Training in progress, step 32000, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3555504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f5cafd52307ebb0d4ad02660f4fa895f4176ab48ccb18d8698902129b3b1209
|
| 3 |
size 3555504
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7141515
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26d3696bade1cccaee17e0a3be137fdd3e3380bab51d20a657d51f20328ef6ef
|
| 3 |
size 7141515
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:819540c05377c6a98947b46ab098a8f4456dd635badbf1ea38d292430af1a819
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d960d60d0c4ed45cc4422d14d1920d93529483656b6082492613ed8fd865f5f
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25361f5602fa6c5f9d3627497e44e73d38bd7e5fabd543717ca1fb3c15c5a95b
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 4000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -2052,6 +2052,298 @@
|
|
| 2052 |
"eval_samples_per_second": 128.429,
|
| 2053 |
"eval_steps_per_second": 8.027,
|
| 2054 |
"step": 28000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2055 |
}
|
| 2056 |
],
|
| 2057 |
"logging_steps": 100,
|
|
@@ -2080,7 +2372,7 @@
|
|
| 2080 |
"attributes": {}
|
| 2081 |
}
|
| 2082 |
},
|
| 2083 |
-
"total_flos": 1.
|
| 2084 |
"train_batch_size": 16,
|
| 2085 |
"trial_name": null,
|
| 2086 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 32000,
|
| 3 |
+
"best_metric": 0.9879419419991998,
|
| 4 |
+
"best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-32000",
|
| 5 |
+
"epoch": 1.024,
|
| 6 |
"eval_steps": 4000,
|
| 7 |
+
"global_step": 32000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2052 |
"eval_samples_per_second": 128.429,
|
| 2053 |
"eval_steps_per_second": 8.027,
|
| 2054 |
"step": 28000
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.8992,
|
| 2058 |
+
"grad_norm": 0.008244618773460388,
|
| 2059 |
+
"learning_rate": 1.6455987158908508e-05,
|
| 2060 |
+
"loss": 0.041,
|
| 2061 |
+
"step": 28100
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.9024,
|
| 2065 |
+
"grad_norm": 0.01580977439880371,
|
| 2066 |
+
"learning_rate": 1.6443146067415733e-05,
|
| 2067 |
+
"loss": 0.057,
|
| 2068 |
+
"step": 28200
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.9056,
|
| 2072 |
+
"grad_norm": 10.525986671447754,
|
| 2073 |
+
"learning_rate": 1.6430304975922954e-05,
|
| 2074 |
+
"loss": 0.0322,
|
| 2075 |
+
"step": 28300
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.9088,
|
| 2079 |
+
"grad_norm": 0.016806138679385185,
|
| 2080 |
+
"learning_rate": 1.641746388443018e-05,
|
| 2081 |
+
"loss": 0.0523,
|
| 2082 |
+
"step": 28400
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.912,
|
| 2086 |
+
"grad_norm": 6.311640739440918,
|
| 2087 |
+
"learning_rate": 1.64046227929374e-05,
|
| 2088 |
+
"loss": 0.0497,
|
| 2089 |
+
"step": 28500
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.9152,
|
| 2093 |
+
"grad_norm": 0.09537007659673691,
|
| 2094 |
+
"learning_rate": 1.6391781701444625e-05,
|
| 2095 |
+
"loss": 0.0523,
|
| 2096 |
+
"step": 28600
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.9184,
|
| 2100 |
+
"grad_norm": 0.010998793877661228,
|
| 2101 |
+
"learning_rate": 1.6378940609951847e-05,
|
| 2102 |
+
"loss": 0.0481,
|
| 2103 |
+
"step": 28700
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.9216,
|
| 2107 |
+
"grad_norm": 0.24172453582286835,
|
| 2108 |
+
"learning_rate": 1.636609951845907e-05,
|
| 2109 |
+
"loss": 0.0537,
|
| 2110 |
+
"step": 28800
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.9248,
|
| 2114 |
+
"grad_norm": 0.00843421183526516,
|
| 2115 |
+
"learning_rate": 1.6353258426966293e-05,
|
| 2116 |
+
"loss": 0.0345,
|
| 2117 |
+
"step": 28900
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.928,
|
| 2121 |
+
"grad_norm": 26.664979934692383,
|
| 2122 |
+
"learning_rate": 1.6340417335473518e-05,
|
| 2123 |
+
"loss": 0.0667,
|
| 2124 |
+
"step": 29000
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.9312,
|
| 2128 |
+
"grad_norm": 0.3694003224372864,
|
| 2129 |
+
"learning_rate": 1.632757624398074e-05,
|
| 2130 |
+
"loss": 0.0555,
|
| 2131 |
+
"step": 29100
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.9344,
|
| 2135 |
+
"grad_norm": 24.855958938598633,
|
| 2136 |
+
"learning_rate": 1.6314735152487964e-05,
|
| 2137 |
+
"loss": 0.058,
|
| 2138 |
+
"step": 29200
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.9376,
|
| 2142 |
+
"grad_norm": 2.051378011703491,
|
| 2143 |
+
"learning_rate": 1.6301894060995186e-05,
|
| 2144 |
+
"loss": 0.0427,
|
| 2145 |
+
"step": 29300
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.9408,
|
| 2149 |
+
"grad_norm": 0.8996158838272095,
|
| 2150 |
+
"learning_rate": 1.6289052969502407e-05,
|
| 2151 |
+
"loss": 0.0462,
|
| 2152 |
+
"step": 29400
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.944,
|
| 2156 |
+
"grad_norm": 14.316937446594238,
|
| 2157 |
+
"learning_rate": 1.6276211878009632e-05,
|
| 2158 |
+
"loss": 0.0658,
|
| 2159 |
+
"step": 29500
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.9472,
|
| 2163 |
+
"grad_norm": 11.959718704223633,
|
| 2164 |
+
"learning_rate": 1.6263370786516853e-05,
|
| 2165 |
+
"loss": 0.0396,
|
| 2166 |
+
"step": 29600
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.9504,
|
| 2170 |
+
"grad_norm": 0.015293744392693043,
|
| 2171 |
+
"learning_rate": 1.6250529695024078e-05,
|
| 2172 |
+
"loss": 0.0489,
|
| 2173 |
+
"step": 29700
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.9536,
|
| 2177 |
+
"grad_norm": 14.037763595581055,
|
| 2178 |
+
"learning_rate": 1.62376886035313e-05,
|
| 2179 |
+
"loss": 0.0746,
|
| 2180 |
+
"step": 29800
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.9568,
|
| 2184 |
+
"grad_norm": 0.04080112278461456,
|
| 2185 |
+
"learning_rate": 1.6224847512038524e-05,
|
| 2186 |
+
"loss": 0.0612,
|
| 2187 |
+
"step": 29900
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.96,
|
| 2191 |
+
"grad_norm": 0.06590835005044937,
|
| 2192 |
+
"learning_rate": 1.6212006420545746e-05,
|
| 2193 |
+
"loss": 0.0597,
|
| 2194 |
+
"step": 30000
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.9632,
|
| 2198 |
+
"grad_norm": 8.91706657409668,
|
| 2199 |
+
"learning_rate": 1.619916532905297e-05,
|
| 2200 |
+
"loss": 0.0489,
|
| 2201 |
+
"step": 30100
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.9664,
|
| 2205 |
+
"grad_norm": 0.019029080867767334,
|
| 2206 |
+
"learning_rate": 1.6186324237560192e-05,
|
| 2207 |
+
"loss": 0.0572,
|
| 2208 |
+
"step": 30200
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.9696,
|
| 2212 |
+
"grad_norm": 4.674193382263184,
|
| 2213 |
+
"learning_rate": 1.6173483146067417e-05,
|
| 2214 |
+
"loss": 0.0587,
|
| 2215 |
+
"step": 30300
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.9728,
|
| 2219 |
+
"grad_norm": 0.14981134235858917,
|
| 2220 |
+
"learning_rate": 1.6160642054574642e-05,
|
| 2221 |
+
"loss": 0.0323,
|
| 2222 |
+
"step": 30400
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.976,
|
| 2226 |
+
"grad_norm": 4.462047100067139,
|
| 2227 |
+
"learning_rate": 1.6147800963081863e-05,
|
| 2228 |
+
"loss": 0.053,
|
| 2229 |
+
"step": 30500
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.9792,
|
| 2233 |
+
"grad_norm": 0.10449015349149704,
|
| 2234 |
+
"learning_rate": 1.6134959871589088e-05,
|
| 2235 |
+
"loss": 0.0465,
|
| 2236 |
+
"step": 30600
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.9824,
|
| 2240 |
+
"grad_norm": 1.134883999824524,
|
| 2241 |
+
"learning_rate": 1.612211878009631e-05,
|
| 2242 |
+
"loss": 0.0534,
|
| 2243 |
+
"step": 30700
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.9856,
|
| 2247 |
+
"grad_norm": 21.06899070739746,
|
| 2248 |
+
"learning_rate": 1.6109277688603534e-05,
|
| 2249 |
+
"loss": 0.0515,
|
| 2250 |
+
"step": 30800
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.9888,
|
| 2254 |
+
"grad_norm": 20.929187774658203,
|
| 2255 |
+
"learning_rate": 1.6096436597110756e-05,
|
| 2256 |
+
"loss": 0.046,
|
| 2257 |
+
"step": 30900
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.992,
|
| 2261 |
+
"grad_norm": 0.008979029022157192,
|
| 2262 |
+
"learning_rate": 1.608359550561798e-05,
|
| 2263 |
+
"loss": 0.0288,
|
| 2264 |
+
"step": 31000
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.9952,
|
| 2268 |
+
"grad_norm": 10.832496643066406,
|
| 2269 |
+
"learning_rate": 1.6070754414125202e-05,
|
| 2270 |
+
"loss": 0.0533,
|
| 2271 |
+
"step": 31100
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.9984,
|
| 2275 |
+
"grad_norm": 10.279513359069824,
|
| 2276 |
+
"learning_rate": 1.6057913322632427e-05,
|
| 2277 |
+
"loss": 0.0535,
|
| 2278 |
+
"step": 31200
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 1.0016,
|
| 2282 |
+
"grad_norm": 0.050070084631443024,
|
| 2283 |
+
"learning_rate": 1.6045072231139648e-05,
|
| 2284 |
+
"loss": 0.0488,
|
| 2285 |
+
"step": 31300
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 1.0048,
|
| 2289 |
+
"grad_norm": 7.610085964202881,
|
| 2290 |
+
"learning_rate": 1.6032231139646873e-05,
|
| 2291 |
+
"loss": 0.0499,
|
| 2292 |
+
"step": 31400
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 1.008,
|
| 2296 |
+
"grad_norm": 0.03847907483577728,
|
| 2297 |
+
"learning_rate": 1.6019390048154095e-05,
|
| 2298 |
+
"loss": 0.0668,
|
| 2299 |
+
"step": 31500
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 1.0112,
|
| 2303 |
+
"grad_norm": 0.009822272695600986,
|
| 2304 |
+
"learning_rate": 1.600654895666132e-05,
|
| 2305 |
+
"loss": 0.0403,
|
| 2306 |
+
"step": 31600
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 1.0144,
|
| 2310 |
+
"grad_norm": 0.1967863291501999,
|
| 2311 |
+
"learning_rate": 1.599370786516854e-05,
|
| 2312 |
+
"loss": 0.0565,
|
| 2313 |
+
"step": 31700
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 1.0176,
|
| 2317 |
+
"grad_norm": 8.522165298461914,
|
| 2318 |
+
"learning_rate": 1.5980866773675762e-05,
|
| 2319 |
+
"loss": 0.0298,
|
| 2320 |
+
"step": 31800
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 1.0208,
|
| 2324 |
+
"grad_norm": 0.7742573618888855,
|
| 2325 |
+
"learning_rate": 1.5968025682182987e-05,
|
| 2326 |
+
"loss": 0.0411,
|
| 2327 |
+
"step": 31900
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 1.024,
|
| 2331 |
+
"grad_norm": 0.07143627107143402,
|
| 2332 |
+
"learning_rate": 1.595518459069021e-05,
|
| 2333 |
+
"loss": 0.0477,
|
| 2334 |
+
"step": 32000
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 1.024,
|
| 2338 |
+
"eval_accuracy": 0.98794,
|
| 2339 |
+
"eval_f1": 0.9879419419991998,
|
| 2340 |
+
"eval_loss": 0.04801899939775467,
|
| 2341 |
+
"eval_precision": 0.9879724568651884,
|
| 2342 |
+
"eval_recall": 0.98794,
|
| 2343 |
+
"eval_runtime": 775.4534,
|
| 2344 |
+
"eval_samples_per_second": 128.957,
|
| 2345 |
+
"eval_steps_per_second": 8.06,
|
| 2346 |
+
"step": 32000
|
| 2347 |
}
|
| 2348 |
],
|
| 2349 |
"logging_steps": 100,
|
|
|
|
| 2372 |
"attributes": {}
|
| 2373 |
}
|
| 2374 |
},
|
| 2375 |
+
"total_flos": 1.3588330900845235e+17,
|
| 2376 |
"train_batch_size": 16,
|
| 2377 |
"trial_name": null,
|
| 2378 |
"trial_params": null
|