| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06720847411195324, | |
| "eval_steps": 500, | |
| "global_step": 46, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001461053785042462, | |
| "grad_norm": 0.30625924468040466, | |
| "learning_rate": 2.0000000000000002e-07, | |
| "loss": 2.1669, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002922107570084924, | |
| "grad_norm": 0.29808640480041504, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 2.0395, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004383161355127386, | |
| "grad_norm": 0.24509362876415253, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 1.8973, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005844215140169848, | |
| "grad_norm": 0.27399635314941406, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 2.0403, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00730526892521231, | |
| "grad_norm": 0.30136558413505554, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 2.0947, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008766322710254772, | |
| "grad_norm": 0.30337047576904297, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 2.0886, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010227376495297234, | |
| "grad_norm": 0.28456181287765503, | |
| "learning_rate": 1.4000000000000001e-06, | |
| "loss": 1.988, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011688430280339696, | |
| "grad_norm": 0.2553723454475403, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 2.0434, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013149484065382157, | |
| "grad_norm": 0.2616969645023346, | |
| "learning_rate": 1.8000000000000001e-06, | |
| "loss": 1.9692, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01461053785042462, | |
| "grad_norm": 0.2795903980731964, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.9994, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01607159163546708, | |
| "grad_norm": 0.27633437514305115, | |
| "learning_rate": 2.2e-06, | |
| "loss": 1.9672, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.017532645420509543, | |
| "grad_norm": 0.3074289858341217, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 2.0757, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.018993699205552005, | |
| "grad_norm": 0.27444779872894287, | |
| "learning_rate": 2.6e-06, | |
| "loss": 1.9697, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.020454752990594467, | |
| "grad_norm": 0.28576454520225525, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 2.0516, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02191580677563693, | |
| "grad_norm": 0.25402647256851196, | |
| "learning_rate": 3e-06, | |
| "loss": 1.9916, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02337686056067939, | |
| "grad_norm": 0.27070897817611694, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 2.0079, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.024837914345721853, | |
| "grad_norm": 0.26685598492622375, | |
| "learning_rate": 3.4000000000000005e-06, | |
| "loss": 1.997, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.026298968130764315, | |
| "grad_norm": 0.2818976044654846, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 2.0454, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.027760021915806777, | |
| "grad_norm": 0.2832131087779999, | |
| "learning_rate": 3.8000000000000005e-06, | |
| "loss": 2.0227, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02922107570084924, | |
| "grad_norm": 0.28652554750442505, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.0293, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0306821294858917, | |
| "grad_norm": 0.28600171208381653, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 2.0214, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03214318327093416, | |
| "grad_norm": 0.2540723383426666, | |
| "learning_rate": 4.4e-06, | |
| "loss": 1.998, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03360423705597662, | |
| "grad_norm": 0.2570485472679138, | |
| "learning_rate": 4.600000000000001e-06, | |
| "loss": 1.9908, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03506529084101909, | |
| "grad_norm": 0.2579878866672516, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 1.9355, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.036526344626061545, | |
| "grad_norm": 0.29550811648368835, | |
| "learning_rate": 5e-06, | |
| "loss": 2.0992, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03798739841110401, | |
| "grad_norm": 0.2850530445575714, | |
| "learning_rate": 5.2e-06, | |
| "loss": 2.042, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03944845219614647, | |
| "grad_norm": 0.2779623568058014, | |
| "learning_rate": 5.400000000000001e-06, | |
| "loss": 1.9592, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.040909505981188934, | |
| "grad_norm": 0.2843893766403198, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 2.0435, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04237055976623139, | |
| "grad_norm": 0.26713600754737854, | |
| "learning_rate": 5.8e-06, | |
| "loss": 2.0014, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04383161355127386, | |
| "grad_norm": 0.2971515357494354, | |
| "learning_rate": 6e-06, | |
| "loss": 2.0246, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04529266733631632, | |
| "grad_norm": 0.2626894414424896, | |
| "learning_rate": 6.200000000000001e-06, | |
| "loss": 2.0402, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04675372112135878, | |
| "grad_norm": 0.27606457471847534, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 2.0549, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04821477490640124, | |
| "grad_norm": 0.27802756428718567, | |
| "learning_rate": 6.600000000000001e-06, | |
| "loss": 1.9889, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.049675828691443706, | |
| "grad_norm": 0.2772068977355957, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 1.9913, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.051136882476486165, | |
| "grad_norm": 0.2816425561904907, | |
| "learning_rate": 7e-06, | |
| "loss": 1.9677, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05259793626152863, | |
| "grad_norm": 0.2521456182003021, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 1.9705, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05405899004657109, | |
| "grad_norm": 0.24795399606227875, | |
| "learning_rate": 7.4e-06, | |
| "loss": 2.0483, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.055520043831613554, | |
| "grad_norm": 0.2924613654613495, | |
| "learning_rate": 7.600000000000001e-06, | |
| "loss": 2.0585, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05698109761665601, | |
| "grad_norm": 0.2479739636182785, | |
| "learning_rate": 7.800000000000002e-06, | |
| "loss": 1.9588, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05844215140169848, | |
| "grad_norm": 0.27038994431495667, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.9146, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.059903205186740936, | |
| "grad_norm": 0.263032466173172, | |
| "learning_rate": 8.2e-06, | |
| "loss": 1.925, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0613642589717834, | |
| "grad_norm": 0.25826576352119446, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 1.9664, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06282531275682586, | |
| "grad_norm": 0.3021976351737976, | |
| "learning_rate": 8.6e-06, | |
| "loss": 2.0211, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06428636654186833, | |
| "grad_norm": 0.2642092704772949, | |
| "learning_rate": 8.8e-06, | |
| "loss": 1.8985, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06574742032691079, | |
| "grad_norm": 0.2693665623664856, | |
| "learning_rate": 9e-06, | |
| "loss": 2.0221, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06720847411195324, | |
| "grad_norm": 0.24328897893428802, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 1.9289, | |
| "step": 46 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 684, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.114263583383142e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |