Training in progress, step 10, checkpoint
Browse files- last-checkpoint/README.md +1 -1
- last-checkpoint/adapter_config.json +10 -8
- last-checkpoint/adapter_model.safetensors +2 -2
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +55 -371
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/README.md
CHANGED
|
@@ -207,4 +207,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 207 |
[More Information Needed]
|
| 208 |
### Framework versions
|
| 209 |
|
| 210 |
-
- PEFT 0.
|
|
|
|
| 207 |
[More Information Needed]
|
| 208 |
### Framework versions
|
| 209 |
|
| 210 |
+
- PEFT 0.19.1
|
last-checkpoint/adapter_config.json
CHANGED
|
@@ -20,30 +20,32 @@
|
|
| 20 |
"layers_pattern": null,
|
| 21 |
"layers_to_transform": null,
|
| 22 |
"loftq_config": {},
|
| 23 |
-
"lora_alpha":
|
| 24 |
"lora_bias": false,
|
| 25 |
-
"lora_dropout": 0.
|
|
|
|
| 26 |
"megatron_config": null,
|
| 27 |
"megatron_core": "megatron.core",
|
| 28 |
"modules_to_save": null,
|
| 29 |
"peft_type": "LORA",
|
| 30 |
-
"peft_version": "0.
|
| 31 |
"qalora_group_size": 16,
|
| 32 |
-
"r":
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
|
|
|
|
|
|
| 36 |
"v_proj",
|
| 37 |
"o_proj",
|
| 38 |
-
"down_proj",
|
| 39 |
-
"k_proj",
|
| 40 |
-
"up_proj",
|
| 41 |
"gate_proj",
|
| 42 |
-
"
|
|
|
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
| 46 |
"trainable_token_indices": null,
|
|
|
|
| 47 |
"use_dora": false,
|
| 48 |
"use_qalora": false,
|
| 49 |
"use_rslora": false
|
|
|
|
| 20 |
"layers_pattern": null,
|
| 21 |
"layers_to_transform": null,
|
| 22 |
"loftq_config": {},
|
| 23 |
+
"lora_alpha": 32,
|
| 24 |
"lora_bias": false,
|
| 25 |
+
"lora_dropout": 0.0,
|
| 26 |
+
"lora_ga_config": null,
|
| 27 |
"megatron_config": null,
|
| 28 |
"megatron_core": "megatron.core",
|
| 29 |
"modules_to_save": null,
|
| 30 |
"peft_type": "LORA",
|
| 31 |
+
"peft_version": "0.19.1",
|
| 32 |
"qalora_group_size": 16,
|
| 33 |
+
"r": 16,
|
| 34 |
"rank_pattern": {},
|
| 35 |
"revision": null,
|
| 36 |
"target_modules": [
|
| 37 |
+
"down_proj",
|
| 38 |
+
"q_proj",
|
| 39 |
"v_proj",
|
| 40 |
"o_proj",
|
|
|
|
|
|
|
|
|
|
| 41 |
"gate_proj",
|
| 42 |
+
"up_proj",
|
| 43 |
+
"k_proj"
|
| 44 |
],
|
| 45 |
"target_parameters": null,
|
| 46 |
"task_type": "CAUSAL_LM",
|
| 47 |
"trainable_token_indices": null,
|
| 48 |
+
"use_bdlora": null,
|
| 49 |
"use_dora": false,
|
| 50 |
"use_qalora": false,
|
| 51 |
"use_rslora": false
|
last-checkpoint/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:f9f0021979b6cdf5f022417c3800dfdb5c51ec6b7ac3228bbe0f98142ddef9d5
|
| 3 |
+
size 35237104
|
last-checkpoint/optimizer.pt
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 sha256:5321ddddef2a96f4d59762067250b61bc0564f1915575df12b264680f3530690
|
| 3 |
+
size 18813829
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c800b778fa7e115e4c34de8529902de8b61c9a1b4bab3eb8295d06dafff030e
|
| 3 |
size 14645
|
last-checkpoint/scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1383
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f573b9f7149922ed73a27c9028f6f2cbdca1c0ef23c998ef777ef3be95e566d
|
| 3 |
size 1383
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:579c3a8590564ed7e91a6b14a7e35d84de8539e45b9a2dc709c0b7ead5628675
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,414 +1,98 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 2.
|
| 4 |
-
"best_model_checkpoint": "/tmp/checkpoints_/
|
| 5 |
-
"epoch":
|
| 6 |
-
"eval_steps":
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
-
"epoch": 0.
|
| 14 |
-
"grad_norm":
|
| 15 |
"learning_rate": 0.0,
|
| 16 |
-
"loss":
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"grad_norm":
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss": 3.
|
| 24 |
"step": 2
|
| 25 |
},
|
| 26 |
{
|
| 27 |
-
"epoch": 0.
|
| 28 |
-
"grad_norm":
|
| 29 |
-
"learning_rate":
|
| 30 |
-
"loss":
|
| 31 |
"step": 3
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch": 0.
|
| 35 |
-
"grad_norm":
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 3.
|
| 38 |
"step": 4
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"grad_norm":
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss": 3.
|
| 45 |
"step": 5
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
| 49 |
-
"grad_norm":
|
| 50 |
-
"learning_rate":
|
| 51 |
-
"loss": 3.
|
| 52 |
"step": 6
|
| 53 |
},
|
| 54 |
{
|
| 55 |
-
"epoch": 0.
|
| 56 |
-
"grad_norm":
|
| 57 |
-
"learning_rate":
|
| 58 |
-
"loss": 3.
|
| 59 |
"step": 7
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 0.
|
| 63 |
-
"grad_norm":
|
| 64 |
-
"learning_rate":
|
| 65 |
-
"loss":
|
| 66 |
"step": 8
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch": 0.
|
| 70 |
-
"grad_norm":
|
| 71 |
-
"learning_rate":
|
| 72 |
-
"loss":
|
| 73 |
"step": 9
|
| 74 |
},
|
| 75 |
{
|
| 76 |
-
"epoch": 0.
|
| 77 |
-
"grad_norm":
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss":
|
| 80 |
"step": 10
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"
|
| 85 |
-
"
|
| 86 |
-
"
|
| 87 |
-
"
|
| 88 |
-
|
| 89 |
-
{
|
| 90 |
-
"epoch": 0.6666666666666666,
|
| 91 |
-
"grad_norm": 1.6800596714019775,
|
| 92 |
-
"learning_rate": 2.63265306122449e-05,
|
| 93 |
-
"loss": 3.2913851737976074,
|
| 94 |
-
"step": 12
|
| 95 |
-
},
|
| 96 |
-
{
|
| 97 |
-
"epoch": 0.7222222222222222,
|
| 98 |
-
"grad_norm": 1.571210265159607,
|
| 99 |
-
"learning_rate": 2.5714285714285714e-05,
|
| 100 |
-
"loss": 3.101820230484009,
|
| 101 |
-
"step": 13
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 0.7777777777777778,
|
| 105 |
-
"grad_norm": 1.5015455484390259,
|
| 106 |
-
"learning_rate": 2.5102040816326533e-05,
|
| 107 |
-
"loss": 3.0722804069519043,
|
| 108 |
-
"step": 14
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 0.8333333333333334,
|
| 112 |
-
"grad_norm": 1.5175955295562744,
|
| 113 |
-
"learning_rate": 2.448979591836735e-05,
|
| 114 |
-
"loss": 3.186123847961426,
|
| 115 |
-
"step": 15
|
| 116 |
-
},
|
| 117 |
-
{
|
| 118 |
-
"epoch": 0.8888888888888888,
|
| 119 |
-
"grad_norm": 1.7556886672973633,
|
| 120 |
-
"learning_rate": 2.3877551020408164e-05,
|
| 121 |
-
"loss": 3.1206796169281006,
|
| 122 |
-
"step": 16
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 0.9444444444444444,
|
| 126 |
-
"grad_norm": 1.4313125610351562,
|
| 127 |
-
"learning_rate": 2.326530612244898e-05,
|
| 128 |
-
"loss": 3.053194046020508,
|
| 129 |
-
"step": 17
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 1.0,
|
| 133 |
-
"grad_norm": 1.7054771184921265,
|
| 134 |
-
"learning_rate": 2.2653061224489794e-05,
|
| 135 |
-
"loss": 3.13295841217041,
|
| 136 |
-
"step": 18
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 1.0555555555555556,
|
| 140 |
-
"grad_norm": 1.358532190322876,
|
| 141 |
-
"learning_rate": 2.2040816326530613e-05,
|
| 142 |
-
"loss": 2.984301805496216,
|
| 143 |
-
"step": 19
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 1.1111111111111112,
|
| 147 |
-
"grad_norm": 1.5754305124282837,
|
| 148 |
-
"learning_rate": 2.1428571428571428e-05,
|
| 149 |
-
"loss": 3.0700297355651855,
|
| 150 |
-
"step": 20
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 1.1666666666666667,
|
| 154 |
-
"grad_norm": 1.483549952507019,
|
| 155 |
-
"learning_rate": 2.0816326530612247e-05,
|
| 156 |
-
"loss": 2.9767420291900635,
|
| 157 |
-
"step": 21
|
| 158 |
-
},
|
| 159 |
-
{
|
| 160 |
-
"epoch": 1.2222222222222223,
|
| 161 |
-
"grad_norm": 1.4538898468017578,
|
| 162 |
-
"learning_rate": 2.0204081632653062e-05,
|
| 163 |
-
"loss": 3.059295654296875,
|
| 164 |
-
"step": 22
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 1.2777777777777777,
|
| 168 |
-
"grad_norm": 1.719199299812317,
|
| 169 |
-
"learning_rate": 1.9591836734693877e-05,
|
| 170 |
-
"loss": 2.92179012298584,
|
| 171 |
-
"step": 23
|
| 172 |
-
},
|
| 173 |
-
{
|
| 174 |
-
"epoch": 1.3333333333333333,
|
| 175 |
-
"grad_norm": 1.480421781539917,
|
| 176 |
-
"learning_rate": 1.8979591836734696e-05,
|
| 177 |
-
"loss": 3.0855214595794678,
|
| 178 |
-
"step": 24
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 1.3888888888888888,
|
| 182 |
-
"grad_norm": 1.6154485940933228,
|
| 183 |
-
"learning_rate": 1.836734693877551e-05,
|
| 184 |
-
"loss": 3.064807891845703,
|
| 185 |
-
"step": 25
|
| 186 |
-
},
|
| 187 |
-
{
|
| 188 |
-
"epoch": 1.4444444444444444,
|
| 189 |
-
"grad_norm": 1.4917209148406982,
|
| 190 |
-
"learning_rate": 1.7755102040816327e-05,
|
| 191 |
-
"loss": 2.91068696975708,
|
| 192 |
-
"step": 26
|
| 193 |
-
},
|
| 194 |
-
{
|
| 195 |
-
"epoch": 1.5,
|
| 196 |
-
"grad_norm": 1.5245044231414795,
|
| 197 |
-
"learning_rate": 1.7142857142857142e-05,
|
| 198 |
-
"loss": 2.9561421871185303,
|
| 199 |
-
"step": 27
|
| 200 |
-
},
|
| 201 |
-
{
|
| 202 |
-
"epoch": 1.5555555555555556,
|
| 203 |
-
"grad_norm": 1.5324742794036865,
|
| 204 |
-
"learning_rate": 1.6530612244897957e-05,
|
| 205 |
-
"loss": 2.79599928855896,
|
| 206 |
-
"step": 28
|
| 207 |
-
},
|
| 208 |
-
{
|
| 209 |
-
"epoch": 1.6111111111111112,
|
| 210 |
-
"grad_norm": 1.4050549268722534,
|
| 211 |
-
"learning_rate": 1.5918367346938776e-05,
|
| 212 |
-
"loss": 2.8820788860321045,
|
| 213 |
-
"step": 29
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 1.6666666666666665,
|
| 217 |
-
"grad_norm": 1.4317318201065063,
|
| 218 |
-
"learning_rate": 1.530612244897959e-05,
|
| 219 |
-
"loss": 2.9031014442443848,
|
| 220 |
-
"step": 30
|
| 221 |
-
},
|
| 222 |
-
{
|
| 223 |
-
"epoch": 1.7222222222222223,
|
| 224 |
-
"grad_norm": 1.8499871492385864,
|
| 225 |
-
"learning_rate": 1.4693877551020408e-05,
|
| 226 |
-
"loss": 2.8744847774505615,
|
| 227 |
-
"step": 31
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 1.7777777777777777,
|
| 231 |
-
"grad_norm": 1.7179501056671143,
|
| 232 |
-
"learning_rate": 1.4081632653061225e-05,
|
| 233 |
-
"loss": 2.789229393005371,
|
| 234 |
-
"step": 32
|
| 235 |
-
},
|
| 236 |
-
{
|
| 237 |
-
"epoch": 1.8333333333333335,
|
| 238 |
-
"grad_norm": 1.6091358661651611,
|
| 239 |
-
"learning_rate": 1.3469387755102042e-05,
|
| 240 |
-
"loss": 2.811561107635498,
|
| 241 |
-
"step": 33
|
| 242 |
-
},
|
| 243 |
-
{
|
| 244 |
-
"epoch": 1.8888888888888888,
|
| 245 |
-
"grad_norm": 1.7572782039642334,
|
| 246 |
-
"learning_rate": 1.2857142857142857e-05,
|
| 247 |
-
"loss": 2.8885252475738525,
|
| 248 |
-
"step": 34
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 1.9444444444444444,
|
| 252 |
-
"grad_norm": 1.3684682846069336,
|
| 253 |
-
"learning_rate": 1.2244897959183674e-05,
|
| 254 |
-
"loss": 2.785585403442383,
|
| 255 |
-
"step": 35
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 2.0,
|
| 259 |
-
"grad_norm": 1.3578567504882812,
|
| 260 |
-
"learning_rate": 1.163265306122449e-05,
|
| 261 |
-
"loss": 2.7695488929748535,
|
| 262 |
-
"step": 36
|
| 263 |
-
},
|
| 264 |
-
{
|
| 265 |
-
"epoch": 2.0555555555555554,
|
| 266 |
-
"grad_norm": 1.3852839469909668,
|
| 267 |
-
"learning_rate": 1.1020408163265306e-05,
|
| 268 |
-
"loss": 2.7894017696380615,
|
| 269 |
-
"step": 37
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 2.111111111111111,
|
| 273 |
-
"grad_norm": 1.378752589225769,
|
| 274 |
-
"learning_rate": 1.0408163265306123e-05,
|
| 275 |
-
"loss": 2.760788679122925,
|
| 276 |
-
"step": 38
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 2.1666666666666665,
|
| 280 |
-
"grad_norm": 1.4855753183364868,
|
| 281 |
-
"learning_rate": 9.795918367346939e-06,
|
| 282 |
-
"loss": 2.8628170490264893,
|
| 283 |
-
"step": 39
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"epoch": 2.2222222222222223,
|
| 287 |
-
"grad_norm": 2.0683376789093018,
|
| 288 |
-
"learning_rate": 9.183673469387756e-06,
|
| 289 |
-
"loss": 2.836902141571045,
|
| 290 |
-
"step": 40
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 2.2777777777777777,
|
| 294 |
-
"grad_norm": 1.4104969501495361,
|
| 295 |
-
"learning_rate": 8.571428571428571e-06,
|
| 296 |
-
"loss": 2.778287410736084,
|
| 297 |
-
"step": 41
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 2.3333333333333335,
|
| 301 |
-
"grad_norm": 1.5490999221801758,
|
| 302 |
-
"learning_rate": 7.959183673469388e-06,
|
| 303 |
-
"loss": 2.7003777027130127,
|
| 304 |
-
"step": 42
|
| 305 |
-
},
|
| 306 |
-
{
|
| 307 |
-
"epoch": 2.388888888888889,
|
| 308 |
-
"grad_norm": 1.451905369758606,
|
| 309 |
-
"learning_rate": 7.346938775510204e-06,
|
| 310 |
-
"loss": 2.713237762451172,
|
| 311 |
-
"step": 43
|
| 312 |
-
},
|
| 313 |
-
{
|
| 314 |
-
"epoch": 2.4444444444444446,
|
| 315 |
-
"grad_norm": 1.5038654804229736,
|
| 316 |
-
"learning_rate": 6.734693877551021e-06,
|
| 317 |
-
"loss": 2.761265516281128,
|
| 318 |
-
"step": 44
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 2.5,
|
| 322 |
-
"grad_norm": 1.767270803451538,
|
| 323 |
-
"learning_rate": 6.122448979591837e-06,
|
| 324 |
-
"loss": 2.8405728340148926,
|
| 325 |
-
"step": 45
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 2.5555555555555554,
|
| 329 |
-
"grad_norm": 1.5915592908859253,
|
| 330 |
-
"learning_rate": 5.510204081632653e-06,
|
| 331 |
-
"loss": 2.914803981781006,
|
| 332 |
-
"step": 46
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 2.611111111111111,
|
| 336 |
-
"grad_norm": 1.4227927923202515,
|
| 337 |
-
"learning_rate": 4.897959183673469e-06,
|
| 338 |
-
"loss": 2.7775824069976807,
|
| 339 |
-
"step": 47
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 2.6666666666666665,
|
| 343 |
-
"grad_norm": 1.753804326057434,
|
| 344 |
-
"learning_rate": 4.2857142857142855e-06,
|
| 345 |
-
"loss": 2.8131468296051025,
|
| 346 |
-
"step": 48
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 2.7222222222222223,
|
| 350 |
-
"grad_norm": 1.6903578042984009,
|
| 351 |
-
"learning_rate": 3.673469387755102e-06,
|
| 352 |
-
"loss": 2.6663997173309326,
|
| 353 |
-
"step": 49
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 2.7777777777777777,
|
| 357 |
-
"grad_norm": 1.4071599245071411,
|
| 358 |
-
"learning_rate": 3.0612244897959185e-06,
|
| 359 |
-
"loss": 2.672032356262207,
|
| 360 |
-
"step": 50
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 2.7777777777777777,
|
| 364 |
-
"eval_loss": 2.717481851577759,
|
| 365 |
-
"eval_runtime": 0.8887,
|
| 366 |
-
"eval_samples_per_second": 9.002,
|
| 367 |
-
"eval_steps_per_second": 2.251,
|
| 368 |
-
"step": 50
|
| 369 |
-
},
|
| 370 |
-
{
|
| 371 |
-
"epoch": 2.8333333333333335,
|
| 372 |
-
"grad_norm": 1.4306644201278687,
|
| 373 |
-
"learning_rate": 2.4489795918367347e-06,
|
| 374 |
-
"loss": 2.6522324085235596,
|
| 375 |
-
"step": 51
|
| 376 |
-
},
|
| 377 |
-
{
|
| 378 |
-
"epoch": 2.888888888888889,
|
| 379 |
-
"grad_norm": 1.5308632850646973,
|
| 380 |
-
"learning_rate": 1.836734693877551e-06,
|
| 381 |
-
"loss": 2.8062734603881836,
|
| 382 |
-
"step": 52
|
| 383 |
-
},
|
| 384 |
-
{
|
| 385 |
-
"epoch": 2.9444444444444446,
|
| 386 |
-
"grad_norm": 1.4577457904815674,
|
| 387 |
-
"learning_rate": 1.2244897959183673e-06,
|
| 388 |
-
"loss": 2.7906250953674316,
|
| 389 |
-
"step": 53
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 3.0,
|
| 393 |
-
"grad_norm": 1.3781952857971191,
|
| 394 |
-
"learning_rate": 6.122448979591837e-07,
|
| 395 |
-
"loss": 2.6654815673828125,
|
| 396 |
-
"step": 54
|
| 397 |
-
},
|
| 398 |
-
{
|
| 399 |
-
"epoch": 3.0,
|
| 400 |
-
"eval_loss": 2.712986469268799,
|
| 401 |
-
"eval_runtime": 0.3363,
|
| 402 |
-
"eval_samples_per_second": 23.788,
|
| 403 |
-
"eval_steps_per_second": 5.947,
|
| 404 |
-
"step": 54
|
| 405 |
}
|
| 406 |
],
|
| 407 |
"logging_steps": 1,
|
| 408 |
-
"max_steps":
|
| 409 |
"num_input_tokens_seen": 0,
|
| 410 |
"num_train_epochs": 3,
|
| 411 |
-
"save_steps":
|
| 412 |
"stateful_callbacks": {
|
| 413 |
"TrainerControl": {
|
| 414 |
"args": {
|
|
@@ -416,12 +100,12 @@
|
|
| 416 |
"should_evaluate": false,
|
| 417 |
"should_log": false,
|
| 418 |
"should_save": true,
|
| 419 |
-
"should_training_stop":
|
| 420 |
},
|
| 421 |
"attributes": {}
|
| 422 |
}
|
| 423 |
},
|
| 424 |
-
"total_flos":
|
| 425 |
"train_batch_size": 1,
|
| 426 |
"trial_name": null,
|
| 427 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 10,
|
| 3 |
+
"best_metric": 2.18822979927063,
|
| 4 |
+
"best_model_checkpoint": "/tmp/checkpoints_/job_0d4521ef-134d-4da5-986e-64cc35a0beaa/checkpoint-10",
|
| 5 |
+
"epoch": 0.2222222222222222,
|
| 6 |
+
"eval_steps": 10,
|
| 7 |
+
"global_step": 10,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
+
"epoch": 0.022222222222222223,
|
| 14 |
+
"grad_norm": 10.740789413452148,
|
| 15 |
"learning_rate": 0.0,
|
| 16 |
+
"loss": 4.085967063903809,
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.044444444444444446,
|
| 21 |
+
"grad_norm": 9.23949909210205,
|
| 22 |
+
"learning_rate": 1e-05,
|
| 23 |
+
"loss": 3.999408006668091,
|
| 24 |
"step": 2
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 0.06666666666666667,
|
| 28 |
+
"grad_norm": 12.284346580505371,
|
| 29 |
+
"learning_rate": 2e-05,
|
| 30 |
+
"loss": 4.025123596191406,
|
| 31 |
"step": 3
|
| 32 |
},
|
| 33 |
{
|
| 34 |
+
"epoch": 0.08888888888888889,
|
| 35 |
+
"grad_norm": 9.18883991241455,
|
| 36 |
+
"learning_rate": 3e-05,
|
| 37 |
+
"loss": 3.792623519897461,
|
| 38 |
"step": 4
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.1111111111111111,
|
| 42 |
+
"grad_norm": 7.945703983306885,
|
| 43 |
+
"learning_rate": 4e-05,
|
| 44 |
+
"loss": 3.6587512493133545,
|
| 45 |
"step": 5
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.13333333333333333,
|
| 49 |
+
"grad_norm": 7.3979291915893555,
|
| 50 |
+
"learning_rate": 5e-05,
|
| 51 |
+
"loss": 3.2053868770599365,
|
| 52 |
"step": 6
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 0.15555555555555556,
|
| 56 |
+
"grad_norm": 6.683148384094238,
|
| 57 |
+
"learning_rate": 4.999270035200483e-05,
|
| 58 |
+
"loss": 3.075692653656006,
|
| 59 |
"step": 7
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 0.17777777777777778,
|
| 63 |
+
"grad_norm": 5.784440994262695,
|
| 64 |
+
"learning_rate": 4.997080567080817e-05,
|
| 65 |
+
"loss": 2.732858419418335,
|
| 66 |
"step": 8
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 0.2,
|
| 70 |
+
"grad_norm": 5.552517414093018,
|
| 71 |
+
"learning_rate": 4.9934328742287285e-05,
|
| 72 |
+
"loss": 2.6176648139953613,
|
| 73 |
"step": 9
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 0.2222222222222222,
|
| 77 |
+
"grad_norm": 6.0725884437561035,
|
| 78 |
+
"learning_rate": 4.988329086794122e-05,
|
| 79 |
+
"loss": 2.3721094131469727,
|
| 80 |
"step": 10
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.2222222222222222,
|
| 84 |
+
"eval_loss": 2.18822979927063,
|
| 85 |
+
"eval_runtime": 0.6219,
|
| 86 |
+
"eval_samples_per_second": 32.162,
|
| 87 |
+
"eval_steps_per_second": 8.04,
|
| 88 |
+
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 89 |
}
|
| 90 |
],
|
| 91 |
"logging_steps": 1,
|
| 92 |
+
"max_steps": 135,
|
| 93 |
"num_input_tokens_seen": 0,
|
| 94 |
"num_train_epochs": 3,
|
| 95 |
+
"save_steps": 10,
|
| 96 |
"stateful_callbacks": {
|
| 97 |
"TrainerControl": {
|
| 98 |
"args": {
|
|
|
|
| 100 |
"should_evaluate": false,
|
| 101 |
"should_log": false,
|
| 102 |
"should_save": true,
|
| 103 |
+
"should_training_stop": false
|
| 104 |
},
|
| 105 |
"attributes": {}
|
| 106 |
}
|
| 107 |
},
|
| 108 |
+
"total_flos": 10910682305280.0,
|
| 109 |
"train_batch_size": 1,
|
| 110 |
"trial_name": null,
|
| 111 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5777
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67f2942c8e11304ba45e0886b5a7898c6beb9db4e00824e268c2c863692b4a72
|
| 3 |
size 5777
|