| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.14450867052023122, | |
| "eval_steps": 100, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000361271676300578, | |
| "eval_loss": 1.744890570640564, | |
| "eval_runtime": 94.9792, | |
| "eval_samples_per_second": 12.276, | |
| "eval_steps_per_second": 6.138, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018063583815028901, | |
| "grad_norm": 4.572258949279785, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 6.4691, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0036127167630057803, | |
| "grad_norm": 5.133723258972168, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 5.8079, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00541907514450867, | |
| "grad_norm": 6.701831817626953, | |
| "learning_rate": 5e-05, | |
| "loss": 6.2285, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0072254335260115606, | |
| "grad_norm": 5.718057632446289, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 6.5028, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009031791907514452, | |
| "grad_norm": 6.74662971496582, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 6.1902, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01083815028901734, | |
| "grad_norm": 7.589154243469238, | |
| "learning_rate": 0.0001, | |
| "loss": 6.8722, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012644508670520232, | |
| "grad_norm": 7.196185111999512, | |
| "learning_rate": 9.995494831023409e-05, | |
| "loss": 5.8428, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.014450867052023121, | |
| "grad_norm": 10.744294166564941, | |
| "learning_rate": 9.981987442712633e-05, | |
| "loss": 6.6387, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01625722543352601, | |
| "grad_norm": 10.513398170471191, | |
| "learning_rate": 9.959502176294383e-05, | |
| "loss": 6.1403, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.018063583815028903, | |
| "grad_norm": 21.8984375, | |
| "learning_rate": 9.928079551738543e-05, | |
| "loss": 6.4882, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.019869942196531792, | |
| "grad_norm": 4.082497596740723, | |
| "learning_rate": 9.887776194738432e-05, | |
| "loss": 5.6698, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.02167630057803468, | |
| "grad_norm": 3.6237664222717285, | |
| "learning_rate": 9.838664734667495e-05, | |
| "loss": 5.6337, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02348265895953757, | |
| "grad_norm": 4.460430145263672, | |
| "learning_rate": 9.780833673696254e-05, | |
| "loss": 5.9547, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.025289017341040464, | |
| "grad_norm": 4.965810775756836, | |
| "learning_rate": 9.714387227305422e-05, | |
| "loss": 6.3579, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.027095375722543353, | |
| "grad_norm": 5.657303810119629, | |
| "learning_rate": 9.639445136482548e-05, | |
| "loss": 6.427, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.028901734104046242, | |
| "grad_norm": 7.635822296142578, | |
| "learning_rate": 9.55614245194068e-05, | |
| "loss": 5.9311, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03070809248554913, | |
| "grad_norm": 6.425141334533691, | |
| "learning_rate": 9.464629290747842e-05, | |
| "loss": 6.1297, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.03251445086705202, | |
| "grad_norm": 7.40579891204834, | |
| "learning_rate": 9.365070565805941e-05, | |
| "loss": 6.6066, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.034320809248554913, | |
| "grad_norm": 9.1989164352417, | |
| "learning_rate": 9.257645688666556e-05, | |
| "loss": 6.4348, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.036127167630057806, | |
| "grad_norm": 22.926342010498047, | |
| "learning_rate": 9.142548246219212e-05, | |
| "loss": 6.5575, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.036127167630057806, | |
| "eval_loss": 1.5481350421905518, | |
| "eval_runtime": 96.2211, | |
| "eval_samples_per_second": 12.118, | |
| "eval_steps_per_second": 6.059, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03793352601156069, | |
| "grad_norm": 4.272301197052002, | |
| "learning_rate": 9.019985651834703e-05, | |
| "loss": 5.456, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.039739884393063585, | |
| "grad_norm": 3.853165626525879, | |
| "learning_rate": 8.890178771592199e-05, | |
| "loss": 5.9443, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04154624277456647, | |
| "grad_norm": 3.7567975521087646, | |
| "learning_rate": 8.753361526263621e-05, | |
| "loss": 5.8409, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.04335260115606936, | |
| "grad_norm": 4.880814552307129, | |
| "learning_rate": 8.609780469772623e-05, | |
| "loss": 6.658, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.045158959537572256, | |
| "grad_norm": 6.830643653869629, | |
| "learning_rate": 8.459694344887732e-05, | |
| "loss": 5.4968, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.04696531791907514, | |
| "grad_norm": 5.208051681518555, | |
| "learning_rate": 8.303373616950408e-05, | |
| "loss": 5.847, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.048771676300578035, | |
| "grad_norm": 7.453110694885254, | |
| "learning_rate": 8.141099986478212e-05, | |
| "loss": 6.782, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.05057803468208093, | |
| "grad_norm": 6.395998477935791, | |
| "learning_rate": 7.973165881521434e-05, | |
| "loss": 6.3193, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.05238439306358381, | |
| "grad_norm": 8.69977855682373, | |
| "learning_rate": 7.799873930687978e-05, | |
| "loss": 5.7748, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.054190751445086706, | |
| "grad_norm": 16.149049758911133, | |
| "learning_rate": 7.621536417786159e-05, | |
| "loss": 6.5888, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0559971098265896, | |
| "grad_norm": 3.4040889739990234, | |
| "learning_rate": 7.438474719068173e-05, | |
| "loss": 5.8179, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.057803468208092484, | |
| "grad_norm": 3.4983773231506348, | |
| "learning_rate": 7.251018724088367e-05, | |
| "loss": 5.7591, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.05960982658959538, | |
| "grad_norm": 4.498758316040039, | |
| "learning_rate": 7.059506241219965e-05, | |
| "loss": 5.892, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.06141618497109826, | |
| "grad_norm": 5.004685878753662, | |
| "learning_rate": 6.864282388901544e-05, | |
| "loss": 5.7729, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06322254335260116, | |
| "grad_norm": 6.281583786010742, | |
| "learning_rate": 6.665698973710288e-05, | |
| "loss": 5.5329, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.06502890173410404, | |
| "grad_norm": 5.321663856506348, | |
| "learning_rate": 6.464113856382752e-05, | |
| "loss": 6.0103, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06683526011560693, | |
| "grad_norm": 5.427529811859131, | |
| "learning_rate": 6.259890306925627e-05, | |
| "loss": 5.473, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.06864161849710983, | |
| "grad_norm": 7.26462984085083, | |
| "learning_rate": 6.0533963499786314e-05, | |
| "loss": 5.9309, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.07044797687861272, | |
| "grad_norm": 10.634440422058105, | |
| "learning_rate": 5.8450041016092464e-05, | |
| "loss": 6.4073, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.07225433526011561, | |
| "grad_norm": 27.388513565063477, | |
| "learning_rate": 5.6350890987343944e-05, | |
| "loss": 7.3339, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07225433526011561, | |
| "eval_loss": 1.511500597000122, | |
| "eval_runtime": 96.0163, | |
| "eval_samples_per_second": 12.144, | |
| "eval_steps_per_second": 6.072, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07406069364161849, | |
| "grad_norm": 3.3720569610595703, | |
| "learning_rate": 5.4240296223775465e-05, | |
| "loss": 5.5126, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.07586705202312138, | |
| "grad_norm": 3.8887689113616943, | |
| "learning_rate": 5.212206015980742e-05, | |
| "loss": 6.0826, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.07767341040462428, | |
| "grad_norm": 3.656919240951538, | |
| "learning_rate": 5e-05, | |
| "loss": 6.0577, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.07947976878612717, | |
| "grad_norm": 4.942195892333984, | |
| "learning_rate": 4.78779398401926e-05, | |
| "loss": 5.8108, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.08128612716763006, | |
| "grad_norm": 5.37594747543335, | |
| "learning_rate": 4.575970377622456e-05, | |
| "loss": 5.8402, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.08309248554913294, | |
| "grad_norm": 6.129786968231201, | |
| "learning_rate": 4.364910901265606e-05, | |
| "loss": 5.8496, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.08489884393063583, | |
| "grad_norm": 6.835684776306152, | |
| "learning_rate": 4.1549958983907555e-05, | |
| "loss": 5.8005, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.08670520231213873, | |
| "grad_norm": 7.933070182800293, | |
| "learning_rate": 3.94660365002137e-05, | |
| "loss": 6.3795, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.08851156069364162, | |
| "grad_norm": 7.715188980102539, | |
| "learning_rate": 3.740109693074375e-05, | |
| "loss": 5.9361, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.09031791907514451, | |
| "grad_norm": 13.9365816116333, | |
| "learning_rate": 3.5358861436172485e-05, | |
| "loss": 6.4969, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.0921242774566474, | |
| "grad_norm": 2.912147045135498, | |
| "learning_rate": 3.334301026289712e-05, | |
| "loss": 5.8817, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.09393063583815028, | |
| "grad_norm": 3.6152451038360596, | |
| "learning_rate": 3.135717611098458e-05, | |
| "loss": 5.6341, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.09573699421965318, | |
| "grad_norm": 3.727494478225708, | |
| "learning_rate": 2.9404937587800375e-05, | |
| "loss": 5.6878, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.09754335260115607, | |
| "grad_norm": 4.728793144226074, | |
| "learning_rate": 2.748981275911633e-05, | |
| "loss": 5.1723, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.09934971098265896, | |
| "grad_norm": 5.2207183837890625, | |
| "learning_rate": 2.5615252809318284e-05, | |
| "loss": 5.5361, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.10115606936416185, | |
| "grad_norm": 5.840899467468262, | |
| "learning_rate": 2.3784635822138424e-05, | |
| "loss": 5.716, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.10296242774566473, | |
| "grad_norm": 7.544865131378174, | |
| "learning_rate": 2.2001260693120233e-05, | |
| "loss": 6.4095, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.10476878612716763, | |
| "grad_norm": 7.941392421722412, | |
| "learning_rate": 2.026834118478567e-05, | |
| "loss": 5.5665, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.10657514450867052, | |
| "grad_norm": 7.984579086303711, | |
| "learning_rate": 1.858900013521788e-05, | |
| "loss": 5.8144, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.10838150289017341, | |
| "grad_norm": 34.44167709350586, | |
| "learning_rate": 1.6966263830495936e-05, | |
| "loss": 6.4331, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.10838150289017341, | |
| "eval_loss": 1.500432014465332, | |
| "eval_runtime": 96.0671, | |
| "eval_samples_per_second": 12.137, | |
| "eval_steps_per_second": 6.069, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1101878612716763, | |
| "grad_norm": 3.1297943592071533, | |
| "learning_rate": 1.5403056551122697e-05, | |
| "loss": 5.1584, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.1119942196531792, | |
| "grad_norm": 3.5680549144744873, | |
| "learning_rate": 1.3902195302273779e-05, | |
| "loss": 5.8807, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.11380057803468208, | |
| "grad_norm": 3.9225680828094482, | |
| "learning_rate": 1.246638473736378e-05, | |
| "loss": 6.0405, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.11560693641618497, | |
| "grad_norm": 5.079793930053711, | |
| "learning_rate": 1.1098212284078036e-05, | |
| "loss": 6.0765, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.11741329479768786, | |
| "grad_norm": 4.278252124786377, | |
| "learning_rate": 9.800143481652979e-06, | |
| "loss": 6.2954, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.11921965317919075, | |
| "grad_norm": 5.204624176025391, | |
| "learning_rate": 8.574517537807897e-06, | |
| "loss": 5.7613, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.12102601156069365, | |
| "grad_norm": 5.653388977050781, | |
| "learning_rate": 7.423543113334436e-06, | |
| "loss": 6.1252, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.12283236994219653, | |
| "grad_norm": 6.901706695556641, | |
| "learning_rate": 6.349294341940593e-06, | |
| "loss": 6.7496, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.12463872832369942, | |
| "grad_norm": 7.3163862228393555, | |
| "learning_rate": 5.353707092521582e-06, | |
| "loss": 5.9329, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.12644508670520233, | |
| "grad_norm": 20.43028450012207, | |
| "learning_rate": 4.43857548059321e-06, | |
| "loss": 5.9438, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1282514450867052, | |
| "grad_norm": 3.276519298553467, | |
| "learning_rate": 3.605548635174533e-06, | |
| "loss": 5.5224, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.13005780346820808, | |
| "grad_norm": 3.398956775665283, | |
| "learning_rate": 2.85612772694579e-06, | |
| "loss": 5.9158, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.13186416184971098, | |
| "grad_norm": 3.6480960845947266, | |
| "learning_rate": 2.191663263037458e-06, | |
| "loss": 5.5869, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.13367052023121387, | |
| "grad_norm": 4.710407257080078, | |
| "learning_rate": 1.6133526533250565e-06, | |
| "loss": 6.0246, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.13547687861271676, | |
| "grad_norm": 6.083166599273682, | |
| "learning_rate": 1.1222380526156928e-06, | |
| "loss": 5.7852, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.13728323699421965, | |
| "grad_norm": 6.078175067901611, | |
| "learning_rate": 7.192044826145771e-07, | |
| "loss": 5.7854, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.13908959537572255, | |
| "grad_norm": 5.755491256713867, | |
| "learning_rate": 4.049782370561583e-07, | |
| "loss": 6.0269, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.14089595375722544, | |
| "grad_norm": 5.526588439941406, | |
| "learning_rate": 1.8012557287367392e-07, | |
| "loss": 5.585, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.14270231213872833, | |
| "grad_norm": 7.929935932159424, | |
| "learning_rate": 4.5051689765929214e-08, | |
| "loss": 6.3004, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.14450867052023122, | |
| "grad_norm": 12.81932544708252, | |
| "learning_rate": 0.0, | |
| "loss": 6.3915, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.14450867052023122, | |
| "eval_loss": 1.4950844049453735, | |
| "eval_runtime": 96.2425, | |
| "eval_samples_per_second": 12.115, | |
| "eval_steps_per_second": 6.058, | |
| "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": 1.4301801881586893e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |