Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -22,11 +22,11 @@
   "target_modules": [
     "q_proj",
     "o_proj",
-    "k_proj",
     "gate_proj",
-    "up_proj",
     "down_proj",
-    "v_proj"
+    "v_proj",
+    "k_proj",
+    "up_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 sha256:0b6a734d5e6d8c648ed67d3cc0634152c9c8eff1cb73426d7a666f7db630f9d8
+oid sha256:67562fe95fd2e0db3ed9fdf9801436bc65f6fa80941296d496efff177b9cf8e4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd780a39cf221cd161fa9e8fc29e820fc2bc64b05b7b2f8b7bdf6c4d1b444118
+oid sha256:181089d8be980e3b97f095712ad79db6957cebf09cca2a4616e2ac5b059e25ab
 size 168037178

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a60def06e8d16b47623b67a4aae8194c19582b3e85d8800ca2e3bc17092d1bb5
+size 14512

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbbfd43de7fb2acc21f9de1871048cc58018d000e5907250651f158a613d62d3
+size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,78 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002532981530343008,
+  "epoch": 0.002532714225411566,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.00042216358839050134,
+      "epoch": 0.0008442380751371887,
       "grad_norm": NaN,
       "learning_rate": 0.0,
-      "loss": 6.2311,
+      "loss": 6.2949,
       "step": 1
     },
     {
-      "epoch": 0.00042216358839050134,
-      "eval_loss": 7.166989326477051,
-      "eval_runtime": 34.0119,
-      "eval_samples_per_second": 14.671,
-      "eval_steps_per_second": 14.671,
+      "epoch": 0.0008442380751371887,
+      "eval_loss": 7.167040824890137,
+      "eval_runtime": 33.9503,
+      "eval_samples_per_second": 14.698,
+      "eval_steps_per_second": 7.364,
       "step": 1
     },
     {
-      "epoch": 0.0008443271767810027,
-      "grad_norm": 5.0110015869140625,
-      "learning_rate": 2e-05,
-      "loss": 6.3049,
+      "epoch": 0.0016884761502743773,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 7.5932,
       "step": 2
     },
     {
-      "epoch": 0.001266490765171504,
-      "grad_norm": NaN,
+      "epoch": 0.002532714225411566,
+      "grad_norm": 4.345782279968262,
       "learning_rate": 2e-05,
-      "loss": 7.0367,
+      "loss": 6.3083,
       "step": 3
     },
     {
-      "epoch": 0.001266490765171504,
-      "eval_loss": 7.166989326477051,
-      "eval_runtime": 33.8177,
-      "eval_samples_per_second": 14.756,
-      "eval_steps_per_second": 14.756,
+      "epoch": 0.002532714225411566,
+      "eval_loss": 7.167040824890137,
+      "eval_runtime": 33.7762,
+      "eval_samples_per_second": 14.774,
+      "eval_steps_per_second": 7.402,
       "step": 3
-    },
-    {
-      "epoch": 0.0016886543535620053,
-      "grad_norm": 7.560422897338867,
-      "learning_rate": 4e-05,
-      "loss": 7.5846,
-      "step": 4
-    },
-    {
-      "epoch": 0.0021108179419525065,
-      "grad_norm": 5.9173455238342285,
-      "learning_rate": 6e-05,
-      "loss": 6.8106,
-      "step": 5
-    },
-    {
-      "epoch": 0.002532981530343008,
-      "grad_norm": 5.743566036224365,
-      "learning_rate": 8e-05,
-      "loss": 5.7917,
-      "step": 6
-    },
-    {
-      "epoch": 0.002532981530343008,
-      "eval_loss": 6.941962718963623,
-      "eval_runtime": 34.2264,
-      "eval_samples_per_second": 14.579,
-      "eval_steps_per_second": 14.579,
-      "step": 6
     }
   ],
   "logging_steps": 1,

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8a0e1d575435a385945acb2379c55d79d6b7da826961709cf6ad2467a2bcd7a
+oid sha256:91b17704c84342df8c4881fcb5acc78d90d7b0fb6bb4b955a77926f3bd16d0fc
 size 6776