Training in progress, step 350400, 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:bacab94e8f87cf35ef411c7c65fecbb666c260c1a519a8e6d62cb87b739b0e41
 size 1342238560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cd506869b94b5be970fca409bc95398841b5ffd9a592fb2c061dc58227eceba
+oid sha256:5dc881684d7c831327ac9144b6a5ac71fb555a5335d990a22e528402bdcd0393
 size 683268498

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3650e87ca836906ee8691b7d5d7b6eea6cead08041d7a7bfe35d5aa4494083ae
+oid sha256:54f473baf33801100e1396f1bf6d1e31cd670bff28f92fca270eae43b9ac676e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7ddbf1d6d4ba083fc85b63bf4848a26d38ae4d64ba73f9a2514a5c0d3a9d8c
+oid sha256:d5a5ba44adfd5d04a1ccd87723bb586e5c3cf43220e46fe2cf094e283c8ead53
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24314063140061104,
+  "epoch": 0.243697017284823,
   "eval_steps": 500,
-  "global_step": 349600,
+  "global_step": 350400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12243,6 +12243,34 @@
       "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
     }
   ],
   "logging_steps": 200,
@@ -12262,7 +12290,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.654650097453105e+18,
+  "total_flos": 4.665140080450634e+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