, | |
| "learning_rate": 7e-05, | |
| "loss": 6.816, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04776119402985075, | |
| "grad_norm": 1.6804227828979492, | |
| "learning_rate": 8e-05, | |
| "loss": 6.9157, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05373134328358209, | |
| "grad_norm": 1.4350379705429077, | |
| "learning_rate": 9e-05, | |
| "loss": 6.7714, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05373134328358209, | |
| "eval_loss": 3.358555316925049, | |
| "eval_runtime": 44.0564, | |
| "eval_samples_per_second": 3.2, | |
| "eval_steps_per_second": 0.409, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": 1.7629762887954712, | |
| "learning_rate": 0.0001, | |
| "loss": 6.7025, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06567164179104477, | |
| "grad_norm": 1.9589104652404785, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 6.7321, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07164179104477612, | |
| "grad_norm": 1.3560996055603027, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 6.4935, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07761194029850746, | |
| "grad_norm": 1.097153663635254, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 6.4837, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08358208955223881, | |
| "grad_norm": 0.8275943994522095, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 6.2538, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08955223880597014, | |
| "grad_norm": 0.6273999810218811, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 6.2581, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0955223880597015, | |
| "grad_norm": 0.6474035978317261, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 6.2101, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10149253731343283, | |
| "grad_norm": 0.7804368734359741, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 6.1777, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10746268656716418, | |
| "grad_norm": 0.8049015402793884, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 6.2771, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10746268656716418, | |
| "eval_loss": 3.0857627391815186, | |
| "eval_runtime": 44.0268, | |
| "eval_samples_per_second": 3.203, | |
| "eval_steps_per_second": 0.409, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11343283582089553, | |
| "grad_norm": 0.6202137470245361, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 6.1886, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 0.6927691102027893, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 6.2423, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1253731343283582, | |
| "grad_norm": 0.6712962985038757, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 6.1187, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13134328358208955, | |
| "grad_norm": 0.39803004264831543, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 6.1228, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1373134328358209, | |
| "grad_norm": 0.8054197430610657, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 6.0574, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14328358208955225, | |
| "grad_norm": 0.35388606786727905, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 6.0201, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 0.6076826453208923, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 6.1896, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15522388059701492, | |
| "grad_norm": 0.7924426198005676, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 6.0612, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.16119402985074627, | |
| "grad_norm": 0.4275815784931183, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 6.0404, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.16119402985074627, | |
| "eval_loss": 3.0337231159210205, | |
| "eval_runtime": 44.0377, | |
| "eval_samples_per_second": 3.202, | |
| "eval_steps_per_second": 0.409, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.16716417910447762, | |
| "grad_norm": 0.706186056137085, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 5.9746, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.17313432835820897, | |
| "grad_norm": 0.7469488978385925, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 6.0592, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 0.3669968843460083, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 6.0306, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18507462686567164, | |
| "grad_norm": 1.3864649534225464, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 6.0186, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.191044776119403, | |
| "grad_norm": 0.3378469944000244, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 6.0835, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.19701492537313434, | |
| "grad_norm": 1.3633979558944702, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 6.0245, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.20298507462686566, | |
| "grad_norm": 0.9031431078910828, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 5.9733, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.208955223880597, | |
| "grad_norm": 0.328767865896225, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 6.0025, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.21492537313432836, | |
| "grad_norm": 1.1566050052642822, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 6.0371, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.21492537313432836, | |
| "eval_loss": 3.032942056655884, | |
| "eval_runtime": 44.0184, | |
| "eval_samples_per_second": 3.203, | |
| "eval_steps_per_second": 0.409, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2208955223880597, | |
| "grad_norm": 1.31416654586792, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 6.1139, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.22686567164179106, | |
| "grad_norm": 0.2981594502925873, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 6.0316, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.23283582089552238, | |
| "grad_norm": 0.7097679972648621, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 5.9398, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 1.0947890281677246, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 5.9944, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24477611940298508, | |
| "grad_norm": 0.27537035942077637, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 6.0236, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2507462686567164, | |
| "grad_norm": 0.45621415972709656, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 5.949, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.25671641791044775, | |
| "grad_norm": 0.20884762704372406, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 6.0089, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2626865671641791, | |
| "grad_norm": 0.21904632449150085, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 5.973, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.26865671641791045, | |
| "grad_norm": 0.36318573355674744, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 5.9505, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.26865671641791045, | |
| "eval_loss": 3.018928289413452, | |
| "eval_runtime": 44.0252, | |
| "eval_samples_per_second": 3.203, | |
| "eval_steps_per_second": 0.409, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2746268656716418, | |
| "grad_norm": 0.4027023911476135, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 6.1368, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.28059701492537314, | |
| "grad_norm": 0.7140593528747559, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 6.0893, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2865671641791045, | |
| "grad_norm": 0.27870509028434753, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 6.0323, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.29253731343283584, | |
| "grad_norm": 0.8685962557792664, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 6.1308, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.5305348634719849, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 6.0474, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3044776119402985, | |
| "grad_norm": 0.8471565842628479, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 6.0034, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.31044776119402984, | |
| "grad_norm": 1.006734013557434, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 6.0647, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3164179104477612, | |
| "grad_norm": 1.746330976486206, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 6.1285, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.32238805970149254, | |
| "grad_norm": 0.7526426911354065, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 6.0263, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.32238805970149254, | |
| "eval_loss": 3.018310546875, | |
| "eval_runtime": 43.9264, | |
| "eval_samples_per_second": 3.21, | |
| "eval_steps_per_second": 0.41, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3283582089552239, | |
| "grad_norm": 0.24178102612495422, | |
| "learning_rate": 5e-05, | |
| "loss": 5.9838, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.33432835820895523, | |
| "grad_norm": 1.259934425354004, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 6.0442, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3402985074626866, | |
| "grad_norm": 0.9597307443618774, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 6.0847, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.34626865671641793, | |
| "grad_norm": 0.7438874244689941, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 6.0213, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.3522388059701492, | |
| "grad_norm": 0.2544308304786682, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 6.0455, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 0.6676498055458069, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 6.0191, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3641791044776119, | |
| "grad_norm": 1.6943082809448242, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 5.9287, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.3701492537313433, | |
| "grad_norm": 1.1571624279022217, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 6.0959, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.3761194029850746, | |
| "grad_norm": 0.43850600719451904, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 5.9537, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3761194029850746, | |
| "eval_loss": 3.017953395843506, | |
| "eval_runtime": 43.8204, | |
| "eval_samples_per_second": 3.218, | |
| "eval_steps_per_second": 0.411, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.382089552238806, | |
| "grad_norm": 0.7406497597694397, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 6.1041, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.3880597014925373, | |
| "grad_norm": 1.1883533000946045, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 6.0868, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3940298507462687, | |
| "grad_norm": 1.2352616786956787, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 6.0639, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.7118608355522156, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 5.969, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.4059701492537313, | |
| "grad_norm": 0.40361595153808594, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 5.9868, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.41194029850746267, | |
| "grad_norm": 0.34668585658073425, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 6.0418, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.417910447761194, | |
| "grad_norm": 0.48091813921928406, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 6.0231, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42388059701492536, | |
| "grad_norm": 0.5058419704437256, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 6.0534, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.4298507462686567, | |
| "grad_norm": 0.36839550733566284, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 6.0709, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4298507462686567, | |
| "eval_loss": 3.015293836593628, | |
| "eval_runtime": 43.8313, | |
| "eval_samples_per_second": 3.217, | |
| "eval_steps_per_second": 0.411, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.43582089552238806, | |
| "grad_norm": 0.4969329833984375, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 6.0208, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.4417910447761194, | |
| "grad_norm": 0.3160986304283142, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 6.0143, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 0.43142208456993103, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 6.0745, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.897989119410176e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |