| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 4528, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022084805653710248, | |
| "grad_norm": 0.1020389199256897, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 2.5011, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.044169611307420496, | |
| "grad_norm": 0.1910451352596283, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 2.4789, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06625441696113074, | |
| "grad_norm": 0.26337745785713196, | |
| "learning_rate": 2e-05, | |
| "loss": 2.4291, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.08833922261484099, | |
| "grad_norm": 0.3770335614681244, | |
| "learning_rate": 1.9972406933597812e-05, | |
| "loss": 2.4186, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.11042402826855123, | |
| "grad_norm": 0.36907321214675903, | |
| "learning_rate": 1.988978000985394e-05, | |
| "loss": 2.3774, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.13250883392226148, | |
| "grad_norm": 0.4569687247276306, | |
| "learning_rate": 1.9752575214807077e-05, | |
| "loss": 2.3992, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.15459363957597172, | |
| "grad_norm": 0.4629022777080536, | |
| "learning_rate": 1.9561549728661312e-05, | |
| "loss": 2.325, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.17667844522968199, | |
| "grad_norm": 0.47432681918144226, | |
| "learning_rate": 1.9317757747201386e-05, | |
| "loss": 2.3013, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.19876325088339222, | |
| "grad_norm": 0.46376603841781616, | |
| "learning_rate": 1.9022544664093854e-05, | |
| "loss": 2.3277, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.22084805653710246, | |
| "grad_norm": 0.48484688997268677, | |
| "learning_rate": 1.8677539646179706e-05, | |
| "loss": 2.314, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.24293286219081273, | |
| "grad_norm": 0.655317485332489, | |
| "learning_rate": 1.828464664273263e-05, | |
| "loss": 2.3047, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.26501766784452296, | |
| "grad_norm": 0.520976722240448, | |
| "learning_rate": 1.7846033878299232e-05, | |
| "loss": 2.2971, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.2871024734982332, | |
| "grad_norm": 0.502010703086853, | |
| "learning_rate": 1.7364121887106285e-05, | |
| "loss": 2.3102, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.30918727915194344, | |
| "grad_norm": 0.5849918127059937, | |
| "learning_rate": 1.684157015506839e-05, | |
| "loss": 2.2636, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.33127208480565373, | |
| "grad_norm": 0.6814427375793457, | |
| "learning_rate": 1.628126244311369e-05, | |
| "loss": 2.2854, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.35335689045936397, | |
| "grad_norm": 0.4844237267971039, | |
| "learning_rate": 1.5686290872822504e-05, | |
| "loss": 2.294, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.3754416961130742, | |
| "grad_norm": 0.6080675721168518, | |
| "learning_rate": 1.5059938862204126e-05, | |
| "loss": 2.2631, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.39752650176678445, | |
| "grad_norm": 0.561839759349823, | |
| "learning_rate": 1.440566300578259e-05, | |
| "loss": 2.2489, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.4196113074204947, | |
| "grad_norm": 0.5733577609062195, | |
| "learning_rate": 1.3727073998988202e-05, | |
| "loss": 2.2505, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.4416961130742049, | |
| "grad_norm": 0.6440421342849731, | |
| "learning_rate": 1.3027916712125825e-05, | |
| "loss": 2.2341, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.4637809187279152, | |
| "grad_norm": 0.5807141661643982, | |
| "learning_rate": 1.2312049523883851e-05, | |
| "loss": 2.2842, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.48586572438162545, | |
| "grad_norm": 0.6154150366783142, | |
| "learning_rate": 1.1583423028434343e-05, | |
| "loss": 2.2756, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.5079505300353356, | |
| "grad_norm": 0.8887423276901245, | |
| "learning_rate": 1.0846058233631565e-05, | |
| "loss": 2.2388, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.5300353356890459, | |
| "grad_norm": 0.6062945127487183, | |
| "learning_rate": 1.0104024370624644e-05, | |
| "loss": 2.2708, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.5521201413427562, | |
| "grad_norm": 0.7383410930633545, | |
| "learning_rate": 9.361416437344504e-06, | |
| "loss": 2.2693, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.5742049469964664, | |
| "grad_norm": 0.7274787425994873, | |
| "learning_rate": 8.622332599793906e-06, | |
| "loss": 2.2596, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.5962897526501767, | |
| "grad_norm": 0.6965683102607727, | |
| "learning_rate": 7.890851575854108e-06, | |
| "loss": 2.2652, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.6183745583038869, | |
| "grad_norm": 0.6714246273040771, | |
| "learning_rate": 7.171010126418218e-06, | |
| "loss": 2.2587, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.6404593639575972, | |
| "grad_norm": 0.7770031690597534, | |
| "learning_rate": 6.466780778068903e-06, | |
| "loss": 2.2502, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.6625441696113075, | |
| "grad_norm": 0.7164767980575562, | |
| "learning_rate": 5.782049900240432e-06, | |
| "loss": 2.2477, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.6846289752650176, | |
| "grad_norm": 0.7085398435592651, | |
| "learning_rate": 5.120596257848716e-06, | |
| "loss": 2.268, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.7067137809187279, | |
| "grad_norm": 0.7723512053489685, | |
| "learning_rate": 4.486070157749059e-06, | |
| "loss": 2.2363, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.7287985865724381, | |
| "grad_norm": 0.6914446353912354, | |
| "learning_rate": 3.881973304104252e-06, | |
| "loss": 2.2511, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.7508833922261484, | |
| "grad_norm": 0.6801828742027283, | |
| "learning_rate": 3.311639473833487e-06, | |
| "loss": 2.2672, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.7729681978798587, | |
| "grad_norm": 0.6551490426063538, | |
| "learning_rate": 2.778216118786782e-06, | |
| "loss": 2.2574, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.7950530035335689, | |
| "grad_norm": 0.7881369590759277, | |
| "learning_rate": 2.2846469961753916e-06, | |
| "loss": 2.2728, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.8171378091872792, | |
| "grad_norm": 0.6549363136291504, | |
| "learning_rate": 1.8336559231141726e-06, | |
| "loss": 2.2253, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.8392226148409894, | |
| "grad_norm": 0.6901439428329468, | |
| "learning_rate": 1.4277317449282834e-06, | |
| "loss": 2.2392, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.8613074204946997, | |
| "grad_norm": 0.6845853924751282, | |
| "learning_rate": 1.0691146001783081e-06, | |
| "loss": 2.2545, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.8833922261484098, | |
| "grad_norm": 0.7686012387275696, | |
| "learning_rate": 7.597835582018586e-07, | |
| "loss": 2.2374, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.9054770318021201, | |
| "grad_norm": 0.6920452117919922, | |
| "learning_rate": 5.014456973952375e-07, | |
| "loss": 2.249, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.9275618374558304, | |
| "grad_norm": 0.5871976613998413, | |
| "learning_rate": 2.9552668450792965e-07, | |
| "loss": 2.2629, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.9496466431095406, | |
| "grad_norm": 0.7372850179672241, | |
| "learning_rate": 1.431629069391516e-07, | |
| "loss": 2.2742, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.9717314487632509, | |
| "grad_norm": 0.7272618412971497, | |
| "learning_rate": 4.519520145525369e-08, | |
| "loss": 2.238, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.9938162544169611, | |
| "grad_norm": 0.6909335851669312, | |
| "learning_rate": 2.164213936770576e-09, | |
| "loss": 2.2434, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 4528, | |
| "total_flos": 8.2279274151936e+16, | |
| "train_loss": 2.2892676124303164, | |
| "train_runtime": 1413.0668, | |
| "train_samples_per_second": 6.408, | |
| "train_steps_per_second": 3.204 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4528, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.2279274151936e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |