| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.026784966937306438, | |
| "eval_steps": 100, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.696241734326609e-05, | |
| "eval_loss": 2.174267530441284, | |
| "eval_runtime": 163.7054, | |
| "eval_samples_per_second": 38.41, | |
| "eval_steps_per_second": 19.205, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00033481208671633044, | |
| "grad_norm": 0.9260562658309937, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.1887, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006696241734326609, | |
| "grad_norm": 0.9021257162094116, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.5945, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0010044362601489914, | |
| "grad_norm": 0.9025452733039856, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5915, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013392483468653218, | |
| "grad_norm": 1.0874302387237549, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.628, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0016740604335816524, | |
| "grad_norm": 1.7216452360153198, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 1.7435, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0020088725202979827, | |
| "grad_norm": 2.0254034996032715, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6424, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0023436846070143133, | |
| "grad_norm": 2.3089540004730225, | |
| "learning_rate": 9.995494831023409e-05, | |
| "loss": 1.7435, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0026784966937306435, | |
| "grad_norm": 2.23340106010437, | |
| "learning_rate": 9.981987442712633e-05, | |
| "loss": 1.6411, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003013308780446974, | |
| "grad_norm": 2.5001442432403564, | |
| "learning_rate": 9.959502176294383e-05, | |
| "loss": 1.7324, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0033481208671633047, | |
| "grad_norm": 6.447619915008545, | |
| "learning_rate": 9.928079551738543e-05, | |
| "loss": 2.1026, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003682932953879635, | |
| "grad_norm": 1.4846231937408447, | |
| "learning_rate": 9.887776194738432e-05, | |
| "loss": 0.9139, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0040177450405959655, | |
| "grad_norm": 1.2765096426010132, | |
| "learning_rate": 9.838664734667495e-05, | |
| "loss": 1.2814, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.004352557127312296, | |
| "grad_norm": 1.1545428037643433, | |
| "learning_rate": 9.780833673696254e-05, | |
| "loss": 1.2743, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.004687369214028627, | |
| "grad_norm": 1.2550811767578125, | |
| "learning_rate": 9.714387227305422e-05, | |
| "loss": 1.2456, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.005022181300744957, | |
| "grad_norm": 1.6476733684539795, | |
| "learning_rate": 9.639445136482548e-05, | |
| "loss": 1.3624, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.005356993387461287, | |
| "grad_norm": 1.5332133769989014, | |
| "learning_rate": 9.55614245194068e-05, | |
| "loss": 1.4752, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.005691805474177618, | |
| "grad_norm": 3.8824784755706787, | |
| "learning_rate": 9.464629290747842e-05, | |
| "loss": 1.6035, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.006026617560893948, | |
| "grad_norm": 2.0814363956451416, | |
| "learning_rate": 9.365070565805941e-05, | |
| "loss": 1.6343, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006361429647610279, | |
| "grad_norm": 4.855213642120361, | |
| "learning_rate": 9.257645688666556e-05, | |
| "loss": 1.5957, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.006696241734326609, | |
| "grad_norm": 4.855248928070068, | |
| "learning_rate": 9.142548246219212e-05, | |
| "loss": 1.8685, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.006696241734326609, | |
| "eval_loss": 1.3918159008026123, | |
| "eval_runtime": 163.6718, | |
| "eval_samples_per_second": 38.418, | |
| "eval_steps_per_second": 19.209, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.00703105382104294, | |
| "grad_norm": 1.4969482421875, | |
| "learning_rate": 9.019985651834703e-05, | |
| "loss": 0.8596, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.00736586590775927, | |
| "grad_norm": 1.4642244577407837, | |
| "learning_rate": 8.890178771592199e-05, | |
| "loss": 1.0313, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0077006779944756, | |
| "grad_norm": 1.1550184488296509, | |
| "learning_rate": 8.753361526263621e-05, | |
| "loss": 1.2813, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.008035490081191931, | |
| "grad_norm": 1.5003013610839844, | |
| "learning_rate": 8.609780469772623e-05, | |
| "loss": 1.2205, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.008370302167908262, | |
| "grad_norm": 1.6831740140914917, | |
| "learning_rate": 8.459694344887732e-05, | |
| "loss": 1.4063, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.008705114254624592, | |
| "grad_norm": 2.0073044300079346, | |
| "learning_rate": 8.303373616950408e-05, | |
| "loss": 1.3491, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.009039926341340923, | |
| "grad_norm": 1.970392107963562, | |
| "learning_rate": 8.141099986478212e-05, | |
| "loss": 1.5904, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.009374738428057253, | |
| "grad_norm": 2.2006771564483643, | |
| "learning_rate": 7.973165881521434e-05, | |
| "loss": 1.5045, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.009709550514773584, | |
| "grad_norm": 3.4276771545410156, | |
| "learning_rate": 7.799873930687978e-05, | |
| "loss": 1.4812, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.010044362601489915, | |
| "grad_norm": 3.777205228805542, | |
| "learning_rate": 7.621536417786159e-05, | |
| "loss": 1.7224, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.010379174688206243, | |
| "grad_norm": 0.9603461027145386, | |
| "learning_rate": 7.438474719068173e-05, | |
| "loss": 0.8872, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.010713986774922574, | |
| "grad_norm": 0.9185311198234558, | |
| "learning_rate": 7.251018724088367e-05, | |
| "loss": 0.988, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.011048798861638905, | |
| "grad_norm": 0.8872480392456055, | |
| "learning_rate": 7.059506241219965e-05, | |
| "loss": 1.1061, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.011383610948355235, | |
| "grad_norm": 1.0405540466308594, | |
| "learning_rate": 6.864282388901544e-05, | |
| "loss": 1.1573, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.011718423035071566, | |
| "grad_norm": 1.0770432949066162, | |
| "learning_rate": 6.665698973710288e-05, | |
| "loss": 1.2171, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.012053235121787896, | |
| "grad_norm": 1.2423980236053467, | |
| "learning_rate": 6.464113856382752e-05, | |
| "loss": 1.4636, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.012388047208504227, | |
| "grad_norm": 1.532152771949768, | |
| "learning_rate": 6.259890306925627e-05, | |
| "loss": 1.5803, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.012722859295220558, | |
| "grad_norm": 2.0728421211242676, | |
| "learning_rate": 6.0533963499786314e-05, | |
| "loss": 1.4616, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.013057671381936888, | |
| "grad_norm": 2.2115986347198486, | |
| "learning_rate": 5.8450041016092464e-05, | |
| "loss": 1.4877, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.013392483468653219, | |
| "grad_norm": 5.700234889984131, | |
| "learning_rate": 5.6350890987343944e-05, | |
| "loss": 1.7236, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.013392483468653219, | |
| "eval_loss": 1.354627013206482, | |
| "eval_runtime": 163.8467, | |
| "eval_samples_per_second": 38.377, | |
| "eval_steps_per_second": 19.189, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01372729555536955, | |
| "grad_norm": 0.9484522342681885, | |
| "learning_rate": 5.4240296223775465e-05, | |
| "loss": 0.7298, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.01406210764208588, | |
| "grad_norm": 1.1288779973983765, | |
| "learning_rate": 5.212206015980742e-05, | |
| "loss": 0.9035, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.014396919728802209, | |
| "grad_norm": 1.7266836166381836, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0985, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.01473173181551854, | |
| "grad_norm": 0.995969295501709, | |
| "learning_rate": 4.78779398401926e-05, | |
| "loss": 1.1848, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.01506654390223487, | |
| "grad_norm": 1.5627479553222656, | |
| "learning_rate": 4.575970377622456e-05, | |
| "loss": 1.3387, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.0154013559889512, | |
| "grad_norm": 1.6149134635925293, | |
| "learning_rate": 4.364910901265606e-05, | |
| "loss": 1.4154, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.015736168075667533, | |
| "grad_norm": 1.6124211549758911, | |
| "learning_rate": 4.1549958983907555e-05, | |
| "loss": 1.4861, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.016070980162383862, | |
| "grad_norm": 2.333585739135742, | |
| "learning_rate": 3.94660365002137e-05, | |
| "loss": 1.4805, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.016405792249100194, | |
| "grad_norm": 3.2034616470336914, | |
| "learning_rate": 3.740109693074375e-05, | |
| "loss": 1.5403, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.016740604335816523, | |
| "grad_norm": 4.460490703582764, | |
| "learning_rate": 3.5358861436172485e-05, | |
| "loss": 1.781, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.017075416422532852, | |
| "grad_norm": 1.3614052534103394, | |
| "learning_rate": 3.334301026289712e-05, | |
| "loss": 0.8676, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.017410228509249184, | |
| "grad_norm": 1.2099424600601196, | |
| "learning_rate": 3.135717611098458e-05, | |
| "loss": 1.0425, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.017745040595965513, | |
| "grad_norm": 1.1399760246276855, | |
| "learning_rate": 2.9404937587800375e-05, | |
| "loss": 1.1488, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.018079852682681846, | |
| "grad_norm": 1.2464284896850586, | |
| "learning_rate": 2.748981275911633e-05, | |
| "loss": 1.1467, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.018414664769398174, | |
| "grad_norm": 1.054639220237732, | |
| "learning_rate": 2.5615252809318284e-05, | |
| "loss": 1.3174, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.018749476856114507, | |
| "grad_norm": 1.547200322151184, | |
| "learning_rate": 2.3784635822138424e-05, | |
| "loss": 1.3793, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.019084288942830836, | |
| "grad_norm": 1.627147912979126, | |
| "learning_rate": 2.2001260693120233e-05, | |
| "loss": 1.5391, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.019419101029547168, | |
| "grad_norm": 2.48234486579895, | |
| "learning_rate": 2.026834118478567e-05, | |
| "loss": 1.5285, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.019753913116263497, | |
| "grad_norm": 3.616591453552246, | |
| "learning_rate": 1.858900013521788e-05, | |
| "loss": 1.4661, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.02008872520297983, | |
| "grad_norm": 5.476447105407715, | |
| "learning_rate": 1.6966263830495936e-05, | |
| "loss": 1.7933, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.02008872520297983, | |
| "eval_loss": 1.3094998598098755, | |
| "eval_runtime": 163.9185, | |
| "eval_samples_per_second": 38.361, | |
| "eval_steps_per_second": 19.18, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.020423537289696158, | |
| "grad_norm": 0.7956154346466064, | |
| "learning_rate": 1.5403056551122697e-05, | |
| "loss": 0.8062, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.020758349376412487, | |
| "grad_norm": 0.7887328267097473, | |
| "learning_rate": 1.3902195302273779e-05, | |
| "loss": 0.7704, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.02109316146312882, | |
| "grad_norm": 1.0377590656280518, | |
| "learning_rate": 1.246638473736378e-05, | |
| "loss": 1.051, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.021427973549845148, | |
| "grad_norm": 1.5397368669509888, | |
| "learning_rate": 1.1098212284078036e-05, | |
| "loss": 1.1294, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.02176278563656148, | |
| "grad_norm": 1.3186566829681396, | |
| "learning_rate": 9.800143481652979e-06, | |
| "loss": 1.2664, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.02209759772327781, | |
| "grad_norm": 1.2383577823638916, | |
| "learning_rate": 8.574517537807897e-06, | |
| "loss": 1.3939, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.02243240980999414, | |
| "grad_norm": 2.637763500213623, | |
| "learning_rate": 7.423543113334436e-06, | |
| "loss": 1.5548, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.02276722189671047, | |
| "grad_norm": 1.9864592552185059, | |
| "learning_rate": 6.349294341940593e-06, | |
| "loss": 1.4275, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.023102033983426803, | |
| "grad_norm": 1.9794150590896606, | |
| "learning_rate": 5.353707092521582e-06, | |
| "loss": 1.4501, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.02343684607014313, | |
| "grad_norm": 6.367179870605469, | |
| "learning_rate": 4.43857548059321e-06, | |
| "loss": 1.8257, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.023771658156859464, | |
| "grad_norm": 0.7660558819770813, | |
| "learning_rate": 3.605548635174533e-06, | |
| "loss": 0.7747, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.024106470243575793, | |
| "grad_norm": 1.0603808164596558, | |
| "learning_rate": 2.85612772694579e-06, | |
| "loss": 0.8945, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.024441282330292125, | |
| "grad_norm": 0.7905088067054749, | |
| "learning_rate": 2.191663263037458e-06, | |
| "loss": 1.1056, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.024776094417008454, | |
| "grad_norm": 1.1489086151123047, | |
| "learning_rate": 1.6133526533250565e-06, | |
| "loss": 1.1273, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.025110906503724783, | |
| "grad_norm": 1.1459239721298218, | |
| "learning_rate": 1.1222380526156928e-06, | |
| "loss": 1.2485, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.025445718590441115, | |
| "grad_norm": 1.342341423034668, | |
| "learning_rate": 7.192044826145771e-07, | |
| "loss": 1.3644, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.025780530677157444, | |
| "grad_norm": 1.374852180480957, | |
| "learning_rate": 4.049782370561583e-07, | |
| "loss": 1.4949, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.026115342763873776, | |
| "grad_norm": 1.8837116956710815, | |
| "learning_rate": 1.8012557287367392e-07, | |
| "loss": 1.4726, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.026450154850590105, | |
| "grad_norm": 2.635817527770996, | |
| "learning_rate": 4.5051689765929214e-08, | |
| "loss": 1.5605, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.026784966937306438, | |
| "grad_norm": 4.389669418334961, | |
| "learning_rate": 0.0, | |
| "loss": 1.7267, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.026784966937306438, | |
| "eval_loss": 1.3007175922393799, | |
| "eval_runtime": 163.5244, | |
| "eval_samples_per_second": 38.453, | |
| "eval_steps_per_second": 19.226, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 400, | |
| "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": 8405202663112704.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |