Upload folder using huggingface_hub
Browse files
logs/test_checkpoint_results.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"checkpoint": "qwen25_coder_15b_l4/checkpoint-100",
|
| 4 |
+
"step": 100,
|
| 5 |
+
"test_loss": 0.8084650635719299
|
| 6 |
+
},
|
| 7 |
+
{
|
| 8 |
+
"checkpoint": "qwen25_coder_15b_l4/checkpoint-200",
|
| 9 |
+
"step": 200,
|
| 10 |
+
"test_loss": 0.6265722513198853
|
| 11 |
+
},
|
| 12 |
+
{
|
| 13 |
+
"checkpoint": "qwen25_coder_15b_l4/checkpoint-300",
|
| 14 |
+
"step": 300,
|
| 15 |
+
"test_loss": 0.44794780015945435
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"checkpoint": "qwen25_coder_15b_l4/checkpoint-400",
|
| 19 |
+
"step": 400,
|
| 20 |
+
"test_loss": 0.3127075731754303
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"checkpoint": "qwen25_coder_15b_l4/checkpoint-500",
|
| 24 |
+
"step": 500,
|
| 25 |
+
"test_loss": 0.21881423890590668
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"checkpoint": "qwen25_coder_15b_l4/checkpoint-600",
|
| 29 |
+
"step": 600,
|
| 30 |
+
"test_loss": 0.1875201165676117
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"checkpoint": "qwen25_coder_15b_l4/checkpoint-700",
|
| 34 |
+
"step": 700,
|
| 35 |
+
"test_loss": 0.1734929233789444
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"checkpoint": "qwen25_coder_15b_l4/checkpoint-750",
|
| 39 |
+
"step": 750,
|
| 40 |
+
"test_loss": 0.17274102568626404
|
| 41 |
+
}
|
| 42 |
+
]
|
logs/training_validation_logs.json
ADDED
|
@@ -0,0 +1,317 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"epoch": 0.08,
|
| 4 |
+
"grad_norm": 0.28229808807373047,
|
| 5 |
+
"learning_rate": 0.0003304347826086957,
|
| 6 |
+
"loss": 1.0758,
|
| 7 |
+
"step": 20
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"epoch": 0.16,
|
| 11 |
+
"grad_norm": 0.3910837173461914,
|
| 12 |
+
"learning_rate": 0.0003995221430894122,
|
| 13 |
+
"loss": 0.9148,
|
| 14 |
+
"step": 40
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.24,
|
| 18 |
+
"grad_norm": 0.37663960456848145,
|
| 19 |
+
"learning_rate": 0.00039758476229578745,
|
| 20 |
+
"loss": 0.8888,
|
| 21 |
+
"step": 60
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.32,
|
| 25 |
+
"grad_norm": 0.2441498339176178,
|
| 26 |
+
"learning_rate": 0.0003941724426452488,
|
| 27 |
+
"loss": 0.8392,
|
| 28 |
+
"step": 80
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.4,
|
| 32 |
+
"grad_norm": 0.32805338501930237,
|
| 33 |
+
"learning_rate": 0.0003893106565618147,
|
| 34 |
+
"loss": 0.8178,
|
| 35 |
+
"step": 100
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.4,
|
| 39 |
+
"eval_loss": 0.8086594939231873,
|
| 40 |
+
"eval_runtime": 19.7643,
|
| 41 |
+
"eval_samples_per_second": 25.298,
|
| 42 |
+
"eval_steps_per_second": 3.188,
|
| 43 |
+
"step": 100
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.48,
|
| 47 |
+
"grad_norm": 0.32320863008499146,
|
| 48 |
+
"learning_rate": 0.0003830356965061241,
|
| 49 |
+
"loss": 0.7901,
|
| 50 |
+
"step": 120
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.56,
|
| 54 |
+
"grad_norm": 0.35026517510414124,
|
| 55 |
+
"learning_rate": 0.0003753944040579839,
|
| 56 |
+
"loss": 0.7661,
|
| 57 |
+
"step": 140
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.64,
|
| 61 |
+
"grad_norm": 0.3722197115421295,
|
| 62 |
+
"learning_rate": 0.00036644382025141837,
|
| 63 |
+
"loss": 0.7126,
|
| 64 |
+
"step": 160
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.72,
|
| 68 |
+
"grad_norm": 0.4616721570491791,
|
| 69 |
+
"learning_rate": 0.0003562507597724135,
|
| 70 |
+
"loss": 0.6517,
|
| 71 |
+
"step": 180
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.8,
|
| 75 |
+
"grad_norm": 0.40086525678634644,
|
| 76 |
+
"learning_rate": 0.0003448913121979015,
|
| 77 |
+
"loss": 0.6215,
|
| 78 |
+
"step": 200
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.8,
|
| 82 |
+
"eval_loss": 0.6392109394073486,
|
| 83 |
+
"eval_runtime": 19.766,
|
| 84 |
+
"eval_samples_per_second": 25.296,
|
| 85 |
+
"eval_steps_per_second": 3.187,
|
| 86 |
+
"step": 200
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.88,
|
| 90 |
+
"grad_norm": 0.4292043447494507,
|
| 91 |
+
"learning_rate": 0.00033245027399915895,
|
| 92 |
+
"loss": 0.5898,
|
| 93 |
+
"step": 220
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.96,
|
| 97 |
+
"grad_norm": 0.5536438226699829,
|
| 98 |
+
"learning_rate": 0.0003190205155496219,
|
| 99 |
+
"loss": 0.5709,
|
| 100 |
+
"step": 240
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.04,
|
| 104 |
+
"grad_norm": 0.6616698503494263,
|
| 105 |
+
"learning_rate": 0.00030470228786230405,
|
| 106 |
+
"loss": 0.4551,
|
| 107 |
+
"step": 260
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.12,
|
| 111 |
+
"grad_norm": 0.5763731598854065,
|
| 112 |
+
"learning_rate": 0.0002896024742319127,
|
| 113 |
+
"loss": 0.3672,
|
| 114 |
+
"step": 280
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.2,
|
| 118 |
+
"grad_norm": 0.5821401476860046,
|
| 119 |
+
"learning_rate": 0.0002738337923680367,
|
| 120 |
+
"loss": 0.3648,
|
| 121 |
+
"step": 300
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.2,
|
| 125 |
+
"eval_loss": 0.4687094986438751,
|
| 126 |
+
"eval_runtime": 19.7698,
|
| 127 |
+
"eval_samples_per_second": 25.291,
|
| 128 |
+
"eval_steps_per_second": 3.187,
|
| 129 |
+
"step": 300
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.28,
|
| 133 |
+
"grad_norm": 0.47784799337387085,
|
| 134 |
+
"learning_rate": 0.00025751395297535327,
|
| 135 |
+
"loss": 0.3424,
|
| 136 |
+
"step": 320
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.3599999999999999,
|
| 140 |
+
"grad_norm": 0.5968295931816101,
|
| 141 |
+
"learning_rate": 0.00024076478106192076,
|
| 142 |
+
"loss": 0.3253,
|
| 143 |
+
"step": 340
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.44,
|
| 147 |
+
"grad_norm": 0.5316683053970337,
|
| 148 |
+
"learning_rate": 0.00022371130653484945,
|
| 149 |
+
"loss": 0.2952,
|
| 150 |
+
"step": 360
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.52,
|
| 154 |
+
"grad_norm": 0.4502660930156708,
|
| 155 |
+
"learning_rate": 0.0002064808308719107,
|
| 156 |
+
"loss": 0.2728,
|
| 157 |
+
"step": 380
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.6,
|
| 161 |
+
"grad_norm": 0.512885570526123,
|
| 162 |
+
"learning_rate": 0.00018920197683623203,
|
| 163 |
+
"loss": 0.2615,
|
| 164 |
+
"step": 400
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.6,
|
| 168 |
+
"eval_loss": 0.3294866383075714,
|
| 169 |
+
"eval_runtime": 19.7741,
|
| 170 |
+
"eval_samples_per_second": 25.286,
|
| 171 |
+
"eval_steps_per_second": 3.186,
|
| 172 |
+
"step": 400
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.6800000000000002,
|
| 176 |
+
"grad_norm": 0.510636568069458,
|
| 177 |
+
"learning_rate": 0.00017200372832780684,
|
| 178 |
+
"loss": 0.2468,
|
| 179 |
+
"step": 420
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.76,
|
| 183 |
+
"grad_norm": 0.38415294885635376,
|
| 184 |
+
"learning_rate": 0.00015501446753917467,
|
| 185 |
+
"loss": 0.2153,
|
| 186 |
+
"step": 440
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.8399999999999999,
|
| 190 |
+
"grad_norm": 0.4481910765171051,
|
| 191 |
+
"learning_rate": 0.00013836101660275217,
|
| 192 |
+
"loss": 0.1996,
|
| 193 |
+
"step": 460
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.92,
|
| 197 |
+
"grad_norm": 0.516516387462616,
|
| 198 |
+
"learning_rate": 0.000122167690883765,
|
| 199 |
+
"loss": 0.1803,
|
| 200 |
+
"step": 480
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.0,
|
| 204 |
+
"grad_norm": 0.5795238018035889,
|
| 205 |
+
"learning_rate": 0.00010655537098579868,
|
| 206 |
+
"loss": 0.1915,
|
| 207 |
+
"step": 500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.0,
|
| 211 |
+
"eval_loss": 0.2246081531047821,
|
| 212 |
+
"eval_runtime": 19.7628,
|
| 213 |
+
"eval_samples_per_second": 25.3,
|
| 214 |
+
"eval_steps_per_second": 3.188,
|
| 215 |
+
"step": 500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.08,
|
| 219 |
+
"grad_norm": 0.46038225293159485,
|
| 220 |
+
"learning_rate": 9.164060039629896e-05,
|
| 221 |
+
"loss": 0.1179,
|
| 222 |
+
"step": 520
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.16,
|
| 226 |
+
"grad_norm": 0.43895432353019714,
|
| 227 |
+
"learning_rate": 7.753471550795519e-05,
|
| 228 |
+
"loss": 0.1153,
|
| 229 |
+
"step": 540
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.24,
|
| 233 |
+
"grad_norm": 0.7098507285118103,
|
| 234 |
+
"learning_rate": 6.434301451021892e-05,
|
| 235 |
+
"loss": 0.1261,
|
| 236 |
+
"step": 560
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.32,
|
| 240 |
+
"grad_norm": 0.3989202082157135,
|
| 241 |
+
"learning_rate": 5.216397135505024e-05,
|
| 242 |
+
"loss": 0.1121,
|
| 243 |
+
"step": 580
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.4,
|
| 247 |
+
"grad_norm": 0.525729775428772,
|
| 248 |
+
"learning_rate": 4.108850066451255e-05,
|
| 249 |
+
"loss": 0.1186,
|
| 250 |
+
"step": 600
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.4,
|
| 254 |
+
"eval_loss": 0.19236330687999725,
|
| 255 |
+
"eval_runtime": 19.7599,
|
| 256 |
+
"eval_samples_per_second": 25.304,
|
| 257 |
+
"eval_steps_per_second": 3.188,
|
| 258 |
+
"step": 600
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.48,
|
| 262 |
+
"grad_norm": 0.33528250455856323,
|
| 263 |
+
"learning_rate": 3.1199279067563706e-05,
|
| 264 |
+
"loss": 0.1075,
|
| 265 |
+
"step": 620
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.56,
|
| 269 |
+
"grad_norm": 0.35482296347618103,
|
| 270 |
+
"learning_rate": 2.2570128032157568e-05,
|
| 271 |
+
"loss": 0.1106,
|
| 272 |
+
"step": 640
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.64,
|
| 276 |
+
"grad_norm": 0.2427404522895813,
|
| 277 |
+
"learning_rate": 1.526546279971466e-05,
|
| 278 |
+
"loss": 0.0932,
|
| 279 |
+
"step": 660
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.7199999999999998,
|
| 283 |
+
"grad_norm": 0.27014562487602234,
|
| 284 |
+
"learning_rate": 9.339811535579768e-06,
|
| 285 |
+
"loss": 0.1005,
|
| 286 |
+
"step": 680
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 2.8,
|
| 290 |
+
"grad_norm": 0.3576093018054962,
|
| 291 |
+
"learning_rate": 4.837408284931444e-06,
|
| 292 |
+
"loss": 0.0948,
|
| 293 |
+
"step": 700
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.8,
|
| 297 |
+
"eval_loss": 0.17951039969921112,
|
| 298 |
+
"eval_runtime": 19.7723,
|
| 299 |
+
"eval_samples_per_second": 25.288,
|
| 300 |
+
"eval_steps_per_second": 3.186,
|
| 301 |
+
"step": 700
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.88,
|
| 305 |
+
"grad_norm": 0.3262103199958801,
|
| 306 |
+
"learning_rate": 1.7918627726630777e-06,
|
| 307 |
+
"loss": 0.0939,
|
| 308 |
+
"step": 720
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.96,
|
| 312 |
+
"grad_norm": 0.2655605971813202,
|
| 313 |
+
"learning_rate": 2.259095121265542e-07,
|
| 314 |
+
"loss": 0.0953,
|
| 315 |
+
"step": 740
|
| 316 |
+
}
|
| 317 |
+
]
|