Upload folder using huggingface_hub

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "k_proj",
-    "down_proj",
     "gate_proj",
-    "v_proj",
+    "o_proj",
     "q_proj",
-    "o_proj"
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "k_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:b2113afdf83ffe0eece622986374554b8d9d82640ab5d7774ad2a3e816dc1cde
+oid sha256:f9717cbebc205e1af430c72be6a0465f4095420535c8cc3c8ae5d794f3b5daee
 size 242266152

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af5ac2d38e06d965f0bc4f2e7dc8070f9e50ec66897e639735556e4a41d34c7e
+oid sha256:2b1b5a127f2a457e3248088189f9ae28f0a9d9c039b4eb7be65f9207a18ecafe
 size 484650042

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afa3762e03756c2219cb9f34c64f8d4a8faa707cdc0641ada245005a030dab7b
+oid sha256:79cf4d1393f503ba4a8055192b3a8aa861a1f8a2b16b36313f557224e39afed9
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824a429c5f95423b97fd2ff7dc1e1dffcd96691286babb37392f00bfcecaeb1b
+oid sha256:5e64c27b726a577c804ba18635f5817ee9a88d577397eb271ce5dc27f397651c
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9990680335507922,
+  "epoch": 0.992,
   "eval_steps": 500,
-  "global_step": 67,
+  "global_step": 62,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,208 +11,196 @@
     {
       "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 2.4578,
+      "loss": 1.6287,
       "step": 2
     },
     {
       "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 1.6101,
+      "loss": 1.6844,
       "step": 4
     },
     {
-      "epoch": 0.09,
+      "epoch": 0.1,
       "learning_rate": 0.0002,
-      "loss": 1.5549,
+      "loss": 1.6992,
       "step": 6
     },
     {
-      "epoch": 0.12,
+      "epoch": 0.13,
       "learning_rate": 0.0002,
-      "loss": 1.5769,
+      "loss": 1.7574,
       "step": 8
     },
     {
-      "epoch": 0.15,
+      "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 1.3154,
+      "loss": 1.7539,
       "step": 10
     },
     {
-      "epoch": 0.18,
+      "epoch": 0.19,
       "learning_rate": 0.0002,
-      "loss": 1.3855,
+      "loss": 1.768,
       "step": 12
     },
     {
-      "epoch": 0.21,
+      "epoch": 0.22,
       "learning_rate": 0.0002,
-      "loss": 1.6044,
+      "loss": 2.0735,
       "step": 14
     },
     {
-      "epoch": 0.24,
+      "epoch": 0.26,
       "learning_rate": 0.0002,
-      "loss": 1.8857,
+      "loss": 1.6763,
       "step": 16
     },
     {
-      "epoch": 0.27,
+      "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 2.4409,
+      "loss": 1.2736,
       "step": 18
     },
     {
-      "epoch": 0.3,
+      "epoch": 0.32,
       "learning_rate": 0.0002,
-      "loss": 1.5895,
+      "loss": 1.273,
       "step": 20
     },
     {
-      "epoch": 0.33,
+      "epoch": 0.35,
       "learning_rate": 0.0002,
-      "loss": 1.4653,
+      "loss": 1.3671,
       "step": 22
     },
     {
-      "epoch": 0.36,
+      "epoch": 0.38,
       "learning_rate": 0.0002,
-      "loss": 1.4579,
+      "loss": 1.1594,
       "step": 24
     },
     {
-      "epoch": 0.39,
+      "epoch": 0.42,
       "learning_rate": 0.0002,
-      "loss": 1.2793,
+      "loss": 1.2744,
       "step": 26
     },
     {
-      "epoch": 0.42,
+      "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 1.4457,
+      "loss": 1.3281,
       "step": 28
     },
     {
-      "epoch": 0.45,
+      "epoch": 0.48,
       "learning_rate": 0.0002,
-      "loss": 1.5239,
+      "loss": 1.2365,
       "step": 30
     },
     {
-      "epoch": 0.48,
+      "epoch": 0.51,
       "learning_rate": 0.0002,
-      "loss": 1.7433,
+      "loss": 1.1392,
       "step": 32
     },
     {
-      "epoch": 0.51,
+      "epoch": 0.54,
       "learning_rate": 0.0002,
-      "loss": 2.0031,
+      "loss": 1.1334,
       "step": 34
     },
     {
-      "epoch": 0.54,
+      "epoch": 0.58,
       "learning_rate": 0.0002,
-      "loss": 1.6557,
+      "loss": 1.0542,
       "step": 36
     },
     {
-      "epoch": 0.57,
+      "epoch": 0.61,
       "learning_rate": 0.0002,
-      "loss": 1.4022,
+      "loss": 1.1079,
       "step": 38
     },
     {
-      "epoch": 0.6,
+      "epoch": 0.64,
       "learning_rate": 0.0002,
-      "loss": 1.4538,
+      "loss": 1.1394,
       "step": 40
     },
     {
-      "epoch": 0.63,
+      "epoch": 0.67,
       "learning_rate": 0.0002,
-      "loss": 1.0563,
+      "loss": 1.122,
       "step": 42
     },
     {
-      "epoch": 0.66,
+      "epoch": 0.7,
       "learning_rate": 0.0002,
-      "loss": 1.435,
+      "loss": 1.1356,
       "step": 44
     },
     {
-      "epoch": 0.69,
+      "epoch": 0.74,
       "learning_rate": 0.0002,
-      "loss": 1.5474,
+      "loss": 1.2301,
       "step": 46
     },
     {
-      "epoch": 0.72,
+      "epoch": 0.77,
       "learning_rate": 0.0002,
-      "loss": 1.5729,
+      "loss": 1.1028,
       "step": 48
     },
     {
-      "epoch": 0.75,
+      "epoch": 0.8,
       "learning_rate": 0.0002,
-      "loss": 2.5351,
+      "loss": 1.0714,
       "step": 50
     },
     {
-      "epoch": 0.78,
+      "epoch": 0.83,
       "learning_rate": 0.0002,
-      "loss": 1.636,
+      "loss": 1.0011,
       "step": 52
     },
     {
-      "epoch": 0.81,
+      "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 1.396,
+      "loss": 1.0505,
       "step": 54
     },
     {
-      "epoch": 0.84,
+      "epoch": 0.9,
       "learning_rate": 0.0002,
-      "loss": 1.3188,
+      "loss": 1.0133,
       "step": 56
     },
     {
-      "epoch": 0.86,
+      "epoch": 0.93,
       "learning_rate": 0.0002,
-      "loss": 1.0642,
+      "loss": 1.0462,
       "step": 58
     },
     {
-      "epoch": 0.89,
+      "epoch": 0.96,
       "learning_rate": 0.0002,
-      "loss": 1.3227,
+      "loss": 1.0668,
       "step": 60
     },
     {
-      "epoch": 0.92,
+      "epoch": 0.99,
       "learning_rate": 0.0002,
-      "loss": 1.5333,
+      "loss": 1.0093,
       "step": 62
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.0002,
-      "loss": 1.339,
-      "step": 64
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 0.0002,
-      "loss": 1.6597,
-      "step": 66
     }
   ],
   "logging_steps": 2,
-  "max_steps": 67,
+  "max_steps": 62,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 4514772246331392.0,
+  "total_flos": 2204302063927296.0,
   "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 sha256:46ee3c4ec69ddcbb6e97469db7a5d185731f5a8272274f95011612120afc78aa
+oid sha256:166d7c878fc7bdd81bf59933ee93a8be1489c0c745eba588f488d4cb0a2a4d1a
 size 4728