Commit
•
9c99b97
1
Parent(s):
514b0e7
Upload folder using huggingface_hub (#5)
Browse files- Upload folder using huggingface_hub (7bf47f8d245cb9b01e49872c35478b9a319b0fb7)
- README.md +78 -0
- adapter_model.bin +1 -1
- optimizer.pt +1 -1
- scheduler.pt +1 -1
- tokenizer.json +2 -2
- trainer_state.json +304 -304
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -4,6 +4,78 @@ library_name: peft
|
|
| 4 |
## Training procedure
|
| 5 |
|
| 6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
- quant_method: bitsandbytes
|
| 9 |
- load_in_8bit: True
|
|
@@ -77,6 +149,12 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 77 |
- bnb_4bit_compute_dtype: float32
|
| 78 |
### Framework versions
|
| 79 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
- PEFT 0.6.0.dev0
|
| 81 |
- PEFT 0.6.0.dev0
|
| 82 |
- PEFT 0.6.0.dev0
|
|
|
|
| 4 |
## Training procedure
|
| 5 |
|
| 6 |
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: True
|
| 10 |
+
- load_in_4bit: False
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
|
| 19 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 20 |
+
- quant_method: bitsandbytes
|
| 21 |
+
- load_in_8bit: True
|
| 22 |
+
- load_in_4bit: False
|
| 23 |
+
- llm_int8_threshold: 6.0
|
| 24 |
+
- llm_int8_skip_modules: None
|
| 25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 26 |
+
- llm_int8_has_fp16_weight: False
|
| 27 |
+
- bnb_4bit_quant_type: fp4
|
| 28 |
+
- bnb_4bit_use_double_quant: False
|
| 29 |
+
- bnb_4bit_compute_dtype: float32
|
| 30 |
+
|
| 31 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 32 |
+
- quant_method: bitsandbytes
|
| 33 |
+
- load_in_8bit: True
|
| 34 |
+
- load_in_4bit: False
|
| 35 |
+
- llm_int8_threshold: 6.0
|
| 36 |
+
- llm_int8_skip_modules: None
|
| 37 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 38 |
+
- llm_int8_has_fp16_weight: False
|
| 39 |
+
- bnb_4bit_quant_type: fp4
|
| 40 |
+
- bnb_4bit_use_double_quant: False
|
| 41 |
+
- bnb_4bit_compute_dtype: float32
|
| 42 |
+
|
| 43 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 44 |
+
- quant_method: bitsandbytes
|
| 45 |
+
- load_in_8bit: True
|
| 46 |
+
- load_in_4bit: False
|
| 47 |
+
- llm_int8_threshold: 6.0
|
| 48 |
+
- llm_int8_skip_modules: None
|
| 49 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 50 |
+
- llm_int8_has_fp16_weight: False
|
| 51 |
+
- bnb_4bit_quant_type: fp4
|
| 52 |
+
- bnb_4bit_use_double_quant: False
|
| 53 |
+
- bnb_4bit_compute_dtype: float32
|
| 54 |
+
|
| 55 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 56 |
+
- quant_method: bitsandbytes
|
| 57 |
+
- load_in_8bit: True
|
| 58 |
+
- load_in_4bit: False
|
| 59 |
+
- llm_int8_threshold: 6.0
|
| 60 |
+
- llm_int8_skip_modules: None
|
| 61 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 62 |
+
- llm_int8_has_fp16_weight: False
|
| 63 |
+
- bnb_4bit_quant_type: fp4
|
| 64 |
+
- bnb_4bit_use_double_quant: False
|
| 65 |
+
- bnb_4bit_compute_dtype: float32
|
| 66 |
+
|
| 67 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 68 |
+
- quant_method: bitsandbytes
|
| 69 |
+
- load_in_8bit: True
|
| 70 |
+
- load_in_4bit: False
|
| 71 |
+
- llm_int8_threshold: 6.0
|
| 72 |
+
- llm_int8_skip_modules: None
|
| 73 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 74 |
+
- llm_int8_has_fp16_weight: False
|
| 75 |
+
- bnb_4bit_quant_type: fp4
|
| 76 |
+
- bnb_4bit_use_double_quant: False
|
| 77 |
+
- bnb_4bit_compute_dtype: float32
|
| 78 |
+
|
| 79 |
The following `bitsandbytes` quantization config was used during training:
|
| 80 |
- quant_method: bitsandbytes
|
| 81 |
- load_in_8bit: True
|
|
|
|
| 149 |
- bnb_4bit_compute_dtype: float32
|
| 150 |
### Framework versions
|
| 151 |
|
| 152 |
+
- PEFT 0.6.0.dev0
|
| 153 |
+
- PEFT 0.6.0.dev0
|
| 154 |
+
- PEFT 0.6.0.dev0
|
| 155 |
+
- PEFT 0.6.0.dev0
|
| 156 |
+
- PEFT 0.6.0.dev0
|
| 157 |
+
- PEFT 0.6.0.dev0
|
| 158 |
- PEFT 0.6.0.dev0
|
| 159 |
- PEFT 0.6.0.dev0
|
| 160 |
- PEFT 0.6.0.dev0
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 39409357
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab7d7332df354d85019ef8dbda22bf275f3e4612ebbe07ca7d3538dd755384e9
|
| 3 |
size 39409357
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 78844421
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e7ecf4519b7c7fe30096c1ce0de750678f8cf403d65a166a096e8155b6d1665
|
| 3 |
size 78844421
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02822a64d6ab3629baf2f69c5adf000658973be0bc2532154cc2534085175f34
|
| 3 |
size 627
|
tokenizer.json
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 sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
|
| 3 |
+
size 14500570
|
trainer_state.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
|
@@ -9,611 +9,611 @@
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"learning_rate": 0.
|
| 14 |
-
"loss": 2.
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate": 0.
|
| 20 |
-
"loss": 2.
|
| 21 |
"step": 2
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate": 0.
|
| 26 |
-
"loss": 2.
|
| 27 |
"step": 3
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate": 0.
|
| 32 |
-
"loss": 2.
|
| 33 |
"step": 4
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate": 0.
|
| 38 |
-
"loss": 2.
|
| 39 |
"step": 5
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss": 2.
|
| 45 |
"step": 6
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 2.
|
| 51 |
"step": 7
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"learning_rate": 0.
|
| 56 |
-
"loss": 2.
|
| 57 |
"step": 8
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"learning_rate": 0.
|
| 62 |
-
"loss": 2.
|
| 63 |
"step": 9
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
| 67 |
-
"learning_rate": 0.
|
| 68 |
-
"loss": 2.
|
| 69 |
"step": 10
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
| 73 |
-
"learning_rate": 0.
|
| 74 |
-
"loss": 2.
|
| 75 |
"step": 11
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 0.
|
| 79 |
-
"learning_rate": 0.
|
| 80 |
-
"loss": 2.
|
| 81 |
"step": 12
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
-
"learning_rate": 0.
|
| 86 |
-
"loss": 2.
|
| 87 |
"step": 13
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss": 2.
|
| 93 |
"step": 14
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"learning_rate": 0.
|
| 98 |
-
"loss": 2.
|
| 99 |
"step": 15
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 0.
|
| 103 |
-
"learning_rate": 0.
|
| 104 |
-
"loss": 2.
|
| 105 |
"step": 16
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch": 0.
|
| 109 |
-
"learning_rate": 0.
|
| 110 |
-
"loss": 2.
|
| 111 |
"step": 17
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch": 0.
|
| 115 |
-
"learning_rate": 0.
|
| 116 |
-
"loss": 2.
|
| 117 |
"step": 18
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch": 0.
|
| 121 |
-
"learning_rate": 0.
|
| 122 |
-
"loss": 2.
|
| 123 |
"step": 19
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 0.
|
| 127 |
-
"learning_rate": 0.
|
| 128 |
-
"loss": 2.
|
| 129 |
"step": 20
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 0.
|
| 133 |
-
"learning_rate": 0.
|
| 134 |
-
"loss": 2.
|
| 135 |
"step": 21
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"learning_rate": 0.
|
| 140 |
-
"loss": 2.
|
| 141 |
"step": 22
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch": 0.
|
| 145 |
-
"learning_rate": 0.
|
| 146 |
-
"loss": 2.
|
| 147 |
"step": 23
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch": 0.
|
| 151 |
-
"learning_rate": 0.
|
| 152 |
-
"loss": 2.
|
| 153 |
"step": 24
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch": 0.
|
| 157 |
-
"learning_rate": 0.
|
| 158 |
-
"loss": 2.
|
| 159 |
"step": 25
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 0.
|
| 163 |
-
"learning_rate": 0.
|
| 164 |
-
"loss": 2.
|
| 165 |
"step": 26
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"epoch": 0.
|
| 169 |
-
"learning_rate": 0.
|
| 170 |
-
"loss": 2.
|
| 171 |
"step": 27
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch": 0.
|
| 175 |
-
"learning_rate": 0.
|
| 176 |
-
"loss": 2.
|
| 177 |
"step": 28
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 0.
|
| 181 |
-
"learning_rate": 0.
|
| 182 |
-
"loss": 2.
|
| 183 |
"step": 29
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch": 0.
|
| 187 |
-
"learning_rate": 0.
|
| 188 |
-
"loss": 2.
|
| 189 |
"step": 30
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch": 0.
|
| 193 |
-
"learning_rate": 0.
|
| 194 |
-
"loss": 2.
|
| 195 |
"step": 31
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch": 0.
|
| 199 |
-
"learning_rate": 0.
|
| 200 |
-
"loss": 2.
|
| 201 |
"step": 32
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch": 0.
|
| 205 |
-
"learning_rate": 0.
|
| 206 |
-
"loss": 2.
|
| 207 |
"step": 33
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch": 0.
|
| 211 |
-
"learning_rate": 0.
|
| 212 |
-
"loss": 2.
|
| 213 |
"step": 34
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch": 0.
|
| 217 |
-
"learning_rate": 0.
|
| 218 |
-
"loss": 2.
|
| 219 |
"step": 35
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch": 0.
|
| 223 |
-
"learning_rate": 0.
|
| 224 |
-
"loss": 2.
|
| 225 |
"step": 36
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch": 0.
|
| 229 |
-
"learning_rate": 0.
|
| 230 |
-
"loss": 2.
|
| 231 |
"step": 37
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch": 0.
|
| 235 |
-
"learning_rate": 0.
|
| 236 |
-
"loss": 2.
|
| 237 |
"step": 38
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch": 0.
|
| 241 |
-
"learning_rate": 0.
|
| 242 |
-
"loss": 2.
|
| 243 |
"step": 39
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch": 0.
|
| 247 |
-
"learning_rate": 0.
|
| 248 |
-
"loss": 2.
|
| 249 |
"step": 40
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch": 0.
|
| 253 |
-
"learning_rate": 0.
|
| 254 |
-
"loss": 2.
|
| 255 |
"step": 41
|
| 256 |
},
|
| 257 |
{
|
| 258 |
-
"epoch": 0.
|
| 259 |
-
"learning_rate": 0.
|
| 260 |
-
"loss": 2.
|
| 261 |
"step": 42
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch": 0.
|
| 265 |
-
"learning_rate": 0.
|
| 266 |
-
"loss": 2.
|
| 267 |
"step": 43
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch": 0.
|
| 271 |
-
"learning_rate": 0.
|
| 272 |
-
"loss": 2.
|
| 273 |
"step": 44
|
| 274 |
},
|
| 275 |
{
|
| 276 |
-
"epoch": 0.
|
| 277 |
-
"learning_rate": 0.
|
| 278 |
-
"loss": 2.
|
| 279 |
"step": 45
|
| 280 |
},
|
| 281 |
{
|
| 282 |
-
"epoch": 0.
|
| 283 |
-
"learning_rate": 0.
|
| 284 |
-
"loss": 2.
|
| 285 |
"step": 46
|
| 286 |
},
|
| 287 |
{
|
| 288 |
-
"epoch": 0.
|
| 289 |
-
"learning_rate": 0.
|
| 290 |
-
"loss": 2.
|
| 291 |
"step": 47
|
| 292 |
},
|
| 293 |
{
|
| 294 |
-
"epoch": 0.
|
| 295 |
-
"learning_rate": 0.
|
| 296 |
-
"loss": 2.
|
| 297 |
"step": 48
|
| 298 |
},
|
| 299 |
{
|
| 300 |
-
"epoch": 0.
|
| 301 |
-
"learning_rate": 0.
|
| 302 |
-
"loss": 2.
|
| 303 |
"step": 49
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch": 0.
|
| 307 |
-
"learning_rate": 0.
|
| 308 |
-
"loss": 2.
|
| 309 |
"step": 50
|
| 310 |
},
|
| 311 |
{
|
| 312 |
-
"epoch": 0.
|
| 313 |
-
"learning_rate": 0.
|
| 314 |
-
"loss": 2.
|
| 315 |
"step": 51
|
| 316 |
},
|
| 317 |
{
|
| 318 |
-
"epoch": 0.
|
| 319 |
-
"learning_rate": 0.
|
| 320 |
-
"loss": 2.
|
| 321 |
"step": 52
|
| 322 |
},
|
| 323 |
{
|
| 324 |
-
"epoch": 0.
|
| 325 |
-
"learning_rate": 0.
|
| 326 |
-
"loss": 2.
|
| 327 |
"step": 53
|
| 328 |
},
|
| 329 |
{
|
| 330 |
-
"epoch": 0.
|
| 331 |
-
"learning_rate": 0.
|
| 332 |
-
"loss": 2.
|
| 333 |
"step": 54
|
| 334 |
},
|
| 335 |
{
|
| 336 |
-
"epoch": 0.
|
| 337 |
-
"learning_rate": 0.
|
| 338 |
-
"loss": 2.
|
| 339 |
"step": 55
|
| 340 |
},
|
| 341 |
{
|
| 342 |
-
"epoch": 0.
|
| 343 |
-
"learning_rate": 0.
|
| 344 |
-
"loss": 2.
|
| 345 |
"step": 56
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch": 0.
|
| 349 |
-
"learning_rate": 0.
|
| 350 |
-
"loss": 2.
|
| 351 |
"step": 57
|
| 352 |
},
|
| 353 |
{
|
| 354 |
-
"epoch": 0.
|
| 355 |
-
"learning_rate": 0.
|
| 356 |
-
"loss": 2.
|
| 357 |
"step": 58
|
| 358 |
},
|
| 359 |
{
|
| 360 |
-
"epoch": 0.
|
| 361 |
-
"learning_rate": 0.
|
| 362 |
-
"loss": 2.
|
| 363 |
"step": 59
|
| 364 |
},
|
| 365 |
{
|
| 366 |
-
"epoch": 0.
|
| 367 |
-
"learning_rate": 0.
|
| 368 |
-
"loss": 2.
|
| 369 |
"step": 60
|
| 370 |
},
|
| 371 |
{
|
| 372 |
-
"epoch": 0.
|
| 373 |
-
"learning_rate": 0.
|
| 374 |
-
"loss": 2.
|
| 375 |
"step": 61
|
| 376 |
},
|
| 377 |
{
|
| 378 |
-
"epoch": 0.
|
| 379 |
-
"learning_rate": 0.
|
| 380 |
-
"loss": 2.
|
| 381 |
"step": 62
|
| 382 |
},
|
| 383 |
{
|
| 384 |
-
"epoch": 0.
|
| 385 |
-
"learning_rate": 0.
|
| 386 |
-
"loss": 2.
|
| 387 |
"step": 63
|
| 388 |
},
|
| 389 |
{
|
| 390 |
-
"epoch": 0.
|
| 391 |
-
"learning_rate": 0.
|
| 392 |
-
"loss": 2.
|
| 393 |
"step": 64
|
| 394 |
},
|
| 395 |
{
|
| 396 |
-
"epoch": 0.
|
| 397 |
-
"learning_rate": 0.
|
| 398 |
-
"loss": 2.
|
| 399 |
"step": 65
|
| 400 |
},
|
| 401 |
{
|
| 402 |
-
"epoch": 0.
|
| 403 |
-
"learning_rate": 0.
|
| 404 |
-
"loss": 2.
|
| 405 |
"step": 66
|
| 406 |
},
|
| 407 |
{
|
| 408 |
-
"epoch": 0.
|
| 409 |
-
"learning_rate": 0.
|
| 410 |
-
"loss": 2.
|
| 411 |
"step": 67
|
| 412 |
},
|
| 413 |
{
|
| 414 |
-
"epoch": 0.
|
| 415 |
-
"learning_rate": 0.
|
| 416 |
-
"loss":
|
| 417 |
"step": 68
|
| 418 |
},
|
| 419 |
{
|
| 420 |
-
"epoch": 0.
|
| 421 |
-
"learning_rate": 0.
|
| 422 |
-
"loss": 2.
|
| 423 |
"step": 69
|
| 424 |
},
|
| 425 |
{
|
| 426 |
-
"epoch": 0.
|
| 427 |
-
"learning_rate": 0.
|
| 428 |
-
"loss": 2.
|
| 429 |
"step": 70
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch": 0.
|
| 433 |
-
"learning_rate": 0.
|
| 434 |
-
"loss": 2.
|
| 435 |
"step": 71
|
| 436 |
},
|
| 437 |
{
|
| 438 |
-
"epoch": 0.
|
| 439 |
-
"learning_rate": 0.
|
| 440 |
-
"loss": 2.
|
| 441 |
"step": 72
|
| 442 |
},
|
| 443 |
{
|
| 444 |
-
"epoch": 0.
|
| 445 |
-
"learning_rate": 0.
|
| 446 |
-
"loss": 2.
|
| 447 |
"step": 73
|
| 448 |
},
|
| 449 |
{
|
| 450 |
-
"epoch": 0.
|
| 451 |
-
"learning_rate": 0.
|
| 452 |
-
"loss":
|
| 453 |
"step": 74
|
| 454 |
},
|
| 455 |
{
|
| 456 |
-
"epoch": 0.
|
| 457 |
-
"learning_rate": 0.
|
| 458 |
-
"loss": 2.
|
| 459 |
"step": 75
|
| 460 |
},
|
| 461 |
{
|
| 462 |
-
"epoch": 0.
|
| 463 |
-
"learning_rate": 0.
|
| 464 |
-
"loss": 2.
|
| 465 |
"step": 76
|
| 466 |
},
|
| 467 |
{
|
| 468 |
-
"epoch": 0.
|
| 469 |
-
"learning_rate": 0.
|
| 470 |
-
"loss": 2.
|
| 471 |
"step": 77
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"epoch": 0.
|
| 475 |
-
"learning_rate": 0.
|
| 476 |
-
"loss": 2.
|
| 477 |
"step": 78
|
| 478 |
},
|
| 479 |
{
|
| 480 |
-
"epoch": 0.
|
| 481 |
-
"learning_rate": 0.
|
| 482 |
-
"loss":
|
| 483 |
"step": 79
|
| 484 |
},
|
| 485 |
{
|
| 486 |
-
"epoch": 0.
|
| 487 |
-
"learning_rate": 0.
|
| 488 |
-
"loss": 1.
|
| 489 |
"step": 80
|
| 490 |
},
|
| 491 |
{
|
| 492 |
-
"epoch": 0.
|
| 493 |
-
"learning_rate": 0.
|
| 494 |
-
"loss": 2.
|
| 495 |
"step": 81
|
| 496 |
},
|
| 497 |
{
|
| 498 |
-
"epoch": 0.
|
| 499 |
-
"learning_rate": 0.
|
| 500 |
-
"loss": 2.
|
| 501 |
"step": 82
|
| 502 |
},
|
| 503 |
{
|
| 504 |
-
"epoch": 0.
|
| 505 |
-
"learning_rate": 0.
|
| 506 |
-
"loss": 2.
|
| 507 |
"step": 83
|
| 508 |
},
|
| 509 |
{
|
| 510 |
-
"epoch": 0.
|
| 511 |
-
"learning_rate": 0.
|
| 512 |
-
"loss": 2.
|
| 513 |
"step": 84
|
| 514 |
},
|
| 515 |
{
|
| 516 |
-
"epoch": 0.
|
| 517 |
-
"learning_rate": 0.
|
| 518 |
-
"loss": 2.
|
| 519 |
"step": 85
|
| 520 |
},
|
| 521 |
{
|
| 522 |
-
"epoch": 0.
|
| 523 |
-
"learning_rate": 0.
|
| 524 |
-
"loss": 2.
|
| 525 |
"step": 86
|
| 526 |
},
|
| 527 |
{
|
| 528 |
-
"epoch": 0.
|
| 529 |
-
"learning_rate": 0.
|
| 530 |
-
"loss": 2.
|
| 531 |
"step": 87
|
| 532 |
},
|
| 533 |
{
|
| 534 |
-
"epoch": 0.
|
| 535 |
-
"learning_rate": 0.
|
| 536 |
-
"loss": 2.
|
| 537 |
"step": 88
|
| 538 |
},
|
| 539 |
{
|
| 540 |
-
"epoch": 0.
|
| 541 |
-
"learning_rate": 0.
|
| 542 |
-
"loss":
|
| 543 |
"step": 89
|
| 544 |
},
|
| 545 |
{
|
| 546 |
-
"epoch": 0.
|
| 547 |
-
"learning_rate": 0.
|
| 548 |
-
"loss": 2.
|
| 549 |
"step": 90
|
| 550 |
},
|
| 551 |
{
|
| 552 |
-
"epoch": 0.
|
| 553 |
-
"learning_rate": 0.
|
| 554 |
-
"loss": 2.
|
| 555 |
"step": 91
|
| 556 |
},
|
| 557 |
{
|
| 558 |
-
"epoch": 0.
|
| 559 |
-
"learning_rate": 0.
|
| 560 |
-
"loss":
|
| 561 |
"step": 92
|
| 562 |
},
|
| 563 |
{
|
| 564 |
-
"epoch": 0.
|
| 565 |
-
"learning_rate": 0.
|
| 566 |
-
"loss":
|
| 567 |
"step": 93
|
| 568 |
},
|
| 569 |
{
|
| 570 |
-
"epoch": 0.
|
| 571 |
-
"learning_rate": 0.
|
| 572 |
-
"loss": 2.
|
| 573 |
"step": 94
|
| 574 |
},
|
| 575 |
{
|
| 576 |
-
"epoch": 0.
|
| 577 |
-
"learning_rate": 0.
|
| 578 |
-
"loss":
|
| 579 |
"step": 95
|
| 580 |
},
|
| 581 |
{
|
| 582 |
-
"epoch": 0.
|
| 583 |
-
"learning_rate": 0.
|
| 584 |
-
"loss": 2.
|
| 585 |
"step": 96
|
| 586 |
},
|
| 587 |
{
|
| 588 |
-
"epoch": 0.
|
| 589 |
-
"learning_rate": 0.
|
| 590 |
-
"loss": 2.
|
| 591 |
"step": 97
|
| 592 |
},
|
| 593 |
{
|
| 594 |
-
"epoch": 0.
|
| 595 |
-
"learning_rate": 0.
|
| 596 |
-
"loss":
|
| 597 |
"step": 98
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"epoch": 0.
|
| 601 |
-
"learning_rate": 0.
|
| 602 |
-
"loss":
|
| 603 |
"step": 99
|
| 604 |
},
|
| 605 |
{
|
| 606 |
-
"epoch": 0.
|
| 607 |
-
"learning_rate": 0.
|
| 608 |
-
"loss": 2.
|
| 609 |
"step": 100
|
| 610 |
}
|
| 611 |
],
|
| 612 |
"logging_steps": 1,
|
| 613 |
-
"max_steps":
|
| 614 |
-
"num_train_epochs":
|
| 615 |
"save_steps": 100,
|
| 616 |
-
"total_flos":
|
| 617 |
"trial_name": null,
|
| 618 |
"trial_params": null
|
| 619 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.3429796355841372,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
|
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 0.00019931271477663232,
|
| 14 |
+
"loss": 2.5587,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 0.0001986254295532646,
|
| 20 |
+
"loss": 2.3914,
|
| 21 |
"step": 2
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 0.00019793814432989693,
|
| 26 |
+
"loss": 2.4218,
|
| 27 |
"step": 3
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 0.00019725085910652924,
|
| 32 |
+
"loss": 2.3414,
|
| 33 |
"step": 4
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 0.0001965635738831615,
|
| 38 |
+
"loss": 2.2469,
|
| 39 |
"step": 5
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 0.00019587628865979381,
|
| 44 |
+
"loss": 2.3241,
|
| 45 |
"step": 6
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 0.00019518900343642613,
|
| 50 |
+
"loss": 2.3266,
|
| 51 |
"step": 7
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 0.00019450171821305842,
|
| 56 |
+
"loss": 2.1856,
|
| 57 |
"step": 8
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.03,
|
| 61 |
+
"learning_rate": 0.00019381443298969073,
|
| 62 |
+
"loss": 2.3247,
|
| 63 |
"step": 9
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.03,
|
| 67 |
+
"learning_rate": 0.00019312714776632305,
|
| 68 |
+
"loss": 2.3245,
|
| 69 |
"step": 10
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.04,
|
| 73 |
+
"learning_rate": 0.00019243986254295533,
|
| 74 |
+
"loss": 2.2591,
|
| 75 |
"step": 11
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.04,
|
| 79 |
+
"learning_rate": 0.00019175257731958765,
|
| 80 |
+
"loss": 2.1767,
|
| 81 |
"step": 12
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"learning_rate": 0.00019106529209621996,
|
| 86 |
+
"loss": 2.3478,
|
| 87 |
"step": 13
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 0.05,
|
| 91 |
+
"learning_rate": 0.00019037800687285222,
|
| 92 |
+
"loss": 2.3339,
|
| 93 |
"step": 14
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"learning_rate": 0.00018969072164948454,
|
| 98 |
+
"loss": 2.234,
|
| 99 |
"step": 15
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.05,
|
| 103 |
+
"learning_rate": 0.00018900343642611685,
|
| 104 |
+
"loss": 2.2651,
|
| 105 |
"step": 16
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.06,
|
| 109 |
+
"learning_rate": 0.00018831615120274914,
|
| 110 |
+
"loss": 2.1831,
|
| 111 |
"step": 17
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.06,
|
| 115 |
+
"learning_rate": 0.00018762886597938145,
|
| 116 |
+
"loss": 2.216,
|
| 117 |
"step": 18
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 0.07,
|
| 121 |
+
"learning_rate": 0.00018694158075601377,
|
| 122 |
+
"loss": 2.1359,
|
| 123 |
"step": 19
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.07,
|
| 127 |
+
"learning_rate": 0.00018625429553264605,
|
| 128 |
+
"loss": 2.1215,
|
| 129 |
"step": 20
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.07,
|
| 133 |
+
"learning_rate": 0.00018556701030927837,
|
| 134 |
+
"loss": 2.2179,
|
| 135 |
"step": 21
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.08,
|
| 139 |
+
"learning_rate": 0.00018487972508591068,
|
| 140 |
+
"loss": 2.2598,
|
| 141 |
"step": 22
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 0.08,
|
| 145 |
+
"learning_rate": 0.00018419243986254294,
|
| 146 |
+
"loss": 2.1813,
|
| 147 |
"step": 23
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 0.08,
|
| 151 |
+
"learning_rate": 0.00018350515463917526,
|
| 152 |
+
"loss": 2.2006,
|
| 153 |
"step": 24
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 0.09,
|
| 157 |
+
"learning_rate": 0.00018281786941580757,
|
| 158 |
+
"loss": 2.1564,
|
| 159 |
"step": 25
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 0.09,
|
| 163 |
+
"learning_rate": 0.00018213058419243986,
|
| 164 |
+
"loss": 2.2537,
|
| 165 |
"step": 26
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 0.09,
|
| 169 |
+
"learning_rate": 0.00018144329896907217,
|
| 170 |
+
"loss": 2.1975,
|
| 171 |
"step": 27
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 0.1,
|
| 175 |
+
"learning_rate": 0.0001807560137457045,
|
| 176 |
+
"loss": 2.2566,
|
| 177 |
"step": 28
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.1,
|
| 181 |
+
"learning_rate": 0.00018006872852233677,
|
| 182 |
+
"loss": 2.1464,
|
| 183 |
"step": 29
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 0.1,
|
| 187 |
+
"learning_rate": 0.0001793814432989691,
|
| 188 |
+
"loss": 2.1421,
|
| 189 |
"step": 30
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 0.11,
|
| 193 |
+
"learning_rate": 0.0001786941580756014,
|
| 194 |
+
"loss": 2.1276,
|
| 195 |
"step": 31
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 0.11,
|
| 199 |
+
"learning_rate": 0.00017800687285223366,
|
| 200 |
+
"loss": 2.0649,
|
| 201 |
"step": 32
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 0.11,
|
| 205 |
+
"learning_rate": 0.00017731958762886598,
|
| 206 |
+
"loss": 2.1835,
|
| 207 |
"step": 33
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 0.12,
|
| 211 |
+
"learning_rate": 0.0001766323024054983,
|
| 212 |
+
"loss": 2.1711,
|
| 213 |
"step": 34
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 0.12,
|
| 217 |
+
"learning_rate": 0.00017594501718213058,
|
| 218 |
+
"loss": 2.2591,
|
| 219 |
"step": 35
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.12,
|
| 223 |
+
"learning_rate": 0.0001752577319587629,
|
| 224 |
+
"loss": 2.1471,
|
| 225 |
"step": 36
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 0.13,
|
| 229 |
+
"learning_rate": 0.0001745704467353952,
|
| 230 |
+
"loss": 2.0861,
|
| 231 |
"step": 37
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 0.13,
|
| 235 |
+
"learning_rate": 0.0001738831615120275,
|
| 236 |
+
"loss": 2.0702,
|
| 237 |
"step": 38
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 0.13,
|
| 241 |
+
"learning_rate": 0.0001731958762886598,
|
| 242 |
+
"loss": 2.1096,
|
| 243 |
"step": 39
|
| 244 |
},
|
| 245 |
{
|
| 246 |
+
"epoch": 0.14,
|
| 247 |
+
"learning_rate": 0.00017250859106529212,
|
| 248 |
+
"loss": 2.1062,
|
| 249 |
"step": 40
|
| 250 |
},
|
| 251 |
{
|
| 252 |
+
"epoch": 0.14,
|
| 253 |
+
"learning_rate": 0.00017182130584192438,
|
| 254 |
+
"loss": 2.2545,
|
| 255 |
"step": 41
|
| 256 |
},
|
| 257 |
{
|
| 258 |
+
"epoch": 0.14,
|
| 259 |
+
"learning_rate": 0.0001711340206185567,
|
| 260 |
+
"loss": 2.1572,
|
| 261 |
"step": 42
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 0.15,
|
| 265 |
+
"learning_rate": 0.000170446735395189,
|
| 266 |
+
"loss": 2.0749,
|
| 267 |
"step": 43
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 0.15,
|
| 271 |
+
"learning_rate": 0.0001697594501718213,
|
| 272 |
+
"loss": 2.1922,
|
| 273 |
"step": 44
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"epoch": 0.15,
|
| 277 |
+
"learning_rate": 0.00016907216494845361,
|
| 278 |
+
"loss": 2.1915,
|
| 279 |
"step": 45
|
| 280 |
},
|
| 281 |
{
|
| 282 |
+
"epoch": 0.16,
|
| 283 |
+
"learning_rate": 0.00016838487972508593,
|
| 284 |
+
"loss": 2.1594,
|
| 285 |
"step": 46
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 0.16,
|
| 289 |
+
"learning_rate": 0.00016769759450171822,
|
| 290 |
+
"loss": 2.176,
|
| 291 |
"step": 47
|
| 292 |
},
|
| 293 |
{
|
| 294 |
+
"epoch": 0.16,
|
| 295 |
+
"learning_rate": 0.00016701030927835053,
|
| 296 |
+
"loss": 2.1223,
|
| 297 |
"step": 48
|
| 298 |
},
|
| 299 |
{
|
| 300 |
+
"epoch": 0.17,
|
| 301 |
+
"learning_rate": 0.00016632302405498285,
|
| 302 |
+
"loss": 2.1263,
|
| 303 |
"step": 49
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 0.17,
|
| 307 |
+
"learning_rate": 0.00016563573883161513,
|
| 308 |
+
"loss": 2.0481,
|
| 309 |
"step": 50
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 0.17,
|
| 313 |
+
"learning_rate": 0.00016494845360824742,
|
| 314 |
+
"loss": 2.1043,
|
| 315 |
"step": 51
|
| 316 |
},
|
| 317 |
{
|
| 318 |
+
"epoch": 0.18,
|
| 319 |
+
"learning_rate": 0.00016426116838487973,
|
| 320 |
+
"loss": 2.1678,
|
| 321 |
"step": 52
|
| 322 |
},
|
| 323 |
{
|
| 324 |
+
"epoch": 0.18,
|
| 325 |
+
"learning_rate": 0.00016357388316151202,
|
| 326 |
+
"loss": 2.1602,
|
| 327 |
"step": 53
|
| 328 |
},
|
| 329 |
{
|
| 330 |
+
"epoch": 0.19,
|
| 331 |
+
"learning_rate": 0.00016288659793814434,
|
| 332 |
+
"loss": 2.1448,
|
| 333 |
"step": 54
|
| 334 |
},
|
| 335 |
{
|
| 336 |
+
"epoch": 0.19,
|
| 337 |
+
"learning_rate": 0.00016219931271477665,
|
| 338 |
+
"loss": 2.1536,
|
| 339 |
"step": 55
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 0.19,
|
| 343 |
+
"learning_rate": 0.00016151202749140894,
|
| 344 |
+
"loss": 2.0339,
|
| 345 |
"step": 56
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 0.2,
|
| 349 |
+
"learning_rate": 0.00016082474226804125,
|
| 350 |
+
"loss": 2.023,
|
| 351 |
"step": 57
|
| 352 |
},
|
| 353 |
{
|
| 354 |
+
"epoch": 0.2,
|
| 355 |
+
"learning_rate": 0.00016013745704467357,
|
| 356 |
+
"loss": 2.1407,
|
| 357 |
"step": 58
|
| 358 |
},
|
| 359 |
{
|
| 360 |
+
"epoch": 0.2,
|
| 361 |
+
"learning_rate": 0.00015945017182130585,
|
| 362 |
+
"loss": 2.1134,
|
| 363 |
"step": 59
|
| 364 |
},
|
| 365 |
{
|
| 366 |
+
"epoch": 0.21,
|
| 367 |
+
"learning_rate": 0.00015876288659793814,
|
| 368 |
+
"loss": 2.1652,
|
| 369 |
"step": 60
|
| 370 |
},
|
| 371 |
{
|
| 372 |
+
"epoch": 0.21,
|
| 373 |
+
"learning_rate": 0.00015807560137457046,
|
| 374 |
+
"loss": 2.0051,
|
| 375 |
"step": 61
|
| 376 |
},
|
| 377 |
{
|
| 378 |
+
"epoch": 0.21,
|
| 379 |
+
"learning_rate": 0.00015738831615120274,
|
| 380 |
+
"loss": 2.0604,
|
| 381 |
"step": 62
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 0.22,
|
| 385 |
+
"learning_rate": 0.00015670103092783506,
|
| 386 |
+
"loss": 2.1708,
|
| 387 |
"step": 63
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 0.22,
|
| 391 |
+
"learning_rate": 0.00015601374570446737,
|
| 392 |
+
"loss": 2.1106,
|
| 393 |
"step": 64
|
| 394 |
},
|
| 395 |
{
|
| 396 |
+
"epoch": 0.22,
|
| 397 |
+
"learning_rate": 0.00015532646048109966,
|
| 398 |
+
"loss": 2.1445,
|
| 399 |
"step": 65
|
| 400 |
},
|
| 401 |
{
|
| 402 |
+
"epoch": 0.23,
|
| 403 |
+
"learning_rate": 0.00015463917525773197,
|
| 404 |
+
"loss": 2.0879,
|
| 405 |
"step": 66
|
| 406 |
},
|
| 407 |
{
|
| 408 |
+
"epoch": 0.23,
|
| 409 |
+
"learning_rate": 0.0001539518900343643,
|
| 410 |
+
"loss": 2.1498,
|
| 411 |
"step": 67
|
| 412 |
},
|
| 413 |
{
|
| 414 |
+
"epoch": 0.23,
|
| 415 |
+
"learning_rate": 0.00015326460481099657,
|
| 416 |
+
"loss": 2.0719,
|
| 417 |
"step": 68
|
| 418 |
},
|
| 419 |
{
|
| 420 |
+
"epoch": 0.24,
|
| 421 |
+
"learning_rate": 0.00015257731958762886,
|
| 422 |
+
"loss": 2.2167,
|
| 423 |
"step": 69
|
| 424 |
},
|
| 425 |
{
|
| 426 |
+
"epoch": 0.24,
|
| 427 |
+
"learning_rate": 0.00015189003436426118,
|
| 428 |
+
"loss": 2.0811,
|
| 429 |
"step": 70
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 0.24,
|
| 433 |
+
"learning_rate": 0.00015120274914089346,
|
| 434 |
+
"loss": 2.1058,
|
| 435 |
"step": 71
|
| 436 |
},
|
| 437 |
{
|
| 438 |
+
"epoch": 0.25,
|
| 439 |
+
"learning_rate": 0.00015051546391752578,
|
| 440 |
+
"loss": 2.0392,
|
| 441 |
"step": 72
|
| 442 |
},
|
| 443 |
{
|
| 444 |
+
"epoch": 0.25,
|
| 445 |
+
"learning_rate": 0.0001498281786941581,
|
| 446 |
+
"loss": 2.0957,
|
| 447 |
"step": 73
|
| 448 |
},
|
| 449 |
{
|
| 450 |
+
"epoch": 0.25,
|
| 451 |
+
"learning_rate": 0.00014914089347079038,
|
| 452 |
+
"loss": 1.9994,
|
| 453 |
"step": 74
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 0.26,
|
| 457 |
+
"learning_rate": 0.0001484536082474227,
|
| 458 |
+
"loss": 2.0464,
|
| 459 |
"step": 75
|
| 460 |
},
|
| 461 |
{
|
| 462 |
+
"epoch": 0.26,
|
| 463 |
+
"learning_rate": 0.000147766323024055,
|
| 464 |
+
"loss": 2.0417,
|
| 465 |
"step": 76
|
| 466 |
},
|
| 467 |
{
|
| 468 |
+
"epoch": 0.26,
|
| 469 |
+
"learning_rate": 0.0001470790378006873,
|
| 470 |
+
"loss": 2.105,
|
| 471 |
"step": 77
|
| 472 |
},
|
| 473 |
{
|
| 474 |
+
"epoch": 0.27,
|
| 475 |
+
"learning_rate": 0.00014639175257731958,
|
| 476 |
+
"loss": 2.1147,
|
| 477 |
"step": 78
|
| 478 |
},
|
| 479 |
{
|
| 480 |
+
"epoch": 0.27,
|
| 481 |
+
"learning_rate": 0.0001457044673539519,
|
| 482 |
+
"loss": 1.9964,
|
| 483 |
"step": 79
|
| 484 |
},
|
| 485 |
{
|
| 486 |
+
"epoch": 0.27,
|
| 487 |
+
"learning_rate": 0.00014501718213058418,
|
| 488 |
+
"loss": 1.9723,
|
| 489 |
"step": 80
|
| 490 |
},
|
| 491 |
{
|
| 492 |
+
"epoch": 0.28,
|
| 493 |
+
"learning_rate": 0.0001443298969072165,
|
| 494 |
+
"loss": 2.0621,
|
| 495 |
"step": 81
|
| 496 |
},
|
| 497 |
{
|
| 498 |
+
"epoch": 0.28,
|
| 499 |
+
"learning_rate": 0.00014364261168384881,
|
| 500 |
+
"loss": 2.2703,
|
| 501 |
"step": 82
|
| 502 |
},
|
| 503 |
{
|
| 504 |
+
"epoch": 0.28,
|
| 505 |
+
"learning_rate": 0.0001429553264604811,
|
| 506 |
+
"loss": 2.0815,
|
| 507 |
"step": 83
|
| 508 |
},
|
| 509 |
{
|
| 510 |
+
"epoch": 0.29,
|
| 511 |
+
"learning_rate": 0.00014226804123711342,
|
| 512 |
+
"loss": 2.0774,
|
| 513 |
"step": 84
|
| 514 |
},
|
| 515 |
{
|
| 516 |
+
"epoch": 0.29,
|
| 517 |
+
"learning_rate": 0.00014158075601374573,
|
| 518 |
+
"loss": 2.066,
|
| 519 |
"step": 85
|
| 520 |
},
|
| 521 |
{
|
| 522 |
+
"epoch": 0.29,
|
| 523 |
+
"learning_rate": 0.00014089347079037802,
|
| 524 |
+
"loss": 2.03,
|
| 525 |
"step": 86
|
| 526 |
},
|
| 527 |
{
|
| 528 |
+
"epoch": 0.3,
|
| 529 |
+
"learning_rate": 0.0001402061855670103,
|
| 530 |
+
"loss": 2.1433,
|
| 531 |
"step": 87
|
| 532 |
},
|
| 533 |
{
|
| 534 |
+
"epoch": 0.3,
|
| 535 |
+
"learning_rate": 0.00013951890034364262,
|
| 536 |
+
"loss": 2.0811,
|
| 537 |
"step": 88
|
| 538 |
},
|
| 539 |
{
|
| 540 |
+
"epoch": 0.31,
|
| 541 |
+
"learning_rate": 0.0001388316151202749,
|
| 542 |
+
"loss": 1.9791,
|
| 543 |
"step": 89
|
| 544 |
},
|
| 545 |
{
|
| 546 |
+
"epoch": 0.31,
|
| 547 |
+
"learning_rate": 0.00013814432989690722,
|
| 548 |
+
"loss": 2.0876,
|
| 549 |
"step": 90
|
| 550 |
},
|
| 551 |
{
|
| 552 |
+
"epoch": 0.31,
|
| 553 |
+
"learning_rate": 0.00013745704467353953,
|
| 554 |
+
"loss": 2.0314,
|
| 555 |
"step": 91
|
| 556 |
},
|
| 557 |
{
|
| 558 |
+
"epoch": 0.32,
|
| 559 |
+
"learning_rate": 0.00013676975945017182,
|
| 560 |
+
"loss": 1.9485,
|
| 561 |
"step": 92
|
| 562 |
},
|
| 563 |
{
|
| 564 |
+
"epoch": 0.32,
|
| 565 |
+
"learning_rate": 0.00013608247422680414,
|
| 566 |
+
"loss": 2.078,
|
| 567 |
"step": 93
|
| 568 |
},
|
| 569 |
{
|
| 570 |
+
"epoch": 0.32,
|
| 571 |
+
"learning_rate": 0.00013539518900343645,
|
| 572 |
+
"loss": 2.1251,
|
| 573 |
"step": 94
|
| 574 |
},
|
| 575 |
{
|
| 576 |
+
"epoch": 0.33,
|
| 577 |
+
"learning_rate": 0.00013470790378006874,
|
| 578 |
+
"loss": 1.9736,
|
| 579 |
"step": 95
|
| 580 |
},
|
| 581 |
{
|
| 582 |
+
"epoch": 0.33,
|
| 583 |
+
"learning_rate": 0.00013402061855670103,
|
| 584 |
+
"loss": 2.0189,
|
| 585 |
"step": 96
|
| 586 |
},
|
| 587 |
{
|
| 588 |
+
"epoch": 0.33,
|
| 589 |
+
"learning_rate": 0.00013333333333333334,
|
| 590 |
+
"loss": 2.0061,
|
| 591 |
"step": 97
|
| 592 |
},
|
| 593 |
{
|
| 594 |
+
"epoch": 0.34,
|
| 595 |
+
"learning_rate": 0.00013264604810996563,
|
| 596 |
+
"loss": 1.9595,
|
| 597 |
"step": 98
|
| 598 |
},
|
| 599 |
{
|
| 600 |
+
"epoch": 0.34,
|
| 601 |
+
"learning_rate": 0.00013195876288659794,
|
| 602 |
+
"loss": 1.9702,
|
| 603 |
"step": 99
|
| 604 |
},
|
| 605 |
{
|
| 606 |
+
"epoch": 0.34,
|
| 607 |
+
"learning_rate": 0.00013127147766323026,
|
| 608 |
+
"loss": 2.0322,
|
| 609 |
"step": 100
|
| 610 |
}
|
| 611 |
],
|
| 612 |
"logging_steps": 1,
|
| 613 |
+
"max_steps": 291,
|
| 614 |
+
"num_train_epochs": 1,
|
| 615 |
"save_steps": 100,
|
| 616 |
+
"total_flos": 6.083398113601536e+16,
|
| 617 |
"trial_name": null,
|
| 618 |
"trial_params": null
|
| 619 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4027
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e3410eea0ea0eb09ca576511099334880accaab360c0279f3099c9e4d2e877a
|
| 3 |
size 4027
|