Training in progress, epoch 0
Browse files- adapter_config.json +6 -3
- adapter_model.safetensors +2 -2
- trainer_state.json +254 -0
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -20,10 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"k_proj",
|
| 24 |
-
"q_proj",
|
| 25 |
"o_proj",
|
| 26 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
],
|
| 28 |
"task_type": "CAUSAL_LM",
|
| 29 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
|
|
|
| 23 |
"o_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
adapter_model.safetensors
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:c9a5303cb4d02f961d9e69756e5d867530b63bd93eea0ae84694c5946317e780
|
| 3 |
+
size 39256704
|
trainer_state.json
ADDED
|
@@ -0,0 +1,254 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.770992366412214,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 320,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.3053435114503817,
|
| 13 |
+
"grad_norm": 1.0634765625,
|
| 14 |
+
"learning_rate": 0.0001995184726672197,
|
| 15 |
+
"loss": 1.8094,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.6106870229007634,
|
| 20 |
+
"grad_norm": 0.9521484375,
|
| 21 |
+
"learning_rate": 0.00019807852804032305,
|
| 22 |
+
"loss": 1.1712,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.916030534351145,
|
| 27 |
+
"grad_norm": 2.720703125,
|
| 28 |
+
"learning_rate": 0.0001956940335732209,
|
| 29 |
+
"loss": 1.0862,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.2213740458015268,
|
| 34 |
+
"grad_norm": 2.3515625,
|
| 35 |
+
"learning_rate": 0.0001923879532511287,
|
| 36 |
+
"loss": 0.9789,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.5267175572519083,
|
| 41 |
+
"grad_norm": 0.46435546875,
|
| 42 |
+
"learning_rate": 0.0001881921264348355,
|
| 43 |
+
"loss": 0.8284,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.83206106870229,
|
| 48 |
+
"grad_norm": 2.533203125,
|
| 49 |
+
"learning_rate": 0.00018314696123025454,
|
| 50 |
+
"loss": 0.809,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.1374045801526718,
|
| 55 |
+
"grad_norm": 0.8310546875,
|
| 56 |
+
"learning_rate": 0.0001773010453362737,
|
| 57 |
+
"loss": 0.7111,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.4427480916030535,
|
| 62 |
+
"grad_norm": 4.42578125,
|
| 63 |
+
"learning_rate": 0.00017071067811865476,
|
| 64 |
+
"loss": 0.7286,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.7480916030534353,
|
| 69 |
+
"grad_norm": 0.70947265625,
|
| 70 |
+
"learning_rate": 0.00016343932841636456,
|
| 71 |
+
"loss": 0.7382,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 3.053435114503817,
|
| 76 |
+
"grad_norm": 1.1298828125,
|
| 77 |
+
"learning_rate": 0.00015555702330196023,
|
| 78 |
+
"loss": 0.7349,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 3.3587786259541983,
|
| 83 |
+
"grad_norm": 2.6484375,
|
| 84 |
+
"learning_rate": 0.0001471396736825998,
|
| 85 |
+
"loss": 0.7027,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 3.66412213740458,
|
| 90 |
+
"grad_norm": 0.407958984375,
|
| 91 |
+
"learning_rate": 0.000138268343236509,
|
| 92 |
+
"loss": 0.707,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.969465648854962,
|
| 97 |
+
"grad_norm": 0.427001953125,
|
| 98 |
+
"learning_rate": 0.00012902846772544624,
|
| 99 |
+
"loss": 0.6915,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 4.2748091603053435,
|
| 104 |
+
"grad_norm": 0.34228515625,
|
| 105 |
+
"learning_rate": 0.00011950903220161285,
|
| 106 |
+
"loss": 0.6953,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 4.580152671755725,
|
| 111 |
+
"grad_norm": 0.489990234375,
|
| 112 |
+
"learning_rate": 0.0001098017140329561,
|
| 113 |
+
"loss": 0.6831,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.885496183206107,
|
| 118 |
+
"grad_norm": 0.38525390625,
|
| 119 |
+
"learning_rate": 0.0001,
|
| 120 |
+
"loss": 0.6754,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 5.190839694656488,
|
| 125 |
+
"grad_norm": 0.389892578125,
|
| 126 |
+
"learning_rate": 9.019828596704394e-05,
|
| 127 |
+
"loss": 0.6688,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 5.4961832061068705,
|
| 132 |
+
"grad_norm": 0.467529296875,
|
| 133 |
+
"learning_rate": 8.049096779838719e-05,
|
| 134 |
+
"loss": 0.668,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 5.801526717557252,
|
| 139 |
+
"grad_norm": 0.39794921875,
|
| 140 |
+
"learning_rate": 7.097153227455379e-05,
|
| 141 |
+
"loss": 0.6651,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 6.106870229007634,
|
| 146 |
+
"grad_norm": 0.52294921875,
|
| 147 |
+
"learning_rate": 6.173165676349103e-05,
|
| 148 |
+
"loss": 0.662,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 6.412213740458015,
|
| 153 |
+
"grad_norm": 0.37109375,
|
| 154 |
+
"learning_rate": 5.286032631740023e-05,
|
| 155 |
+
"loss": 0.6603,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 6.717557251908397,
|
| 160 |
+
"grad_norm": 0.354248046875,
|
| 161 |
+
"learning_rate": 4.444297669803981e-05,
|
| 162 |
+
"loss": 0.6439,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 7.022900763358779,
|
| 167 |
+
"grad_norm": 0.43017578125,
|
| 168 |
+
"learning_rate": 3.6560671583635467e-05,
|
| 169 |
+
"loss": 0.6696,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 7.32824427480916,
|
| 174 |
+
"grad_norm": 0.37109375,
|
| 175 |
+
"learning_rate": 2.9289321881345254e-05,
|
| 176 |
+
"loss": 0.6603,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 7.633587786259542,
|
| 181 |
+
"grad_norm": 0.4580078125,
|
| 182 |
+
"learning_rate": 2.26989546637263e-05,
|
| 183 |
+
"loss": 0.6418,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 7.938931297709924,
|
| 188 |
+
"grad_norm": 0.40185546875,
|
| 189 |
+
"learning_rate": 1.6853038769745467e-05,
|
| 190 |
+
"loss": 0.6404,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 8.244274809160306,
|
| 195 |
+
"grad_norm": 0.391357421875,
|
| 196 |
+
"learning_rate": 1.1807873565164506e-05,
|
| 197 |
+
"loss": 0.6574,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 8.549618320610687,
|
| 202 |
+
"grad_norm": 0.383544921875,
|
| 203 |
+
"learning_rate": 7.612046748871327e-06,
|
| 204 |
+
"loss": 0.6405,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 8.854961832061068,
|
| 209 |
+
"grad_norm": 0.358642578125,
|
| 210 |
+
"learning_rate": 4.305966426779118e-06,
|
| 211 |
+
"loss": 0.6382,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 9.16030534351145,
|
| 216 |
+
"grad_norm": 0.365234375,
|
| 217 |
+
"learning_rate": 1.921471959676957e-06,
|
| 218 |
+
"loss": 0.6499,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 9.465648854961833,
|
| 223 |
+
"grad_norm": 0.40673828125,
|
| 224 |
+
"learning_rate": 4.815273327803182e-07,
|
| 225 |
+
"loss": 0.6562,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 9.770992366412214,
|
| 230 |
+
"grad_norm": 0.364013671875,
|
| 231 |
+
"learning_rate": 0.0,
|
| 232 |
+
"loss": 0.6581,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 9.770992366412214,
|
| 237 |
+
"step": 320,
|
| 238 |
+
"total_flos": 1.561516427968512e+16,
|
| 239 |
+
"train_loss": 0.7572343468666076,
|
| 240 |
+
"train_runtime": 291.1608,
|
| 241 |
+
"train_samples_per_second": 4.499,
|
| 242 |
+
"train_steps_per_second": 1.099
|
| 243 |
+
}
|
| 244 |
+
],
|
| 245 |
+
"logging_steps": 10,
|
| 246 |
+
"max_steps": 320,
|
| 247 |
+
"num_input_tokens_seen": 0,
|
| 248 |
+
"num_train_epochs": 10,
|
| 249 |
+
"save_steps": 500,
|
| 250 |
+
"total_flos": 1.561516427968512e+16,
|
| 251 |
+
"train_batch_size": 1,
|
| 252 |
+
"trial_name": null,
|
| 253 |
+
"trial_params": null
|
| 254 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e9c6052eba1c43477483ead19d87e3162e2ad2ba8566036d9f5969b1c27e79c
|
| 3 |
size 4984
|