Training in progress, step 50, checkpoint
Browse files- last-checkpoint/adapter_config.json +1 -1
- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/global_step50/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/global_step50/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/global_step50/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/global_step50/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/latest +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +51 -585
- last-checkpoint/training_args.bin +1 -1
last-checkpoint/adapter_config.json
CHANGED
|
@@ -19,7 +19,7 @@
|
|
| 19 |
"r": 8,
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
-
"target_modules": "^(?!.*patch_embed).*(?:
|
| 23 |
"task_type": "CAUSAL_LM",
|
| 24 |
"use_dora": false,
|
| 25 |
"use_rslora": false
|
|
|
|
| 19 |
"r": 8,
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
+
"target_modules": "^(?!.*patch_embed).*(?:k_proj|gate_proj|up_proj|fc2|v_proj|down_proj|proj|fc1|qkv|q_proj|o_proj).*",
|
| 23 |
"task_type": "CAUSAL_LM",
|
| 24 |
"use_dora": false,
|
| 25 |
"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 29034840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72a1dc75a4969cd4402c49224cdbeb8259d9c8645a8db3aac5f2374a463b3078
|
| 3 |
size 29034840
|
last-checkpoint/global_step50/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43429616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7c505d6abf258ee9c48764b56a1b54a9b537c8f7f6620c954d636e30695ebf3
|
| 3 |
size 43429616
|
last-checkpoint/global_step50/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43429616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e429059273aae561b31750be91a7e0b5527171d6cd29798def53c3a20a71ad9
|
| 3 |
size 43429616
|
last-checkpoint/global_step50/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43429616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:633189312a6d347dd04c28f96f91ca6de9203641fb44b01657e3fffafb5d6511
|
| 3 |
size 43429616
|
last-checkpoint/global_step50/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43429616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c3fafe9c1cf642ec6773405177d559dc9380e81a5ab08e42d2baefebc08e60d
|
| 3 |
size 43429616
|
last-checkpoint/latest
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
global_step50
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbe0d720c4c75a6a04213fa3b64bacbe794718a53e2b56ebb67a1a795014dfad
|
| 3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72452d3138d0ca2ff89429e3294a834ae7a68e8596fc757735ca56ae52509d57
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f36e306fb8ebcf53a167bfd6c9af74db410a269ada1e619e3e816f5269543b9d
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb47ce0c6f815a6f8302b0e3819b4c2315ca71dae3138d97fdceb765cdd0a039
|
| 3 |
size 15024
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e54bce6b4aaf0a5592cd43962528d57d1fed20da37bdb85e37a6f6789f8da9f
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,640 +1,106 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily/lora/sft/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"grad_norm":
|
| 14 |
"learning_rate": 6.944444444444445e-06,
|
| 15 |
-
"loss": 2.
|
| 16 |
"num_input_tokens_seen": 77944,
|
| 17 |
"step": 5
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 0.
|
| 21 |
-
"grad_norm": 21.
|
| 22 |
"learning_rate": 1.388888888888889e-05,
|
| 23 |
-
"loss":
|
| 24 |
-
"num_input_tokens_seen":
|
| 25 |
"step": 10
|
| 26 |
},
|
| 27 |
{
|
| 28 |
-
"epoch": 0.
|
| 29 |
-
"grad_norm":
|
| 30 |
"learning_rate": 2.0833333333333336e-05,
|
| 31 |
-
"loss": 2.
|
| 32 |
"num_input_tokens_seen": 233896,
|
| 33 |
"step": 15
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"grad_norm":
|
| 38 |
"learning_rate": 2.777777777777778e-05,
|
| 39 |
-
"loss": 1.
|
| 40 |
-
"num_input_tokens_seen":
|
| 41 |
"step": 20
|
| 42 |
},
|
| 43 |
{
|
| 44 |
-
"epoch": 0.
|
| 45 |
-
"grad_norm":
|
| 46 |
"learning_rate": 3.472222222222222e-05,
|
| 47 |
-
"loss":
|
| 48 |
-
"num_input_tokens_seen":
|
| 49 |
"step": 25
|
| 50 |
},
|
| 51 |
{
|
| 52 |
-
"epoch": 0.
|
| 53 |
-
"grad_norm":
|
| 54 |
"learning_rate": 4.166666666666667e-05,
|
| 55 |
-
"loss": 0.
|
| 56 |
-
"num_input_tokens_seen":
|
| 57 |
"step": 30
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch": 0.
|
| 61 |
-
"grad_norm":
|
| 62 |
"learning_rate": 4.8611111111111115e-05,
|
| 63 |
-
"loss": 0.
|
| 64 |
-
"num_input_tokens_seen":
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm": 0.
|
| 70 |
"learning_rate": 5.555555555555556e-05,
|
| 71 |
-
"loss": 0.
|
| 72 |
-
"num_input_tokens_seen":
|
| 73 |
"step": 40
|
| 74 |
},
|
| 75 |
{
|
| 76 |
-
"epoch": 0.
|
| 77 |
-
"grad_norm": 0.
|
| 78 |
"learning_rate": 6.25e-05,
|
| 79 |
-
"loss": 0.
|
| 80 |
-
"num_input_tokens_seen":
|
| 81 |
"step": 45
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
| 85 |
-
"grad_norm": 0.
|
| 86 |
"learning_rate": 6.944444444444444e-05,
|
| 87 |
-
"loss": 0.
|
| 88 |
-
"num_input_tokens_seen":
|
| 89 |
"step": 50
|
| 90 |
},
|
| 91 |
{
|
| 92 |
-
"epoch": 0.
|
| 93 |
-
"eval_loss": 0.
|
| 94 |
-
"eval_runtime":
|
| 95 |
-
"eval_samples_per_second": 1.
|
| 96 |
-
"eval_steps_per_second": 0.
|
| 97 |
-
"num_input_tokens_seen":
|
| 98 |
"step": 50
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 0.1527777777777778,
|
| 102 |
-
"grad_norm": 0.679315264214148,
|
| 103 |
-
"learning_rate": 7.638888888888889e-05,
|
| 104 |
-
"loss": 0.9113,
|
| 105 |
-
"num_input_tokens_seen": 857840,
|
| 106 |
-
"step": 55
|
| 107 |
-
},
|
| 108 |
-
{
|
| 109 |
-
"epoch": 0.16666666666666666,
|
| 110 |
-
"grad_norm": 0.6447084432724877,
|
| 111 |
-
"learning_rate": 8.333333333333334e-05,
|
| 112 |
-
"loss": 0.8999,
|
| 113 |
-
"num_input_tokens_seen": 935880,
|
| 114 |
-
"step": 60
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.18055555555555555,
|
| 118 |
-
"grad_norm": 0.4717419386009716,
|
| 119 |
-
"learning_rate": 9.027777777777779e-05,
|
| 120 |
-
"loss": 0.9027,
|
| 121 |
-
"num_input_tokens_seen": 1013824,
|
| 122 |
-
"step": 65
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 0.19444444444444445,
|
| 126 |
-
"grad_norm": 0.21169543073461422,
|
| 127 |
-
"learning_rate": 9.722222222222223e-05,
|
| 128 |
-
"loss": 0.8994,
|
| 129 |
-
"num_input_tokens_seen": 1091808,
|
| 130 |
-
"step": 70
|
| 131 |
-
},
|
| 132 |
-
{
|
| 133 |
-
"epoch": 0.20833333333333334,
|
| 134 |
-
"grad_norm": 0.40266651181937524,
|
| 135 |
-
"learning_rate": 9.999471159635539e-05,
|
| 136 |
-
"loss": 0.9049,
|
| 137 |
-
"num_input_tokens_seen": 1169744,
|
| 138 |
-
"step": 75
|
| 139 |
-
},
|
| 140 |
-
{
|
| 141 |
-
"epoch": 0.2222222222222222,
|
| 142 |
-
"grad_norm": 0.5050973334018934,
|
| 143 |
-
"learning_rate": 9.996239762521151e-05,
|
| 144 |
-
"loss": 0.9054,
|
| 145 |
-
"num_input_tokens_seen": 1247784,
|
| 146 |
-
"step": 80
|
| 147 |
-
},
|
| 148 |
-
{
|
| 149 |
-
"epoch": 0.2361111111111111,
|
| 150 |
-
"grad_norm": 0.5873934366128214,
|
| 151 |
-
"learning_rate": 9.990072664903717e-05,
|
| 152 |
-
"loss": 0.8997,
|
| 153 |
-
"num_input_tokens_seen": 1325712,
|
| 154 |
-
"step": 85
|
| 155 |
-
},
|
| 156 |
-
{
|
| 157 |
-
"epoch": 0.25,
|
| 158 |
-
"grad_norm": 0.4823533866978058,
|
| 159 |
-
"learning_rate": 9.980973490458728e-05,
|
| 160 |
-
"loss": 0.9019,
|
| 161 |
-
"num_input_tokens_seen": 1403680,
|
| 162 |
-
"step": 90
|
| 163 |
-
},
|
| 164 |
-
{
|
| 165 |
-
"epoch": 0.2638888888888889,
|
| 166 |
-
"grad_norm": 0.36744550192138214,
|
| 167 |
-
"learning_rate": 9.968947585697214e-05,
|
| 168 |
-
"loss": 0.9014,
|
| 169 |
-
"num_input_tokens_seen": 1481584,
|
| 170 |
-
"step": 95
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.2777777777777778,
|
| 174 |
-
"grad_norm": 0.5064142218129948,
|
| 175 |
-
"learning_rate": 9.954002016824227e-05,
|
| 176 |
-
"loss": 0.9068,
|
| 177 |
-
"num_input_tokens_seen": 1559560,
|
| 178 |
-
"step": 100
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 0.2777777777777778,
|
| 182 |
-
"eval_loss": 0.8995540738105774,
|
| 183 |
-
"eval_runtime": 47.1233,
|
| 184 |
-
"eval_samples_per_second": 3.098,
|
| 185 |
-
"eval_steps_per_second": 0.785,
|
| 186 |
-
"num_input_tokens_seen": 1559560,
|
| 187 |
-
"step": 100
|
| 188 |
-
},
|
| 189 |
-
{
|
| 190 |
-
"epoch": 0.2916666666666667,
|
| 191 |
-
"grad_norm": 0.7063850677986605,
|
| 192 |
-
"learning_rate": 9.936145565586871e-05,
|
| 193 |
-
"loss": 0.9044,
|
| 194 |
-
"num_input_tokens_seen": 1637512,
|
| 195 |
-
"step": 105
|
| 196 |
-
},
|
| 197 |
-
{
|
| 198 |
-
"epoch": 0.3055555555555556,
|
| 199 |
-
"grad_norm": 0.4612572104309768,
|
| 200 |
-
"learning_rate": 9.915388724114301e-05,
|
| 201 |
-
"loss": 0.8938,
|
| 202 |
-
"num_input_tokens_seen": 1715496,
|
| 203 |
-
"step": 110
|
| 204 |
-
},
|
| 205 |
-
{
|
| 206 |
-
"epoch": 0.3194444444444444,
|
| 207 |
-
"grad_norm": 0.28644492571570335,
|
| 208 |
-
"learning_rate": 9.891743688752738e-05,
|
| 209 |
-
"loss": 0.8986,
|
| 210 |
-
"num_input_tokens_seen": 1793520,
|
| 211 |
-
"step": 115
|
| 212 |
-
},
|
| 213 |
-
{
|
| 214 |
-
"epoch": 0.3333333333333333,
|
| 215 |
-
"grad_norm": 0.40522057279685425,
|
| 216 |
-
"learning_rate": 9.865224352899119e-05,
|
| 217 |
-
"loss": 0.8954,
|
| 218 |
-
"num_input_tokens_seen": 1871496,
|
| 219 |
-
"step": 120
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 0.3472222222222222,
|
| 223 |
-
"grad_norm": 0.36152742532038146,
|
| 224 |
-
"learning_rate": 9.835846298837584e-05,
|
| 225 |
-
"loss": 0.9014,
|
| 226 |
-
"num_input_tokens_seen": 1949496,
|
| 227 |
-
"step": 125
|
| 228 |
-
},
|
| 229 |
-
{
|
| 230 |
-
"epoch": 0.3611111111111111,
|
| 231 |
-
"grad_norm": 0.4355502300592313,
|
| 232 |
-
"learning_rate": 9.803626788583603e-05,
|
| 233 |
-
"loss": 0.9069,
|
| 234 |
-
"num_input_tokens_seen": 2027472,
|
| 235 |
-
"step": 130
|
| 236 |
-
},
|
| 237 |
-
{
|
| 238 |
-
"epoch": 0.375,
|
| 239 |
-
"grad_norm": 0.26465732155670246,
|
| 240 |
-
"learning_rate": 9.768584753741134e-05,
|
| 241 |
-
"loss": 0.9036,
|
| 242 |
-
"num_input_tokens_seen": 2105488,
|
| 243 |
-
"step": 135
|
| 244 |
-
},
|
| 245 |
-
{
|
| 246 |
-
"epoch": 0.3888888888888889,
|
| 247 |
-
"grad_norm": 0.4321544586407889,
|
| 248 |
-
"learning_rate": 9.730740784378753e-05,
|
| 249 |
-
"loss": 0.8974,
|
| 250 |
-
"num_input_tokens_seen": 2183488,
|
| 251 |
-
"step": 140
|
| 252 |
-
},
|
| 253 |
-
{
|
| 254 |
-
"epoch": 0.4027777777777778,
|
| 255 |
-
"grad_norm": 0.34548611738400625,
|
| 256 |
-
"learning_rate": 9.69011711693129e-05,
|
| 257 |
-
"loss": 0.8999,
|
| 258 |
-
"num_input_tokens_seen": 2261472,
|
| 259 |
-
"step": 145
|
| 260 |
-
},
|
| 261 |
-
{
|
| 262 |
-
"epoch": 0.4166666666666667,
|
| 263 |
-
"grad_norm": 0.39871875335322654,
|
| 264 |
-
"learning_rate": 9.646737621134112e-05,
|
| 265 |
-
"loss": 0.908,
|
| 266 |
-
"num_input_tokens_seen": 2339512,
|
| 267 |
-
"step": 150
|
| 268 |
-
},
|
| 269 |
-
{
|
| 270 |
-
"epoch": 0.4166666666666667,
|
| 271 |
-
"eval_loss": 0.8949049115180969,
|
| 272 |
-
"eval_runtime": 46.7248,
|
| 273 |
-
"eval_samples_per_second": 3.125,
|
| 274 |
-
"eval_steps_per_second": 0.792,
|
| 275 |
-
"num_input_tokens_seen": 2339512,
|
| 276 |
-
"step": 150
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 0.4305555555555556,
|
| 280 |
-
"grad_norm": 0.4541004672886896,
|
| 281 |
-
"learning_rate": 9.600627785997696e-05,
|
| 282 |
-
"loss": 0.8971,
|
| 283 |
-
"num_input_tokens_seen": 2417488,
|
| 284 |
-
"step": 155
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 0.4444444444444444,
|
| 288 |
-
"grad_norm": 0.4613539033606643,
|
| 289 |
-
"learning_rate": 9.551814704830734e-05,
|
| 290 |
-
"loss": 0.8952,
|
| 291 |
-
"num_input_tokens_seen": 2495464,
|
| 292 |
-
"step": 160
|
| 293 |
-
},
|
| 294 |
-
{
|
| 295 |
-
"epoch": 0.4583333333333333,
|
| 296 |
-
"grad_norm": 0.37123415305068785,
|
| 297 |
-
"learning_rate": 9.500327059320606e-05,
|
| 298 |
-
"loss": 0.8972,
|
| 299 |
-
"num_input_tokens_seen": 2573408,
|
| 300 |
-
"step": 165
|
| 301 |
-
},
|
| 302 |
-
{
|
| 303 |
-
"epoch": 0.4722222222222222,
|
| 304 |
-
"grad_norm": 0.38977847466547694,
|
| 305 |
-
"learning_rate": 9.446195102680531e-05,
|
| 306 |
-
"loss": 0.8979,
|
| 307 |
-
"num_input_tokens_seen": 2651368,
|
| 308 |
-
"step": 170
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 0.4861111111111111,
|
| 312 |
-
"grad_norm": 0.30747699940882145,
|
| 313 |
-
"learning_rate": 9.389450641873323e-05,
|
| 314 |
-
"loss": 0.8908,
|
| 315 |
-
"num_input_tokens_seen": 2729352,
|
| 316 |
-
"step": 175
|
| 317 |
-
},
|
| 318 |
-
{
|
| 319 |
-
"epoch": 0.5,
|
| 320 |
-
"grad_norm": 0.33529998689248586,
|
| 321 |
-
"learning_rate": 9.330127018922194e-05,
|
| 322 |
-
"loss": 0.8997,
|
| 323 |
-
"num_input_tokens_seen": 2807320,
|
| 324 |
-
"step": 180
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 0.5138888888888888,
|
| 328 |
-
"grad_norm": 0.5426765737063947,
|
| 329 |
-
"learning_rate": 9.268259091319582e-05,
|
| 330 |
-
"loss": 0.9024,
|
| 331 |
-
"num_input_tokens_seen": 2885368,
|
| 332 |
-
"step": 185
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 0.5277777777777778,
|
| 336 |
-
"grad_norm": 0.4593898499279331,
|
| 337 |
-
"learning_rate": 9.203883211545517e-05,
|
| 338 |
-
"loss": 0.9002,
|
| 339 |
-
"num_input_tokens_seen": 2963376,
|
| 340 |
-
"step": 190
|
| 341 |
-
},
|
| 342 |
-
{
|
| 343 |
-
"epoch": 0.5416666666666666,
|
| 344 |
-
"grad_norm": 0.27583660078148825,
|
| 345 |
-
"learning_rate": 9.137037205707552e-05,
|
| 346 |
-
"loss": 0.9,
|
| 347 |
-
"num_input_tokens_seen": 3041376,
|
| 348 |
-
"step": 195
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 0.5555555555555556,
|
| 352 |
-
"grad_norm": 0.26593205655845514,
|
| 353 |
-
"learning_rate": 9.067760351314838e-05,
|
| 354 |
-
"loss": 0.8989,
|
| 355 |
-
"num_input_tokens_seen": 3119304,
|
| 356 |
-
"step": 200
|
| 357 |
-
},
|
| 358 |
-
{
|
| 359 |
-
"epoch": 0.5555555555555556,
|
| 360 |
-
"eval_loss": 0.8992709517478943,
|
| 361 |
-
"eval_runtime": 46.6014,
|
| 362 |
-
"eval_samples_per_second": 3.133,
|
| 363 |
-
"eval_steps_per_second": 0.794,
|
| 364 |
-
"num_input_tokens_seen": 3119304,
|
| 365 |
-
"step": 200
|
| 366 |
-
},
|
| 367 |
-
{
|
| 368 |
-
"epoch": 0.5694444444444444,
|
| 369 |
-
"grad_norm": 0.5150976787458876,
|
| 370 |
-
"learning_rate": 8.996093354199349e-05,
|
| 371 |
-
"loss": 0.8994,
|
| 372 |
-
"num_input_tokens_seen": 3197320,
|
| 373 |
-
"step": 205
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 0.5833333333333334,
|
| 377 |
-
"grad_norm": 0.5612526379811666,
|
| 378 |
-
"learning_rate": 8.922078324597879e-05,
|
| 379 |
-
"loss": 0.9036,
|
| 380 |
-
"num_input_tokens_seen": 3275288,
|
| 381 |
-
"step": 210
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"epoch": 0.5972222222222222,
|
| 385 |
-
"grad_norm": 0.6484992865693107,
|
| 386 |
-
"learning_rate": 8.845758752408826e-05,
|
| 387 |
-
"loss": 0.8988,
|
| 388 |
-
"num_input_tokens_seen": 3353240,
|
| 389 |
-
"step": 215
|
| 390 |
-
},
|
| 391 |
-
{
|
| 392 |
-
"epoch": 0.6111111111111112,
|
| 393 |
-
"grad_norm": 0.4709224015616086,
|
| 394 |
-
"learning_rate": 8.767179481638303e-05,
|
| 395 |
-
"loss": 0.9015,
|
| 396 |
-
"num_input_tokens_seen": 3431248,
|
| 397 |
-
"step": 220
|
| 398 |
-
},
|
| 399 |
-
{
|
| 400 |
-
"epoch": 0.625,
|
| 401 |
-
"grad_norm": 0.6046638090352222,
|
| 402 |
-
"learning_rate": 8.68638668405062e-05,
|
| 403 |
-
"loss": 0.9047,
|
| 404 |
-
"num_input_tokens_seen": 3509192,
|
| 405 |
-
"step": 225
|
| 406 |
-
},
|
| 407 |
-
{
|
| 408 |
-
"epoch": 0.6388888888888888,
|
| 409 |
-
"grad_norm": 0.4688289739018474,
|
| 410 |
-
"learning_rate": 8.603427832038574e-05,
|
| 411 |
-
"loss": 0.901,
|
| 412 |
-
"num_input_tokens_seen": 3587152,
|
| 413 |
-
"step": 230
|
| 414 |
-
},
|
| 415 |
-
{
|
| 416 |
-
"epoch": 0.6527777777777778,
|
| 417 |
-
"grad_norm": 0.5904442121458054,
|
| 418 |
-
"learning_rate": 8.518351670729529e-05,
|
| 419 |
-
"loss": 0.8898,
|
| 420 |
-
"num_input_tokens_seen": 3665128,
|
| 421 |
-
"step": 235
|
| 422 |
-
},
|
| 423 |
-
{
|
| 424 |
-
"epoch": 0.6666666666666666,
|
| 425 |
-
"grad_norm": 0.6120652373129304,
|
| 426 |
-
"learning_rate": 8.43120818934367e-05,
|
| 427 |
-
"loss": 0.8896,
|
| 428 |
-
"num_input_tokens_seen": 3743128,
|
| 429 |
-
"step": 240
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 0.6805555555555556,
|
| 433 |
-
"grad_norm": 1.313292312803758,
|
| 434 |
-
"learning_rate": 8.342048591821212e-05,
|
| 435 |
-
"loss": 0.8993,
|
| 436 |
-
"num_input_tokens_seen": 3821088,
|
| 437 |
-
"step": 245
|
| 438 |
-
},
|
| 439 |
-
{
|
| 440 |
-
"epoch": 0.6944444444444444,
|
| 441 |
-
"grad_norm": 0.9735602658006927,
|
| 442 |
-
"learning_rate": 8.250925266735918e-05,
|
| 443 |
-
"loss": 0.8907,
|
| 444 |
-
"num_input_tokens_seen": 3899064,
|
| 445 |
-
"step": 250
|
| 446 |
-
},
|
| 447 |
-
{
|
| 448 |
-
"epoch": 0.6944444444444444,
|
| 449 |
-
"eval_loss": 0.8925368785858154,
|
| 450 |
-
"eval_runtime": 46.6124,
|
| 451 |
-
"eval_samples_per_second": 3.132,
|
| 452 |
-
"eval_steps_per_second": 0.794,
|
| 453 |
-
"num_input_tokens_seen": 3899064,
|
| 454 |
-
"step": 250
|
| 455 |
-
},
|
| 456 |
-
{
|
| 457 |
-
"epoch": 0.7083333333333334,
|
| 458 |
-
"grad_norm": 1.2050807227161144,
|
| 459 |
-
"learning_rate": 8.157891756512488e-05,
|
| 460 |
-
"loss": 0.878,
|
| 461 |
-
"num_input_tokens_seen": 3977048,
|
| 462 |
-
"step": 255
|
| 463 |
-
},
|
| 464 |
-
{
|
| 465 |
-
"epoch": 0.7222222222222222,
|
| 466 |
-
"grad_norm": 1.9771414914416532,
|
| 467 |
-
"learning_rate": 8.063002725966015e-05,
|
| 468 |
-
"loss": 0.8881,
|
| 469 |
-
"num_input_tokens_seen": 4055080,
|
| 470 |
-
"step": 260
|
| 471 |
-
},
|
| 472 |
-
{
|
| 473 |
-
"epoch": 0.7361111111111112,
|
| 474 |
-
"grad_norm": 1.605957774581815,
|
| 475 |
-
"learning_rate": 7.966313930181912e-05,
|
| 476 |
-
"loss": 0.8755,
|
| 477 |
-
"num_input_tokens_seen": 4133008,
|
| 478 |
-
"step": 265
|
| 479 |
-
},
|
| 480 |
-
{
|
| 481 |
-
"epoch": 0.75,
|
| 482 |
-
"grad_norm": 9.19186897524454,
|
| 483 |
-
"learning_rate": 7.86788218175523e-05,
|
| 484 |
-
"loss": 0.8558,
|
| 485 |
-
"num_input_tokens_seen": 4210992,
|
| 486 |
-
"step": 270
|
| 487 |
-
},
|
| 488 |
-
{
|
| 489 |
-
"epoch": 0.7638888888888888,
|
| 490 |
-
"grad_norm": 4.328337833890427,
|
| 491 |
-
"learning_rate": 7.767765317408613e-05,
|
| 492 |
-
"loss": 0.9057,
|
| 493 |
-
"num_input_tokens_seen": 4288976,
|
| 494 |
-
"step": 275
|
| 495 |
-
},
|
| 496 |
-
{
|
| 497 |
-
"epoch": 0.7777777777777778,
|
| 498 |
-
"grad_norm": 3.1206913180819185,
|
| 499 |
-
"learning_rate": 7.666022164008457e-05,
|
| 500 |
-
"loss": 0.845,
|
| 501 |
-
"num_input_tokens_seen": 4366920,
|
| 502 |
-
"step": 280
|
| 503 |
-
},
|
| 504 |
-
{
|
| 505 |
-
"epoch": 0.7916666666666666,
|
| 506 |
-
"grad_norm": 3.6462009524262773,
|
| 507 |
-
"learning_rate": 7.562712503999327e-05,
|
| 508 |
-
"loss": 0.8524,
|
| 509 |
-
"num_input_tokens_seen": 4444912,
|
| 510 |
-
"step": 285
|
| 511 |
-
},
|
| 512 |
-
{
|
| 513 |
-
"epoch": 0.8055555555555556,
|
| 514 |
-
"grad_norm": 2.1379581270956285,
|
| 515 |
-
"learning_rate": 7.457897040276853e-05,
|
| 516 |
-
"loss": 0.8694,
|
| 517 |
-
"num_input_tokens_seen": 4522912,
|
| 518 |
-
"step": 290
|
| 519 |
-
},
|
| 520 |
-
{
|
| 521 |
-
"epoch": 0.8194444444444444,
|
| 522 |
-
"grad_norm": 3.553029913178992,
|
| 523 |
-
"learning_rate": 7.351637360519813e-05,
|
| 524 |
-
"loss": 0.8605,
|
| 525 |
-
"num_input_tokens_seen": 4600848,
|
| 526 |
-
"step": 295
|
| 527 |
-
},
|
| 528 |
-
{
|
| 529 |
-
"epoch": 0.8333333333333334,
|
| 530 |
-
"grad_norm": 3.332905153564647,
|
| 531 |
-
"learning_rate": 7.243995901002312e-05,
|
| 532 |
-
"loss": 0.8739,
|
| 533 |
-
"num_input_tokens_seen": 4678776,
|
| 534 |
-
"step": 300
|
| 535 |
-
},
|
| 536 |
-
{
|
| 537 |
-
"epoch": 0.8333333333333334,
|
| 538 |
-
"eval_loss": 0.8601770997047424,
|
| 539 |
-
"eval_runtime": 46.9817,
|
| 540 |
-
"eval_samples_per_second": 3.108,
|
| 541 |
-
"eval_steps_per_second": 0.788,
|
| 542 |
-
"num_input_tokens_seen": 4678776,
|
| 543 |
-
"step": 300
|
| 544 |
-
},
|
| 545 |
-
{
|
| 546 |
-
"epoch": 0.8472222222222222,
|
| 547 |
-
"grad_norm": 3.824074793385472,
|
| 548 |
-
"learning_rate": 7.135035909907358e-05,
|
| 549 |
-
"loss": 0.8838,
|
| 550 |
-
"num_input_tokens_seen": 4756744,
|
| 551 |
-
"step": 305
|
| 552 |
-
},
|
| 553 |
-
{
|
| 554 |
-
"epoch": 0.8611111111111112,
|
| 555 |
-
"grad_norm": 1.8566349178683659,
|
| 556 |
-
"learning_rate": 7.024821410163368e-05,
|
| 557 |
-
"loss": 0.8843,
|
| 558 |
-
"num_input_tokens_seen": 4834648,
|
| 559 |
-
"step": 310
|
| 560 |
-
},
|
| 561 |
-
{
|
| 562 |
-
"epoch": 0.875,
|
| 563 |
-
"grad_norm": 1.8800583465943999,
|
| 564 |
-
"learning_rate": 6.91341716182545e-05,
|
| 565 |
-
"loss": 0.8637,
|
| 566 |
-
"num_input_tokens_seen": 4912632,
|
| 567 |
-
"step": 315
|
| 568 |
-
},
|
| 569 |
-
{
|
| 570 |
-
"epoch": 0.8888888888888888,
|
| 571 |
-
"grad_norm": 2.339387141795884,
|
| 572 |
-
"learning_rate": 6.800888624023553e-05,
|
| 573 |
-
"loss": 0.8714,
|
| 574 |
-
"num_input_tokens_seen": 4990632,
|
| 575 |
-
"step": 320
|
| 576 |
-
},
|
| 577 |
-
{
|
| 578 |
-
"epoch": 0.9027777777777778,
|
| 579 |
-
"grad_norm": 1.650009361432866,
|
| 580 |
-
"learning_rate": 6.687301916499871e-05,
|
| 581 |
-
"loss": 0.8581,
|
| 582 |
-
"num_input_tokens_seen": 5068632,
|
| 583 |
-
"step": 325
|
| 584 |
-
},
|
| 585 |
-
{
|
| 586 |
-
"epoch": 0.9166666666666666,
|
| 587 |
-
"grad_norm": 2.8384085546182294,
|
| 588 |
-
"learning_rate": 6.572723780758069e-05,
|
| 589 |
-
"loss": 0.8655,
|
| 590 |
-
"num_input_tokens_seen": 5146648,
|
| 591 |
-
"step": 330
|
| 592 |
-
},
|
| 593 |
-
{
|
| 594 |
-
"epoch": 0.9305555555555556,
|
| 595 |
-
"grad_norm": 6.227674605881871,
|
| 596 |
-
"learning_rate": 6.457221540847176e-05,
|
| 597 |
-
"loss": 0.8721,
|
| 598 |
-
"num_input_tokens_seen": 5224624,
|
| 599 |
-
"step": 335
|
| 600 |
-
},
|
| 601 |
-
{
|
| 602 |
-
"epoch": 0.9444444444444444,
|
| 603 |
-
"grad_norm": 3.498647817420285,
|
| 604 |
-
"learning_rate": 6.340863063803188e-05,
|
| 605 |
-
"loss": 0.8563,
|
| 606 |
-
"num_input_tokens_seen": 5302600,
|
| 607 |
-
"step": 340
|
| 608 |
-
},
|
| 609 |
-
{
|
| 610 |
-
"epoch": 0.9583333333333334,
|
| 611 |
-
"grad_norm": 4.211929847119524,
|
| 612 |
-
"learning_rate": 6.22371671977162e-05,
|
| 613 |
-
"loss": 0.8634,
|
| 614 |
-
"num_input_tokens_seen": 5380600,
|
| 615 |
-
"step": 345
|
| 616 |
-
},
|
| 617 |
-
{
|
| 618 |
-
"epoch": 0.9722222222222222,
|
| 619 |
-
"grad_norm": 3.696407127177043,
|
| 620 |
-
"learning_rate": 6.105851341834439e-05,
|
| 621 |
-
"loss": 0.8526,
|
| 622 |
-
"num_input_tokens_seen": 5458520,
|
| 623 |
-
"step": 350
|
| 624 |
-
},
|
| 625 |
-
{
|
| 626 |
-
"epoch": 0.9722222222222222,
|
| 627 |
-
"eval_loss": 0.830344021320343,
|
| 628 |
-
"eval_runtime": 46.3813,
|
| 629 |
-
"eval_samples_per_second": 3.148,
|
| 630 |
-
"eval_steps_per_second": 0.798,
|
| 631 |
-
"num_input_tokens_seen": 5458520,
|
| 632 |
-
"step": 350
|
| 633 |
}
|
| 634 |
],
|
| 635 |
"logging_steps": 5,
|
| 636 |
-
"max_steps":
|
| 637 |
-
"num_input_tokens_seen":
|
| 638 |
"num_train_epochs": 2,
|
| 639 |
"save_steps": 50,
|
| 640 |
"stateful_callbacks": {
|
|
@@ -649,7 +115,7 @@
|
|
| 649 |
"attributes": {}
|
| 650 |
}
|
| 651 |
},
|
| 652 |
-
"total_flos":
|
| 653 |
"train_batch_size": 1,
|
| 654 |
"trial_name": null,
|
| 655 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9039102792739868,
|
| 3 |
+
"best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_classily/lora/sft/checkpoint-50",
|
| 4 |
+
"epoch": 0.13961605584642234,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 50,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.013961605584642234,
|
| 13 |
+
"grad_norm": 21.25276507868793,
|
| 14 |
"learning_rate": 6.944444444444445e-06,
|
| 15 |
+
"loss": 2.9908,
|
| 16 |
"num_input_tokens_seen": 77944,
|
| 17 |
"step": 5
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 0.027923211169284468,
|
| 21 |
+
"grad_norm": 21.89043285054519,
|
| 22 |
"learning_rate": 1.388888888888889e-05,
|
| 23 |
+
"loss": 3.0071,
|
| 24 |
+
"num_input_tokens_seen": 155896,
|
| 25 |
"step": 10
|
| 26 |
},
|
| 27 |
{
|
| 28 |
+
"epoch": 0.041884816753926704,
|
| 29 |
+
"grad_norm": 16.65776874449816,
|
| 30 |
"learning_rate": 2.0833333333333336e-05,
|
| 31 |
+
"loss": 2.354,
|
| 32 |
"num_input_tokens_seen": 233896,
|
| 33 |
"step": 15
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.055846422338568937,
|
| 37 |
+
"grad_norm": 3.772799389266845,
|
| 38 |
"learning_rate": 2.777777777777778e-05,
|
| 39 |
+
"loss": 1.2959,
|
| 40 |
+
"num_input_tokens_seen": 311840,
|
| 41 |
"step": 20
|
| 42 |
},
|
| 43 |
{
|
| 44 |
+
"epoch": 0.06980802792321117,
|
| 45 |
+
"grad_norm": 2.5936011954385334,
|
| 46 |
"learning_rate": 3.472222222222222e-05,
|
| 47 |
+
"loss": 1.0206,
|
| 48 |
+
"num_input_tokens_seen": 389816,
|
| 49 |
"step": 25
|
| 50 |
},
|
| 51 |
{
|
| 52 |
+
"epoch": 0.08376963350785341,
|
| 53 |
+
"grad_norm": 1.380523901017673,
|
| 54 |
"learning_rate": 4.166666666666667e-05,
|
| 55 |
+
"loss": 0.9285,
|
| 56 |
+
"num_input_tokens_seen": 467808,
|
| 57 |
"step": 30
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.09773123909249563,
|
| 61 |
+
"grad_norm": 0.9535971270874376,
|
| 62 |
"learning_rate": 4.8611111111111115e-05,
|
| 63 |
+
"loss": 0.9052,
|
| 64 |
+
"num_input_tokens_seen": 545776,
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.11169284467713787,
|
| 69 |
+
"grad_norm": 0.7487685762175865,
|
| 70 |
"learning_rate": 5.555555555555556e-05,
|
| 71 |
+
"loss": 0.929,
|
| 72 |
+
"num_input_tokens_seen": 623744,
|
| 73 |
"step": 40
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 0.1256544502617801,
|
| 77 |
+
"grad_norm": 0.9517829869317949,
|
| 78 |
"learning_rate": 6.25e-05,
|
| 79 |
+
"loss": 0.9076,
|
| 80 |
+
"num_input_tokens_seen": 701720,
|
| 81 |
"step": 45
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.13961605584642234,
|
| 85 |
+
"grad_norm": 0.5105376471286923,
|
| 86 |
"learning_rate": 6.944444444444444e-05,
|
| 87 |
+
"loss": 0.9039,
|
| 88 |
+
"num_input_tokens_seen": 779728,
|
| 89 |
"step": 50
|
| 90 |
},
|
| 91 |
{
|
| 92 |
+
"epoch": 0.13961605584642234,
|
| 93 |
+
"eval_loss": 0.9039102792739868,
|
| 94 |
+
"eval_runtime": 74.9579,
|
| 95 |
+
"eval_samples_per_second": 1.948,
|
| 96 |
+
"eval_steps_per_second": 0.494,
|
| 97 |
+
"num_input_tokens_seen": 779728,
|
| 98 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
}
|
| 100 |
],
|
| 101 |
"logging_steps": 5,
|
| 102 |
+
"max_steps": 716,
|
| 103 |
+
"num_input_tokens_seen": 779728,
|
| 104 |
"num_train_epochs": 2,
|
| 105 |
"save_steps": 50,
|
| 106 |
"stateful_callbacks": {
|
|
|
|
| 115 |
"attributes": {}
|
| 116 |
}
|
| 117 |
},
|
| 118 |
+
"total_flos": 52663320313856.0,
|
| 119 |
"train_batch_size": 1,
|
| 120 |
"trial_name": null,
|
| 121 |
"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 7352
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b0af6075e02b8e93a59ce938db15a9c8a754a7d6b6c53d6278e322b07db3808
|
| 3 |
size 7352
|