Upload 11 files
Browse files- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +252 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:872d7b9701d8d7b2a9df16eb5c7940013ae4c0ab32d96039b3651ba65e7c70ba
|
| 3 |
+
size 150346986
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97e92e08cd1c210745787fb53c3aec8b820b463c1f5d67263a0c4fecb69f69ca
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b2e7f09e07aa3c7be669ba27bfff15efcc0eca70c4fe2d063cc724177dea8a7
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,252 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.986425339366516,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 330,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09,
|
| 13 |
+
"grad_norm": 14.758803367614746,
|
| 14 |
+
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 23.3472,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.18,
|
| 20 |
+
"grad_norm": 59.627952575683594,
|
| 21 |
+
"learning_rate": 0.0002,
|
| 22 |
+
"loss": 15.2238,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.27,
|
| 27 |
+
"grad_norm": 4.7137131690979,
|
| 28 |
+
"learning_rate": 0.0002,
|
| 29 |
+
"loss": 2.488,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.36,
|
| 34 |
+
"grad_norm": 1.8212027549743652,
|
| 35 |
+
"learning_rate": 0.0002,
|
| 36 |
+
"loss": 1.0811,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.45,
|
| 41 |
+
"grad_norm": 2.546755313873291,
|
| 42 |
+
"learning_rate": 0.0002,
|
| 43 |
+
"loss": 0.8055,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.54,
|
| 48 |
+
"grad_norm": 1.0168941020965576,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 0.705,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.63,
|
| 55 |
+
"grad_norm": 0.9273145794868469,
|
| 56 |
+
"learning_rate": 0.0002,
|
| 57 |
+
"loss": 0.6457,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.72,
|
| 62 |
+
"grad_norm": 0.7880547642707825,
|
| 63 |
+
"learning_rate": 0.0002,
|
| 64 |
+
"loss": 0.5931,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.81,
|
| 69 |
+
"grad_norm": 0.8284961581230164,
|
| 70 |
+
"learning_rate": 0.0002,
|
| 71 |
+
"loss": 0.5887,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.9,
|
| 76 |
+
"grad_norm": 1.7326173782348633,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 0.5627,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.0,
|
| 83 |
+
"grad_norm": 1.3316080570220947,
|
| 84 |
+
"learning_rate": 0.0002,
|
| 85 |
+
"loss": 0.5699,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.09,
|
| 90 |
+
"grad_norm": 0.7548896074295044,
|
| 91 |
+
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 0.5371,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.18,
|
| 97 |
+
"grad_norm": 0.612474262714386,
|
| 98 |
+
"learning_rate": 0.0002,
|
| 99 |
+
"loss": 0.479,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.27,
|
| 104 |
+
"grad_norm": 0.8262041807174683,
|
| 105 |
+
"learning_rate": 0.0002,
|
| 106 |
+
"loss": 0.5065,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.36,
|
| 111 |
+
"grad_norm": 0.9287819862365723,
|
| 112 |
+
"learning_rate": 0.0002,
|
| 113 |
+
"loss": 0.4441,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.45,
|
| 118 |
+
"grad_norm": 0.7204004526138306,
|
| 119 |
+
"learning_rate": 0.0002,
|
| 120 |
+
"loss": 0.5144,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.54,
|
| 125 |
+
"grad_norm": 0.5320543646812439,
|
| 126 |
+
"learning_rate": 0.0002,
|
| 127 |
+
"loss": 0.4624,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.63,
|
| 132 |
+
"grad_norm": 0.5815476775169373,
|
| 133 |
+
"learning_rate": 0.0002,
|
| 134 |
+
"loss": 0.4536,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.72,
|
| 139 |
+
"grad_norm": 0.4539355933666229,
|
| 140 |
+
"learning_rate": 0.0002,
|
| 141 |
+
"loss": 0.5108,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.81,
|
| 146 |
+
"grad_norm": 0.8424472212791443,
|
| 147 |
+
"learning_rate": 0.0002,
|
| 148 |
+
"loss": 0.4603,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.9,
|
| 153 |
+
"grad_norm": 0.485895574092865,
|
| 154 |
+
"learning_rate": 0.0002,
|
| 155 |
+
"loss": 0.4843,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.99,
|
| 160 |
+
"grad_norm": 0.4039005935192108,
|
| 161 |
+
"learning_rate": 0.0002,
|
| 162 |
+
"loss": 0.4872,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.08,
|
| 167 |
+
"grad_norm": 1.0310947895050049,
|
| 168 |
+
"learning_rate": 0.0002,
|
| 169 |
+
"loss": 0.3785,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.17,
|
| 174 |
+
"grad_norm": 0.635901153087616,
|
| 175 |
+
"learning_rate": 0.0002,
|
| 176 |
+
"loss": 0.3905,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.26,
|
| 181 |
+
"grad_norm": 0.38871026039123535,
|
| 182 |
+
"learning_rate": 0.0002,
|
| 183 |
+
"loss": 0.3745,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.35,
|
| 188 |
+
"grad_norm": 0.5501377582550049,
|
| 189 |
+
"learning_rate": 0.0002,
|
| 190 |
+
"loss": 0.3759,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.44,
|
| 195 |
+
"grad_norm": 0.6457089781761169,
|
| 196 |
+
"learning_rate": 0.0002,
|
| 197 |
+
"loss": 0.394,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.53,
|
| 202 |
+
"grad_norm": 0.8598196506500244,
|
| 203 |
+
"learning_rate": 0.0002,
|
| 204 |
+
"loss": 0.3909,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.62,
|
| 209 |
+
"grad_norm": 0.5458590984344482,
|
| 210 |
+
"learning_rate": 0.0002,
|
| 211 |
+
"loss": 0.3725,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.71,
|
| 216 |
+
"grad_norm": 0.6310967803001404,
|
| 217 |
+
"learning_rate": 0.0002,
|
| 218 |
+
"loss": 0.3884,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.81,
|
| 223 |
+
"grad_norm": 1.0128086805343628,
|
| 224 |
+
"learning_rate": 0.0002,
|
| 225 |
+
"loss": 0.3829,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.9,
|
| 230 |
+
"grad_norm": 0.5322939157485962,
|
| 231 |
+
"learning_rate": 0.0002,
|
| 232 |
+
"loss": 0.3866,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.99,
|
| 237 |
+
"grad_norm": 0.5951926708221436,
|
| 238 |
+
"learning_rate": 0.0002,
|
| 239 |
+
"loss": 0.3494,
|
| 240 |
+
"step": 330
|
| 241 |
+
}
|
| 242 |
+
],
|
| 243 |
+
"logging_steps": 10,
|
| 244 |
+
"max_steps": 330,
|
| 245 |
+
"num_input_tokens_seen": 0,
|
| 246 |
+
"num_train_epochs": 3,
|
| 247 |
+
"save_steps": 500,
|
| 248 |
+
"total_flos": 9.290508651144806e+16,
|
| 249 |
+
"train_batch_size": 2,
|
| 250 |
+
"trial_name": null,
|
| 251 |
+
"trial_params": null
|
| 252 |
+
}
|