Upload 7 files
Browse files- adapter_config.json +22 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +400 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "/media/khalid/HDD2/Huggingface_models/bloom_7b/",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"enable_lora": [
|
| 5 |
+
true,
|
| 6 |
+
false,
|
| 7 |
+
true
|
| 8 |
+
],
|
| 9 |
+
"fan_in_fan_out": true,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"merge_weights": false,
|
| 15 |
+
"modules_to_save": null,
|
| 16 |
+
"peft_type": "LORA",
|
| 17 |
+
"r": 8,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"query_key_value"
|
| 20 |
+
],
|
| 21 |
+
"task_type": "CAUSAL_LM"
|
| 22 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddd5bfd67d744bb43d3e618680e7eeb188edf15fcbc347b69c7616169c897836
|
| 3 |
+
size 15751077
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6c507466de3de98009072657ac6b0328d5945b93254ab15f872ff9e78c49f78
|
| 3 |
+
size 31508037
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ab10d8d7784a14238171a89bbb55fdd9731bb0b3d4bf3dcfe2ab8cd4e8b17b1
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6438f2ca77a65e596f6f7ef18a8b80e529f3d76354bc4374010b0b285837e13
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,400 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.8643771409988403,
|
| 3 |
+
"best_model_checkpoint": "./lora_weights/checkpoint-600",
|
| 4 |
+
"epoch": 2.496424392146665,
|
| 5 |
+
"global_step": 600,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 13 |
+
"loss": 2.7371,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.08,
|
| 18 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 19 |
+
"loss": 2.713,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.12,
|
| 24 |
+
"learning_rate": 8.999999999999999e-05,
|
| 25 |
+
"loss": 2.6222,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.17,
|
| 30 |
+
"learning_rate": 0.00011999999999999999,
|
| 31 |
+
"loss": 2.4152,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.21,
|
| 36 |
+
"learning_rate": 0.00015,
|
| 37 |
+
"loss": 2.2329,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.25,
|
| 42 |
+
"learning_rate": 0.00017999999999999998,
|
| 43 |
+
"loss": 2.1497,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.29,
|
| 48 |
+
"learning_rate": 0.00020999999999999998,
|
| 49 |
+
"loss": 2.0945,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.33,
|
| 54 |
+
"learning_rate": 0.00023999999999999998,
|
| 55 |
+
"loss": 2.069,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.37,
|
| 60 |
+
"learning_rate": 0.00027,
|
| 61 |
+
"loss": 2.0207,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.42,
|
| 66 |
+
"learning_rate": 0.0003,
|
| 67 |
+
"loss": 2.0078,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.46,
|
| 72 |
+
"learning_rate": 0.00029516129032258065,
|
| 73 |
+
"loss": 1.9622,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.5,
|
| 78 |
+
"learning_rate": 0.00029032258064516127,
|
| 79 |
+
"loss": 1.9848,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.54,
|
| 84 |
+
"learning_rate": 0.00028548387096774194,
|
| 85 |
+
"loss": 1.9573,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.58,
|
| 90 |
+
"learning_rate": 0.00028064516129032256,
|
| 91 |
+
"loss": 1.9482,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.62,
|
| 96 |
+
"learning_rate": 0.0002758064516129032,
|
| 97 |
+
"loss": 1.9576,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.67,
|
| 102 |
+
"learning_rate": 0.00027096774193548386,
|
| 103 |
+
"loss": 1.9558,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.71,
|
| 108 |
+
"learning_rate": 0.0002661290322580645,
|
| 109 |
+
"loss": 1.9453,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.75,
|
| 114 |
+
"learning_rate": 0.00026129032258064515,
|
| 115 |
+
"loss": 1.9386,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.79,
|
| 120 |
+
"learning_rate": 0.00025645161290322577,
|
| 121 |
+
"loss": 1.9421,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.83,
|
| 126 |
+
"learning_rate": 0.00025161290322580645,
|
| 127 |
+
"loss": 1.9392,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.83,
|
| 132 |
+
"eval_loss": 1.9201855659484863,
|
| 133 |
+
"eval_runtime": 141.1699,
|
| 134 |
+
"eval_samples_per_second": 14.167,
|
| 135 |
+
"eval_steps_per_second": 1.771,
|
| 136 |
+
"step": 200
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.87,
|
| 140 |
+
"learning_rate": 0.00024677419354838707,
|
| 141 |
+
"loss": 1.9406,
|
| 142 |
+
"step": 210
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.92,
|
| 146 |
+
"learning_rate": 0.00024193548387096771,
|
| 147 |
+
"loss": 1.9091,
|
| 148 |
+
"step": 220
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.96,
|
| 152 |
+
"learning_rate": 0.00023709677419354836,
|
| 153 |
+
"loss": 1.905,
|
| 154 |
+
"step": 230
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.0,
|
| 158 |
+
"learning_rate": 0.000232258064516129,
|
| 159 |
+
"loss": 1.9165,
|
| 160 |
+
"step": 240
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.04,
|
| 164 |
+
"learning_rate": 0.00022741935483870966,
|
| 165 |
+
"loss": 1.9074,
|
| 166 |
+
"step": 250
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.08,
|
| 170 |
+
"learning_rate": 0.0002225806451612903,
|
| 171 |
+
"loss": 1.8788,
|
| 172 |
+
"step": 260
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.12,
|
| 176 |
+
"learning_rate": 0.00021774193548387095,
|
| 177 |
+
"loss": 1.9058,
|
| 178 |
+
"step": 270
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.16,
|
| 182 |
+
"learning_rate": 0.0002129032258064516,
|
| 183 |
+
"loss": 1.9167,
|
| 184 |
+
"step": 280
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.21,
|
| 188 |
+
"learning_rate": 0.00020806451612903225,
|
| 189 |
+
"loss": 1.9063,
|
| 190 |
+
"step": 290
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.25,
|
| 194 |
+
"learning_rate": 0.00020322580645161287,
|
| 195 |
+
"loss": 1.8964,
|
| 196 |
+
"step": 300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.29,
|
| 200 |
+
"learning_rate": 0.0001983870967741935,
|
| 201 |
+
"loss": 1.8961,
|
| 202 |
+
"step": 310
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.33,
|
| 206 |
+
"learning_rate": 0.00019354838709677416,
|
| 207 |
+
"loss": 1.8911,
|
| 208 |
+
"step": 320
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.37,
|
| 212 |
+
"learning_rate": 0.0001887096774193548,
|
| 213 |
+
"loss": 1.8947,
|
| 214 |
+
"step": 330
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.41,
|
| 218 |
+
"learning_rate": 0.00018387096774193548,
|
| 219 |
+
"loss": 1.8794,
|
| 220 |
+
"step": 340
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.46,
|
| 224 |
+
"learning_rate": 0.00017903225806451613,
|
| 225 |
+
"loss": 1.9045,
|
| 226 |
+
"step": 350
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.5,
|
| 230 |
+
"learning_rate": 0.00017419354838709678,
|
| 231 |
+
"loss": 1.8951,
|
| 232 |
+
"step": 360
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.54,
|
| 236 |
+
"learning_rate": 0.00016935483870967742,
|
| 237 |
+
"loss": 1.8777,
|
| 238 |
+
"step": 370
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.58,
|
| 242 |
+
"learning_rate": 0.00016451612903225804,
|
| 243 |
+
"loss": 1.8832,
|
| 244 |
+
"step": 380
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.62,
|
| 248 |
+
"learning_rate": 0.0001596774193548387,
|
| 249 |
+
"loss": 1.8811,
|
| 250 |
+
"step": 390
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.66,
|
| 254 |
+
"learning_rate": 0.00015483870967741934,
|
| 255 |
+
"loss": 1.8763,
|
| 256 |
+
"step": 400
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.66,
|
| 260 |
+
"eval_loss": 1.8789199590682983,
|
| 261 |
+
"eval_runtime": 141.9625,
|
| 262 |
+
"eval_samples_per_second": 14.088,
|
| 263 |
+
"eval_steps_per_second": 1.761,
|
| 264 |
+
"step": 400
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.71,
|
| 268 |
+
"learning_rate": 0.00015,
|
| 269 |
+
"loss": 1.8746,
|
| 270 |
+
"step": 410
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.75,
|
| 274 |
+
"learning_rate": 0.00014516129032258063,
|
| 275 |
+
"loss": 1.8887,
|
| 276 |
+
"step": 420
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.79,
|
| 280 |
+
"learning_rate": 0.00014032258064516128,
|
| 281 |
+
"loss": 1.8878,
|
| 282 |
+
"step": 430
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.83,
|
| 286 |
+
"learning_rate": 0.00013548387096774193,
|
| 287 |
+
"loss": 1.8893,
|
| 288 |
+
"step": 440
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.87,
|
| 292 |
+
"learning_rate": 0.00013064516129032258,
|
| 293 |
+
"loss": 1.8852,
|
| 294 |
+
"step": 450
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.91,
|
| 298 |
+
"learning_rate": 0.00012580645161290322,
|
| 299 |
+
"loss": 1.8952,
|
| 300 |
+
"step": 460
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.96,
|
| 304 |
+
"learning_rate": 0.00012096774193548386,
|
| 305 |
+
"loss": 1.8755,
|
| 306 |
+
"step": 470
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.0,
|
| 310 |
+
"learning_rate": 0.0001161290322580645,
|
| 311 |
+
"loss": 1.8865,
|
| 312 |
+
"step": 480
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.04,
|
| 316 |
+
"learning_rate": 0.00011129032258064515,
|
| 317 |
+
"loss": 1.8651,
|
| 318 |
+
"step": 490
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.08,
|
| 322 |
+
"learning_rate": 0.0001064516129032258,
|
| 323 |
+
"loss": 1.8589,
|
| 324 |
+
"step": 500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.12,
|
| 328 |
+
"learning_rate": 0.00010161290322580643,
|
| 329 |
+
"loss": 1.8578,
|
| 330 |
+
"step": 510
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.16,
|
| 334 |
+
"learning_rate": 9.677419354838708e-05,
|
| 335 |
+
"loss": 1.8727,
|
| 336 |
+
"step": 520
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.21,
|
| 340 |
+
"learning_rate": 9.193548387096774e-05,
|
| 341 |
+
"loss": 1.8558,
|
| 342 |
+
"step": 530
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.25,
|
| 346 |
+
"learning_rate": 8.709677419354839e-05,
|
| 347 |
+
"loss": 1.8616,
|
| 348 |
+
"step": 540
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.29,
|
| 352 |
+
"learning_rate": 8.225806451612902e-05,
|
| 353 |
+
"loss": 1.8502,
|
| 354 |
+
"step": 550
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.33,
|
| 358 |
+
"learning_rate": 7.741935483870967e-05,
|
| 359 |
+
"loss": 1.861,
|
| 360 |
+
"step": 560
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.37,
|
| 364 |
+
"learning_rate": 7.258064516129032e-05,
|
| 365 |
+
"loss": 1.8473,
|
| 366 |
+
"step": 570
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.41,
|
| 370 |
+
"learning_rate": 6.774193548387096e-05,
|
| 371 |
+
"loss": 1.8586,
|
| 372 |
+
"step": 580
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.45,
|
| 376 |
+
"learning_rate": 6.290322580645161e-05,
|
| 377 |
+
"loss": 1.8621,
|
| 378 |
+
"step": 590
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.5,
|
| 382 |
+
"learning_rate": 5.806451612903225e-05,
|
| 383 |
+
"loss": 1.8692,
|
| 384 |
+
"step": 600
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.5,
|
| 388 |
+
"eval_loss": 1.8643771409988403,
|
| 389 |
+
"eval_runtime": 141.1773,
|
| 390 |
+
"eval_samples_per_second": 14.167,
|
| 391 |
+
"eval_steps_per_second": 1.771,
|
| 392 |
+
"step": 600
|
| 393 |
+
}
|
| 394 |
+
],
|
| 395 |
+
"max_steps": 720,
|
| 396 |
+
"num_train_epochs": 3,
|
| 397 |
+
"total_flos": 7.128893746084577e+17,
|
| 398 |
+
"trial_name": null,
|
| 399 |
+
"trial_params": null
|
| 400 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29cb87e3825099bb48be263dad3fc0232499f2817244c3697bc5ba19daa29943
|
| 3 |
+
size 3899
|