Upload folder using huggingface_hub

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
     "gate_proj",
-    "o_proj",
-    "down_proj",
+    "k_proj",
     "v_proj",
-    "k_proj"
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "o_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:cc805562df8d1ecadb0c7ceffd216b6ce1fc1b37b12c12a52bb95c28b1936981
+oid sha256:a8f5db884fc45383555cc36baa2554ecddf823c116a79ec54d1163fb1548ac99
 size 242266152

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbc845a86ea49fcb13768bd2e1dffa9c405dc1c7d0f7bd8eff6b9a03d0a4e377
+oid sha256:27cb53e0532028dc175b4be3d2cbe99024374fb69b15bff2321f9ef10a55746f
 size 484650042

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c1c57b943500bdd422828e26395d31b84f5a9794fe4c32c901ecbc4e90724e
+oid sha256:d08e7663e93154b5e276ea55350b152fcbdc9cfad091cadc5f979b68c7b3ec95
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53465f7cbdf87cbc584b429a13bf1f7b1601c644d5e6387bef7542821ec7e747
+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": 1.6044,
+      "loss": 2.299,
       "step": 2
     },
     {
-      "epoch": 0.06,
+      "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 1.5881,
+      "loss": 2.2134,
       "step": 4
     },
     {
-      "epoch": 0.1,
+      "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 1.5893,
+      "loss": 2.2087,
       "step": 6
     },
     {
-      "epoch": 0.13,
+      "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 1.6713,
+      "loss": 2.1724,
       "step": 8
     },
     {
-      "epoch": 0.16,
+      "epoch": 0.1,
       "learning_rate": 0.0002,
-      "loss": 1.6675,
+      "loss": 2.1269,
       "step": 10
     },
     {
-      "epoch": 0.19,
+      "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 1.728,
+      "loss": 2.0387,
       "step": 12
     },
     {
-      "epoch": 0.22,
+      "epoch": 0.14,
       "learning_rate": 0.0002,
-      "loss": 2.0484,
+      "loss": 2.0762,
       "step": 14
     },
     {
-      "epoch": 0.26,
+      "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 1.6691,
+      "loss": 2.0761,
       "step": 16
     },
     {
-      "epoch": 0.29,
+      "epoch": 0.18,
       "learning_rate": 0.0002,
-      "loss": 1.2777,
+      "loss": 1.8674,
       "step": 18
     },
     {
-      "epoch": 0.32,
+      "epoch": 0.2,
       "learning_rate": 0.0002,
-      "loss": 1.3286,
+      "loss": 1.9787,
       "step": 20
     },
     {
-      "epoch": 0.35,
+      "epoch": 0.22,
       "learning_rate": 0.0002,
-      "loss": 1.2907,
+      "loss": 2.0048,
       "step": 22
     },
     {
-      "epoch": 0.38,
+      "epoch": 0.24,
       "learning_rate": 0.0002,
-      "loss": 1.2286,
+      "loss": 2.0804,
       "step": 24
     },
     {
-      "epoch": 0.42,
+      "epoch": 0.26,
       "learning_rate": 0.0002,
-      "loss": 1.3034,
+      "loss": 1.9884,
       "step": 26
     },
     {
-      "epoch": 0.45,
+      "epoch": 0.28,
       "learning_rate": 0.0002,
-      "loss": 1.2253,
+      "loss": 1.9077,
       "step": 28
     },
     {
-      "epoch": 0.48,
+      "epoch": 0.3,
       "learning_rate": 0.0002,
-      "loss": 1.398,
+      "loss": 2.0288,
       "step": 30
     },
     {
-      "epoch": 0.51,
+      "epoch": 0.32,
       "learning_rate": 0.0002,
-      "loss": 1.1233,
+      "loss": 2.0835,
       "step": 32
     },
     {
-      "epoch": 0.54,
+      "epoch": 0.34,
       "learning_rate": 0.0002,
-      "loss": 1.181,
+      "loss": 1.9311,
       "step": 34
     },
     {
-      "epoch": 0.58,
+      "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 1.1303,
+      "loss": 2.1007,
       "step": 36
     },
     {
-      "epoch": 0.61,
+      "epoch": 0.38,
       "learning_rate": 0.0002,
-      "loss": 1.12,
+      "loss": 2.0232,
       "step": 38
     },
     {
-      "epoch": 0.64,
+      "epoch": 0.4,
       "learning_rate": 0.0002,
-      "loss": 1.191,
+      "loss": 2.051,
       "step": 40
     },
     {
-      "epoch": 0.67,
+      "epoch": 0.42,
       "learning_rate": 0.0002,
-      "loss": 1.1562,
+      "loss": 1.7143,
       "step": 42
     },
     {
-      "epoch": 0.7,
+      "epoch": 0.44,
       "learning_rate": 0.0002,
-      "loss": 1.1221,
+      "loss": 1.9928,
       "step": 44
     },
     {
-      "epoch": 0.74,
+      "epoch": 0.46,
       "learning_rate": 0.0002,
-      "loss": 1.2625,
+      "loss": 1.8427,
       "step": 46
     },
     {
-      "epoch": 0.77,
+      "epoch": 0.48,
       "learning_rate": 0.0002,
-      "loss": 1.0936,
+      "loss": 1.7931,
       "step": 48
     },
     {
-      "epoch": 0.8,
+      "epoch": 0.5,
       "learning_rate": 0.0002,
-      "loss": 1.048,
+      "loss": 1.7877,
       "step": 50
     },
     {
-      "epoch": 0.83,
+      "epoch": 0.52,
       "learning_rate": 0.0002,
-      "loss": 0.9645,
+      "loss": 1.848,
       "step": 52
     },
     {
-      "epoch": 0.86,
+      "epoch": 0.54,
       "learning_rate": 0.0002,
-      "loss": 1.0299,
+      "loss": 1.9819,
       "step": 54
     },
     {
-      "epoch": 0.9,
+      "epoch": 0.56,
       "learning_rate": 0.0002,
-      "loss": 1.0774,
+      "loss": 1.9553,
       "step": 56
     },
     {
-      "epoch": 0.93,
+      "epoch": 0.58,
       "learning_rate": 0.0002,
-      "loss": 1.1457,
+      "loss": 1.8433,
       "step": 58
     },
     {
-      "epoch": 0.96,
+      "epoch": 0.6,
       "learning_rate": 0.0002,
-      "loss": 1.1011,
+      "loss": 2.0258,
       "step": 60
     },
     {
-      "epoch": 0.99,
+      "epoch": 0.62,
       "learning_rate": 0.0002,
-      "loss": 1.0221,
+      "loss": 1.993,
       "step": 62
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002,
+      "loss": 1.9873,
+      "step": 64
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 1.9893,
+      "step": 66
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002,
+      "loss": 1.9959,
+      "step": 68
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002,
+      "loss": 1.6584,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0002,
+      "loss": 1.783,
+      "step": 72
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0002,
+      "loss": 1.8985,
+      "step": 74
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002,
+      "loss": 1.9153,
+      "step": 76
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0002,
+      "loss": 1.8917,
+      "step": 78
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 2.0094,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0002,
+      "loss": 1.8109,
+      "step": 82
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0002,
+      "loss": 1.9792,
+      "step": 84
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0002,
+      "loss": 1.9665,
+      "step": 86
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0002,
+      "loss": 1.8619,
+      "step": 88
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0002,
+      "loss": 1.9619,
+      "step": 90
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0002,
+      "loss": 1.9721,
+      "step": 92
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 1.7786,
+      "step": 94
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 1.8752,
+      "step": 96
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0002,
+      "loss": 1.9436,
+      "step": 98
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0002,
+      "loss": 1.7658,
+      "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": 2179055645245440.0,
+  "total_flos": 1.3487030941507584e+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 sha256:085df06261844d8e43666229030657ce5dd5cc1aac22d14d759f080cd507fb4e
+oid sha256:69b4f56b7a5ccf808ddbcc2509aa1d5cece9cfcc9008087d876e23c44c321a6e
 size 4728