Commit
·
54db0be
1
Parent(s):
7b1e60e
Training in progress, step 9000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +254 -5
- pytorch_model.bin +1 -1
- runs/Apr09_14-45-21_gpu07.cyverse.org/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2524414853
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0c2be3452d8137d689d35c0df6e890c78020bf9843bc1e5ee746f483f22d91d
|
| 3 |
size 2524414853
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262229869
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c2f9145d655487602d0119001d797a278a1eb42e4a3b0bd88e042a0adbe3136
|
| 3 |
size 1262229869
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14639
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70a396db9e5798714b943d735d77ab7ab39ac707fd4daa400a37b45acbc4d16e
|
| 3 |
size 14639
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e7b0809e95e7bb66d8269d06cf0ed6189035774c3ca188b731868d7c85cab50
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -1998,11 +1998,260 @@
|
|
| 1998 |
"eval_steps_per_second": 1.204,
|
| 1999 |
"eval_wer": 0.0680377854836781,
|
| 2000 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2001 |
}
|
| 2002 |
],
|
| 2003 |
"max_steps": 10000,
|
| 2004 |
"num_train_epochs": 89,
|
| 2005 |
-
"total_flos": 3.
|
| 2006 |
"trial_name": null,
|
| 2007 |
"trial_params": null
|
| 2008 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.065048427597752,
|
| 3 |
+
"best_model_checkpoint": "./wav2vec2-xls-r-300m-ar/checkpoint-9000",
|
| 4 |
+
"epoch": 79.64601769911505,
|
| 5 |
+
"global_step": 9000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 1998 |
"eval_steps_per_second": 1.204,
|
| 1999 |
"eval_wer": 0.0680377854836781,
|
| 2000 |
"step": 8000
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 71.02,
|
| 2004 |
+
"learning_rate": 6.236842105263157e-05,
|
| 2005 |
+
"loss": 0.0061,
|
| 2006 |
+
"step": 8025
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 71.24,
|
| 2010 |
+
"learning_rate": 6.157894736842104e-05,
|
| 2011 |
+
"loss": 0.0059,
|
| 2012 |
+
"step": 8050
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 71.46,
|
| 2016 |
+
"learning_rate": 6.078947368421052e-05,
|
| 2017 |
+
"loss": 0.008,
|
| 2018 |
+
"step": 8075
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 71.68,
|
| 2022 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 2023 |
+
"loss": 0.0105,
|
| 2024 |
+
"step": 8100
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 71.9,
|
| 2028 |
+
"learning_rate": 5.921052631578947e-05,
|
| 2029 |
+
"loss": 0.0066,
|
| 2030 |
+
"step": 8125
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 72.12,
|
| 2034 |
+
"learning_rate": 5.842105263157894e-05,
|
| 2035 |
+
"loss": 0.0075,
|
| 2036 |
+
"step": 8150
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 72.35,
|
| 2040 |
+
"learning_rate": 5.763157894736841e-05,
|
| 2041 |
+
"loss": 0.01,
|
| 2042 |
+
"step": 8175
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 72.57,
|
| 2046 |
+
"learning_rate": 5.684210526315789e-05,
|
| 2047 |
+
"loss": 0.0097,
|
| 2048 |
+
"step": 8200
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 72.79,
|
| 2052 |
+
"learning_rate": 5.605263157894736e-05,
|
| 2053 |
+
"loss": 0.007,
|
| 2054 |
+
"step": 8225
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 73.01,
|
| 2058 |
+
"learning_rate": 5.526315789473683e-05,
|
| 2059 |
+
"loss": 0.0047,
|
| 2060 |
+
"step": 8250
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 73.23,
|
| 2064 |
+
"learning_rate": 5.4473684210526315e-05,
|
| 2065 |
+
"loss": 0.006,
|
| 2066 |
+
"step": 8275
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 73.45,
|
| 2070 |
+
"learning_rate": 5.3684210526315784e-05,
|
| 2071 |
+
"loss": 0.0078,
|
| 2072 |
+
"step": 8300
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 73.67,
|
| 2076 |
+
"learning_rate": 5.2894736842105254e-05,
|
| 2077 |
+
"loss": 0.0085,
|
| 2078 |
+
"step": 8325
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 73.89,
|
| 2082 |
+
"learning_rate": 5.210526315789474e-05,
|
| 2083 |
+
"loss": 0.0075,
|
| 2084 |
+
"step": 8350
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 74.12,
|
| 2088 |
+
"learning_rate": 5.1315789473684206e-05,
|
| 2089 |
+
"loss": 0.0062,
|
| 2090 |
+
"step": 8375
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 74.34,
|
| 2094 |
+
"learning_rate": 5.0526315789473676e-05,
|
| 2095 |
+
"loss": 0.0073,
|
| 2096 |
+
"step": 8400
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 74.56,
|
| 2100 |
+
"learning_rate": 4.973684210526315e-05,
|
| 2101 |
+
"loss": 0.0063,
|
| 2102 |
+
"step": 8425
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 74.78,
|
| 2106 |
+
"learning_rate": 4.894736842105263e-05,
|
| 2107 |
+
"loss": 0.006,
|
| 2108 |
+
"step": 8450
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 75.0,
|
| 2112 |
+
"learning_rate": 4.81578947368421e-05,
|
| 2113 |
+
"loss": 0.0064,
|
| 2114 |
+
"step": 8475
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 75.22,
|
| 2118 |
+
"learning_rate": 4.7368421052631574e-05,
|
| 2119 |
+
"loss": 0.0058,
|
| 2120 |
+
"step": 8500
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 75.44,
|
| 2124 |
+
"learning_rate": 4.657894736842105e-05,
|
| 2125 |
+
"loss": 0.0059,
|
| 2126 |
+
"step": 8525
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 75.66,
|
| 2130 |
+
"learning_rate": 4.578947368421052e-05,
|
| 2131 |
+
"loss": 0.0064,
|
| 2132 |
+
"step": 8550
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 75.88,
|
| 2136 |
+
"learning_rate": 4.4999999999999996e-05,
|
| 2137 |
+
"loss": 0.0085,
|
| 2138 |
+
"step": 8575
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 76.11,
|
| 2142 |
+
"learning_rate": 4.4210526315789466e-05,
|
| 2143 |
+
"loss": 0.0065,
|
| 2144 |
+
"step": 8600
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 76.33,
|
| 2148 |
+
"learning_rate": 4.342105263157895e-05,
|
| 2149 |
+
"loss": 0.0068,
|
| 2150 |
+
"step": 8625
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 76.55,
|
| 2154 |
+
"learning_rate": 4.263157894736842e-05,
|
| 2155 |
+
"loss": 0.0084,
|
| 2156 |
+
"step": 8650
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 76.77,
|
| 2160 |
+
"learning_rate": 4.184210526315789e-05,
|
| 2161 |
+
"loss": 0.0049,
|
| 2162 |
+
"step": 8675
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 76.99,
|
| 2166 |
+
"learning_rate": 4.105263157894737e-05,
|
| 2167 |
+
"loss": 0.0055,
|
| 2168 |
+
"step": 8700
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 77.21,
|
| 2172 |
+
"learning_rate": 4.026315789473684e-05,
|
| 2173 |
+
"loss": 0.0077,
|
| 2174 |
+
"step": 8725
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 77.43,
|
| 2178 |
+
"learning_rate": 3.947368421052631e-05,
|
| 2179 |
+
"loss": 0.0071,
|
| 2180 |
+
"step": 8750
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 77.65,
|
| 2184 |
+
"learning_rate": 3.868421052631579e-05,
|
| 2185 |
+
"loss": 0.005,
|
| 2186 |
+
"step": 8775
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 77.88,
|
| 2190 |
+
"learning_rate": 3.789473684210526e-05,
|
| 2191 |
+
"loss": 0.0066,
|
| 2192 |
+
"step": 8800
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 78.1,
|
| 2196 |
+
"learning_rate": 3.710526315789473e-05,
|
| 2197 |
+
"loss": 0.0067,
|
| 2198 |
+
"step": 8825
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 78.32,
|
| 2202 |
+
"learning_rate": 3.631578947368421e-05,
|
| 2203 |
+
"loss": 0.0058,
|
| 2204 |
+
"step": 8850
|
| 2205 |
+
},
|
| 2206 |
+
{
|
| 2207 |
+
"epoch": 78.54,
|
| 2208 |
+
"learning_rate": 3.552631578947368e-05,
|
| 2209 |
+
"loss": 0.004,
|
| 2210 |
+
"step": 8875
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 78.76,
|
| 2214 |
+
"learning_rate": 3.4736842105263153e-05,
|
| 2215 |
+
"loss": 0.0044,
|
| 2216 |
+
"step": 8900
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 78.98,
|
| 2220 |
+
"learning_rate": 3.394736842105263e-05,
|
| 2221 |
+
"loss": 0.0052,
|
| 2222 |
+
"step": 8925
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 79.2,
|
| 2226 |
+
"learning_rate": 3.31578947368421e-05,
|
| 2227 |
+
"loss": 0.0058,
|
| 2228 |
+
"step": 8950
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 79.42,
|
| 2232 |
+
"learning_rate": 3.2368421052631575e-05,
|
| 2233 |
+
"loss": 0.0063,
|
| 2234 |
+
"step": 8975
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 79.65,
|
| 2238 |
+
"learning_rate": 3.1578947368421045e-05,
|
| 2239 |
+
"loss": 0.0058,
|
| 2240 |
+
"step": 9000
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 79.65,
|
| 2244 |
+
"eval_loss": 0.31133854389190674,
|
| 2245 |
+
"eval_runtime": 10.8234,
|
| 2246 |
+
"eval_samples_per_second": 9.239,
|
| 2247 |
+
"eval_steps_per_second": 1.201,
|
| 2248 |
+
"eval_wer": 0.065048427597752,
|
| 2249 |
+
"step": 9000
|
| 2250 |
}
|
| 2251 |
],
|
| 2252 |
"max_steps": 10000,
|
| 2253 |
"num_train_epochs": 89,
|
| 2254 |
+
"total_flos": 3.5456385787518284e+19,
|
| 2255 |
"trial_name": null,
|
| 2256 |
"trial_params": null
|
| 2257 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262229869
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c2f9145d655487602d0119001d797a278a1eb42e4a3b0bd88e042a0adbe3136
|
| 3 |
size 1262229869
|
runs/Apr09_14-45-21_gpu07.cyverse.org/events.out.tfevents.1681076808.gpu07.cyverse.org.48142.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d5ae4f462216938e728a8fba4681e7f5455b3d2c2795cb02eb92e4c0cd05237
|
| 3 |
+
size 64764
|