Upload folder using huggingface_hub

adapter_config.json

@@ -19,9 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "o_proj",
     "gate_proj",
-    "down_proj",
-    "up_proj"
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:030df8c30a66a1b2d7a1edd7a4267c77e80234033ccf2042f410b4db87c65af3
-size 58221088
+oid sha256:aa405f6df81cd6621d9fecf2363a7b3292f01b7790557a885c26421a53061412
+size 100198584

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57a3b322fae3803f6115be766a996014f2cafbaf84c56b8ee45e201d1d44bf16
-size 116508154
+oid sha256:5739b541d9500aa245f1e5d17fa010f4ce2fe6299f41ccd02e7a615ae4291b4f
+size 200545402

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca428527922547719a3a8da12c376222f09b0f08bb0c2b20baeef54f220f95b8
+oid sha256:96134f70cea7e3c39093ded4a11b22c9c544ebe4cafa4eef41fc7db0ed207135
 size 14244

trainer_state.json

@@ -11,145 +11,145 @@
     {
       "epoch": 0.04,
       "learning_rate": 2e-05,
-      "loss": 1.8538,
+      "loss": 1.8529,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 2e-05,
-      "loss": 2.2228,
+      "loss": 2.219,
       "step": 4
     },
     {
       "epoch": 0.12,
       "learning_rate": 2e-05,
-      "loss": 2.246,
+      "loss": 2.2383,
       "step": 6
     },
     {
       "epoch": 0.16,
       "learning_rate": 2e-05,
-      "loss": 2.3182,
+      "loss": 2.3014,
       "step": 8
     },
     {
       "epoch": 0.21,
       "learning_rate": 2e-05,
-      "loss": 2.4862,
+      "loss": 2.4572,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 2e-05,
-      "loss": 2.8649,
+      "loss": 2.7778,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 2e-05,
-      "loss": 1.9152,
+      "loss": 1.9011,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 2e-05,
-      "loss": 1.8919,
+      "loss": 1.8648,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 2e-05,
-      "loss": 2.2002,
+      "loss": 2.1674,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 2e-05,
-      "loss": 2.1343,
+      "loss": 2.0898,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 2e-05,
-      "loss": 2.3809,
+      "loss": 2.326,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 2e-05,
-      "loss": 2.65,
+      "loss": 2.5082,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 2e-05,
-      "loss": 1.8329,
+      "loss": 1.8068,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 2e-05,
-      "loss": 2.0931,
+      "loss": 2.0524,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 2e-05,
-      "loss": 2.3318,
+      "loss": 2.2911,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 2e-05,
-      "loss": 2.0929,
+      "loss": 2.0351,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 2e-05,
-      "loss": 2.1388,
+      "loss": 2.0601,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 2e-05,
-      "loss": 2.5487,
+      "loss": 2.3926,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 2e-05,
-      "loss": 1.8645,
+      "loss": 1.8453,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 2e-05,
-      "loss": 2.1712,
+      "loss": 2.1355,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 2e-05,
-      "loss": 2.2737,
+      "loss": 2.2368,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 2e-05,
-      "loss": 2.3037,
+      "loss": 2.2696,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 2e-05,
-      "loss": 2.1125,
+      "loss": 2.0637,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 2e-05,
-      "loss": 2.4756,
+      "loss": 2.3634,
       "step": 48
     }
   ],
@@ -158,7 +158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 6721315396724736.0,
+  "total_flos": 6747601288636416.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74e83a165fa225d16722a027928462e982b5e88fc5d6526c61bb1e20e6decc8
+oid sha256:a5bad23ca216ebbd9b73663d7744425ce42a5f56e20a4740af2ac918b77e5f4e
 size 4728