Hugging Face's logo

Marcus2112
/
crux_ablation

Model card Files
xet
 Community
Marcus2112 commited on
Commit
57dd7d5
·
verified ·
1 Parent(s): 25dcc09

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. final.pt +3 -0
  2. logs/metrics.jsonl +102 -0
final.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47962d2eb5e6ad65b28a2cc7dd7c40b8a923f8f2ca6de10cdbdc2bb765c1bb06
3
+ size 304304359
logs/metrics.jsonl ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"step": 0, "val_loss": 10.825744774891414, "val_perplexity": 50299.21627192595}
2
+ {"step": 0, "val_loss": 10.825744774891414, "val_perplexity": 50299.21627192595}
3
+ {"step": 1000, "val_loss": 10.689736016575488, "val_perplexity": 43902.91582561654}
4
+ {"step": 2000, "val_loss": 10.433539775086976, "val_perplexity": 33980.42067028248}
5
+ {"step": 3000, "val_loss": 9.699867817209386, "val_perplexity": 16315.450433706554}
6
+ {"step": 4000, "val_loss": 7.975991479512034, "val_perplexity": 2910.241887350923}
7
+ {"step": 5000, "val_loss": 7.3839335973528755, "val_perplexity": 1609.9100669046134}
8
+ {"step": 6000, "val_loss": 7.123817476527341, "val_perplexity": 1241.1795749226658}
9
+ {"step": 7000, "val_loss": 6.93326405729873, "val_perplexity": 1025.8369113520998}
10
+ {"step": 8000, "val_loss": 6.718656777023613, "val_perplexity": 827.7049721183079}
11
+ {"step": 9000, "val_loss": 6.4967232516194775, "val_perplexity": 662.9656982178569}
12
+ {"step": 10000, "val_loss": 6.268896476932619, "val_perplexity": 527.8945125624202}
13
+ {"step": 11000, "val_loss": 6.077692753914418, "val_perplexity": 436.02202316270376}
14
+ {"step": 12000, "val_loss": 5.864625998530881, "val_perplexity": 352.3503519125041}
15
+ {"step": 13000, "val_loss": 5.621483257259352, "val_perplexity": 276.2989018008563}
16
+ {"step": 14000, "val_loss": 5.430720788231487, "val_perplexity": 228.3137519952063}
17
+ {"step": 15000, "val_loss": 5.348461539701201, "val_perplexity": 210.2845344742303}
18
+ {"step": 16000, "val_loss": 5.172298092195664, "val_perplexity": 176.31957087839228}
19
+ {"step": 17000, "val_loss": 5.154795171261549, "val_perplexity": 173.26031443245617}
20
+ {"step": 18000, "val_loss": 4.9594926745847445, "val_perplexity": 142.52147278749976}
21
+ {"step": 19000, "val_loss": 4.865670127591948, "val_perplexity": 129.75786380787983}
22
+ {"step": 20000, "val_loss": 4.619028402484018, "val_perplexity": 101.39546866980153}
23
+ {"step": 21000, "val_loss": 4.598245897431442, "val_perplexity": 99.30996290932829}
24
+ {"step": 22000, "val_loss": 4.481863986497643, "val_perplexity": 88.39929429271452}
25
+ {"step": 23000, "val_loss": 4.595661891586128, "val_perplexity": 99.05367664987267}
26
+ {"step": 24000, "val_loss": 4.2548980779681225, "val_perplexity": 70.4496364524089}
27
+ {"step": 25000, "val_loss": 4.305100770876848, "val_perplexity": 74.07667984872775}
28
+ {"step": 26000, "val_loss": 4.337328298023905, "val_perplexity": 76.5028731790972}
29
+ {"step": 27000, "val_loss": 4.304209994220209, "val_perplexity": 74.01072345208766}
30
+ {"step": 28000, "val_loss": 4.244395425046545, "val_perplexity": 69.71360030413672}
31
+ {"step": 29000, "val_loss": 4.192933628832239, "val_perplexity": 66.21676170352634}
32
+ {"step": 30000, "val_loss": 4.336854466442587, "val_perplexity": 76.46663228844069}
33
+ {"step": 31000, "val_loss": 4.053855293807296, "val_perplexity": 57.61916821237945}
34
+ {"step": 32000, "val_loss": 4.06435650822638, "val_perplexity": 58.227427593855}
35
+ {"step": 33000, "val_loss": 4.18760727130514, "val_perplexity": 65.86500517852713}
36
+ {"step": 34000, "val_loss": 4.202326839956538, "val_perplexity": 66.84168012668538}
37
+ {"step": 35000, "val_loss": 4.121915236421082, "val_perplexity": 61.67725574304972}
38
+ {"step": 36000, "val_loss": 4.2215694388847105, "val_perplexity": 68.14034251692064}
39
+ {"step": 37000, "val_loss": 3.989921209870606, "val_perplexity": 54.050630539378126}
40
+ {"step": 38000, "val_loss": 4.066742621522477, "val_perplexity": 58.36653072495045}
41
+ {"step": 39000, "val_loss": 3.9866048712441775, "val_perplexity": 53.87167724441196}
42
+ {"step": 40000, "val_loss": 4.127016034348122, "val_perplexity": 61.99266269098427}
43
+ {"step": 41000, "val_loss": 4.0143460805205, "val_perplexity": 55.387064877226265}
44
+ {"step": 42000, "val_loss": 4.321677796658186, "val_perplexity": 75.3148854085713}
45
+ {"step": 43000, "val_loss": 4.023634690532331, "val_perplexity": 55.90393048792984}
46
+ {"step": 44000, "val_loss": 4.22541426801276, "val_perplexity": 68.40283478622423}
47
+ {"step": 45000, "val_loss": 4.035941032840944, "val_perplexity": 56.596154026633265}
48
+ {"step": 46000, "val_loss": 4.091956697027942, "val_perplexity": 59.85689900928358}
49
+ {"step": 47000, "val_loss": 4.138214429060539, "val_perplexity": 62.6907826127185}
50
+ {"step": 48000, "val_loss": 4.099424802046409, "val_perplexity": 60.30558996737639}
51
+ {"step": 49000, "val_loss": 4.01823715569676, "val_perplexity": 55.60299994780596}
52
+ {"step": 50000, "val_loss": 4.248477826779219, "val_perplexity": 69.99878094170532}
53
+ {"step": 51000, "val_loss": 4.157940181152053, "val_perplexity": 63.93968269983898}
54
+ {"step": 52000, "val_loss": 3.9643685601841754, "val_perplexity": 52.68699022045566}
55
+ {"step": 53000, "val_loss": 3.912029364635015, "val_perplexity": 50.00031796135444}
56
+ {"step": 54000, "val_loss": 4.112006359424753, "val_perplexity": 61.06912134274656}
57
+ {"step": 55000, "val_loss": 3.8616734626831084, "val_perplexity": 47.544849363020546}
58
+ {"step": 56000, "val_loss": 4.109003791694584, "val_perplexity": 60.886032176056894}
59
+ {"step": 57000, "val_loss": 4.1741195089999525, "val_perplexity": 64.98259787168921}
60
+ {"step": 58000, "val_loss": 3.9863957266261303, "val_perplexity": 53.860411451182195}
61
+ {"step": 59000, "val_loss": 3.9894471907985394, "val_perplexity": 54.02501558111423}
62
+ {"step": 60000, "val_loss": 4.069726937529205, "val_perplexity": 58.54097506590077}
63
+ {"step": 61000, "val_loss": 4.152612483638594, "val_perplexity": 63.59993724543505}
64
+ {"step": 62000, "val_loss": 3.929075597941488, "val_perplexity": 50.85994089804492}
65
+ {"step": 63000, "val_loss": 3.953994500392553, "val_perplexity": 52.14323757151089}
66
+ {"step": 64000, "val_loss": 4.127124303814886, "val_perplexity": 61.99937496687784}
67
+ {"step": 65000, "val_loss": 3.8555567511443556, "val_perplexity": 47.2549188489323}
68
+ {"step": 66000, "val_loss": 3.936258910714894, "val_perplexity": 51.226599094778216}
69
+ {"step": 67000, "val_loss": 3.939015494399574, "val_perplexity": 51.36800431017743}
70
+ {"step": 68000, "val_loss": 3.97920528025911, "val_perplexity": 53.47452007957059}
71
+ {"step": 69000, "val_loss": 3.965456073077814, "val_perplexity": 52.74431916898261}
72
+ {"step": 70000, "val_loss": 3.92843952985213, "val_perplexity": 50.82760079895593}
73
+ {"step": 71000, "val_loss": 4.156702865297166, "val_perplexity": 63.86061804074312}
74
+ {"step": 72000, "val_loss": 3.9580430380996314, "val_perplexity": 52.35476934323668}
75
+ {"step": 73000, "val_loss": 3.9494376774130013, "val_perplexity": 51.90617061461253}
76
+ {"step": 74000, "val_loss": 4.129416203844721, "val_perplexity": 62.14163429602277}
77
+ {"step": 75000, "val_loss": 4.057544733536965, "val_perplexity": 57.832143298560815}
78
+ {"step": 76000, "val_loss": 3.931178355348176, "val_perplexity": 50.96699953519567}
79
+ {"step": 77000, "val_loss": 4.17460839470486, "val_perplexity": 65.01437470184251}
80
+ {"step": 78000, "val_loss": 4.0674727374521, "val_perplexity": 58.40916061927831}
81
+ {"step": 79000, "val_loss": 4.109246380153807, "val_perplexity": 60.90080421648149}
82
+ {"step": 80000, "val_loss": 3.848056246484143, "val_perplexity": 46.90180901628413}
83
+ {"step": 81000, "val_loss": 3.976353486935576, "val_perplexity": 53.32223904045877}
84
+ {"step": 82000, "val_loss": 3.9818217462155148, "val_perplexity": 53.61461754108883}
85
+ {"step": 83000, "val_loss": 4.002650684091435, "val_perplexity": 54.74306445718919}
86
+ {"step": 84000, "val_loss": 3.895567115394398, "val_perplexity": 49.18393842354999}
87
+ {"step": 85000, "val_loss": 4.309513480022826, "val_perplexity": 74.40428096403147}
88
+ {"step": 86000, "val_loss": 4.150610932115915, "val_perplexity": 63.47276600654878}
89
+ {"step": 87000, "val_loss": 4.032884273843923, "val_perplexity": 56.4234173652884}
90
+ {"step": 88000, "val_loss": 3.9995721442035106, "val_perplexity": 54.57479489484689}
91
+ {"step": 89000, "val_loss": 3.8571679237903864, "val_perplexity": 47.33111604851072}
92
+ {"step": 90000, "val_loss": 4.083757469450133, "val_perplexity": 59.36812519431964}
93
+ {"step": 91000, "val_loss": 4.111885510664573, "val_perplexity": 61.061741661068666}
94
+ {"step": 92000, "val_loss": 4.104862103645893, "val_perplexity": 60.63438271077653}
95
+ {"step": 93000, "val_loss": 4.079413568096915, "val_perplexity": 59.110795227585434}
96
+ {"step": 94000, "val_loss": 4.022256333807697, "val_perplexity": 55.82692801004111}
97
+ {"step": 95000, "val_loss": 3.9508867892341173, "val_perplexity": 51.98144298590835}
98
+ {"step": 96000, "val_loss": 4.001017938798043, "val_perplexity": 54.65375590525009}
99
+ {"step": 97000, "val_loss": 3.8267948008466206, "val_perplexity": 45.91513498024922}
100
+ {"step": 98000, "val_loss": 3.9409920747069016, "val_perplexity": 51.4696377061191}
101
+ {"step": 99000, "val_loss": 3.924658268198125, "val_perplexity": 50.63577124851523}
102
+ {"training_complete": true, "final_step": 100000}