Commit
•
27a13e1
1
Parent(s):
c284126
Training in progress, step 104700, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
|
@@ -20,12 +20,12 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"v_proj",
|
| 24 |
"k_proj",
|
| 25 |
-
"gate_proj",
|
| 26 |
-
"down_proj",
|
| 27 |
-
"q_proj",
|
| 28 |
"up_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"o_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
|
|
|
| 23 |
"k_proj",
|
|
|
|
|
|
|
|
|
|
| 24 |
"up_proj",
|
| 25 |
+
"q_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"down_proj",
|
| 28 |
+
"gate_proj",
|
| 29 |
"o_proj"
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5544997664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63c0aa71f3cfd50d12015fb156d56fb1510befaf633dbc7dfb4bc6a2e4501432
|
| 3 |
size 5544997664
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 674093138
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cce687928fc27a474101bcd1dcd60948b9f30226f11fd1f8d7c5c45c3716d78c
|
| 3 |
size 674093138
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e6f208079d34a7c3379ca2cff27b8ff531c5746d617776194ed8b2336cc03f9
|
| 3 |
size 14244
|
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 sha256:39613d106da5b53a64cdbd94e8c8eb25273617d7901a3bb57dfebcbe017755d6
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 200,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -7070,6 +7070,272 @@
|
|
| 7070 |
"learning_rate": 1.9988888715649357e-05,
|
| 7071 |
"loss": 1.5441,
|
| 7072 |
"step": 100900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7073 |
}
|
| 7074 |
],
|
| 7075 |
"logging_steps": 100,
|
|
@@ -7089,7 +7355,7 @@
|
|
| 7089 |
"attributes": {}
|
| 7090 |
}
|
| 7091 |
},
|
| 7092 |
-
"total_flos": 1.
|
| 7093 |
"train_batch_size": 1,
|
| 7094 |
"trial_name": null,
|
| 7095 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.077863549149971,
|
| 5 |
"eval_steps": 200,
|
| 6 |
+
"global_step": 104700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 7070 |
"learning_rate": 1.9988888715649357e-05,
|
| 7071 |
"loss": 1.5441,
|
| 7072 |
"step": 100900
|
| 7073 |
+
},
|
| 7074 |
+
{
|
| 7075 |
+
"epoch": 0.07511192420388797,
|
| 7076 |
+
"grad_norm": 1.068562388420105,
|
| 7077 |
+
"learning_rate": 1.998886668338319e-05,
|
| 7078 |
+
"loss": 1.4998,
|
| 7079 |
+
"step": 101000
|
| 7080 |
+
},
|
| 7081 |
+
{
|
| 7082 |
+
"epoch": 0.075186292445674,
|
| 7083 |
+
"grad_norm": 0.6331286430358887,
|
| 7084 |
+
"learning_rate": 1.998884462930723e-05,
|
| 7085 |
+
"loss": 1.5633,
|
| 7086 |
+
"step": 101100
|
| 7087 |
+
},
|
| 7088 |
+
{
|
| 7089 |
+
"epoch": 0.07526066068746003,
|
| 7090 |
+
"grad_norm": 1.3566038608551025,
|
| 7091 |
+
"learning_rate": 1.998882255342152e-05,
|
| 7092 |
+
"loss": 1.4621,
|
| 7093 |
+
"step": 101200
|
| 7094 |
+
},
|
| 7095 |
+
{
|
| 7096 |
+
"epoch": 0.07533502892924605,
|
| 7097 |
+
"grad_norm": 0.9672004580497742,
|
| 7098 |
+
"learning_rate": 1.998880045572611e-05,
|
| 7099 |
+
"loss": 1.5249,
|
| 7100 |
+
"step": 101300
|
| 7101 |
+
},
|
| 7102 |
+
{
|
| 7103 |
+
"epoch": 0.07540939717103208,
|
| 7104 |
+
"grad_norm": 0.36732280254364014,
|
| 7105 |
+
"learning_rate": 1.9988778336221045e-05,
|
| 7106 |
+
"loss": 1.574,
|
| 7107 |
+
"step": 101400
|
| 7108 |
+
},
|
| 7109 |
+
{
|
| 7110 |
+
"epoch": 0.07548376541281811,
|
| 7111 |
+
"grad_norm": 0.4788234829902649,
|
| 7112 |
+
"learning_rate": 1.998875619490638e-05,
|
| 7113 |
+
"loss": 1.5418,
|
| 7114 |
+
"step": 101500
|
| 7115 |
+
},
|
| 7116 |
+
{
|
| 7117 |
+
"epoch": 0.07555813365460413,
|
| 7118 |
+
"grad_norm": 0.8955681324005127,
|
| 7119 |
+
"learning_rate": 1.9988734031782157e-05,
|
| 7120 |
+
"loss": 1.5568,
|
| 7121 |
+
"step": 101600
|
| 7122 |
+
},
|
| 7123 |
+
{
|
| 7124 |
+
"epoch": 0.07563250189639016,
|
| 7125 |
+
"grad_norm": 0.8049163222312927,
|
| 7126 |
+
"learning_rate": 1.9988711846848427e-05,
|
| 7127 |
+
"loss": 1.4838,
|
| 7128 |
+
"step": 101700
|
| 7129 |
+
},
|
| 7130 |
+
{
|
| 7131 |
+
"epoch": 0.07570687013817619,
|
| 7132 |
+
"grad_norm": 0.7558008432388306,
|
| 7133 |
+
"learning_rate": 1.9988689640105235e-05,
|
| 7134 |
+
"loss": 1.4955,
|
| 7135 |
+
"step": 101800
|
| 7136 |
+
},
|
| 7137 |
+
{
|
| 7138 |
+
"epoch": 0.07578123837996222,
|
| 7139 |
+
"grad_norm": 0.4749026596546173,
|
| 7140 |
+
"learning_rate": 1.9988667411552635e-05,
|
| 7141 |
+
"loss": 1.5929,
|
| 7142 |
+
"step": 101900
|
| 7143 |
+
},
|
| 7144 |
+
{
|
| 7145 |
+
"epoch": 0.07585560662174824,
|
| 7146 |
+
"grad_norm": 0.6597522497177124,
|
| 7147 |
+
"learning_rate": 1.998864516119067e-05,
|
| 7148 |
+
"loss": 1.5584,
|
| 7149 |
+
"step": 102000
|
| 7150 |
+
},
|
| 7151 |
+
{
|
| 7152 |
+
"epoch": 0.07592997486353428,
|
| 7153 |
+
"grad_norm": 0.7412188053131104,
|
| 7154 |
+
"learning_rate": 1.9988622889019395e-05,
|
| 7155 |
+
"loss": 1.5842,
|
| 7156 |
+
"step": 102100
|
| 7157 |
+
},
|
| 7158 |
+
{
|
| 7159 |
+
"epoch": 0.07600434310532031,
|
| 7160 |
+
"grad_norm": 0.5564984679222107,
|
| 7161 |
+
"learning_rate": 1.9988600595038853e-05,
|
| 7162 |
+
"loss": 1.5764,
|
| 7163 |
+
"step": 102200
|
| 7164 |
+
},
|
| 7165 |
+
{
|
| 7166 |
+
"epoch": 0.07607871134710634,
|
| 7167 |
+
"grad_norm": 1.0488529205322266,
|
| 7168 |
+
"learning_rate": 1.9988578279249097e-05,
|
| 7169 |
+
"loss": 1.458,
|
| 7170 |
+
"step": 102300
|
| 7171 |
+
},
|
| 7172 |
+
{
|
| 7173 |
+
"epoch": 0.07615307958889236,
|
| 7174 |
+
"grad_norm": 1.40269136428833,
|
| 7175 |
+
"learning_rate": 1.998855594165017e-05,
|
| 7176 |
+
"loss": 1.4588,
|
| 7177 |
+
"step": 102400
|
| 7178 |
+
},
|
| 7179 |
+
{
|
| 7180 |
+
"epoch": 0.07622744783067839,
|
| 7181 |
+
"grad_norm": 0.8488138318061829,
|
| 7182 |
+
"learning_rate": 1.9988533582242127e-05,
|
| 7183 |
+
"loss": 1.522,
|
| 7184 |
+
"step": 102500
|
| 7185 |
+
},
|
| 7186 |
+
{
|
| 7187 |
+
"epoch": 0.07630181607246442,
|
| 7188 |
+
"grad_norm": 0.5191701054573059,
|
| 7189 |
+
"learning_rate": 1.9988511201025015e-05,
|
| 7190 |
+
"loss": 1.5036,
|
| 7191 |
+
"step": 102600
|
| 7192 |
+
},
|
| 7193 |
+
{
|
| 7194 |
+
"epoch": 0.07637618431425044,
|
| 7195 |
+
"grad_norm": 0.6648279428482056,
|
| 7196 |
+
"learning_rate": 1.9988488797998878e-05,
|
| 7197 |
+
"loss": 1.4929,
|
| 7198 |
+
"step": 102700
|
| 7199 |
+
},
|
| 7200 |
+
{
|
| 7201 |
+
"epoch": 0.07645055255603647,
|
| 7202 |
+
"grad_norm": 1.8600202798843384,
|
| 7203 |
+
"learning_rate": 1.9988466373163774e-05,
|
| 7204 |
+
"loss": 1.5692,
|
| 7205 |
+
"step": 102800
|
| 7206 |
+
},
|
| 7207 |
+
{
|
| 7208 |
+
"epoch": 0.0765249207978225,
|
| 7209 |
+
"grad_norm": 0.7583739757537842,
|
| 7210 |
+
"learning_rate": 1.9988443926519743e-05,
|
| 7211 |
+
"loss": 1.5145,
|
| 7212 |
+
"step": 102900
|
| 7213 |
+
},
|
| 7214 |
+
{
|
| 7215 |
+
"epoch": 0.07659928903960853,
|
| 7216 |
+
"grad_norm": 0.6128048300743103,
|
| 7217 |
+
"learning_rate": 1.998842145806684e-05,
|
| 7218 |
+
"loss": 1.5729,
|
| 7219 |
+
"step": 103000
|
| 7220 |
+
},
|
| 7221 |
+
{
|
| 7222 |
+
"epoch": 0.07667365728139455,
|
| 7223 |
+
"grad_norm": 0.7574602365493774,
|
| 7224 |
+
"learning_rate": 1.998839896780511e-05,
|
| 7225 |
+
"loss": 1.4356,
|
| 7226 |
+
"step": 103100
|
| 7227 |
+
},
|
| 7228 |
+
{
|
| 7229 |
+
"epoch": 0.07674802552318058,
|
| 7230 |
+
"grad_norm": 1.4134727716445923,
|
| 7231 |
+
"learning_rate": 1.9988376455734606e-05,
|
| 7232 |
+
"loss": 1.5048,
|
| 7233 |
+
"step": 103200
|
| 7234 |
+
},
|
| 7235 |
+
{
|
| 7236 |
+
"epoch": 0.0768223937649666,
|
| 7237 |
+
"grad_norm": 0.7592337727546692,
|
| 7238 |
+
"learning_rate": 1.9988353921855374e-05,
|
| 7239 |
+
"loss": 1.4988,
|
| 7240 |
+
"step": 103300
|
| 7241 |
+
},
|
| 7242 |
+
{
|
| 7243 |
+
"epoch": 0.07689676200675263,
|
| 7244 |
+
"grad_norm": 0.522486686706543,
|
| 7245 |
+
"learning_rate": 1.9988331366167465e-05,
|
| 7246 |
+
"loss": 1.5654,
|
| 7247 |
+
"step": 103400
|
| 7248 |
+
},
|
| 7249 |
+
{
|
| 7250 |
+
"epoch": 0.07697113024853866,
|
| 7251 |
+
"grad_norm": 0.6535342335700989,
|
| 7252 |
+
"learning_rate": 1.9988308788670925e-05,
|
| 7253 |
+
"loss": 1.4593,
|
| 7254 |
+
"step": 103500
|
| 7255 |
+
},
|
| 7256 |
+
{
|
| 7257 |
+
"epoch": 0.07704549849032469,
|
| 7258 |
+
"grad_norm": 0.6663926243782043,
|
| 7259 |
+
"learning_rate": 1.9988286189365808e-05,
|
| 7260 |
+
"loss": 1.477,
|
| 7261 |
+
"step": 103600
|
| 7262 |
+
},
|
| 7263 |
+
{
|
| 7264 |
+
"epoch": 0.07711986673211071,
|
| 7265 |
+
"grad_norm": 0.5006215572357178,
|
| 7266 |
+
"learning_rate": 1.998826356825216e-05,
|
| 7267 |
+
"loss": 1.5326,
|
| 7268 |
+
"step": 103700
|
| 7269 |
+
},
|
| 7270 |
+
{
|
| 7271 |
+
"epoch": 0.07719423497389674,
|
| 7272 |
+
"grad_norm": 0.6826842427253723,
|
| 7273 |
+
"learning_rate": 1.9988240925330032e-05,
|
| 7274 |
+
"loss": 1.5102,
|
| 7275 |
+
"step": 103800
|
| 7276 |
+
},
|
| 7277 |
+
{
|
| 7278 |
+
"epoch": 0.07726860321568277,
|
| 7279 |
+
"grad_norm": 0.2680438756942749,
|
| 7280 |
+
"learning_rate": 1.9988218260599477e-05,
|
| 7281 |
+
"loss": 1.4773,
|
| 7282 |
+
"step": 103900
|
| 7283 |
+
},
|
| 7284 |
+
{
|
| 7285 |
+
"epoch": 0.07734297145746881,
|
| 7286 |
+
"grad_norm": 0.9159733057022095,
|
| 7287 |
+
"learning_rate": 1.9988195574060536e-05,
|
| 7288 |
+
"loss": 1.4984,
|
| 7289 |
+
"step": 104000
|
| 7290 |
+
},
|
| 7291 |
+
{
|
| 7292 |
+
"epoch": 0.07741733969925484,
|
| 7293 |
+
"grad_norm": 1.0930269956588745,
|
| 7294 |
+
"learning_rate": 1.9988172865713266e-05,
|
| 7295 |
+
"loss": 1.4196,
|
| 7296 |
+
"step": 104100
|
| 7297 |
+
},
|
| 7298 |
+
{
|
| 7299 |
+
"epoch": 0.07749170794104086,
|
| 7300 |
+
"grad_norm": 0.6656064391136169,
|
| 7301 |
+
"learning_rate": 1.998815013555771e-05,
|
| 7302 |
+
"loss": 1.5282,
|
| 7303 |
+
"step": 104200
|
| 7304 |
+
},
|
| 7305 |
+
{
|
| 7306 |
+
"epoch": 0.07756607618282689,
|
| 7307 |
+
"grad_norm": 0.6679131388664246,
|
| 7308 |
+
"learning_rate": 1.9988127383593923e-05,
|
| 7309 |
+
"loss": 1.4922,
|
| 7310 |
+
"step": 104300
|
| 7311 |
+
},
|
| 7312 |
+
{
|
| 7313 |
+
"epoch": 0.07764044442461292,
|
| 7314 |
+
"grad_norm": 0.5231404304504395,
|
| 7315 |
+
"learning_rate": 1.9988104609821953e-05,
|
| 7316 |
+
"loss": 1.4648,
|
| 7317 |
+
"step": 104400
|
| 7318 |
+
},
|
| 7319 |
+
{
|
| 7320 |
+
"epoch": 0.07771481266639894,
|
| 7321 |
+
"grad_norm": 0.6543662548065186,
|
| 7322 |
+
"learning_rate": 1.998808181424185e-05,
|
| 7323 |
+
"loss": 1.5349,
|
| 7324 |
+
"step": 104500
|
| 7325 |
+
},
|
| 7326 |
+
{
|
| 7327 |
+
"epoch": 0.07778918090818497,
|
| 7328 |
+
"grad_norm": 0.4422987997531891,
|
| 7329 |
+
"learning_rate": 1.9988058996853666e-05,
|
| 7330 |
+
"loss": 1.5031,
|
| 7331 |
+
"step": 104600
|
| 7332 |
+
},
|
| 7333 |
+
{
|
| 7334 |
+
"epoch": 0.077863549149971,
|
| 7335 |
+
"grad_norm": 0.74057537317276,
|
| 7336 |
+
"learning_rate": 1.9988036157657444e-05,
|
| 7337 |
+
"loss": 1.5373,
|
| 7338 |
+
"step": 104700
|
| 7339 |
}
|
| 7340 |
],
|
| 7341 |
"logging_steps": 100,
|
|
|
|
| 7355 |
"attributes": {}
|
| 7356 |
}
|
| 7357 |
},
|
| 7358 |
+
"total_flos": 1.4266624174398996e+18,
|
| 7359 |
"train_batch_size": 1,
|
| 7360 |
"trial_name": null,
|
| 7361 |
"trial_params": null
|