Training in progress, step 354000, checkpoint

last-checkpoint/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "v_proj",
     "o_proj",
-    "q_proj",
     "k_proj",
     "down_proj",
-    "up_proj"
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cdea3181ff20981cb33a156aeb80b8e43818a8f05858b95c059340e21aa8733
+oid sha256:e9c2bac8b502b19efc41232812d63c71fee5df5671162a7150c06e61fa051ae9
 size 1342238560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cd506869b94b5be970fca409bc95398841b5ffd9a592fb2c061dc58227eceba
+oid sha256:5c4a3d4af06483be93d8df8956639f5a14629f88f01f5e9197bad971be65ed91
 size 683268498

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3650e87ca836906ee8691b7d5d7b6eea6cead08041d7a7bfe35d5aa4494083ae
+oid sha256:9e162559635122d1fd8bf513b6383eeaef54f892ebd418422f5439a78e18e22f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7ddbf1d6d4ba083fc85b63bf4848a26d38ae4d64ba73f9a2514a5c0d3a9d8c
+oid sha256:dad438b9465aa0569ad2c4a4ce56c9f5f47a608feb10b35e8561cd9dadb0857d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24314063140061104,
+  "epoch": 0.24620075376377665,
   "eval_steps": 500,
-  "global_step": 349600,
+  "global_step": 354000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12243,6 +12243,160 @@
       "learning_rate": 1.94956437917686e-05,
       "loss": 1.6643,
       "step": 349600
+    },
+    {
+      "epoch": 0.24327972787166402,
+      "grad_norm": 4.202829837799072,
+      "learning_rate": 1.949507360178391e-05,
+      "loss": 1.6291,
+      "step": 349800
+    },
+    {
+      "epoch": 0.243418824342717,
+      "grad_norm": 6.402523517608643,
+      "learning_rate": 1.949450310173186e-05,
+      "loss": 1.6366,
+      "step": 350000
+    },
+    {
+      "epoch": 0.24355792081377,
+      "grad_norm": 5.324528694152832,
+      "learning_rate": 1.9493932291639685e-05,
+      "loss": 1.6421,
+      "step": 350200
+    },
+    {
+      "epoch": 0.243697017284823,
+      "grad_norm": 0.4841703772544861,
+      "learning_rate": 1.9493361171534633e-05,
+      "loss": 1.6182,
+      "step": 350400
+    },
+    {
+      "epoch": 0.24383611375587597,
+      "grad_norm": 4.352268218994141,
+      "learning_rate": 1.949278974144397e-05,
+      "loss": 1.6553,
+      "step": 350600
+    },
+    {
+      "epoch": 0.24397521022692895,
+      "grad_norm": 4.935366630554199,
+      "learning_rate": 1.9492218001394977e-05,
+      "loss": 1.6541,
+      "step": 350800
+    },
+    {
+      "epoch": 0.24411430669798193,
+      "grad_norm": 3.1909875869750977,
+      "learning_rate": 1.9491645951414943e-05,
+      "loss": 1.7019,
+      "step": 351000
+    },
+    {
+      "epoch": 0.2442534031690349,
+      "grad_norm": 4.752991199493408,
+      "learning_rate": 1.9491073591531178e-05,
+      "loss": 1.6571,
+      "step": 351200
+    },
+    {
+      "epoch": 0.24439249964008788,
+      "grad_norm": 6.217344284057617,
+      "learning_rate": 1.949050092177101e-05,
+      "loss": 1.723,
+      "step": 351400
+    },
+    {
+      "epoch": 0.24453159611114086,
+      "grad_norm": 6.201177597045898,
+      "learning_rate": 1.948992794216178e-05,
+      "loss": 1.6802,
+      "step": 351600
+    },
+    {
+      "epoch": 0.24467069258219384,
+      "grad_norm": 2.825784683227539,
+      "learning_rate": 1.948935465273083e-05,
+      "loss": 1.5842,
+      "step": 351800
+    },
+    {
+      "epoch": 0.24480978905324682,
+      "grad_norm": 4.810288429260254,
+      "learning_rate": 1.948878105350554e-05,
+      "loss": 1.7099,
+      "step": 352000
+    },
+    {
+      "epoch": 0.2449488855242998,
+      "grad_norm": 4.089555263519287,
+      "learning_rate": 1.9488207144513284e-05,
+      "loss": 1.7244,
+      "step": 352200
+    },
+    {
+      "epoch": 0.24508798199535278,
+      "grad_norm": 6.472701549530029,
+      "learning_rate": 1.948763292578147e-05,
+      "loss": 1.6518,
+      "step": 352400
+    },
+    {
+      "epoch": 0.24522707846640576,
+      "grad_norm": 3.4730377197265625,
+      "learning_rate": 1.9487058397337498e-05,
+      "loss": 1.708,
+      "step": 352600
+    },
+    {
+      "epoch": 0.24536617493745874,
+      "grad_norm": 3.145690441131592,
+      "learning_rate": 1.9486483559208805e-05,
+      "loss": 1.6469,
+      "step": 352800
+    },
+    {
+      "epoch": 0.24550527140851172,
+      "grad_norm": 3.899048089981079,
+      "learning_rate": 1.948590841142283e-05,
+      "loss": 1.6595,
+      "step": 353000
+    },
+    {
+      "epoch": 0.2456443678795647,
+      "grad_norm": 5.847311973571777,
+      "learning_rate": 1.948533295400703e-05,
+      "loss": 1.6287,
+      "step": 353200
+    },
+    {
+      "epoch": 0.24578346435061768,
+      "grad_norm": 3.397681713104248,
+      "learning_rate": 1.9484757186988875e-05,
+      "loss": 1.6518,
+      "step": 353400
+    },
+    {
+      "epoch": 0.24592256082167066,
+      "grad_norm": 4.522960662841797,
+      "learning_rate": 1.9484181110395854e-05,
+      "loss": 1.6843,
+      "step": 353600
+    },
+    {
+      "epoch": 0.24606165729272367,
+      "grad_norm": 4.118208408355713,
+      "learning_rate": 1.9483604724255466e-05,
+      "loss": 1.6792,
+      "step": 353800
+    },
+    {
+      "epoch": 0.24620075376377665,
+      "grad_norm": 3.8641409873962402,
+      "learning_rate": 1.9483028028595225e-05,
+      "loss": 1.6484,
+      "step": 354000
     }
   ],
   "logging_steps": 200,
@@ -12262,7 +12416,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.654650097453105e+18,
+  "total_flos": 4.712916903428727e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:078136780f82e4c02daf15d387ce5ace039d2fead953e9b2034a974f0b6417e9
+oid sha256:7a29a5a0f0399f7044a026f76e298444ea587cc6f3dc814a0d8be9df650c7561
 size 6840