Upload 3 files
Browse files- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- trainer_state.json +383 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "Felladrin/TinyMistral-248M-Chat-v2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"o_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a15eb8cb355fabd6168bb9f76c1fab728133b3010cd4ea970b7a9ee538aff85
|
| 3 |
+
size 16930368
|
trainer_state.json
ADDED
|
@@ -0,0 +1,383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.004,
|
| 13 |
+
"grad_norm": 0.14456839859485626,
|
| 14 |
+
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 2.6994,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.008,
|
| 20 |
+
"grad_norm": 0.12785384058952332,
|
| 21 |
+
"learning_rate": 0.0002,
|
| 22 |
+
"loss": 2.5263,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.012,
|
| 27 |
+
"grad_norm": 0.13556812703609467,
|
| 28 |
+
"learning_rate": 0.0002,
|
| 29 |
+
"loss": 2.4,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.016,
|
| 34 |
+
"grad_norm": 0.16702307760715485,
|
| 35 |
+
"learning_rate": 0.0002,
|
| 36 |
+
"loss": 2.2516,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 0.3053046464920044,
|
| 42 |
+
"learning_rate": 0.0002,
|
| 43 |
+
"loss": 2.1036,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.024,
|
| 48 |
+
"grad_norm": 0.22266729176044464,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 2.3971,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.028,
|
| 55 |
+
"grad_norm": 0.14757753908634186,
|
| 56 |
+
"learning_rate": 0.0002,
|
| 57 |
+
"loss": 2.3272,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.032,
|
| 62 |
+
"grad_norm": 0.1445876806974411,
|
| 63 |
+
"learning_rate": 0.0002,
|
| 64 |
+
"loss": 2.3242,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.036,
|
| 69 |
+
"grad_norm": 0.1639222800731659,
|
| 70 |
+
"learning_rate": 0.0002,
|
| 71 |
+
"loss": 2.0874,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04,
|
| 76 |
+
"grad_norm": 0.30435118079185486,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 1.9193,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.044,
|
| 83 |
+
"grad_norm": 0.19899794459342957,
|
| 84 |
+
"learning_rate": 0.0002,
|
| 85 |
+
"loss": 2.3188,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.048,
|
| 90 |
+
"grad_norm": 0.171605184674263,
|
| 91 |
+
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 2.285,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.052,
|
| 97 |
+
"grad_norm": 0.18728512525558472,
|
| 98 |
+
"learning_rate": 0.0002,
|
| 99 |
+
"loss": 2.2458,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.056,
|
| 104 |
+
"grad_norm": 0.21194487810134888,
|
| 105 |
+
"learning_rate": 0.0002,
|
| 106 |
+
"loss": 2.038,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06,
|
| 111 |
+
"grad_norm": 0.3907397985458374,
|
| 112 |
+
"learning_rate": 0.0002,
|
| 113 |
+
"loss": 1.8128,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.064,
|
| 118 |
+
"grad_norm": 0.2305271327495575,
|
| 119 |
+
"learning_rate": 0.0002,
|
| 120 |
+
"loss": 2.2758,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.068,
|
| 125 |
+
"grad_norm": 0.1841125786304474,
|
| 126 |
+
"learning_rate": 0.0002,
|
| 127 |
+
"loss": 2.2169,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.072,
|
| 132 |
+
"grad_norm": 0.18488088250160217,
|
| 133 |
+
"learning_rate": 0.0002,
|
| 134 |
+
"loss": 2.1981,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.076,
|
| 139 |
+
"grad_norm": 0.22125467658042908,
|
| 140 |
+
"learning_rate": 0.0002,
|
| 141 |
+
"loss": 2.0181,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.08,
|
| 146 |
+
"grad_norm": 0.36263903975486755,
|
| 147 |
+
"learning_rate": 0.0002,
|
| 148 |
+
"loss": 1.7492,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.084,
|
| 153 |
+
"grad_norm": 0.23995819687843323,
|
| 154 |
+
"learning_rate": 0.0002,
|
| 155 |
+
"loss": 2.2287,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.088,
|
| 160 |
+
"grad_norm": 0.18997274339199066,
|
| 161 |
+
"learning_rate": 0.0002,
|
| 162 |
+
"loss": 2.2265,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.092,
|
| 167 |
+
"grad_norm": 0.19529950618743896,
|
| 168 |
+
"learning_rate": 0.0002,
|
| 169 |
+
"loss": 2.2107,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.096,
|
| 174 |
+
"grad_norm": 0.23907797038555145,
|
| 175 |
+
"learning_rate": 0.0002,
|
| 176 |
+
"loss": 1.9434,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1,
|
| 181 |
+
"grad_norm": 0.3128001093864441,
|
| 182 |
+
"learning_rate": 0.0002,
|
| 183 |
+
"loss": 1.7463,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.104,
|
| 188 |
+
"grad_norm": 0.22716236114501953,
|
| 189 |
+
"learning_rate": 0.0002,
|
| 190 |
+
"loss": 2.2284,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.108,
|
| 195 |
+
"grad_norm": 0.19475902616977692,
|
| 196 |
+
"learning_rate": 0.0002,
|
| 197 |
+
"loss": 2.1706,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.112,
|
| 202 |
+
"grad_norm": 0.19292621314525604,
|
| 203 |
+
"learning_rate": 0.0002,
|
| 204 |
+
"loss": 2.1211,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.116,
|
| 209 |
+
"grad_norm": 0.27429261803627014,
|
| 210 |
+
"learning_rate": 0.0002,
|
| 211 |
+
"loss": 1.916,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.12,
|
| 216 |
+
"grad_norm": 0.35040974617004395,
|
| 217 |
+
"learning_rate": 0.0002,
|
| 218 |
+
"loss": 1.6903,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.124,
|
| 223 |
+
"grad_norm": 0.25687935948371887,
|
| 224 |
+
"learning_rate": 0.0002,
|
| 225 |
+
"loss": 2.1812,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.128,
|
| 230 |
+
"grad_norm": 0.20279887318611145,
|
| 231 |
+
"learning_rate": 0.0002,
|
| 232 |
+
"loss": 2.2005,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.132,
|
| 237 |
+
"grad_norm": 0.22153416275978088,
|
| 238 |
+
"learning_rate": 0.0002,
|
| 239 |
+
"loss": 2.1195,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.136,
|
| 244 |
+
"grad_norm": 0.2411063015460968,
|
| 245 |
+
"learning_rate": 0.0002,
|
| 246 |
+
"loss": 1.8694,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.14,
|
| 251 |
+
"grad_norm": 0.3698059320449829,
|
| 252 |
+
"learning_rate": 0.0002,
|
| 253 |
+
"loss": 1.6522,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.144,
|
| 258 |
+
"grad_norm": 0.263630211353302,
|
| 259 |
+
"learning_rate": 0.0002,
|
| 260 |
+
"loss": 2.1644,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.148,
|
| 265 |
+
"grad_norm": 0.22328948974609375,
|
| 266 |
+
"learning_rate": 0.0002,
|
| 267 |
+
"loss": 2.1753,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.152,
|
| 272 |
+
"grad_norm": 0.21132981777191162,
|
| 273 |
+
"learning_rate": 0.0002,
|
| 274 |
+
"loss": 2.1191,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.156,
|
| 279 |
+
"grad_norm": 0.2776873707771301,
|
| 280 |
+
"learning_rate": 0.0002,
|
| 281 |
+
"loss": 1.8539,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.16,
|
| 286 |
+
"grad_norm": 0.34315550327301025,
|
| 287 |
+
"learning_rate": 0.0002,
|
| 288 |
+
"loss": 1.6447,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.164,
|
| 293 |
+
"grad_norm": 0.2831268906593323,
|
| 294 |
+
"learning_rate": 0.0002,
|
| 295 |
+
"loss": 2.1451,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.168,
|
| 300 |
+
"grad_norm": 0.2178158015012741,
|
| 301 |
+
"learning_rate": 0.0002,
|
| 302 |
+
"loss": 2.1368,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.172,
|
| 307 |
+
"grad_norm": 0.22629423439502716,
|
| 308 |
+
"learning_rate": 0.0002,
|
| 309 |
+
"loss": 2.1039,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.176,
|
| 314 |
+
"grad_norm": 0.2540661096572876,
|
| 315 |
+
"learning_rate": 0.0002,
|
| 316 |
+
"loss": 1.856,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.18,
|
| 321 |
+
"grad_norm": 0.3525744676589966,
|
| 322 |
+
"learning_rate": 0.0002,
|
| 323 |
+
"loss": 1.6286,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.184,
|
| 328 |
+
"grad_norm": 0.24233509600162506,
|
| 329 |
+
"learning_rate": 0.0002,
|
| 330 |
+
"loss": 2.1296,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.188,
|
| 335 |
+
"grad_norm": 0.20195922255516052,
|
| 336 |
+
"learning_rate": 0.0002,
|
| 337 |
+
"loss": 2.1321,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.192,
|
| 342 |
+
"grad_norm": 0.25681406259536743,
|
| 343 |
+
"learning_rate": 0.0002,
|
| 344 |
+
"loss": 2.0255,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.196,
|
| 349 |
+
"grad_norm": 0.2791021764278412,
|
| 350 |
+
"learning_rate": 0.0002,
|
| 351 |
+
"loss": 1.8141,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.2,
|
| 356 |
+
"grad_norm": 0.3304845690727234,
|
| 357 |
+
"learning_rate": 0.0002,
|
| 358 |
+
"loss": 1.6042,
|
| 359 |
+
"step": 500
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"logging_steps": 10,
|
| 363 |
+
"max_steps": 1000,
|
| 364 |
+
"num_input_tokens_seen": 0,
|
| 365 |
+
"num_train_epochs": 1,
|
| 366 |
+
"save_steps": 100,
|
| 367 |
+
"stateful_callbacks": {
|
| 368 |
+
"TrainerControl": {
|
| 369 |
+
"args": {
|
| 370 |
+
"should_epoch_stop": false,
|
| 371 |
+
"should_evaluate": false,
|
| 372 |
+
"should_log": false,
|
| 373 |
+
"should_save": true,
|
| 374 |
+
"should_training_stop": false
|
| 375 |
+
},
|
| 376 |
+
"attributes": {}
|
| 377 |
+
}
|
| 378 |
+
},
|
| 379 |
+
"total_flos": 1.7342773566308352e+16,
|
| 380 |
+
"train_batch_size": 12,
|
| 381 |
+
"trial_name": null,
|
| 382 |
+
"trial_params": null
|
| 383 |
+
}
|