| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.9885714285714284, |
| "eval_steps": 21, |
| "global_step": 348, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02857142857142857, |
| "grad_norm": 2.3125, |
| "learning_rate": 2.136096164208358e-05, |
| "loss": 1.5322, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.05714285714285714, |
| "grad_norm": 1.46875, |
| "learning_rate": 4.8062163694688055e-05, |
| "loss": 1.3936, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.08571428571428572, |
| "grad_norm": 1.53125, |
| "learning_rate": 7.476336574729253e-05, |
| "loss": 1.371, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.11428571428571428, |
| "grad_norm": 1.25, |
| "learning_rate": 8.009448792360797e-05, |
| "loss": 1.3719, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.14285714285714285, |
| "grad_norm": 1.171875, |
| "learning_rate": 8.005745458430277e-05, |
| "loss": 1.346, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.17142857142857143, |
| "grad_norm": 1.0859375, |
| "learning_rate": 7.999197135159387e-05, |
| "loss": 1.3286, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 1.1953125, |
| "learning_rate": 7.989810034029404e-05, |
| "loss": 1.3428, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.22857142857142856, |
| "grad_norm": 1.0859375, |
| "learning_rate": 7.977593059274359e-05, |
| "loss": 1.364, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2571428571428571, |
| "grad_norm": 1.1484375, |
| "learning_rate": 7.962557799434825e-05, |
| "loss": 1.3312, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.2857142857142857, |
| "grad_norm": 1.125, |
| "learning_rate": 7.944718516365498e-05, |
| "loss": 1.3337, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.3142857142857143, |
| "grad_norm": 1.078125, |
| "learning_rate": 7.924092131706952e-05, |
| "loss": 1.3135, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.34285714285714286, |
| "grad_norm": 1.09375, |
| "learning_rate": 7.900698210834442e-05, |
| "loss": 1.3493, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.37142857142857144, |
| "grad_norm": 1.03125, |
| "learning_rate": 7.874558944298964e-05, |
| "loss": 1.3573, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 1.046875, |
| "learning_rate": 7.845699126778165e-05, |
| "loss": 1.3147, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.42857142857142855, |
| "grad_norm": 0.984375, |
| "learning_rate": 7.814146133557099e-05, |
| "loss": 1.3092, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.45714285714285713, |
| "grad_norm": 1.140625, |
| "learning_rate": 7.779929894561104e-05, |
| "loss": 1.3013, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.4857142857142857, |
| "grad_norm": 1.0390625, |
| "learning_rate": 7.743082865965456e-05, |
| "loss": 1.3152, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.5142857142857142, |
| "grad_norm": 1.046875, |
| "learning_rate": 7.703639999408725e-05, |
| "loss": 1.3191, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.5428571428571428, |
| "grad_norm": 1.1171875, |
| "learning_rate": 7.66163870883902e-05, |
| "loss": 1.3175, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.5714285714285714, |
| "grad_norm": 1.046875, |
| "learning_rate": 7.617118835024606e-05, |
| "loss": 1.3164, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 1.0703125, |
| "learning_rate": 7.570122607762506e-05, |
| "loss": 1.3, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.6285714285714286, |
| "grad_norm": 1.0234375, |
| "learning_rate": 7.520694605820996e-05, |
| "loss": 1.3114, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.6571428571428571, |
| "grad_norm": 1.125, |
| "learning_rate": 7.468881714653933e-05, |
| "loss": 1.3152, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.6857142857142857, |
| "grad_norm": 1.078125, |
| "learning_rate": 7.414733081927064e-05, |
| "loss": 1.2929, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 0.98828125, |
| "learning_rate": 7.35830007089849e-05, |
| "loss": 1.322, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.7428571428571429, |
| "grad_norm": 1.0078125, |
| "learning_rate": 7.299636211697504e-05, |
| "loss": 1.3029, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.7714285714285715, |
| "grad_norm": 1.015625, |
| "learning_rate": 7.238797150548021e-05, |
| "loss": 1.2898, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 1.0234375, |
| "learning_rate": 7.175840596984761e-05, |
| "loss": 1.3134, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.8285714285714286, |
| "grad_norm": 1.0390625, |
| "learning_rate": 7.110826269112261e-05, |
| "loss": 1.3068, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.84, |
| "eval_loss": 1.300465703010559, |
| "eval_runtime": 25.4924, |
| "eval_samples_per_second": 13.573, |
| "eval_steps_per_second": 13.573, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.8571428571428571, |
| "grad_norm": 1.0078125, |
| "learning_rate": 7.043815836958643e-05, |
| "loss": 1.3157, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.8857142857142857, |
| "grad_norm": 1.03125, |
| "learning_rate": 6.97487286397784e-05, |
| "loss": 1.3015, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.9142857142857143, |
| "grad_norm": 1.03125, |
| "learning_rate": 6.90406274675583e-05, |
| "loss": 1.3116, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.9428571428571428, |
| "grad_norm": 1.015625, |
| "learning_rate": 6.831452652977996e-05, |
| "loss": 1.3044, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_loss": 1.296446681022644, |
| "eval_runtime": 24.9384, |
| "eval_samples_per_second": 13.874, |
| "eval_steps_per_second": 13.874, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.9714285714285714, |
| "grad_norm": 1.109375, |
| "learning_rate": 6.757111457716519e-05, |
| "loss": 1.2939, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.9942857142857143, |
| "eval_loss": 1.2951465845108032, |
| "eval_runtime": 18.8312, |
| "eval_samples_per_second": 18.374, |
| "eval_steps_per_second": 18.374, |
| "step": 174 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 2.171875, |
| "learning_rate": 6.68110967809819e-05, |
| "loss": 1.2973, |
| "step": 175 |
| }, |
| { |
| "epoch": 1.0285714285714285, |
| "grad_norm": 1.1875, |
| "learning_rate": 6.603519406414658e-05, |
| "loss": 1.1405, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.0571428571428572, |
| "grad_norm": 1.0546875, |
| "learning_rate": 6.524414241738508e-05, |
| "loss": 1.1044, |
| "step": 185 |
| }, |
| { |
| "epoch": 1.08, |
| "eval_loss": 1.3059316873550415, |
| "eval_runtime": 24.2498, |
| "eval_samples_per_second": 14.268, |
| "eval_steps_per_second": 14.268, |
| "step": 189 |
| }, |
| { |
| "epoch": 1.0857142857142856, |
| "grad_norm": 0.9453125, |
| "learning_rate": 6.443869220110093e-05, |
| "loss": 1.0947, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.1142857142857143, |
| "grad_norm": 1.015625, |
| "learning_rate": 6.361960743361305e-05, |
| "loss": 1.0869, |
| "step": 195 |
| }, |
| { |
| "epoch": 1.1428571428571428, |
| "grad_norm": 1.046875, |
| "learning_rate": 6.278766506643805e-05, |
| "loss": 1.1195, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.1714285714285715, |
| "grad_norm": 0.9765625, |
| "learning_rate": 6.194365424730462e-05, |
| "loss": 1.1142, |
| "step": 205 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 0.9609375, |
| "learning_rate": 6.108837557159925e-05, |
| "loss": 1.1012, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.2, |
| "eval_loss": 1.304489254951477, |
| "eval_runtime": 24.3939, |
| "eval_samples_per_second": 14.184, |
| "eval_steps_per_second": 14.184, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.2285714285714286, |
| "grad_norm": 1.0, |
| "learning_rate": 6.022264032295284e-05, |
| "loss": 1.117, |
| "step": 215 |
| }, |
| { |
| "epoch": 1.2571428571428571, |
| "grad_norm": 0.9609375, |
| "learning_rate": 5.934726970368916e-05, |
| "loss": 1.0962, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.2857142857142856, |
| "grad_norm": 0.9609375, |
| "learning_rate": 5.846309405586463e-05, |
| "loss": 1.1065, |
| "step": 225 |
| }, |
| { |
| "epoch": 1.3142857142857143, |
| "grad_norm": 1.0390625, |
| "learning_rate": 5.757095207363863e-05, |
| "loss": 1.1156, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.32, |
| "eval_loss": 1.3012893199920654, |
| "eval_runtime": 24.0742, |
| "eval_samples_per_second": 14.372, |
| "eval_steps_per_second": 14.372, |
| "step": 231 |
| }, |
| { |
| "epoch": 1.342857142857143, |
| "grad_norm": 0.98046875, |
| "learning_rate": 5.667169000772126e-05, |
| "loss": 1.1, |
| "step": 235 |
| }, |
| { |
| "epoch": 1.3714285714285714, |
| "grad_norm": 0.96484375, |
| "learning_rate": 5.576616086265328e-05, |
| "loss": 1.0933, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 0.9765625, |
| "learning_rate": 5.4855223587679644e-05, |
| "loss": 1.0924, |
| "step": 245 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 0.9375, |
| "learning_rate": 5.39397422619841e-05, |
| "loss": 1.0746, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.44, |
| "eval_loss": 1.2984005212783813, |
| "eval_runtime": 23.9306, |
| "eval_samples_per_second": 14.458, |
| "eval_steps_per_second": 14.458, |
| "step": 252 |
| }, |
| { |
| "epoch": 1.457142857142857, |
| "grad_norm": 0.97265625, |
| "learning_rate": 5.302058527505779e-05, |
| "loss": 1.1031, |
| "step": 255 |
| }, |
| { |
| "epoch": 1.4857142857142858, |
| "grad_norm": 1.015625, |
| "learning_rate": 5.209862450297916e-05, |
| "loss": 1.0942, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.5142857142857142, |
| "grad_norm": 1.0, |
| "learning_rate": 5.1174734481386675e-05, |
| "loss": 1.1044, |
| "step": 265 |
| }, |
| { |
| "epoch": 1.5428571428571427, |
| "grad_norm": 0.98046875, |
| "learning_rate": 5.0249791575928875e-05, |
| "loss": 1.1163, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.56, |
| "eval_loss": 1.2957829236984253, |
| "eval_runtime": 24.2754, |
| "eval_samples_per_second": 14.253, |
| "eval_steps_per_second": 14.253, |
| "step": 273 |
| }, |
| { |
| "epoch": 1.5714285714285714, |
| "grad_norm": 0.93359375, |
| "learning_rate": 4.932467315097839e-05, |
| "loss": 1.1149, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 1.0, |
| "learning_rate": 4.840025673739873e-05, |
| "loss": 1.1083, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.6285714285714286, |
| "grad_norm": 0.94140625, |
| "learning_rate": 4.7477419200153126e-05, |
| "loss": 1.1093, |
| "step": 285 |
| }, |
| { |
| "epoch": 1.657142857142857, |
| "grad_norm": 0.953125, |
| "learning_rate": 4.655703590654491e-05, |
| "loss": 1.1062, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.6800000000000002, |
| "eval_loss": 1.2940247058868408, |
| "eval_runtime": 24.1132, |
| "eval_samples_per_second": 14.349, |
| "eval_steps_per_second": 14.349, |
| "step": 294 |
| }, |
| { |
| "epoch": 1.6857142857142857, |
| "grad_norm": 0.92578125, |
| "learning_rate": 4.56399798958787e-05, |
| "loss": 1.1142, |
| "step": 295 |
| }, |
| { |
| "epoch": 1.7142857142857144, |
| "grad_norm": 0.98046875, |
| "learning_rate": 4.472712105132971e-05, |
| "loss": 1.1044, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.7428571428571429, |
| "grad_norm": 0.984375, |
| "learning_rate": 4.381932527480683e-05, |
| "loss": 1.1191, |
| "step": 305 |
| }, |
| { |
| "epoch": 1.7714285714285714, |
| "grad_norm": 0.94921875, |
| "learning_rate": 4.291745366559223e-05, |
| "loss": 1.092, |
| "step": 310 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 0.96875, |
| "learning_rate": 4.2022361703536566e-05, |
| "loss": 1.1018, |
| "step": 315 |
| }, |
| { |
| "epoch": 1.8, |
| "eval_loss": 1.293960452079773, |
| "eval_runtime": 25.4885, |
| "eval_samples_per_second": 13.575, |
| "eval_steps_per_second": 13.575, |
| "step": 315 |
| }, |
| { |
| "epoch": 1.8285714285714287, |
| "grad_norm": 0.95703125, |
| "learning_rate": 4.1134898437584525e-05, |
| "loss": 1.1147, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.8571428571428572, |
| "grad_norm": 0.94140625, |
| "learning_rate": 4.025590568040038e-05, |
| "loss": 1.1128, |
| "step": 325 |
| }, |
| { |
| "epoch": 1.8857142857142857, |
| "grad_norm": 0.9140625, |
| "learning_rate": 3.93862172098578e-05, |
| "loss": 1.0975, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.9142857142857141, |
| "grad_norm": 0.8984375, |
| "learning_rate": 3.8526657978150965e-05, |
| "loss": 1.0877, |
| "step": 335 |
| }, |
| { |
| "epoch": 1.92, |
| "eval_loss": 1.2903681993484497, |
| "eval_runtime": 24.5314, |
| "eval_samples_per_second": 14.104, |
| "eval_steps_per_second": 14.104, |
| "step": 336 |
| }, |
| { |
| "epoch": 1.9428571428571428, |
| "grad_norm": 0.9140625, |
| "learning_rate": 3.767804332927745e-05, |
| "loss": 1.082, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.9714285714285715, |
| "grad_norm": 0.9140625, |
| "learning_rate": 3.6841178225635085e-05, |
| "loss": 1.109, |
| "step": 345 |
| }, |
| { |
| "epoch": 1.9885714285714284, |
| "eval_loss": 1.2870495319366455, |
| "eval_runtime": 24.6305, |
| "eval_samples_per_second": 14.048, |
| "eval_steps_per_second": 14.048, |
| "step": 348 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 525, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 21, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.0559827832773018e+17, |
| "train_batch_size": 100, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
