Upload folder using huggingface_hub

adapter_config.json

@@ -20,12 +20,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "o_proj",
+    "down_proj",
     "q_proj",
-    "v_proj",
+    "k_proj",
+    "o_proj",
     "up_proj",
-    "down_proj",
-    "k_proj"
+    "v_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:f9717cbebc205e1af430c72be6a0465f4095420535c8cc3c8ae5d794f3b5daee
+oid sha256:26a39646999558a6ce48dbf17c3548121786b79bb9464da89c0ba77968ab8185
 size 242266152

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b1b5a127f2a457e3248088189f9ae28f0a9d9c039b4eb7be65f9207a18ecafe
+oid sha256:15deade411f073d7e729a7b332555536850456a049144f6c87b5081190796925
 size 484650042

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79cf4d1393f503ba4a8055192b3a8aa861a1f8a2b16b36313f557224e39afed9
+oid sha256:7c5f87417d8ff5e70cd9b14c5c26c6569a88421c7b969200f8d5a0e12c3ee048
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e64c27b726a577c804ba18635f5817ee9a88d577397eb271ce5dc27f397651c
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

trainer_state.json

@@ -1,206 +1,320 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.992,
+  "epoch": 0.9944064636420137,
   "eval_steps": 500,
-  "global_step": 62,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.03,
+      "epoch": 0.02,
       "learning_rate": 0.0002,
-      "loss": 1.6287,
+      "loss": 2.2936,
       "step": 2
     },
     {
-      "epoch": 0.06,
+      "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 1.6844,
+      "loss": 2.1803,
       "step": 4
     },
     {
-      "epoch": 0.1,
+      "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 1.6992,
+      "loss": 2.1587,
       "step": 6
     },
     {
-      "epoch": 0.13,
+      "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 1.7574,
+      "loss": 2.1444,
       "step": 8
     },
     {
-      "epoch": 0.16,
+      "epoch": 0.1,
       "learning_rate": 0.0002,
-      "loss": 1.7539,
+      "loss": 2.0706,
       "step": 10
     },
     {
-      "epoch": 0.19,
+      "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 1.768,
+      "loss": 2.1399,
       "step": 12
     },
     {
-      "epoch": 0.22,
+      "epoch": 0.14,
       "learning_rate": 0.0002,
-      "loss": 2.0735,
+      "loss": 2.0224,
       "step": 14
     },
     {
-      "epoch": 0.26,
+      "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 1.6763,
+      "loss": 2.0933,
       "step": 16
     },
     {
-      "epoch": 0.29,
+      "epoch": 0.18,
       "learning_rate": 0.0002,
-      "loss": 1.2736,
+      "loss": 2.021,
       "step": 18
     },
     {
-      "epoch": 0.32,
+      "epoch": 0.2,
       "learning_rate": 0.0002,
-      "loss": 1.273,
+      "loss": 1.9728,
       "step": 20
     },
     {
-      "epoch": 0.35,
+      "epoch": 0.22,
       "learning_rate": 0.0002,
-      "loss": 1.3671,
+      "loss": 2.111,
       "step": 22
     },
     {
-      "epoch": 0.38,
+      "epoch": 0.24,
       "learning_rate": 0.0002,
-      "loss": 1.1594,
+      "loss": 1.8839,
       "step": 24
     },
     {
-      "epoch": 0.42,
+      "epoch": 0.26,
       "learning_rate": 0.0002,
-      "loss": 1.2744,
+      "loss": 1.8489,
       "step": 26
     },
     {
-      "epoch": 0.45,
+      "epoch": 0.28,
       "learning_rate": 0.0002,
-      "loss": 1.3281,
+      "loss": 2.0654,
       "step": 28
     },
     {
-      "epoch": 0.48,
+      "epoch": 0.3,
       "learning_rate": 0.0002,
-      "loss": 1.2365,
+      "loss": 2.0341,
       "step": 30
     },
     {
-      "epoch": 0.51,
+      "epoch": 0.32,
       "learning_rate": 0.0002,
-      "loss": 1.1392,
+      "loss": 1.9521,
       "step": 32
     },
     {
-      "epoch": 0.54,
+      "epoch": 0.34,
       "learning_rate": 0.0002,
-      "loss": 1.1334,
+      "loss": 1.9955,
       "step": 34
     },
     {
-      "epoch": 0.58,
+      "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 1.0542,
+      "loss": 2.0216,
       "step": 36
     },
     {
-      "epoch": 0.61,
+      "epoch": 0.38,
       "learning_rate": 0.0002,
-      "loss": 1.1079,
+      "loss": 2.0376,
       "step": 38
     },
     {
-      "epoch": 0.64,
+      "epoch": 0.4,
       "learning_rate": 0.0002,
-      "loss": 1.1394,
+      "loss": 1.8855,
       "step": 40
     },
     {
-      "epoch": 0.67,
+      "epoch": 0.42,
       "learning_rate": 0.0002,
-      "loss": 1.122,
+      "loss": 1.8584,
       "step": 42
     },
     {
-      "epoch": 0.7,
+      "epoch": 0.44,
       "learning_rate": 0.0002,
-      "loss": 1.1356,
+      "loss": 2.0344,
       "step": 44
     },
     {
-      "epoch": 0.74,
+      "epoch": 0.46,
       "learning_rate": 0.0002,
-      "loss": 1.2301,
+      "loss": 1.8226,
       "step": 46
     },
     {
-      "epoch": 0.77,
+      "epoch": 0.48,
       "learning_rate": 0.0002,
-      "loss": 1.1028,
+      "loss": 1.923,
       "step": 48
     },
     {
-      "epoch": 0.8,
+      "epoch": 0.5,
       "learning_rate": 0.0002,
-      "loss": 1.0714,
+      "loss": 1.88,
       "step": 50
     },
     {
-      "epoch": 0.83,
+      "epoch": 0.52,
       "learning_rate": 0.0002,
-      "loss": 1.0011,
+      "loss": 1.8955,
       "step": 52
     },
     {
-      "epoch": 0.86,
+      "epoch": 0.54,
       "learning_rate": 0.0002,
-      "loss": 1.0505,
+      "loss": 2.0179,
       "step": 54
     },
     {
-      "epoch": 0.9,
+      "epoch": 0.56,
       "learning_rate": 0.0002,
-      "loss": 1.0133,
+      "loss": 1.992,
       "step": 56
     },
     {
-      "epoch": 0.93,
+      "epoch": 0.58,
       "learning_rate": 0.0002,
-      "loss": 1.0462,
+      "loss": 2.0401,
       "step": 58
     },
     {
-      "epoch": 0.96,
+      "epoch": 0.6,
       "learning_rate": 0.0002,
-      "loss": 1.0668,
+      "loss": 2.1087,
       "step": 60
     },
     {
-      "epoch": 0.99,
+      "epoch": 0.62,
       "learning_rate": 0.0002,
-      "loss": 1.0093,
+      "loss": 1.9005,
       "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002,
+      "loss": 2.0037,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 2.0415,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002,
+      "loss": 1.8825,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002,
+      "loss": 1.6636,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002,
+      "loss": 1.9599,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 2.0305,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002,
+      "loss": 1.9139,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002,
+      "loss": 1.8878,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 1.9189,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002,
+      "loss": 1.9306,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0002,
+      "loss": 1.9141,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002,
+      "loss": 2.0502,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002,
+      "loss": 1.923,
+      "step": 88
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002,
+      "loss": 1.8456,
+      "step": 90
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002,
+      "loss": 1.7748,
+      "step": 92
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 1.845,
+      "step": 94
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 1.8059,
+      "step": 96
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002,
+      "loss": 1.7629,
+      "step": 98
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002,
+      "loss": 1.8387,
+      "step": 100
     }
   ],
   "logging_steps": 2,
-  "max_steps": 62,
+  "max_steps": 100,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 2204302063927296.0,
+  "total_flos": 1.345730386833408e+16,
   "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 sha256:166d7c878fc7bdd81bf59933ee93a8be1489c0c745eba588f488d4cb0a2a4d1a
+oid sha256:9650c9dcad2c0f3bac47ee99b13131759e632e0b89f52434ba29ffe7b05520e4
 size 4728