Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "v_proj",
+    "down_proj",
     "o_proj",
     "q_proj",
-    "k_proj",
-    "down_proj",
     "gate_proj",
-    "v_proj"
+    "up_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f87369f969a8727b29418baf6a1bb4e1ca43bb2c08102cdc4d024196806b875
+oid sha256:2f9deaefb906514604bb6873bca5a2a8c97c017312d4156325e0fd14270d4af1
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c73461fee0dda72220a2b4789b8b4c357e53616a241ad70bc6402ebfdb5ad4fe
+oid sha256:c5ad4b7618083a721ff31924e60ac3852e7e9960c460aafb49e5ebcdbaa98788
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01df7b97b445c21bfe49f63c99d75eb4e03716d822d7dff7f977e3b84a2ecc05
+oid sha256:29425389f96c76b576bcff3abe69f0a48e741ce688d6737071ae45a2ad2d7584
 size 14244

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.00010075820549636011,
-      "grad_norm": 6.578465480158216e+18,
+      "grad_norm": 8.359752932236722e+18,
       "learning_rate": 2e-05,
       "loss": 1.8654,
       "step": 1
@@ -18,30 +18,30 @@
     {
       "epoch": 0.00010075820549636011,
       "eval_loss": 1.7779617309570312,
-      "eval_runtime": 1454.0406,
-      "eval_samples_per_second": 2.874,
-      "eval_steps_per_second": 1.437,
+      "eval_runtime": 1454.9416,
+      "eval_samples_per_second": 2.872,
+      "eval_steps_per_second": 1.436,
       "step": 1
     },
     {
       "epoch": 0.00020151641099272022,
-      "grad_norm": 2.1462115130466632e+18,
+      "grad_norm": 2.626370165041791e+18,
       "learning_rate": 4e-05,
       "loss": 1.3359,
       "step": 2
     },
     {
       "epoch": 0.0003022746164890803,
-      "grad_norm": 2.517414610043142e+18,
+      "grad_norm": 3.249743505089626e+18,
       "learning_rate": 6e-05,
-      "loss": 1.3138,
+      "loss": 1.3042,
       "step": 3
     },
     {
       "epoch": 0.0003022746164890803,
-      "eval_loss": 1.7785661220550537,
-      "eval_runtime": 1454.8386,
-      "eval_samples_per_second": 2.872,
+      "eval_loss": 1.7708849906921387,
+      "eval_runtime": 1454.6249,
+      "eval_samples_per_second": 2.873,
       "eval_steps_per_second": 1.437,
       "step": 3
     }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b28660bfe89cc0538651f48cd70f7a481a8052384d78f5c68e3271d050811326
+oid sha256:58a3eb8d82e5fbac81f07720d857f56891a89c37b161f0eab5a75ef832506307
 size 6776