Upload folder using huggingface_hub
Browse files- attention_kindselective_n_heads4_seed1340/log2.txt +35 -0
- attention_kindselective_n_heads4_seed1340/model_47500.pt +1 -1
- attention_kindselective_n_heads4_seed1340/model_49999.pt +1 -1
- attention_kindselective_n_heads4_seed1340/optimizer_47500.pt +1 -1
- attention_kindselective_n_heads4_seed1340/optimizer_49999.pt +1 -1
attention_kindselective_n_heads4_seed1340/log2.txt
CHANGED
|
@@ -3229,3 +3229,38 @@ max_steps: 50000
|
|
| 3229 |
48800 val loss 5.6216
|
| 3230 |
48800 val perplexity 276.3209
|
| 3231 |
48800 train 5.845224 (lr=3.0387e-06) (hash(x)=52737449)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3229 |
48800 val loss 5.6216
|
| 3230 |
48800 val perplexity 276.3209
|
| 3231 |
48800 train 5.845224 (lr=3.0387e-06) (hash(x)=52737449)
|
| 3232 |
+
48900 val loss 5.6206
|
| 3233 |
+
48900 val perplexity 276.0498
|
| 3234 |
+
48900 train 5.472835 (lr=3.0325e-06) (hash(x)=47057569)
|
| 3235 |
+
49000 val loss 5.6223
|
| 3236 |
+
49000 val perplexity 276.5252
|
| 3237 |
+
49000 train 5.599955 (lr=3.0269e-06) (hash(x)=49908975)
|
| 3238 |
+
49100 val loss 5.6220
|
| 3239 |
+
49100 val perplexity 276.4531
|
| 3240 |
+
49100 train 5.443539 (lr=3.0218e-06) (hash(x)=48427414)
|
| 3241 |
+
49200 val loss 5.6210
|
| 3242 |
+
49200 val perplexity 276.1581
|
| 3243 |
+
49200 train 5.420611 (lr=3.0172e-06) (hash(x)=50246074)
|
| 3244 |
+
49300 val loss 5.6214
|
| 3245 |
+
49300 val perplexity 276.2842
|
| 3246 |
+
49300 train 5.669698 (lr=3.0132e-06) (hash(x)=47715359)
|
| 3247 |
+
49400 val loss 5.6240
|
| 3248 |
+
49400 val perplexity 276.9970
|
| 3249 |
+
49400 train 5.644059 (lr=3.0097e-06) (hash(x)=50175867)
|
| 3250 |
+
49500 val loss 5.6251
|
| 3251 |
+
49500 val perplexity 277.3116
|
| 3252 |
+
49500 train 5.464098 (lr=3.0067e-06) (hash(x)=49336040)
|
| 3253 |
+
49600 val loss 5.6235
|
| 3254 |
+
49600 val perplexity 276.8593
|
| 3255 |
+
49600 train 5.676532 (lr=3.0043e-06) (hash(x)=52039357)
|
| 3256 |
+
49700 val loss 5.6247
|
| 3257 |
+
49700 val perplexity 277.1861
|
| 3258 |
+
49700 train 5.447358 (lr=3.0024e-06) (hash(x)=47568707)
|
| 3259 |
+
49800 val loss 5.6250
|
| 3260 |
+
49800 val perplexity 277.2704
|
| 3261 |
+
49800 train 5.547525 (lr=3.0011e-06) (hash(x)=48451274)
|
| 3262 |
+
49900 val loss 5.6272
|
| 3263 |
+
49900 val perplexity 277.8765
|
| 3264 |
+
49900 train 5.305177 (lr=3.0003e-06) (hash(x)=44523603)
|
| 3265 |
+
49999 val loss 5.6201
|
| 3266 |
+
49999 val perplexity 275.9033
|
attention_kindselective_n_heads4_seed1340/model_47500.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 92843394
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a73c3b261de2262152da721dec986ed12d824371a88adf40037adf8d1cc5c8b
|
| 3 |
size 92843394
|
attention_kindselective_n_heads4_seed1340/model_49999.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 92843394
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f365079a2b85923374bdff77c4a3275bd86c230a7c629e85f3094934a908b6d8
|
| 3 |
size 92843394
|
attention_kindselective_n_heads4_seed1340/optimizer_47500.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 179406214
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18538af6328bf7af3d5ccf4852fe349a90f89347d4c63da2d5c76d963c09e640
|
| 3 |
size 179406214
|
attention_kindselective_n_heads4_seed1340/optimizer_49999.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 179406214
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58f7d8387db3a93f661e46064cfe947c85b00e44e061bbdfac226b8aa4d7c467
|
| 3 |
size 179406214
|