Shardul007 commited on
Commit
ad0ace4
·
verified ·
1 Parent(s): 3ae1185

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ outputs/c2_training_curves.png filter=lfs diff=lfs merge=lfs -text
37
+ outputs/c3_training_curves.png filter=lfs diff=lfs merge=lfs -text
38
+ outputs/c4_training_curves.png filter=lfs diff=lfs merge=lfs -text
39
+ outputs/c5_training_curves.png filter=lfs diff=lfs merge=lfs -text
c1/best_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99be207968fec5aed39992a490b7d36893f154588b7ee413ad9a7256bf671a87
3
+ size 130437710
c2/best_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3c9b2822ed6d179488aff65bc33f83d69542de6386d6f30c9891127148b6cd6
3
+ size 130044687
c3/best_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f82706a45394bf81bbd138804206f4782fd55155b68f98d68a0f29074c2895ec
3
+ size 116226254
c4/best_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49e069a8369e1d9ad68c6b4417a624c4e60420b55303f91ae9154a54adc954d2
3
+ size 130344566
c5/best_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58221a3d3465c51968fa36d7a41c428799d1369c27068387bbe42643697f8e43
3
+ size 103853528
outputs/c2_training_curves.png ADDED

Git LFS Details

  • SHA256: ced31e88326f4faf22eb36ebb48f08a367551b54a80afac9ce2ceecaeeffb512
  • Pointer size: 131 Bytes
  • Size of remote file: 184 kB
outputs/c3_training_curves.png ADDED

Git LFS Details

  • SHA256: cb39a4d2f43eb98fea6a91ae29cc0b7f3775637c5e76f857b4671e1fe2856d5c
  • Pointer size: 131 Bytes
  • Size of remote file: 173 kB
outputs/c4_training_curves.png ADDED

Git LFS Details

  • SHA256: 5b3a779d003b4318a7e612d0e5540b3c4a62eeaf0bd9e3dac15d3609fb1c61c7
  • Pointer size: 131 Bytes
  • Size of remote file: 170 kB
outputs/c5_training_curves.png ADDED

Git LFS Details

  • SHA256: 79816703289fd5c94380f17d6d8e5310a26d66ab0501d0a57be6fe1120ed4e05
  • Pointer size: 131 Bytes
  • Size of remote file: 169 kB
outputs/losses_c1.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train": [8.009647439462556, 7.204252335122014, 6.968240380053518, 6.5551057428936925, 6.048239216214173, 5.511634719417554, 5.019441888226802, 4.508286171337003, 4.006455042575496, 3.522632106813491, 3.115535345925836, 2.7826156571816933, 2.514902911335655, 2.3155738153872356, 2.1616944597796643, 2.0439221247227772, 1.95469974610474, 1.882766814836907, 1.8236253756591145, 1.7768451509580792, 1.7376475142019685, 1.7004083488350124, 1.6710997396062182, 1.6457853705093526, 1.622692717626951, 1.6034839491664903, 1.584243210310343, 1.5692573495825772, 1.5551218378728149, 1.5422104348730439, 1.5294419592512574, 1.5184114254507888, 1.5090044242672445, 1.5006782094878406, 1.4919730042608699, 1.4841802935550252, 1.4786081107037912, 1.4728148718208571, 1.4683794500479874, 1.4631597047193137, 1.4599550656501767, 1.4565168165905762, 1.4539682094656137, 1.4515668812063833, 1.4497392483657747, 1.4485044391460562, 1.4475267005772676, 1.4475631590582116, 1.4462992399050256, 1.4459759415174727], "val": [7.35326704249356, 7.1147475332722365, 6.71701177552083, 6.309879588244573, 5.695902854688196, 5.199319410372574, 4.6427668693817346, 4.168633612921072, 3.599752690310641, 3.1223307380077574, 2.777856655132363, 2.518104378367216, 2.3307975300810573, 2.1707466894251097, 2.034388058275564, 1.954969089257549, 1.895240131456465, 1.8417479679672066, 1.811900183533089, 1.7906458343585727, 1.7550815429737796, 1.7321938854961174, 1.7153625485190807, 1.6962363203078763, 1.678095193634283, 1.669601220449236, 1.6624072736457003, 1.6553547448890154, 1.637366982366218, 1.6304175312659355, 1.6208438641522949, 1.6116562878665908, 1.6082521885000989, 1.606737169673746, 1.598208873510391, 1.5972968410454857, 1.5915949731243355, 1.5897990453984052, 1.584562926714174, 1.5855729686439772, 1.5820728001835114, 1.5802192667052046, 1.57890785920573, 1.5769274853920752, 1.5755009422506459, 1.5760515868580467, 1.5753867064668832, 1.5749283690754954, 1.5749552945455036, 1.574870114678545]}
outputs/losses_c2.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train": [8.032424485882279, 7.216334268537636, 6.901274588772954, 6.465948904319092, 6.14097699743259, 5.778927460884959, 5.308028359323128, 4.728140130918496, 4.041543300601583, 3.3751979012752837, 2.8526869188450754, 2.5031038909906886, 2.2707680807479886, 2.112538962491442, 2.0002058569999304, 1.9165845495657854, 1.850401358741721, 1.7958045642210172, 1.750563512155359, 1.7113187475389215, 1.6802466714352542, 1.6517050808300395, 1.624222681594654, 1.6010050755538627, 1.5786755076521997, 1.5627535485270934, 1.5433260580354484, 1.5293295590014544, 1.5152322064099653, 1.5017646876827424, 1.4908712303626686, 1.480737146838508, 1.4710299442489811, 1.4630867403821022, 1.4558946534199357, 1.4493015486587955, 1.443380491631428, 1.4380308432028988, 1.4335065440407175, 1.4293835602264615, 1.4260080669917437, 1.423711767482158, 1.4208139299637497, 1.4185072833273158, 1.4174874550366974, 1.416026875112042, 1.4148983746509, 1.4145213310453828, 1.4143335247753066, 1.414242005448399], "val": [7.371155685287128, 7.104833334757846, 6.620996549529729, 6.290053069223396, 5.980223263208377, 5.608692701157689, 5.111950022784344, 4.361931679133373, 3.5898190200245508, 2.964291508380484, 2.5566155506492283, 2.2968591985715845, 2.141128015095525, 2.028707126388557, 1.9479102154943961, 1.9015839479099554, 1.846462088410502, 1.806529711121176, 1.7764823124299345, 1.7532357304822477, 1.7381624490034022, 1.7129686636821122, 1.695747159772338, 1.6806532138714054, 1.6659662870200953, 1.6574617013526487, 1.6494965551647573, 1.6424258404893666, 1.6302854359657433, 1.626478232107588, 1.616738926429642, 1.611346592632269, 1.6074726669938944, 1.6036806816778426, 1.599515797452894, 1.5966126359028683, 1.5918899566779705, 1.5915642567777106, 1.5877630334188892, 1.5843939111926288, 1.583052989451551, 1.5814943345790746, 1.5801001891760802, 1.5797010911436635, 1.5785922045961605, 1.5778753123511837, 1.5776133366651555, 1.5775789674392784, 1.577526022676198, 1.5775054334730672]}
outputs/losses_c3.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train": [8.029573042007316, 7.212584228810322, 7.024473377647353, 6.608096349048503, 6.270119593706454, 5.748185843233524, 5.302944021503573, 4.861620436216762, 4.457067000577885, 4.068069085055355, 3.691647267692921, 3.3500905546814654, 3.034967532531425, 2.7662349477696937, 2.5457091575269124, 2.369640266629348, 2.2308549638670336, 2.119732914135793, 2.0330913496027034, 1.9614041316424966, 1.9036167784315432, 1.852469317047439, 1.8100816288701433, 1.7756683127123098, 1.743525752742038, 1.7160124605079563, 1.6919911600323831, 1.670717406121284, 1.6518881061742945, 1.6355172628179755, 1.6214510803215543, 1.608242314224041, 1.5952733187094563, 1.584916563878865, 1.5741608682698391, 1.5661578895811175, 1.5588320974907355, 1.5521744779602487, 1.5459706844283778, 1.5407329198184514, 1.5362574369309048, 1.5332177357610224, 1.5287249536731216, 1.5267368028356874, 1.5247378611644993, 1.5229701075269004, 1.5214099370584224, 1.5212362173424674, 1.5199276119641336, 1.520892012558841], "val": [7.362069850386681, 7.1403861793663985, 6.764258884689771, 6.439691970938875, 5.957458463959203, 5.537163866355528, 4.992637452844107, 4.508008351085419, 4.133973180119094, 3.7350514586687784, 3.5061143181711523, 3.0206896873634825, 2.737546249123143, 2.543865036052433, 2.3355690205683475, 2.2333081006943187, 2.121615978471356, 2.0320104241704438, 1.9563028046175552, 1.9031912305785612, 1.8740496976643115, 1.8379406000550116, 1.8112759757396424, 1.787336112966924, 1.7651646899410451, 1.749566953508535, 1.731538585459721, 1.7160000203721995, 1.7014216688843056, 1.6956444272214506, 1.6841555344269166, 1.6734586804760565, 1.6662933498541455, 1.6590310014041076, 1.6558426617136872, 1.648227001109107, 1.6430774917898252, 1.644290271649474, 1.6372274949447916, 1.6333406040501544, 1.6304046870808027, 1.6270698291583685, 1.6271004791165233, 1.6262583980355485, 1.6241627233336546, 1.6231990938902294, 1.6228568173421354, 1.6228277582439932, 1.6223340055284756, 1.6223491176048217]}
outputs/losses_c4.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train": [8.014688733647812, 7.20870573113716, 6.983436113353328, 6.571889468560421, 6.090606917409538, 5.537797287350832, 5.03660698947788, 4.507810627504133, 3.9781716085054804, 3.4967483801341728, 3.092550331749605, 2.7703983101038587, 2.5117383868854897, 2.31226084821927, 2.16194324241697, 2.0478774657046945, 1.9591845567047215, 1.8869085887044166, 1.8287147769583973, 1.7816325924248035, 1.7390107050857084, 1.7046102900446007, 1.6768923926613173, 1.649570475092832, 1.6260465794810515, 1.606137379113556, 1.5887801527841623, 1.5723459942435773, 1.5586801725282766, 1.544854054310394, 1.5320939312999868, 1.5215902024083943, 1.5118198537740926, 1.5031001502189225, 1.495589895435501, 1.4883819241099265, 1.4818827181227285, 1.4763769323342784, 1.4713118706335149, 1.466320757347564, 1.4627786737616297, 1.4594033854001363, 1.4564576762938832, 1.4543903401106437, 1.45231654742881, 1.4512863142732197, 1.4505467019838985, 1.4496300085165381, 1.4490026936511367, 1.4489675017867598], "val": [7.359423464773752, 7.125607463095206, 6.71650559592238, 6.3569453876253945, 5.724021257628842, 5.382667965409655, 4.7224210914988, 4.100500142530378, 3.536168442006971, 3.09226182207005, 2.7660158404735555, 2.5104621385525134, 2.3059463209626574, 2.152750756331844, 2.0535779727900523, 1.984624069604172, 1.8978976050012826, 1.869406021133677, 1.8086521443197818, 1.7917492354305504, 1.7545189626972229, 1.7390451974162215, 1.7128987242463796, 1.6948296841179527, 1.6856048337157974, 1.6681900683163173, 1.6577249575046045, 1.6454964355904926, 1.6400669273419368, 1.6333887384449577, 1.6212047388341833, 1.614037762778674, 1.610689863672037, 1.6079858636383424, 1.6001315282160422, 1.6015736223145807, 1.591044122737371, 1.5857588797955398, 1.5866482024332789, 1.5825764171185495, 1.5811478790144315, 1.5789991795660687, 1.5769051125458924, 1.5749178493033522, 1.5763405391306142, 1.5742215812789513, 1.5746412612246898, 1.5739551846462037, 1.573994856125246, 1.5738149266470824]}
outputs/losses_c5.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train": [3.698369105315304, 3.0665278543765164, 2.9853990625711297, 2.849333064751755, 2.730140821769624, 2.6342114507274816, 2.550424433675992, 2.477238940592594, 2.419146765280805, 2.3728881778772575, 2.335141154976467, 2.3025586728518377, 2.2760859876829063, 2.253502570414363, 2.233526045380953, 2.216346185137706, 2.2008541422609644, 2.1876846523212357, 2.1760593224092344, 2.164333387068831, 2.1539266168472575, 2.1453303621367756, 2.137330875513547, 2.1289358246155863, 2.122272683565417, 2.1156731344776967, 2.109861883436327, 2.1041960503700796, 2.098836495713575, 2.094252359386432, 2.089663900970603, 2.0854096438585357, 2.0819653279997508, 2.078501639522801, 2.0748483817797223, 2.072032643212428, 2.0691391988209604, 2.0663351577148585, 2.064456632690413, 2.062641631266678, 2.060969152616517, 2.059205412871146, 2.058097421927689, 2.056821727922314, 2.0556681568582102, 2.0555285625198243, 2.0545986040055366, 2.05439710146345, 2.05382235618844, 2.0540341920936593], "val": [3.080754773884154, 3.02801990614159, 2.8751603803691737, 2.7176180688489158, 2.6037136185893206, 2.5140923708498244, 2.4280358947560696, 2.3661617371198207, 2.3198487782333754, 2.280658936111542, 2.2480461494209942, 2.2286027307067693, 2.2046509575922717, 2.1911050455333316, 2.1752897422243813, 2.160465357891034, 2.150342756359966, 2.1431514015134963, 2.130321069554748, 2.1216984625642965, 2.1181127929486796, 2.1103937753677755, 2.1049902204364432, 2.1012228847108703, 2.096115134070332, 2.0904772636058837, 2.0861745103903124, 2.0849621145929955, 2.080048746655348, 2.077065443107715, 2.0737332750991646, 2.0705699702302596, 2.0700884541713127, 2.0667036703723145, 2.065068793203164, 2.0632990888817377, 2.06188294969767, 2.0609701859047442, 2.0591780164761424, 2.058915951574766, 2.057855419483765, 2.057265697137699, 2.0565183358939363, 2.0562435007289337, 2.05573952415107, 2.0556290309015015, 2.0556472284617797, 2.0554999813471913, 2.0554940337750716, 2.0554854403783485]}
outputs/metrics_c1.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bit_accuracy": 0.9073953901570623,
3
+ "sequence_accuracy": 0.2525041736227045,
4
+ "levenshtein_raw": 3.1060100166944906,
5
+ "levenshtein_normalized": 0.025872581660680294,
6
+ "bleu": 82.75308351993817,
7
+ "rouge1": 0.9241532621881826,
8
+ "rouge2": 0.860207681904057,
9
+ "rougeL": 0.9241368950403218,
10
+ "best_val_loss": 1.574870114678545,
11
+ "best_epoch": 50,
12
+ "num_params": 10808082,
13
+ "baselines": {
14
+ "baseline_a": {
15
+ "bit_accuracy": 0.6614201212154834,
16
+ "sequence_accuracy": 0.0,
17
+ "levenshtein_raw": 100.0534223706177,
18
+ "levenshtein_normalized": 0.8317380919427361
19
+ },
20
+ "baseline_b": {
21
+ "bit_accuracy": 0.6740084497177649,
22
+ "sequence_accuracy": 0.0,
23
+ "levenshtein_raw": 100.51585976627713,
24
+ "levenshtein_normalized": 0.8361840804340469
25
+ }
26
+ },
27
+ "speed": {
28
+ "wall_time_per_epoch": 83.5378258228302,
29
+ "tokens_per_sec": 7927.40286782776,
30
+ "bytes_per_sec": 27280.31257161573,
31
+ "peak_memory_mb": 2990.63037109375
32
+ }
33
+ }
outputs/metrics_c2.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bit_accuracy": 0.9114307792644809,
3
+ "sequence_accuracy": 0.24707846410684475,
4
+ "levenshtein_raw": 3.1419031719532553,
5
+ "levenshtein_normalized": 0.02616971530275171,
6
+ "bleu": 82.74193878070596,
7
+ "rouge1": 0.9239669286870346,
8
+ "rouge2": 0.8596410509261702,
9
+ "rougeL": 0.9239081185489255,
10
+ "best_val_loss": 1.5775054334730672,
11
+ "best_epoch": 50,
12
+ "num_params": 10808082,
13
+ "baselines": {
14
+ "baseline_a": {
15
+ "bit_accuracy": 0.6614201212154834,
16
+ "sequence_accuracy": 0.0,
17
+ "levenshtein_raw": 100.0534223706177,
18
+ "levenshtein_normalized": 0.8317380919427361
19
+ },
20
+ "baseline_b": {
21
+ "bit_accuracy": 0.6740084497177649,
22
+ "sequence_accuracy": 0.0,
23
+ "levenshtein_raw": 100.51585976627713,
24
+ "levenshtein_normalized": 0.8361840804340469
25
+ }
26
+ },
27
+ "speed": {
28
+ "wall_time_per_epoch": 80.18073105812073,
29
+ "tokens_per_sec": 8259.316063356451,
30
+ "bytes_per_sec": 28422.514610749342,
31
+ "peak_memory_mb": 2990.95849609375
32
+ }
33
+ }
outputs/metrics_c3.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bit_accuracy": 0.8934682746752526,
3
+ "sequence_accuracy": 0.2141068447412354,
4
+ "levenshtein_raw": 3.6389816360601004,
5
+ "levenshtein_normalized": 0.030214716446420722,
6
+ "bleu": 80.86012910438292,
7
+ "rouge1": 0.9148822238958909,
8
+ "rouge2": 0.8448190699568484,
9
+ "rougeL": 0.9148640777102192,
10
+ "best_val_loss": 1.6223340055284756,
11
+ "best_epoch": 49,
12
+ "num_params": 9623826,
13
+ "baselines": {
14
+ "baseline_a": {
15
+ "bit_accuracy": 0.6614201212154834,
16
+ "sequence_accuracy": 0.0,
17
+ "levenshtein_raw": 100.0534223706177,
18
+ "levenshtein_normalized": 0.8317380919427361
19
+ },
20
+ "baseline_b": {
21
+ "bit_accuracy": 0.6740084497177649,
22
+ "sequence_accuracy": 0.0,
23
+ "levenshtein_raw": 100.51585976627713,
24
+ "levenshtein_normalized": 0.8361840804340469
25
+ }
26
+ },
27
+ "speed": {
28
+ "wall_time_per_epoch": 83.60789370536804,
29
+ "tokens_per_sec": 7920.7592806213825,
30
+ "bytes_per_sec": 27330.684923752455,
31
+ "peak_memory_mb": 2974.09521484375
32
+ }
33
+ }
outputs/metrics_c4.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bit_accuracy": 0.9064977774847581,
3
+ "sequence_accuracy": 0.25751252086811355,
4
+ "levenshtein_raw": 3.1348080133555927,
5
+ "levenshtein_normalized": 0.02610006223728226,
6
+ "bleu": 82.79626290557455,
7
+ "rouge1": 0.9237609930946259,
8
+ "rouge2": 0.8601809628334061,
9
+ "rougeL": 0.9237226595114781,
10
+ "best_val_loss": 1.5738149266470824,
11
+ "best_epoch": 50,
12
+ "num_params": 10802450,
13
+ "baselines": {
14
+ "baseline_a": {
15
+ "bit_accuracy": 0.6614201212154834,
16
+ "sequence_accuracy": 0.0,
17
+ "levenshtein_raw": 100.0534223706177,
18
+ "levenshtein_normalized": 0.8317380919427361
19
+ },
20
+ "baseline_b": {
21
+ "bit_accuracy": 0.6740084497177649,
22
+ "sequence_accuracy": 0.0,
23
+ "levenshtein_raw": 100.51585976627713,
24
+ "levenshtein_normalized": 0.8361840804340469
25
+ }
26
+ },
27
+ "speed": {
28
+ "wall_time_per_epoch": 99.70713949203491,
29
+ "tokens_per_sec": 6641.831300885959,
30
+ "bytes_per_sec": 22856.3171264386,
31
+ "peak_memory_mb": 2832.91943359375
32
+ }
33
+ }
outputs/metrics_c5.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bit_accuracy": 0.682489157319329,
3
+ "sequence_accuracy": 0.0,
4
+ "levenshtein_raw": 91.48873121869784,
5
+ "levenshtein_normalized": 0.7598321758400012,
6
+ "bleu": "N/A - token-free",
7
+ "rouge1": "N/A - token-free",
8
+ "rouge2": "N/A - token-free",
9
+ "rougeL": "N/A - token-free",
10
+ "best_val_loss": 2.0554854403783485,
11
+ "best_epoch": 50,
12
+ "num_params": 8430083,
13
+ "baselines": {
14
+ "baseline_a": {
15
+ "bit_accuracy": 0.6614201212154834,
16
+ "sequence_accuracy": 0.0,
17
+ "levenshtein_raw": 100.0534223706177,
18
+ "levenshtein_normalized": 0.8317380919427361
19
+ },
20
+ "baseline_b": {
21
+ "bit_accuracy": 0.6740084497177649,
22
+ "sequence_accuracy": 0.0,
23
+ "levenshtein_raw": 100.51585976627713,
24
+ "levenshtein_normalized": 0.8361840804340469
25
+ }
26
+ },
27
+ "speed": {
28
+ "wall_time_per_epoch": 59.37626600265503,
29
+ "tokens_per_sec": 40705.72575062105,
30
+ "bytes_per_sec": 430484.9348198664,
31
+ "peak_memory_mb": 4563.95458984375
32
+ }
33
+ }