Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "down_proj",
     "k_proj",
     "v_proj",
     "q_proj",
-    "up_proj",
-    "gate_proj"
+    "gate_proj",
+    "down_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 sha256:6aee6bb013fc8ea429d729acf7270e8468011967bb2e9b5e6a1e18618de0f56a
+oid sha256:0fc1c6da5518569e9a500a08a91781175557d822cff833744ccc5c35c0c5dfb3
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bbb243eab50ad3f978d2bd6df3bbac3ca9ba945a743cfe83c832345de43231c
+oid sha256:4323947ba6180f1c9298f312c0ba3b542f703ff84fd68e767185d0ac11ed31c9
 size 111142

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.0003251239535072746,
-      "grad_norm": 0.021640103310346603,
+      "grad_norm": 0.024652473628520966,
       "learning_rate": 1e-05,
       "loss": 11.7645,
       "step": 1
@@ -18,88 +18,88 @@
     {
       "epoch": 0.0003251239535072746,
       "eval_loss": 11.76447582244873,
-      "eval_runtime": 249.3031,
-      "eval_samples_per_second": 41.56,
-      "eval_steps_per_second": 20.782,
+      "eval_runtime": 276.626,
+      "eval_samples_per_second": 37.455,
+      "eval_steps_per_second": 18.729,
       "step": 1
     },
     {
       "epoch": 0.0006502479070145493,
-      "grad_norm": 0.024706723168492317,
+      "grad_norm": 0.027672940865159035,
       "learning_rate": 2e-05,
       "loss": 11.7658,
       "step": 2
     },
     {
       "epoch": 0.000975371860521824,
-      "grad_norm": 0.022929754108190536,
+      "grad_norm": 0.025643622502684593,
       "learning_rate": 3e-05,
       "loss": 11.7649,
       "step": 3
     },
     {
       "epoch": 0.0013004958140290985,
-      "grad_norm": 0.022171195596456528,
+      "grad_norm": 0.025678519159555435,
       "learning_rate": 4e-05,
       "loss": 11.7648,
       "step": 4
     },
     {
       "epoch": 0.0016256197675363732,
-      "grad_norm": 0.02208411693572998,
+      "grad_norm": 0.02572811394929886,
       "learning_rate": 5e-05,
       "loss": 11.7649,
       "step": 5
     },
     {
       "epoch": 0.0016256197675363732,
-      "eval_loss": 11.764402389526367,
-      "eval_runtime": 249.1579,
-      "eval_samples_per_second": 41.584,
-      "eval_steps_per_second": 20.794,
+      "eval_loss": 11.764395713806152,
+      "eval_runtime": 276.5749,
+      "eval_samples_per_second": 37.462,
+      "eval_steps_per_second": 18.733,
       "step": 5
     },
     {
       "epoch": 0.001950743721043648,
-      "grad_norm": 0.02443164400756359,
+      "grad_norm": 0.026358768343925476,
       "learning_rate": 6e-05,
       "loss": 11.7634,
       "step": 6
     },
     {
       "epoch": 0.0022758676745509225,
-      "grad_norm": 0.023470092564821243,
+      "grad_norm": 0.026500564068555832,
       "learning_rate": 7e-05,
       "loss": 11.7654,
       "step": 7
     },
     {
       "epoch": 0.002600991628058197,
-      "grad_norm": 0.023716744035482407,
+      "grad_norm": 0.02642131596803665,
       "learning_rate": 8e-05,
       "loss": 11.7644,
       "step": 8
     },
     {
       "epoch": 0.002926115581565472,
-      "grad_norm": 0.022970277816057205,
+      "grad_norm": 0.02585265040397644,
       "learning_rate": 9e-05,
       "loss": 11.7658,
       "step": 9
     },
     {
       "epoch": 0.0032512395350727465,
-      "grad_norm": 0.022244542837142944,
+      "grad_norm": 0.024854907765984535,
       "learning_rate": 0.0001,
       "loss": 11.7641,
       "step": 10
     },
     {
       "epoch": 0.0032512395350727465,
-      "eval_loss": 11.764139175415039,
-      "eval_runtime": 248.9949,
-      "eval_samples_per_second": 41.611,
-      "eval_steps_per_second": 20.808,
+      "eval_loss": 11.76411247253418,
+      "eval_runtime": 276.5048,
+      "eval_samples_per_second": 37.471,
+      "eval_steps_per_second": 18.737,
       "step": 10
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a413dd30c82bf1458b4c9aa8cd9fc6df506b56de5b15f10d2e2a254ff755ea0
+oid sha256:e17a6c83dec956fb9efedd2c17093957afde82b766a4186ec8d108b6cbea110d
 size 6776