Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "o_proj",
-    "gate_proj",
     "v_proj",
-    "k_proj",
+    "up_proj",
     "down_proj",
-    "q_proj"
+    "gate_proj",
+    "o_proj",
+    "q_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 sha256:8d6774c2f3e9f6f2132a4c7df8c004a7c78dbb0cc88a1bb84fa017267ba66638
+oid sha256:56736da540e8c0936ddcb0782690cac58466eab2b768309f1b847eb9f83d0d9b
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ae659f6062603ef01f9041f43bb6b82ee9690bac22d36fee8736c0e506096c6
+oid sha256:57f11a33ee7c3186996e7c295c3b8ee106f2c84067908c6aff9b293efd027a95
 size 202110330

last-checkpoint/trainer_state.json

@@ -18,9 +18,9 @@
     {
       "epoch": 0.0028268551236749115,
       "eval_loss": 7.129258632659912,
-      "eval_runtime": 13.6697,
-      "eval_samples_per_second": 43.6,
-      "eval_steps_per_second": 5.487,
+      "eval_runtime": 20.9973,
+      "eval_samples_per_second": 28.385,
+      "eval_steps_per_second": 3.572,
       "step": 1
     },
     {
@@ -32,14 +32,14 @@
     },
     {
       "epoch": 0.008480565371024734,
-      "grad_norm": 5.114774703979492,
+      "grad_norm": 5.082520484924316,
       "learning_rate": 2e-05,
       "loss": 7.4669,
       "step": 3
     },
     {
       "epoch": 0.011307420494699646,
-      "grad_norm": 4.991275310516357,
+      "grad_norm": 4.920047760009766,
       "learning_rate": 4e-05,
       "loss": 7.1521,
       "step": 4
@@ -48,58 +48,58 @@
       "epoch": 0.014134275618374558,
       "grad_norm": NaN,
       "learning_rate": 4e-05,
-      "loss": 7.7429,
+      "loss": 7.7426,
       "step": 5
     },
     {
       "epoch": 0.014134275618374558,
-      "eval_loss": 7.097643852233887,
-      "eval_runtime": 20.7137,
-      "eval_samples_per_second": 28.773,
-      "eval_steps_per_second": 3.621,
+      "eval_loss": 7.097348213195801,
+      "eval_runtime": 20.8903,
+      "eval_samples_per_second": 28.53,
+      "eval_steps_per_second": 3.59,
       "step": 5
     },
     {
       "epoch": 0.01696113074204947,
-      "grad_norm": 4.559197902679443,
+      "grad_norm": 4.500086784362793,
       "learning_rate": 6e-05,
-      "loss": 7.1861,
+      "loss": 7.1859,
       "step": 6
     },
     {
       "epoch": 0.019787985865724382,
-      "grad_norm": 3.6284019947052,
+      "grad_norm": 3.6024482250213623,
       "learning_rate": 8e-05,
-      "loss": 6.9673,
+      "loss": 6.9672,
       "step": 7
     },
     {
       "epoch": 0.022614840989399292,
-      "grad_norm": 4.3491082191467285,
+      "grad_norm": 4.331362724304199,
       "learning_rate": 0.0001,
-      "loss": 7.2919,
+      "loss": 7.2915,
       "step": 8
     },
     {
       "epoch": 0.025441696113074206,
-      "grad_norm": 3.08682918548584,
+      "grad_norm": 3.071237564086914,
       "learning_rate": 0.00012,
-      "loss": 7.258,
+      "loss": 7.2579,
       "step": 9
     },
     {
       "epoch": 0.028268551236749116,
-      "grad_norm": 3.268092393875122,
+      "grad_norm": 3.218928813934326,
       "learning_rate": 0.00014,
-      "loss": 7.0434,
+      "loss": 7.0417,
       "step": 10
     },
     {
       "epoch": 0.028268551236749116,
-      "eval_loss": 6.333721160888672,
-      "eval_runtime": 20.9199,
-      "eval_samples_per_second": 28.49,
-      "eval_steps_per_second": 3.585,
+      "eval_loss": 6.332116603851318,
+      "eval_runtime": 20.7973,
+      "eval_samples_per_second": 28.658,
+      "eval_steps_per_second": 3.606,
       "step": 10
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:676c5b957839737d77485c6332fc96de69385066f3eef0d74b47f677462f11dc
+oid sha256:0b55d7424e01d2da7c827809f0e75e814ca3307809331f5d1880db7934ea6a65
 size 6712