| { | |
| "best_metric": 0.07559170573949814, | |
| "best_model_checkpoint": "./trained_models/Mistral-7B-Instruct-v0.2_-1pos_-1neg_perNE_top-1NEs_TrueDef-IT/checkpoint-420", | |
| "epoch": 0.7190241814680077, | |
| "eval_steps": 20, | |
| "global_step": 420, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 2.4999999999999998e-05, | |
| "loss": 6.4943, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9999999999999996e-05, | |
| "loss": 3.9486, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.4566, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.999999999999999e-05, | |
| "loss": 0.3512, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": 0.3139978051185608, | |
| "eval_runtime": 222.18, | |
| "eval_samples_per_second": 7.84, | |
| "eval_steps_per_second": 7.84, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.000125, | |
| "loss": 0.1879, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00015, | |
| "loss": 0.1468, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.000175, | |
| "loss": 0.152, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019999999999999998, | |
| "loss": 0.1357, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": 0.20455242693424225, | |
| "eval_runtime": 222.1053, | |
| "eval_samples_per_second": 7.843, | |
| "eval_steps_per_second": 7.843, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.000225, | |
| "loss": 0.1162, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00025, | |
| "loss": 0.1099, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00027499999999999996, | |
| "loss": 0.3812, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0003, | |
| "loss": 0.2093, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": 0.12376075983047485, | |
| "eval_runtime": 222.1103, | |
| "eval_samples_per_second": 7.843, | |
| "eval_steps_per_second": 7.843, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0002999994460825163, | |
| "loss": 0.1396, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002999977843341562, | |
| "loss": 0.1036, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00029999501476719257, | |
| "loss": 0.0634, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0002999911374020804, | |
| "loss": 0.0933, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": 0.1939181536436081, | |
| "eval_runtime": 222.0528, | |
| "eval_samples_per_second": 7.845, | |
| "eval_steps_per_second": 7.845, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00029998615226745605, | |
| "loss": 0.0656, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002999800594001376, | |
| "loss": 0.0519, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002999728588451245, | |
| "loss": 0.0476, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002999645506555967, | |
| "loss": 0.0098, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": 0.24784570932388306, | |
| "eval_runtime": 222.2602, | |
| "eval_samples_per_second": 7.838, | |
| "eval_steps_per_second": 7.838, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00029995513489291506, | |
| "loss": 0.356, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00029994461162662024, | |
| "loss": 0.1972, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00029993298093443246, | |
| "loss": 0.1255, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.000299920242902251, | |
| "loss": 0.0923, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": 0.12546367943286896, | |
| "eval_runtime": 222.0682, | |
| "eval_samples_per_second": 7.844, | |
| "eval_steps_per_second": 7.844, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002999063976241536, | |
| "loss": 0.0504, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002998914452023953, | |
| "loss": 0.1582, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00029987538574740826, | |
| "loss": 0.0452, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002998582193778006, | |
| "loss": 0.0258, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 0.21805395185947418, | |
| "eval_runtime": 224.118, | |
| "eval_samples_per_second": 7.773, | |
| "eval_steps_per_second": 7.773, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00029983994622035585, | |
| "loss": 0.032, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00029982056641003147, | |
| "loss": 0.0224, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00029980008008995834, | |
| "loss": 0.2454, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00029977848741143966, | |
| "loss": 0.1583, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 0.10049739480018616, | |
| "eval_runtime": 224.1576, | |
| "eval_samples_per_second": 7.771, | |
| "eval_steps_per_second": 7.771, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002997557885339494, | |
| "loss": 0.1388, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0002997319836251319, | |
| "loss": 0.0962, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00029970707286079966, | |
| "loss": 0.0602, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00029968105642493286, | |
| "loss": 0.0642, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": 0.10171639919281006, | |
| "eval_runtime": 223.682, | |
| "eval_samples_per_second": 7.788, | |
| "eval_steps_per_second": 7.788, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0002996539345096776, | |
| "loss": 0.0499, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002996257073153446, | |
| "loss": 0.0486, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00029959637505040773, | |
| "loss": 0.0198, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00029956593793150233, | |
| "loss": 0.0359, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": 0.1516859233379364, | |
| "eval_runtime": 228.4243, | |
| "eval_samples_per_second": 7.626, | |
| "eval_steps_per_second": 7.626, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002995343961834238, | |
| "loss": 0.2612, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00029950175003912573, | |
| "loss": 0.1232, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002994679997397185, | |
| "loss": 0.0861, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00029943314553446706, | |
| "loss": 0.0867, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 0.08929727226495743, | |
| "eval_runtime": 229.1014, | |
| "eval_samples_per_second": 7.604, | |
| "eval_steps_per_second": 7.604, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.0002993971876807896, | |
| "loss": 0.0485, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00029936012644425517, | |
| "loss": 0.0516, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00029932196209858197, | |
| "loss": 0.0583, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00029928269492563537, | |
| "loss": 0.0271, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": 0.13832463324069977, | |
| "eval_runtime": 227.2299, | |
| "eval_samples_per_second": 7.666, | |
| "eval_steps_per_second": 7.666, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00029924232521542557, | |
| "loss": 0.0213, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.00029920085326610595, | |
| "loss": 0.0388, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00029915827938397017, | |
| "loss": 0.3212, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0002991146038834505, | |
| "loss": 0.1213, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": 0.09067531675100327, | |
| "eval_runtime": 228.6975, | |
| "eval_samples_per_second": 7.617, | |
| "eval_steps_per_second": 7.617, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00029906982708711533, | |
| "loss": 0.0905, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00029902394932566657, | |
| "loss": 0.0397, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.00029897697093793753, | |
| "loss": 0.0497, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0002989288922708902, | |
| "loss": 0.0549, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": 0.10685621201992035, | |
| "eval_runtime": 227.369, | |
| "eval_samples_per_second": 7.662, | |
| "eval_steps_per_second": 7.662, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.0002988797136796128, | |
| "loss": 0.0281, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00029882943552731703, | |
| "loss": 0.0586, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0002987780581853355, | |
| "loss": 0.0284, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00029872558203311914, | |
| "loss": 0.0436, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 0.1119319349527359, | |
| "eval_runtime": 221.5402, | |
| "eval_samples_per_second": 7.863, | |
| "eval_steps_per_second": 7.863, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00029867200745823384, | |
| "loss": 0.1798, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.00029861733485635834, | |
| "loss": 0.1191, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0002985615646312807, | |
| "loss": 0.0841, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00029850469719489573, | |
| "loss": 0.1025, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 0.08742260932922363, | |
| "eval_runtime": 221.4467, | |
| "eval_samples_per_second": 7.866, | |
| "eval_steps_per_second": 7.866, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00029844673296720154, | |
| "loss": 0.0457, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.00029838767237629684, | |
| "loss": 0.0465, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002983275158583775, | |
| "loss": 0.063, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002982662638577335, | |
| "loss": 0.0238, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": 0.14248833060264587, | |
| "eval_runtime": 225.6871, | |
| "eval_samples_per_second": 7.719, | |
| "eval_steps_per_second": 7.719, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00029820391682674563, | |
| "loss": 0.0205, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00029814047522588194, | |
| "loss": 0.0218, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 0.00029807593952369465, | |
| "loss": 0.2612, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.00029801031019681645, | |
| "loss": 0.1889, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": 0.09468888491392136, | |
| "eval_runtime": 228.9494, | |
| "eval_samples_per_second": 7.609, | |
| "eval_steps_per_second": 7.609, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.0002979435877299571, | |
| "loss": 0.0905, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.0002978757726158998, | |
| "loss": 0.0619, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00029780686535549756, | |
| "loss": 0.0625, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0002977368664576696, | |
| "loss": 0.0585, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": 0.08509568870067596, | |
| "eval_runtime": 227.8786, | |
| "eval_samples_per_second": 7.644, | |
| "eval_steps_per_second": 7.644, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.00029766577643939744, | |
| "loss": 0.0327, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00029759359582572103, | |
| "loss": 0.043, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00029752032514973516, | |
| "loss": 0.0234, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.00029744596495258525, | |
| "loss": 0.0119, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": 0.09636981785297394, | |
| "eval_runtime": 228.541, | |
| "eval_samples_per_second": 7.622, | |
| "eval_steps_per_second": 7.622, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00029737051578346345, | |
| "loss": 0.1557, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.0002972939781996047, | |
| "loss": 0.1116, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0002972163527662824, | |
| "loss": 0.0638, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.00029713764005680427, | |
| "loss": 0.0726, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": 0.07559170573949814, | |
| "eval_runtime": 228.1262, | |
| "eval_samples_per_second": 7.636, | |
| "eval_steps_per_second": 7.636, | |
| "step": 420 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 5840, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 20, | |
| "total_flos": 2.1261537057551155e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |