sediba-XLM-R / checkpoint-11776 /trainer_state.json
Sediba-AI's picture
Sepedi-Llama v1 - loss 83 to 19
6c6d805 verified
Raw
History Blame Contribute Delete
44.1 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 11776,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004246239424209934,
"grad_norm": 324.3861999511719,
"learning_rate": 1.225e-05,
"loss": 83.27494140625,
"step": 50
},
{
"epoch": 0.008492478848419869,
"grad_norm": 294.6669921875,
"learning_rate": 2.4750000000000002e-05,
"loss": 72.928427734375,
"step": 100
},
{
"epoch": 0.012738718272629802,
"grad_norm": 254.57310485839844,
"learning_rate": 3.7250000000000004e-05,
"loss": 65.434755859375,
"step": 150
},
{
"epoch": 0.016984957696839737,
"grad_norm": 285.2427062988281,
"learning_rate": 4.975e-05,
"loss": 59.52314453125,
"step": 200
},
{
"epoch": 0.02123119712104967,
"grad_norm": 276.11651611328125,
"learning_rate": 4.978835521769178e-05,
"loss": 56.26099609375,
"step": 250
},
{
"epoch": 0.025477436545259604,
"grad_norm": 264.0826416015625,
"learning_rate": 4.9572391154111955e-05,
"loss": 52.364111328125,
"step": 300
},
{
"epoch": 0.029723675969469537,
"grad_norm": 237.80140686035156,
"learning_rate": 4.9356427090532136e-05,
"loss": 49.438955078125,
"step": 350
},
{
"epoch": 0.033969915393679474,
"grad_norm": 245.1451873779297,
"learning_rate": 4.914046302695232e-05,
"loss": 48.1695849609375,
"step": 400
},
{
"epoch": 0.038216154817889404,
"grad_norm": 207.61068725585938,
"learning_rate": 4.892449896337249e-05,
"loss": 45.5499365234375,
"step": 450
},
{
"epoch": 0.04246239424209934,
"grad_norm": 200.3720703125,
"learning_rate": 4.870853489979268e-05,
"loss": 44.5572998046875,
"step": 500
},
{
"epoch": 0.04670863366630928,
"grad_norm": 197.68887329101562,
"learning_rate": 4.8492570836212855e-05,
"loss": 42.489599609375,
"step": 550
},
{
"epoch": 0.05095487309051921,
"grad_norm": 179.29957580566406,
"learning_rate": 4.827660677263304e-05,
"loss": 41.3450439453125,
"step": 600
},
{
"epoch": 0.055201112514729145,
"grad_norm": 226.55911254882812,
"learning_rate": 4.806064270905322e-05,
"loss": 41.2511376953125,
"step": 650
},
{
"epoch": 0.059447351938939075,
"grad_norm": 202.10791015625,
"learning_rate": 4.784467864547339e-05,
"loss": 39.70830322265625,
"step": 700
},
{
"epoch": 0.063693591363149,
"grad_norm": 207.3136444091797,
"learning_rate": 4.7628714581893575e-05,
"loss": 39.89173828125,
"step": 750
},
{
"epoch": 0.06793983078735895,
"grad_norm": 189.1178436279297,
"learning_rate": 4.7412750518313756e-05,
"loss": 38.6139501953125,
"step": 800
},
{
"epoch": 0.07218607021156888,
"grad_norm": 190.94015502929688,
"learning_rate": 4.719678645473393e-05,
"loss": 38.68489501953125,
"step": 850
},
{
"epoch": 0.07643230963577881,
"grad_norm": 191.75172424316406,
"learning_rate": 4.698082239115412e-05,
"loss": 36.644111328125,
"step": 900
},
{
"epoch": 0.08067854905998875,
"grad_norm": 206.9021453857422,
"learning_rate": 4.6764858327574294e-05,
"loss": 37.54802978515625,
"step": 950
},
{
"epoch": 0.08492478848419868,
"grad_norm": 184.31649780273438,
"learning_rate": 4.6548894263994475e-05,
"loss": 35.32251953125,
"step": 1000
},
{
"epoch": 0.08917102790840861,
"grad_norm": 190.4438934326172,
"learning_rate": 4.633293020041466e-05,
"loss": 35.93584228515625,
"step": 1050
},
{
"epoch": 0.09341726733261856,
"grad_norm": 216.86279296875,
"learning_rate": 4.611696613683483e-05,
"loss": 34.81772216796875,
"step": 1100
},
{
"epoch": 0.09766350675682849,
"grad_norm": 179.98419189453125,
"learning_rate": 4.590100207325501e-05,
"loss": 34.99229248046875,
"step": 1150
},
{
"epoch": 0.10190974618103842,
"grad_norm": 186.61732482910156,
"learning_rate": 4.568503800967519e-05,
"loss": 33.92795654296875,
"step": 1200
},
{
"epoch": 0.10615598560524835,
"grad_norm": 185.78001403808594,
"learning_rate": 4.546907394609537e-05,
"loss": 34.2297021484375,
"step": 1250
},
{
"epoch": 0.11040222502945829,
"grad_norm": 236.7795867919922,
"learning_rate": 4.525310988251556e-05,
"loss": 33.76176513671875,
"step": 1300
},
{
"epoch": 0.11464846445366822,
"grad_norm": 210.53762817382812,
"learning_rate": 4.503714581893573e-05,
"loss": 32.79689453125,
"step": 1350
},
{
"epoch": 0.11889470387787815,
"grad_norm": 278.4184875488281,
"learning_rate": 4.4821181755355913e-05,
"loss": 31.72260009765625,
"step": 1400
},
{
"epoch": 0.1231409433020881,
"grad_norm": 255.81129455566406,
"learning_rate": 4.460521769177609e-05,
"loss": 32.5959912109375,
"step": 1450
},
{
"epoch": 0.127387182726298,
"grad_norm": 188.4405975341797,
"learning_rate": 4.438925362819627e-05,
"loss": 31.72834716796875,
"step": 1500
},
{
"epoch": 0.13163342215050797,
"grad_norm": 196.35501098632812,
"learning_rate": 4.417328956461645e-05,
"loss": 32.69740478515625,
"step": 1550
},
{
"epoch": 0.1358796615747179,
"grad_norm": 186.20811462402344,
"learning_rate": 4.3957325501036626e-05,
"loss": 31.13796875,
"step": 1600
},
{
"epoch": 0.14012590099892783,
"grad_norm": 158.75543212890625,
"learning_rate": 4.374136143745681e-05,
"loss": 32.08728271484375,
"step": 1650
},
{
"epoch": 0.14437214042313776,
"grad_norm": 207.9669952392578,
"learning_rate": 4.352539737387699e-05,
"loss": 31.42122802734375,
"step": 1700
},
{
"epoch": 0.1486183798473477,
"grad_norm": 184.7431640625,
"learning_rate": 4.330943331029717e-05,
"loss": 31.1582763671875,
"step": 1750
},
{
"epoch": 0.15286461927155762,
"grad_norm": 155.47659301757812,
"learning_rate": 4.309346924671735e-05,
"loss": 30.77266845703125,
"step": 1800
},
{
"epoch": 0.15711085869576757,
"grad_norm": 163.03013610839844,
"learning_rate": 4.2877505183137527e-05,
"loss": 30.72901123046875,
"step": 1850
},
{
"epoch": 0.1613570981199775,
"grad_norm": 240.4451904296875,
"learning_rate": 4.266154111955771e-05,
"loss": 30.06856689453125,
"step": 1900
},
{
"epoch": 0.16560333754418743,
"grad_norm": 193.2200164794922,
"learning_rate": 4.244557705597789e-05,
"loss": 29.64366455078125,
"step": 1950
},
{
"epoch": 0.16984957696839736,
"grad_norm": 197.7560577392578,
"learning_rate": 4.2229612992398064e-05,
"loss": 29.403779296875,
"step": 2000
},
{
"epoch": 0.1740958163926073,
"grad_norm": 172.2969512939453,
"learning_rate": 4.2013648928818246e-05,
"loss": 29.76959716796875,
"step": 2050
},
{
"epoch": 0.17834205581681722,
"grad_norm": 171.65423583984375,
"learning_rate": 4.179768486523843e-05,
"loss": 28.84666259765625,
"step": 2100
},
{
"epoch": 0.18258829524102715,
"grad_norm": 253.046875,
"learning_rate": 4.158172080165861e-05,
"loss": 28.4874462890625,
"step": 2150
},
{
"epoch": 0.1868345346652371,
"grad_norm": 174.5941162109375,
"learning_rate": 4.136575673807879e-05,
"loss": 28.8812744140625,
"step": 2200
},
{
"epoch": 0.19108077408944704,
"grad_norm": 187.45791625976562,
"learning_rate": 4.1149792674498965e-05,
"loss": 29.3225390625,
"step": 2250
},
{
"epoch": 0.19532701351365697,
"grad_norm": 158.6984405517578,
"learning_rate": 4.0933828610919146e-05,
"loss": 29.0456494140625,
"step": 2300
},
{
"epoch": 0.1995732529378669,
"grad_norm": 162.81512451171875,
"learning_rate": 4.071786454733932e-05,
"loss": 29.16901123046875,
"step": 2350
},
{
"epoch": 0.20381949236207683,
"grad_norm": 201.16639709472656,
"learning_rate": 4.05019004837595e-05,
"loss": 29.002841796875,
"step": 2400
},
{
"epoch": 0.20806573178628676,
"grad_norm": 185.6593475341797,
"learning_rate": 4.0285936420179684e-05,
"loss": 28.537255859375,
"step": 2450
},
{
"epoch": 0.2123119712104967,
"grad_norm": 166.38766479492188,
"learning_rate": 4.0069972356599866e-05,
"loss": 27.69727294921875,
"step": 2500
},
{
"epoch": 0.21655821063470665,
"grad_norm": 174.38104248046875,
"learning_rate": 3.985400829302005e-05,
"loss": 28.5172802734375,
"step": 2550
},
{
"epoch": 0.22080445005891658,
"grad_norm": 149.02406311035156,
"learning_rate": 3.963804422944022e-05,
"loss": 28.4050244140625,
"step": 2600
},
{
"epoch": 0.2250506894831265,
"grad_norm": 192.12002563476562,
"learning_rate": 3.94220801658604e-05,
"loss": 26.98137451171875,
"step": 2650
},
{
"epoch": 0.22929692890733644,
"grad_norm": 170.00814819335938,
"learning_rate": 3.9206116102280585e-05,
"loss": 26.99474853515625,
"step": 2700
},
{
"epoch": 0.23354316833154637,
"grad_norm": 145.735595703125,
"learning_rate": 3.899015203870076e-05,
"loss": 27.34177001953125,
"step": 2750
},
{
"epoch": 0.2377894077557563,
"grad_norm": 169.86480712890625,
"learning_rate": 3.877418797512094e-05,
"loss": 27.52475830078125,
"step": 2800
},
{
"epoch": 0.24203564717996623,
"grad_norm": 135.18838500976562,
"learning_rate": 3.855822391154112e-05,
"loss": 27.2542626953125,
"step": 2850
},
{
"epoch": 0.2462818866041762,
"grad_norm": 149.96510314941406,
"learning_rate": 3.8342259847961304e-05,
"loss": 27.07297119140625,
"step": 2900
},
{
"epoch": 0.2505281260283861,
"grad_norm": 159.20584106445312,
"learning_rate": 3.8126295784381485e-05,
"loss": 27.08953125,
"step": 2950
},
{
"epoch": 0.254774365452596,
"grad_norm": 136.2477569580078,
"learning_rate": 3.791033172080166e-05,
"loss": 26.437490234375,
"step": 3000
},
{
"epoch": 0.259020604876806,
"grad_norm": 164.90737915039062,
"learning_rate": 3.769436765722184e-05,
"loss": 26.1881103515625,
"step": 3050
},
{
"epoch": 0.26326684430101593,
"grad_norm": 154.27102661132812,
"learning_rate": 3.747840359364202e-05,
"loss": 26.475185546875,
"step": 3100
},
{
"epoch": 0.26751308372522586,
"grad_norm": 174.78500366210938,
"learning_rate": 3.72624395300622e-05,
"loss": 26.410517578125,
"step": 3150
},
{
"epoch": 0.2717593231494358,
"grad_norm": 167.15457153320312,
"learning_rate": 3.704647546648238e-05,
"loss": 25.28077880859375,
"step": 3200
},
{
"epoch": 0.2760055625736457,
"grad_norm": 182.3014373779297,
"learning_rate": 3.6830511402902554e-05,
"loss": 26.1413818359375,
"step": 3250
},
{
"epoch": 0.28025180199785565,
"grad_norm": 185.13711547851562,
"learning_rate": 3.661454733932274e-05,
"loss": 25.593623046875,
"step": 3300
},
{
"epoch": 0.2844980414220656,
"grad_norm": 136.2028045654297,
"learning_rate": 3.639858327574292e-05,
"loss": 26.10810791015625,
"step": 3350
},
{
"epoch": 0.2887442808462755,
"grad_norm": 160.10540771484375,
"learning_rate": 3.61826192121631e-05,
"loss": 26.09581298828125,
"step": 3400
},
{
"epoch": 0.29299052027048544,
"grad_norm": 170.12704467773438,
"learning_rate": 3.596665514858328e-05,
"loss": 26.3189306640625,
"step": 3450
},
{
"epoch": 0.2972367596946954,
"grad_norm": 154.6916961669922,
"learning_rate": 3.5750691085003455e-05,
"loss": 25.707509765625,
"step": 3500
},
{
"epoch": 0.3014829991189053,
"grad_norm": 175.77297973632812,
"learning_rate": 3.5534727021423636e-05,
"loss": 26.1056396484375,
"step": 3550
},
{
"epoch": 0.30572923854311523,
"grad_norm": 143.42288208007812,
"learning_rate": 3.531876295784382e-05,
"loss": 25.2949560546875,
"step": 3600
},
{
"epoch": 0.30997547796732516,
"grad_norm": 171.7968292236328,
"learning_rate": 3.510279889426399e-05,
"loss": 25.76105712890625,
"step": 3650
},
{
"epoch": 0.31422171739153515,
"grad_norm": 165.98411560058594,
"learning_rate": 3.488683483068418e-05,
"loss": 25.60622802734375,
"step": 3700
},
{
"epoch": 0.3184679568157451,
"grad_norm": 157.76429748535156,
"learning_rate": 3.4670870767104355e-05,
"loss": 24.7918017578125,
"step": 3750
},
{
"epoch": 0.322714196239955,
"grad_norm": 168.3741455078125,
"learning_rate": 3.445490670352454e-05,
"loss": 24.83272705078125,
"step": 3800
},
{
"epoch": 0.32696043566416494,
"grad_norm": 165.90496826171875,
"learning_rate": 3.423894263994472e-05,
"loss": 26.2589599609375,
"step": 3850
},
{
"epoch": 0.33120667508837487,
"grad_norm": 142.2030792236328,
"learning_rate": 3.402297857636489e-05,
"loss": 24.28029541015625,
"step": 3900
},
{
"epoch": 0.3354529145125848,
"grad_norm": 159.05149841308594,
"learning_rate": 3.3807014512785074e-05,
"loss": 24.80717041015625,
"step": 3950
},
{
"epoch": 0.33969915393679473,
"grad_norm": 138.15611267089844,
"learning_rate": 3.359105044920525e-05,
"loss": 24.88008056640625,
"step": 4000
},
{
"epoch": 0.34394539336100466,
"grad_norm": 196.62498474121094,
"learning_rate": 3.337508638562543e-05,
"loss": 24.37576171875,
"step": 4050
},
{
"epoch": 0.3481916327852146,
"grad_norm": 155.42593383789062,
"learning_rate": 3.315912232204562e-05,
"loss": 25.1333447265625,
"step": 4100
},
{
"epoch": 0.3524378722094245,
"grad_norm": 146.24502563476562,
"learning_rate": 3.2943158258465794e-05,
"loss": 23.95904296875,
"step": 4150
},
{
"epoch": 0.35668411163363445,
"grad_norm": 140.36927795410156,
"learning_rate": 3.2727194194885975e-05,
"loss": 24.21125,
"step": 4200
},
{
"epoch": 0.3609303510578444,
"grad_norm": 151.30316162109375,
"learning_rate": 3.251123013130615e-05,
"loss": 24.09343505859375,
"step": 4250
},
{
"epoch": 0.3651765904820543,
"grad_norm": 209.92578125,
"learning_rate": 3.229526606772633e-05,
"loss": 23.6073779296875,
"step": 4300
},
{
"epoch": 0.36942282990626424,
"grad_norm": 162.1195526123047,
"learning_rate": 3.207930200414651e-05,
"loss": 24.49541748046875,
"step": 4350
},
{
"epoch": 0.3736690693304742,
"grad_norm": 170.38694763183594,
"learning_rate": 3.186333794056669e-05,
"loss": 24.1321630859375,
"step": 4400
},
{
"epoch": 0.37791530875468415,
"grad_norm": 161.4326934814453,
"learning_rate": 3.164737387698687e-05,
"loss": 23.7575341796875,
"step": 4450
},
{
"epoch": 0.3821615481788941,
"grad_norm": 171.4528045654297,
"learning_rate": 3.143140981340705e-05,
"loss": 24.50120849609375,
"step": 4500
},
{
"epoch": 0.386407787603104,
"grad_norm": 160.71112060546875,
"learning_rate": 3.121544574982723e-05,
"loss": 23.270244140625,
"step": 4550
},
{
"epoch": 0.39065402702731394,
"grad_norm": 139.88951110839844,
"learning_rate": 3.099948168624741e-05,
"loss": 24.25181640625,
"step": 4600
},
{
"epoch": 0.3949002664515239,
"grad_norm": 152.9877166748047,
"learning_rate": 3.078351762266759e-05,
"loss": 23.2979345703125,
"step": 4650
},
{
"epoch": 0.3991465058757338,
"grad_norm": 179.30581665039062,
"learning_rate": 3.056755355908777e-05,
"loss": 24.148583984375,
"step": 4700
},
{
"epoch": 0.40339274529994373,
"grad_norm": 143.60121154785156,
"learning_rate": 3.0351589495507948e-05,
"loss": 24.34101318359375,
"step": 4750
},
{
"epoch": 0.40763898472415366,
"grad_norm": 133.65771484375,
"learning_rate": 3.0135625431928126e-05,
"loss": 23.299140625,
"step": 4800
},
{
"epoch": 0.4118852241483636,
"grad_norm": 162.5352783203125,
"learning_rate": 2.9919661368348307e-05,
"loss": 23.08830322265625,
"step": 4850
},
{
"epoch": 0.4161314635725735,
"grad_norm": 158.4131317138672,
"learning_rate": 2.9703697304768485e-05,
"loss": 22.8610205078125,
"step": 4900
},
{
"epoch": 0.42037770299678345,
"grad_norm": 124.68849182128906,
"learning_rate": 2.948773324118867e-05,
"loss": 23.79708740234375,
"step": 4950
},
{
"epoch": 0.4246239424209934,
"grad_norm": 163.76657104492188,
"learning_rate": 2.9271769177608848e-05,
"loss": 23.52044189453125,
"step": 5000
},
{
"epoch": 0.42887018184520337,
"grad_norm": 187.97413635253906,
"learning_rate": 2.9055805114029026e-05,
"loss": 24.02717529296875,
"step": 5050
},
{
"epoch": 0.4331164212694133,
"grad_norm": 154.0001220703125,
"learning_rate": 2.8839841050449208e-05,
"loss": 23.41170166015625,
"step": 5100
},
{
"epoch": 0.43736266069362323,
"grad_norm": 141.18080139160156,
"learning_rate": 2.8623876986869386e-05,
"loss": 23.554814453125,
"step": 5150
},
{
"epoch": 0.44160890011783316,
"grad_norm": 158.98216247558594,
"learning_rate": 2.8407912923289564e-05,
"loss": 23.31008544921875,
"step": 5200
},
{
"epoch": 0.4458551395420431,
"grad_norm": 146.218994140625,
"learning_rate": 2.8191948859709742e-05,
"loss": 23.71553955078125,
"step": 5250
},
{
"epoch": 0.450101378966253,
"grad_norm": 156.51646423339844,
"learning_rate": 2.7975984796129924e-05,
"loss": 22.9737060546875,
"step": 5300
},
{
"epoch": 0.45434761839046295,
"grad_norm": 144.48443603515625,
"learning_rate": 2.776002073255011e-05,
"loss": 24.7643798828125,
"step": 5350
},
{
"epoch": 0.4585938578146729,
"grad_norm": 160.95411682128906,
"learning_rate": 2.7544056668970287e-05,
"loss": 23.05649658203125,
"step": 5400
},
{
"epoch": 0.4628400972388828,
"grad_norm": 152.6392059326172,
"learning_rate": 2.7328092605390465e-05,
"loss": 23.15297119140625,
"step": 5450
},
{
"epoch": 0.46708633666309274,
"grad_norm": 190.5279083251953,
"learning_rate": 2.7112128541810643e-05,
"loss": 21.804638671875,
"step": 5500
},
{
"epoch": 0.47133257608730267,
"grad_norm": 170.51712036132812,
"learning_rate": 2.6896164478230824e-05,
"loss": 22.71973388671875,
"step": 5550
},
{
"epoch": 0.4755788155115126,
"grad_norm": 151.53326416015625,
"learning_rate": 2.6680200414651002e-05,
"loss": 22.90906494140625,
"step": 5600
},
{
"epoch": 0.47982505493572253,
"grad_norm": 147.06654357910156,
"learning_rate": 2.646423635107118e-05,
"loss": 24.11918701171875,
"step": 5650
},
{
"epoch": 0.48407129435993246,
"grad_norm": 167.34326171875,
"learning_rate": 2.624827228749136e-05,
"loss": 22.7313134765625,
"step": 5700
},
{
"epoch": 0.48831753378414244,
"grad_norm": 136.9669647216797,
"learning_rate": 2.6032308223911543e-05,
"loss": 21.70623046875,
"step": 5750
},
{
"epoch": 0.4925637732083524,
"grad_norm": 159.77626037597656,
"learning_rate": 2.5816344160331725e-05,
"loss": 22.6339453125,
"step": 5800
},
{
"epoch": 0.4968100126325623,
"grad_norm": 198.8340301513672,
"learning_rate": 2.5600380096751903e-05,
"loss": 22.50951171875,
"step": 5850
},
{
"epoch": 0.5010562520567722,
"grad_norm": 139.2235870361328,
"learning_rate": 2.538441603317208e-05,
"loss": 22.05862548828125,
"step": 5900
},
{
"epoch": 0.5053024914809822,
"grad_norm": 145.6766815185547,
"learning_rate": 2.516845196959226e-05,
"loss": 23.03335205078125,
"step": 5950
},
{
"epoch": 0.509548730905192,
"grad_norm": 159.59835815429688,
"learning_rate": 2.495248790601244e-05,
"loss": 23.1497705078125,
"step": 6000
},
{
"epoch": 0.513794970329402,
"grad_norm": 200.4053497314453,
"learning_rate": 2.4736523842432622e-05,
"loss": 22.751318359375,
"step": 6050
},
{
"epoch": 0.518041209753612,
"grad_norm": 146.4293670654297,
"learning_rate": 2.45205597788528e-05,
"loss": 22.441064453125,
"step": 6100
},
{
"epoch": 0.5222874491778219,
"grad_norm": 140.7433319091797,
"learning_rate": 2.430459571527298e-05,
"loss": 21.8677880859375,
"step": 6150
},
{
"epoch": 0.5265336886020319,
"grad_norm": 145.3983154296875,
"learning_rate": 2.4088631651693156e-05,
"loss": 21.99537109375,
"step": 6200
},
{
"epoch": 0.5307799280262417,
"grad_norm": 171.57505798339844,
"learning_rate": 2.387266758811334e-05,
"loss": 22.0473974609375,
"step": 6250
},
{
"epoch": 0.5350261674504517,
"grad_norm": 190.87144470214844,
"learning_rate": 2.365670352453352e-05,
"loss": 22.20819580078125,
"step": 6300
},
{
"epoch": 0.5392724068746616,
"grad_norm": 131.15647888183594,
"learning_rate": 2.3440739460953698e-05,
"loss": 22.3381689453125,
"step": 6350
},
{
"epoch": 0.5435186462988716,
"grad_norm": 130.159423828125,
"learning_rate": 2.3224775397373876e-05,
"loss": 21.13576171875,
"step": 6400
},
{
"epoch": 0.5477648857230815,
"grad_norm": 153.32504272460938,
"learning_rate": 2.3008811333794057e-05,
"loss": 21.22865478515625,
"step": 6450
},
{
"epoch": 0.5520111251472914,
"grad_norm": 137.8641357421875,
"learning_rate": 2.279284727021424e-05,
"loss": 21.42198974609375,
"step": 6500
},
{
"epoch": 0.5562573645715013,
"grad_norm": 152.36447143554688,
"learning_rate": 2.2576883206634417e-05,
"loss": 22.49668212890625,
"step": 6550
},
{
"epoch": 0.5605036039957113,
"grad_norm": 170.3688507080078,
"learning_rate": 2.2360919143054595e-05,
"loss": 21.45054443359375,
"step": 6600
},
{
"epoch": 0.5647498434199212,
"grad_norm": 119.01740264892578,
"learning_rate": 2.2144955079474776e-05,
"loss": 22.2169287109375,
"step": 6650
},
{
"epoch": 0.5689960828441312,
"grad_norm": 147.85865783691406,
"learning_rate": 2.1928991015894958e-05,
"loss": 22.83664794921875,
"step": 6700
},
{
"epoch": 0.5732423222683412,
"grad_norm": 153.3690948486328,
"learning_rate": 2.1713026952315136e-05,
"loss": 21.9330712890625,
"step": 6750
},
{
"epoch": 0.577488561692551,
"grad_norm": 137.37164306640625,
"learning_rate": 2.1497062888735314e-05,
"loss": 20.79832763671875,
"step": 6800
},
{
"epoch": 0.581734801116761,
"grad_norm": 130.9550018310547,
"learning_rate": 2.1281098825155495e-05,
"loss": 21.09296630859375,
"step": 6850
},
{
"epoch": 0.5859810405409709,
"grad_norm": 121.02996063232422,
"learning_rate": 2.1065134761575674e-05,
"loss": 21.2236083984375,
"step": 6900
},
{
"epoch": 0.5902272799651809,
"grad_norm": 169.94479370117188,
"learning_rate": 2.0849170697995855e-05,
"loss": 21.0869140625,
"step": 6950
},
{
"epoch": 0.5944735193893907,
"grad_norm": 139.7215576171875,
"learning_rate": 2.0633206634416033e-05,
"loss": 20.95746337890625,
"step": 7000
},
{
"epoch": 0.5987197588136007,
"grad_norm": 135.5031280517578,
"learning_rate": 2.0417242570836215e-05,
"loss": 21.83375,
"step": 7050
},
{
"epoch": 0.6029659982378106,
"grad_norm": 143.67396545410156,
"learning_rate": 2.0201278507256393e-05,
"loss": 21.9516015625,
"step": 7100
},
{
"epoch": 0.6072122376620206,
"grad_norm": 242.10548400878906,
"learning_rate": 1.9985314443676574e-05,
"loss": 21.42175537109375,
"step": 7150
},
{
"epoch": 0.6114584770862305,
"grad_norm": 157.11415100097656,
"learning_rate": 1.9769350380096752e-05,
"loss": 21.08699951171875,
"step": 7200
},
{
"epoch": 0.6157047165104405,
"grad_norm": 124.51484680175781,
"learning_rate": 1.9553386316516934e-05,
"loss": 21.26003662109375,
"step": 7250
},
{
"epoch": 0.6199509559346503,
"grad_norm": 175.8770751953125,
"learning_rate": 1.9337422252937112e-05,
"loss": 21.37485107421875,
"step": 7300
},
{
"epoch": 0.6241971953588603,
"grad_norm": 139.2329559326172,
"learning_rate": 1.912145818935729e-05,
"loss": 21.006982421875,
"step": 7350
},
{
"epoch": 0.6284434347830703,
"grad_norm": 142.4539031982422,
"learning_rate": 1.890549412577747e-05,
"loss": 20.92181640625,
"step": 7400
},
{
"epoch": 0.6326896742072802,
"grad_norm": 143.5320281982422,
"learning_rate": 1.8689530062197653e-05,
"loss": 21.85162109375,
"step": 7450
},
{
"epoch": 0.6369359136314902,
"grad_norm": 152.91880798339844,
"learning_rate": 1.847356599861783e-05,
"loss": 20.92374755859375,
"step": 7500
},
{
"epoch": 0.6411821530557,
"grad_norm": 162.99484252929688,
"learning_rate": 1.825760193503801e-05,
"loss": 21.4075537109375,
"step": 7550
},
{
"epoch": 0.64542839247991,
"grad_norm": 164.03475952148438,
"learning_rate": 1.804163787145819e-05,
"loss": 21.6792919921875,
"step": 7600
},
{
"epoch": 0.6496746319041199,
"grad_norm": 154.84764099121094,
"learning_rate": 1.7825673807878372e-05,
"loss": 20.593271484375,
"step": 7650
},
{
"epoch": 0.6539208713283299,
"grad_norm": 136.49598693847656,
"learning_rate": 1.760970974429855e-05,
"loss": 20.4891650390625,
"step": 7700
},
{
"epoch": 0.6581671107525398,
"grad_norm": 144.41871643066406,
"learning_rate": 1.739374568071873e-05,
"loss": 21.7032177734375,
"step": 7750
},
{
"epoch": 0.6624133501767497,
"grad_norm": 172.35324096679688,
"learning_rate": 1.7177781617138906e-05,
"loss": 21.29265380859375,
"step": 7800
},
{
"epoch": 0.6666595896009596,
"grad_norm": 154.5519256591797,
"learning_rate": 1.6961817553559088e-05,
"loss": 20.79191650390625,
"step": 7850
},
{
"epoch": 0.6709058290251696,
"grad_norm": 157.8460235595703,
"learning_rate": 1.674585348997927e-05,
"loss": 20.80486328125,
"step": 7900
},
{
"epoch": 0.6751520684493795,
"grad_norm": 160.06161499023438,
"learning_rate": 1.6529889426399447e-05,
"loss": 20.06711669921875,
"step": 7950
},
{
"epoch": 0.6793983078735895,
"grad_norm": 150.2727813720703,
"learning_rate": 1.6313925362819626e-05,
"loss": 20.79498046875,
"step": 8000
},
{
"epoch": 0.6836445472977993,
"grad_norm": 144.0926971435547,
"learning_rate": 1.6097961299239807e-05,
"loss": 21.199130859375,
"step": 8050
},
{
"epoch": 0.6878907867220093,
"grad_norm": 149.16781616210938,
"learning_rate": 1.588199723565999e-05,
"loss": 20.359921875,
"step": 8100
},
{
"epoch": 0.6921370261462193,
"grad_norm": 167.05862426757812,
"learning_rate": 1.5666033172080167e-05,
"loss": 20.74350341796875,
"step": 8150
},
{
"epoch": 0.6963832655704292,
"grad_norm": 164.15008544921875,
"learning_rate": 1.5450069108500345e-05,
"loss": 19.6603076171875,
"step": 8200
},
{
"epoch": 0.7006295049946392,
"grad_norm": 175.12493896484375,
"learning_rate": 1.5234105044920526e-05,
"loss": 20.55838623046875,
"step": 8250
},
{
"epoch": 0.704875744418849,
"grad_norm": 146.61241149902344,
"learning_rate": 1.5018140981340706e-05,
"loss": 20.462938232421877,
"step": 8300
},
{
"epoch": 0.709121983843059,
"grad_norm": 132.65420532226562,
"learning_rate": 1.4802176917760884e-05,
"loss": 20.41062255859375,
"step": 8350
},
{
"epoch": 0.7133682232672689,
"grad_norm": 145.90028381347656,
"learning_rate": 1.4586212854181064e-05,
"loss": 20.371319580078126,
"step": 8400
},
{
"epoch": 0.7176144626914789,
"grad_norm": 147.31033325195312,
"learning_rate": 1.4370248790601245e-05,
"loss": 20.66120361328125,
"step": 8450
},
{
"epoch": 0.7218607021156888,
"grad_norm": 136.2473602294922,
"learning_rate": 1.4154284727021425e-05,
"loss": 20.56037109375,
"step": 8500
},
{
"epoch": 0.7261069415398987,
"grad_norm": 152.7163848876953,
"learning_rate": 1.3938320663441603e-05,
"loss": 20.41483154296875,
"step": 8550
},
{
"epoch": 0.7303531809641086,
"grad_norm": 144.92152404785156,
"learning_rate": 1.3722356599861783e-05,
"loss": 21.3026416015625,
"step": 8600
},
{
"epoch": 0.7345994203883186,
"grad_norm": 146.7015380859375,
"learning_rate": 1.3506392536281965e-05,
"loss": 20.11982177734375,
"step": 8650
},
{
"epoch": 0.7388456598125285,
"grad_norm": 122.79088592529297,
"learning_rate": 1.3290428472702143e-05,
"loss": 20.265406494140624,
"step": 8700
},
{
"epoch": 0.7430918992367385,
"grad_norm": 124.77399444580078,
"learning_rate": 1.3074464409122322e-05,
"loss": 20.56513427734375,
"step": 8750
},
{
"epoch": 0.7473381386609484,
"grad_norm": 131.1453094482422,
"learning_rate": 1.28585003455425e-05,
"loss": 19.999232177734374,
"step": 8800
},
{
"epoch": 0.7515843780851583,
"grad_norm": 143.78489685058594,
"learning_rate": 1.2642536281962684e-05,
"loss": 20.73391845703125,
"step": 8850
},
{
"epoch": 0.7558306175093683,
"grad_norm": 144.25245666503906,
"learning_rate": 1.2426572218382862e-05,
"loss": 20.422523193359375,
"step": 8900
},
{
"epoch": 0.7600768569335782,
"grad_norm": 173.52023315429688,
"learning_rate": 1.2210608154803042e-05,
"loss": 19.5886962890625,
"step": 8950
},
{
"epoch": 0.7643230963577882,
"grad_norm": 138.1155242919922,
"learning_rate": 1.1994644091223221e-05,
"loss": 19.826878662109376,
"step": 9000
},
{
"epoch": 0.768569335781998,
"grad_norm": 141.95608520507812,
"learning_rate": 1.17786800276434e-05,
"loss": 20.6840185546875,
"step": 9050
},
{
"epoch": 0.772815575206208,
"grad_norm": 130.37266540527344,
"learning_rate": 1.1562715964063581e-05,
"loss": 20.7981884765625,
"step": 9100
},
{
"epoch": 0.7770618146304179,
"grad_norm": 129.22499084472656,
"learning_rate": 1.1346751900483759e-05,
"loss": 20.298045654296875,
"step": 9150
},
{
"epoch": 0.7813080540546279,
"grad_norm": 196.2136993408203,
"learning_rate": 1.113078783690394e-05,
"loss": 20.010155029296875,
"step": 9200
},
{
"epoch": 0.7855542934788378,
"grad_norm": 143.95925903320312,
"learning_rate": 1.0914823773324119e-05,
"loss": 20.69479248046875,
"step": 9250
},
{
"epoch": 0.7898005329030477,
"grad_norm": 140.12205505371094,
"learning_rate": 1.06988597097443e-05,
"loss": 20.101761474609376,
"step": 9300
},
{
"epoch": 0.7940467723272576,
"grad_norm": 148.62911987304688,
"learning_rate": 1.0482895646164478e-05,
"loss": 20.48222900390625,
"step": 9350
},
{
"epoch": 0.7982930117514676,
"grad_norm": 134.18821716308594,
"learning_rate": 1.0266931582584658e-05,
"loss": 21.5114208984375,
"step": 9400
},
{
"epoch": 0.8025392511756776,
"grad_norm": 112.08241271972656,
"learning_rate": 1.0050967519004838e-05,
"loss": 19.884307861328125,
"step": 9450
},
{
"epoch": 0.8067854905998875,
"grad_norm": 130.55465698242188,
"learning_rate": 9.835003455425018e-06,
"loss": 19.306004638671876,
"step": 9500
},
{
"epoch": 0.8110317300240975,
"grad_norm": 175.3483428955078,
"learning_rate": 9.619039391845197e-06,
"loss": 20.79504638671875,
"step": 9550
},
{
"epoch": 0.8152779694483073,
"grad_norm": 123.85011291503906,
"learning_rate": 9.403075328265377e-06,
"loss": 19.556348876953123,
"step": 9600
},
{
"epoch": 0.8195242088725173,
"grad_norm": 140.8203125,
"learning_rate": 9.187111264685557e-06,
"loss": 20.43146484375,
"step": 9650
},
{
"epoch": 0.8237704482967272,
"grad_norm": 136.66036987304688,
"learning_rate": 8.971147201105737e-06,
"loss": 20.33073486328125,
"step": 9700
},
{
"epoch": 0.8280166877209372,
"grad_norm": 146.3016815185547,
"learning_rate": 8.755183137525917e-06,
"loss": 19.646549072265625,
"step": 9750
},
{
"epoch": 0.832262927145147,
"grad_norm": 148.30975341796875,
"learning_rate": 8.539219073946096e-06,
"loss": 19.05823486328125,
"step": 9800
},
{
"epoch": 0.836509166569357,
"grad_norm": 140.53770446777344,
"learning_rate": 8.323255010366274e-06,
"loss": 19.65471923828125,
"step": 9850
},
{
"epoch": 0.8407554059935669,
"grad_norm": 137.27951049804688,
"learning_rate": 8.107290946786456e-06,
"loss": 20.391009521484374,
"step": 9900
},
{
"epoch": 0.8450016454177769,
"grad_norm": 151.11325073242188,
"learning_rate": 7.891326883206634e-06,
"loss": 19.69550048828125,
"step": 9950
},
{
"epoch": 0.8492478848419868,
"grad_norm": 137.7413787841797,
"learning_rate": 7.675362819626816e-06,
"loss": 19.3516943359375,
"step": 10000
},
{
"epoch": 0.8534941242661968,
"grad_norm": 112.80725860595703,
"learning_rate": 7.459398756046994e-06,
"loss": 19.201815185546874,
"step": 10050
},
{
"epoch": 0.8577403636904067,
"grad_norm": 150.98226928710938,
"learning_rate": 7.243434692467174e-06,
"loss": 19.6190673828125,
"step": 10100
},
{
"epoch": 0.8619866031146166,
"grad_norm": 151.21493530273438,
"learning_rate": 7.027470628887353e-06,
"loss": 20.10290771484375,
"step": 10150
},
{
"epoch": 0.8662328425388266,
"grad_norm": 166.5272674560547,
"learning_rate": 6.811506565307534e-06,
"loss": 20.10521728515625,
"step": 10200
},
{
"epoch": 0.8704790819630365,
"grad_norm": 126.49415588378906,
"learning_rate": 6.595542501727713e-06,
"loss": 19.93487548828125,
"step": 10250
},
{
"epoch": 0.8747253213872465,
"grad_norm": 130.64857482910156,
"learning_rate": 6.379578438147893e-06,
"loss": 19.3108447265625,
"step": 10300
},
{
"epoch": 0.8789715608114563,
"grad_norm": 155.81996154785156,
"learning_rate": 6.1636143745680715e-06,
"loss": 19.91413330078125,
"step": 10350
},
{
"epoch": 0.8832178002356663,
"grad_norm": 158.0801544189453,
"learning_rate": 5.947650310988251e-06,
"loss": 19.63139892578125,
"step": 10400
},
{
"epoch": 0.8874640396598762,
"grad_norm": 138.51763916015625,
"learning_rate": 5.731686247408431e-06,
"loss": 19.44971923828125,
"step": 10450
},
{
"epoch": 0.8917102790840862,
"grad_norm": 200.97584533691406,
"learning_rate": 5.515722183828611e-06,
"loss": 19.995697021484375,
"step": 10500
},
{
"epoch": 0.895956518508296,
"grad_norm": 125.70748901367188,
"learning_rate": 5.299758120248791e-06,
"loss": 19.891861572265626,
"step": 10550
},
{
"epoch": 0.900202757932506,
"grad_norm": 175.50962829589844,
"learning_rate": 5.0837940566689705e-06,
"loss": 19.681768798828124,
"step": 10600
},
{
"epoch": 0.9044489973567159,
"grad_norm": 129.02464294433594,
"learning_rate": 4.86782999308915e-06,
"loss": 19.740001220703125,
"step": 10650
},
{
"epoch": 0.9086952367809259,
"grad_norm": 170.73489379882812,
"learning_rate": 4.651865929509329e-06,
"loss": 20.2353564453125,
"step": 10700
},
{
"epoch": 0.9129414762051358,
"grad_norm": 141.15484619140625,
"learning_rate": 4.435901865929509e-06,
"loss": 19.27646240234375,
"step": 10750
},
{
"epoch": 0.9171877156293458,
"grad_norm": 139.16778564453125,
"learning_rate": 4.219937802349689e-06,
"loss": 20.000045166015624,
"step": 10800
},
{
"epoch": 0.9214339550535557,
"grad_norm": 160.3579559326172,
"learning_rate": 4.003973738769869e-06,
"loss": 18.942919921875,
"step": 10850
},
{
"epoch": 0.9256801944777656,
"grad_norm": 133.4417724609375,
"learning_rate": 3.7880096751900484e-06,
"loss": 19.30787841796875,
"step": 10900
},
{
"epoch": 0.9299264339019756,
"grad_norm": 147.41517639160156,
"learning_rate": 3.572045611610228e-06,
"loss": 19.907716064453126,
"step": 10950
},
{
"epoch": 0.9341726733261855,
"grad_norm": 137.2278289794922,
"learning_rate": 3.3560815480304076e-06,
"loss": 19.394835205078124,
"step": 11000
},
{
"epoch": 0.9384189127503955,
"grad_norm": 148.608642578125,
"learning_rate": 3.1401174844505873e-06,
"loss": 19.870865478515626,
"step": 11050
},
{
"epoch": 0.9426651521746053,
"grad_norm": 148.3636016845703,
"learning_rate": 2.9241534208707676e-06,
"loss": 20.17911376953125,
"step": 11100
},
{
"epoch": 0.9469113915988153,
"grad_norm": 136.2633056640625,
"learning_rate": 2.708189357290947e-06,
"loss": 19.6819775390625,
"step": 11150
},
{
"epoch": 0.9511576310230252,
"grad_norm": 132.42396545410156,
"learning_rate": 2.4922252937111267e-06,
"loss": 19.143297119140627,
"step": 11200
},
{
"epoch": 0.9554038704472352,
"grad_norm": 137.15524291992188,
"learning_rate": 2.2762612301313065e-06,
"loss": 19.832156982421875,
"step": 11250
},
{
"epoch": 0.9596501098714451,
"grad_norm": 145.9365234375,
"learning_rate": 2.060297166551486e-06,
"loss": 19.251436767578124,
"step": 11300
},
{
"epoch": 0.963896349295655,
"grad_norm": 142.9067840576172,
"learning_rate": 1.8443331029716657e-06,
"loss": 19.578409423828123,
"step": 11350
},
{
"epoch": 0.9681425887198649,
"grad_norm": 160.01657104492188,
"learning_rate": 1.6283690393918455e-06,
"loss": 19.1957666015625,
"step": 11400
},
{
"epoch": 0.9723888281440749,
"grad_norm": 138.53872680664062,
"learning_rate": 1.4124049758120248e-06,
"loss": 18.92045654296875,
"step": 11450
},
{
"epoch": 0.9766350675682849,
"grad_norm": 150.38726806640625,
"learning_rate": 1.1964409122322046e-06,
"loss": 19.44462890625,
"step": 11500
},
{
"epoch": 0.9808813069924948,
"grad_norm": 174.97015380859375,
"learning_rate": 9.804768486523842e-07,
"loss": 19.37765869140625,
"step": 11550
},
{
"epoch": 0.9851275464167047,
"grad_norm": 171.67678833007812,
"learning_rate": 7.64512785072564e-07,
"loss": 19.446109619140625,
"step": 11600
},
{
"epoch": 0.9893737858409146,
"grad_norm": 163.58985900878906,
"learning_rate": 5.485487214927436e-07,
"loss": 18.67140625,
"step": 11650
},
{
"epoch": 0.9936200252651246,
"grad_norm": 128.6081085205078,
"learning_rate": 3.325846579129233e-07,
"loss": 19.808094482421875,
"step": 11700
},
{
"epoch": 0.9978662646893345,
"grad_norm": 132.29139709472656,
"learning_rate": 1.1662059433310296e-07,
"loss": 19.043531494140623,
"step": 11750
}
],
"logging_steps": 50,
"max_steps": 11776,
"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": 3.43911674761974e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}