| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.4033333333333333, | |
| "eval_steps": 500, | |
| "global_step": 242, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008333333333333333, | |
| "grad_norm": 0.48900601267814636, | |
| "learning_rate": 4.999904807660428e-05, | |
| "loss": 0.4212, | |
| "num_input_tokens_seen": 30064, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016666666666666666, | |
| "grad_norm": 0.3595407009124756, | |
| "learning_rate": 4.9996192378909786e-05, | |
| "loss": 0.2803, | |
| "num_input_tokens_seen": 57376, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 0.2623545527458191, | |
| "learning_rate": 4.999143312438893e-05, | |
| "loss": 0.1484, | |
| "num_input_tokens_seen": 86160, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03333333333333333, | |
| "grad_norm": 0.2743065357208252, | |
| "learning_rate": 4.99847706754774e-05, | |
| "loss": 0.1151, | |
| "num_input_tokens_seen": 110592, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.041666666666666664, | |
| "grad_norm": 0.2651338577270508, | |
| "learning_rate": 4.997620553954645e-05, | |
| "loss": 0.0751, | |
| "num_input_tokens_seen": 138880, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.10798148065805435, | |
| "learning_rate": 4.996573836886435e-05, | |
| "loss": 0.0471, | |
| "num_input_tokens_seen": 169600, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.058333333333333334, | |
| "grad_norm": 0.1552838534116745, | |
| "learning_rate": 4.9953369960546676e-05, | |
| "loss": 0.0368, | |
| "num_input_tokens_seen": 201664, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06666666666666667, | |
| "grad_norm": 0.11832074075937271, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 0.0311, | |
| "num_input_tokens_seen": 229936, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 0.10593917220830917, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.0262, | |
| "num_input_tokens_seen": 259088, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08333333333333333, | |
| "grad_norm": 0.09650842100381851, | |
| "learning_rate": 4.990486745229364e-05, | |
| "loss": 0.0244, | |
| "num_input_tokens_seen": 289824, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09166666666666666, | |
| "grad_norm": 0.14155137538909912, | |
| "learning_rate": 4.988490495917947e-05, | |
| "loss": 0.0266, | |
| "num_input_tokens_seen": 317760, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.1490347981452942, | |
| "learning_rate": 4.9867570427929354e-05, | |
| "loss": 0.0283, | |
| "num_input_tokens_seen": 343120, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10833333333333334, | |
| "grad_norm": 0.17539122700691223, | |
| "learning_rate": 4.984419797901491e-05, | |
| "loss": 0.0265, | |
| "num_input_tokens_seen": 371600, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.11666666666666667, | |
| "grad_norm": 0.1336919367313385, | |
| "learning_rate": 4.981893354823614e-05, | |
| "loss": 0.0235, | |
| "num_input_tokens_seen": 398720, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 0.12203177809715271, | |
| "learning_rate": 4.979177905957726e-05, | |
| "loss": 0.0229, | |
| "num_input_tokens_seen": 426416, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 0.2557654082775116, | |
| "learning_rate": 4.976273658095772e-05, | |
| "loss": 0.0238, | |
| "num_input_tokens_seen": 452944, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14166666666666666, | |
| "grad_norm": 0.13327105343341827, | |
| "learning_rate": 4.9731808324074717e-05, | |
| "loss": 0.0208, | |
| "num_input_tokens_seen": 480896, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.1262751668691635, | |
| "learning_rate": 4.969899664423473e-05, | |
| "loss": 0.0191, | |
| "num_input_tokens_seen": 510096, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15833333333333333, | |
| "grad_norm": 0.16084067523479462, | |
| "learning_rate": 4.966430404017424e-05, | |
| "loss": 0.0205, | |
| "num_input_tokens_seen": 536672, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.15870437026023865, | |
| "learning_rate": 4.962773315386935e-05, | |
| "loss": 0.0193, | |
| "num_input_tokens_seen": 566528, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.175, | |
| "grad_norm": 0.07833187282085419, | |
| "learning_rate": 4.9589286770334654e-05, | |
| "loss": 0.024, | |
| "num_input_tokens_seen": 593584, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.18333333333333332, | |
| "grad_norm": 0.09176061302423477, | |
| "learning_rate": 4.954896781741109e-05, | |
| "loss": 0.0206, | |
| "num_input_tokens_seen": 620992, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.19166666666666668, | |
| "grad_norm": 0.08285439014434814, | |
| "learning_rate": 4.9506779365543046e-05, | |
| "loss": 0.0188, | |
| "num_input_tokens_seen": 647504, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.13359522819519043, | |
| "learning_rate": 4.9462724627544466e-05, | |
| "loss": 0.0183, | |
| "num_input_tokens_seen": 676336, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.20833333333333334, | |
| "grad_norm": 0.07570718228816986, | |
| "learning_rate": 4.94168069583542e-05, | |
| "loss": 0.0189, | |
| "num_input_tokens_seen": 701488, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.21666666666666667, | |
| "grad_norm": 0.11286037415266037, | |
| "learning_rate": 4.936902985478055e-05, | |
| "loss": 0.0213, | |
| "num_input_tokens_seen": 731152, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.225, | |
| "grad_norm": 0.17183929681777954, | |
| "learning_rate": 4.931939695523492e-05, | |
| "loss": 0.0214, | |
| "num_input_tokens_seen": 757792, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.23333333333333334, | |
| "grad_norm": 0.11746834218502045, | |
| "learning_rate": 4.926791203945477e-05, | |
| "loss": 0.0214, | |
| "num_input_tokens_seen": 786064, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24166666666666667, | |
| "grad_norm": 0.09453292936086655, | |
| "learning_rate": 4.9214579028215776e-05, | |
| "loss": 0.0203, | |
| "num_input_tokens_seen": 814640, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.2074723094701767, | |
| "learning_rate": 4.915940198303324e-05, | |
| "loss": 0.0194, | |
| "num_input_tokens_seen": 842656, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.25833333333333336, | |
| "grad_norm": 0.15371476113796234, | |
| "learning_rate": 4.910238510585276e-05, | |
| "loss": 0.0158, | |
| "num_input_tokens_seen": 868512, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 0.07177837193012238, | |
| "learning_rate": 4.9043532738730284e-05, | |
| "loss": 0.0172, | |
| "num_input_tokens_seen": 896416, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.275, | |
| "grad_norm": 0.07891824096441269, | |
| "learning_rate": 4.898284936350144e-05, | |
| "loss": 0.0193, | |
| "num_input_tokens_seen": 924720, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.2833333333333333, | |
| "grad_norm": 0.08302944153547287, | |
| "learning_rate": 4.892033960144019e-05, | |
| "loss": 0.0189, | |
| "num_input_tokens_seen": 955584, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.2916666666666667, | |
| "grad_norm": 0.25554358959198, | |
| "learning_rate": 4.8856008212906925e-05, | |
| "loss": 0.019, | |
| "num_input_tokens_seen": 985072, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.1445908546447754, | |
| "learning_rate": 4.878986009698596e-05, | |
| "loss": 0.0168, | |
| "num_input_tokens_seen": 1013296, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.30833333333333335, | |
| "grad_norm": 0.21417762339115143, | |
| "learning_rate": 4.8721900291112415e-05, | |
| "loss": 0.0194, | |
| "num_input_tokens_seen": 1043664, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.31666666666666665, | |
| "grad_norm": 0.1550753116607666, | |
| "learning_rate": 4.8652133970688636e-05, | |
| "loss": 0.0155, | |
| "num_input_tokens_seen": 1070912, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.325, | |
| "grad_norm": 0.132898211479187, | |
| "learning_rate": 4.858056644869002e-05, | |
| "loss": 0.0193, | |
| "num_input_tokens_seen": 1097856, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.09164389222860336, | |
| "learning_rate": 4.850720317526047e-05, | |
| "loss": 0.0164, | |
| "num_input_tokens_seen": 1126128, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3416666666666667, | |
| "grad_norm": 0.07462836056947708, | |
| "learning_rate": 4.843204973729729e-05, | |
| "loss": 0.014, | |
| "num_input_tokens_seen": 1157584, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.08473635464906693, | |
| "learning_rate": 4.835511185802574e-05, | |
| "loss": 0.0154, | |
| "num_input_tokens_seen": 1184800, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.35833333333333334, | |
| "grad_norm": 0.07371218502521515, | |
| "learning_rate": 4.827639539656321e-05, | |
| "loss": 0.0147, | |
| "num_input_tokens_seen": 1213104, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.36666666666666664, | |
| "grad_norm": 0.1394609957933426, | |
| "learning_rate": 4.8195906347473e-05, | |
| "loss": 0.0185, | |
| "num_input_tokens_seen": 1241808, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 0.11585802584886551, | |
| "learning_rate": 4.8113650840307834e-05, | |
| "loss": 0.016, | |
| "num_input_tokens_seen": 1270160, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.38333333333333336, | |
| "grad_norm": 0.1538001149892807, | |
| "learning_rate": 4.802963513914304e-05, | |
| "loss": 0.0168, | |
| "num_input_tokens_seen": 1297456, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.39166666666666666, | |
| "grad_norm": 0.09096246212720871, | |
| "learning_rate": 4.794386564209953e-05, | |
| "loss": 0.0154, | |
| "num_input_tokens_seen": 1323392, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.11348401010036469, | |
| "learning_rate": 4.7856348880856595e-05, | |
| "loss": 0.0149, | |
| "num_input_tokens_seen": 1358576, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4033333333333333, | |
| "num_input_tokens_seen": 1371584, | |
| "step": 242, | |
| "total_flos": 4652852538507264.0, | |
| "train_loss": 0.040362141964849364, | |
| "train_runtime": 4583.2214, | |
| "train_samples_per_second": 6.284, | |
| "train_steps_per_second": 0.393 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 1800, | |
| "num_input_tokens_seen": 1371584, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4652852538507264.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |