| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.05959475566150179, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011918951132300357, | |
| "grad_norm": 1.8323841453219294, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1039, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023837902264600714, | |
| "grad_norm": 1.837920719204094, | |
| "learning_rate": 1.9979453927503366e-05, | |
| "loss": 2.1015, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003575685339690107, | |
| "grad_norm": 0.9173452411852326, | |
| "learning_rate": 1.991790013823246e-05, | |
| "loss": 2.0311, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004767580452920143, | |
| "grad_norm": 1.265146161082013, | |
| "learning_rate": 1.9815591569910654e-05, | |
| "loss": 2.0187, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0059594755661501785, | |
| "grad_norm": 1.0055189392399428, | |
| "learning_rate": 1.9672948630390296e-05, | |
| "loss": 2.0142, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007151370679380214, | |
| "grad_norm": 1.6116133535057522, | |
| "learning_rate": 1.949055747010669e-05, | |
| "loss": 2.047, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00834326579261025, | |
| "grad_norm": 1.0164569935770877, | |
| "learning_rate": 1.926916757346022e-05, | |
| "loss": 2.0114, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009535160905840286, | |
| "grad_norm": 0.8088386058968114, | |
| "learning_rate": 1.900968867902419e-05, | |
| "loss": 1.979, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010727056019070322, | |
| "grad_norm": 0.7238192809262382, | |
| "learning_rate": 1.8713187041233896e-05, | |
| "loss": 1.9969, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011918951132300357, | |
| "grad_norm": 0.5757195660436086, | |
| "learning_rate": 1.8380881048918406e-05, | |
| "loss": 1.9719, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013110846245530394, | |
| "grad_norm": 0.6136131835485481, | |
| "learning_rate": 1.8014136218679566e-05, | |
| "loss": 1.9736, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.014302741358760428, | |
| "grad_norm": 0.6462531692000065, | |
| "learning_rate": 1.7614459583691346e-05, | |
| "loss": 1.9625, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015494636471990465, | |
| "grad_norm": 0.5160196738824037, | |
| "learning_rate": 1.7183493500977277e-05, | |
| "loss": 1.9524, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0166865315852205, | |
| "grad_norm": 0.48508132154258404, | |
| "learning_rate": 1.672300890261317e-05, | |
| "loss": 1.9584, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017878426698450536, | |
| "grad_norm": 0.5181005310771087, | |
| "learning_rate": 1.6234898018587336e-05, | |
| "loss": 1.967, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01907032181168057, | |
| "grad_norm": 0.4150834616993424, | |
| "learning_rate": 1.5721166601221697e-05, | |
| "loss": 1.9456, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02026221692491061, | |
| "grad_norm": 0.3379165251881648, | |
| "learning_rate": 1.5183925683105254e-05, | |
| "loss": 1.9637, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.021454112038140644, | |
| "grad_norm": 0.3484808167274383, | |
| "learning_rate": 1.4625382902408356e-05, | |
| "loss": 1.9582, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02264600715137068, | |
| "grad_norm": 0.35126742165373703, | |
| "learning_rate": 1.4047833431223938e-05, | |
| "loss": 1.9716, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.023837902264600714, | |
| "grad_norm": 0.2995298854480071, | |
| "learning_rate": 1.3453650544213078e-05, | |
| "loss": 1.9804, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025029797377830752, | |
| "grad_norm": 0.2812553357334388, | |
| "learning_rate": 1.2845275866310325e-05, | |
| "loss": 1.943, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.026221692491060787, | |
| "grad_norm": 0.29784459167074245, | |
| "learning_rate": 1.2225209339563144e-05, | |
| "loss": 1.9517, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.027413587604290822, | |
| "grad_norm": 0.28759384963571305, | |
| "learning_rate": 1.1595998950333794e-05, | |
| "loss": 1.9676, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.028605482717520857, | |
| "grad_norm": 0.26154732718281476, | |
| "learning_rate": 1.0960230259076819e-05, | |
| "loss": 1.9585, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.029797377830750895, | |
| "grad_norm": 0.2417322199141499, | |
| "learning_rate": 1.0320515775716556e-05, | |
| "loss": 1.9658, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03098927294398093, | |
| "grad_norm": 0.2647008811703257, | |
| "learning_rate": 9.67948422428345e-06, | |
| "loss": 1.9677, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03218116805721097, | |
| "grad_norm": 0.28156330533090274, | |
| "learning_rate": 9.039769740923183e-06, | |
| "loss": 1.971, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.033373063170441, | |
| "grad_norm": 0.23451944041424483, | |
| "learning_rate": 8.404001049666211e-06, | |
| "loss": 1.9777, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03456495828367104, | |
| "grad_norm": 0.20425845712936946, | |
| "learning_rate": 7.774790660436857e-06, | |
| "loss": 1.9455, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03575685339690107, | |
| "grad_norm": 0.20003632743257047, | |
| "learning_rate": 7.154724133689677e-06, | |
| "loss": 1.9219, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03694874851013111, | |
| "grad_norm": 0.22248700808509062, | |
| "learning_rate": 6.546349455786926e-06, | |
| "loss": 1.9595, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03814064362336114, | |
| "grad_norm": 0.22141566358189815, | |
| "learning_rate": 5.952166568776062e-06, | |
| "loss": 1.9736, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.03933253873659118, | |
| "grad_norm": 0.20350762417692123, | |
| "learning_rate": 5.37461709759165e-06, | |
| "loss": 1.9491, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04052443384982122, | |
| "grad_norm": 0.18362905257668707, | |
| "learning_rate": 4.81607431689475e-06, | |
| "loss": 1.9877, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.041716328963051254, | |
| "grad_norm": 0.18209143534810343, | |
| "learning_rate": 4.278833398778306e-06, | |
| "loss": 1.9711, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04290822407628129, | |
| "grad_norm": 0.1870043994840097, | |
| "learning_rate": 3.7651019814126656e-06, | |
| "loss": 1.9997, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04410011918951132, | |
| "grad_norm": 0.18563803773188292, | |
| "learning_rate": 3.2769910973868314e-06, | |
| "loss": 1.9611, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04529201430274136, | |
| "grad_norm": 0.1803488628139512, | |
| "learning_rate": 2.8165064990227255e-06, | |
| "loss": 1.9779, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04648390941597139, | |
| "grad_norm": 0.18280901111654344, | |
| "learning_rate": 2.3855404163086558e-06, | |
| "loss": 1.9753, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04767580452920143, | |
| "grad_norm": 0.18003744910780412, | |
| "learning_rate": 1.9858637813204352e-06, | |
| "loss": 1.9327, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04886769964243146, | |
| "grad_norm": 0.1751954707202772, | |
| "learning_rate": 1.6191189510815942e-06, | |
| "loss": 1.9578, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.050059594755661505, | |
| "grad_norm": 0.17152593814056669, | |
| "learning_rate": 1.286812958766106e-06, | |
| "loss": 1.9176, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05125148986889154, | |
| "grad_norm": 0.16959349088820902, | |
| "learning_rate": 9.903113209758098e-07, | |
| "loss": 1.9505, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.052443384982121574, | |
| "grad_norm": 0.16660058312767648, | |
| "learning_rate": 7.308324265397837e-07, | |
| "loss": 1.9683, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.05363528009535161, | |
| "grad_norm": 0.17674746764132468, | |
| "learning_rate": 5.094425298933136e-07, | |
| "loss": 1.9643, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.054827175208581644, | |
| "grad_norm": 0.16795370746145422, | |
| "learning_rate": 3.2705136960970554e-07, | |
| "loss": 1.9812, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05601907032181168, | |
| "grad_norm": 0.17056366756389463, | |
| "learning_rate": 1.844084300893456e-07, | |
| "loss": 1.959, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.057210965435041714, | |
| "grad_norm": 0.16170892183194993, | |
| "learning_rate": 8.209986176753947e-08, | |
| "loss": 1.9624, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.058402860548271755, | |
| "grad_norm": 0.17173937225335953, | |
| "learning_rate": 2.054607249663665e-08, | |
| "loss": 1.9578, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.05959475566150179, | |
| "grad_norm": 0.17021831986392572, | |
| "learning_rate": 0.0, | |
| "loss": 1.9973, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05959475566150179, | |
| "step": 50, | |
| "total_flos": 106890730143744.0, | |
| "train_loss": 1.9756734085083008, | |
| "train_runtime": 1598.4061, | |
| "train_samples_per_second": 58.058, | |
| "train_steps_per_second": 0.031 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 106890730143744.0, | |
| "train_batch_size": 58, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |