Upload folder using huggingface_hub

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f092c94a07f4d55cd5d7a00ec213432c151abe8f78711028fd6aa9654fe8baf
+oid sha256:642f477bb24d61218babd0670664f3a4df918b5d8bb35c0f50583a34a92be0b7
 size 242266152

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29b44e545ad0fe7183464094b9b2dec3f04949f1245f59d9322650c7a102d70e
+oid sha256:639e62b4dffb7f663a3bddbc13c477870e8d84e0071e56ab04cc450206838a09
 size 484650042

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80bde0336a267c111569a8143afc5a48a7cefcfc2b02d9ae756ea1799ded6e26
+oid sha256:324b380e4b844f229ef1eb78c684dbffa81653737123018b945caa09ff6d0595
 size 14244

trainer_state.json

@@ -11,208 +11,208 @@
     {
       "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 2.2668,
+      "loss": 2.0495,
       "step": 2
     },
     {
       "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 1.8551,
+      "loss": 1.9142,
       "step": 4
     },
     {
       "epoch": 0.09,
       "learning_rate": 0.0002,
-      "loss": 1.5604,
+      "loss": 1.6721,
       "step": 6
     },
     {
       "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 1.6692,
+      "loss": 1.7108,
       "step": 8
     },
     {
       "epoch": 0.15,
       "learning_rate": 0.0002,
-      "loss": 1.3129,
+      "loss": 1.2174,
       "step": 10
     },
     {
       "epoch": 0.18,
       "learning_rate": 0.0002,
-      "loss": 1.3419,
+      "loss": 1.5764,
       "step": 12
     },
     {
       "epoch": 0.21,
       "learning_rate": 0.0002,
-      "loss": 1.7095,
+      "loss": 1.8746,
       "step": 14
     },
     {
       "epoch": 0.24,
       "learning_rate": 0.0002,
-      "loss": 2.0765,
+      "loss": 2.0229,
       "step": 16
     },
     {
       "epoch": 0.27,
       "learning_rate": 0.0002,
-      "loss": 2.5753,
+      "loss": 2.6714,
       "step": 18
     },
     {
       "epoch": 0.3,
       "learning_rate": 0.0002,
-      "loss": 1.6241,
+      "loss": 1.5431,
       "step": 20
     },
     {
       "epoch": 0.33,
       "learning_rate": 0.0002,
-      "loss": 1.4522,
+      "loss": 1.4803,
       "step": 22
     },
     {
       "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 1.3241,
+      "loss": 1.399,
       "step": 24
     },
     {
       "epoch": 0.39,
       "learning_rate": 0.0002,
-      "loss": 1.2951,
+      "loss": 1.3031,
       "step": 26
     },
     {
       "epoch": 0.42,
       "learning_rate": 0.0002,
-      "loss": 1.4782,
+      "loss": 1.5004,
       "step": 28
     },
     {
       "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 1.5635,
+      "loss": 1.5976,
       "step": 30
     },
     {
       "epoch": 0.48,
       "learning_rate": 0.0002,
-      "loss": 1.6126,
+      "loss": 1.698,
       "step": 32
     },
     {
       "epoch": 0.51,
       "learning_rate": 0.0002,
-      "loss": 2.3792,
+      "loss": 2.5133,
       "step": 34
     },
     {
       "epoch": 0.54,
       "learning_rate": 0.0002,
-      "loss": 1.5842,
+      "loss": 1.6247,
       "step": 36
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 1.5121,
+      "loss": 1.436,
       "step": 38
     },
     {
       "epoch": 0.6,
       "learning_rate": 0.0002,
-      "loss": 1.4825,
+      "loss": 1.4314,
       "step": 40
     },
     {
       "epoch": 0.63,
       "learning_rate": 0.0002,
-      "loss": 1.1322,
+      "loss": 1.1464,
       "step": 42
     },
     {
       "epoch": 0.66,
       "learning_rate": 0.0002,
-      "loss": 1.4946,
+      "loss": 1.2779,
       "step": 44
     },
     {
       "epoch": 0.69,
       "learning_rate": 0.0002,
-      "loss": 1.6078,
+      "loss": 1.4408,
       "step": 46
     },
     {
       "epoch": 0.72,
       "learning_rate": 0.0002,
-      "loss": 1.4013,
+      "loss": 1.4426,
       "step": 48
     },
     {
       "epoch": 0.75,
       "learning_rate": 0.0002,
-      "loss": 2.5368,
+      "loss": 2.4268,
       "step": 50
     },
     {
       "epoch": 0.78,
       "learning_rate": 0.0002,
-      "loss": 1.3368,
+      "loss": 1.5227,
       "step": 52
     },
     {
       "epoch": 0.81,
       "learning_rate": 0.0002,
-      "loss": 1.3519,
+      "loss": 1.4014,
       "step": 54
     },
     {
       "epoch": 0.84,
       "learning_rate": 0.0002,
-      "loss": 1.483,
+      "loss": 1.3023,
       "step": 56
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 1.1371,
+      "loss": 1.2205,
       "step": 58
     },
     {
       "epoch": 0.89,
       "learning_rate": 0.0002,
-      "loss": 1.2318,
+      "loss": 1.3143,
       "step": 60
     },
     {
       "epoch": 0.92,
       "learning_rate": 0.0002,
-      "loss": 1.408,
+      "loss": 1.491,
       "step": 62
     },
     {
       "epoch": 0.95,
       "learning_rate": 0.0002,
-      "loss": 1.4301,
+      "loss": 1.4041,
       "step": 64
     },
     {
       "epoch": 0.98,
       "learning_rate": 0.0002,
-      "loss": 1.4105,
+      "loss": 1.3281,
       "step": 66
     }
   ],
   "logging_steps": 2,
-  "max_steps": 67,
+  "max_steps": 201,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 4514565308473344.0,
+  "total_flos": 4514943194996736.0,
   "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 sha256:903a6aa184e2e7fcae2e29042c8eb8efa1074a06a9fde91beb5c74ea253ca05b
+oid sha256:350aeb7e91825c3df5a43a0c3c9800fdd74e2dbfb83d316d704b621b3807540a
 size 4728