Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value",
-    "dense_4h_to_h",
     "dense",
-    "dense_h_to_4h"
+    "query_key_value",
+    "dense_h_to_4h",
+    "dense_4h_to_h"
   ],
   "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:dffc7c91f2e0f3c9b8cac9bde625c461f6abe144c439357f18c2ba216b302c14
+oid sha256:1483d19dcca2096e96a8bbc7dcd813774e26bf2316711d890249ef2317b67a0a
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf8945539674cf888aa52070f472421d589d3fef11606149f89b6d1aae04d10
+oid sha256:5e3716edcb4a7b14cac52509504cfd791a1695a6bf9cbddb103c8b3a48555974
 size 1656058

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 1.4832558950151478e-05,
-      "grad_norm": 1106.373779296875,
+      "grad_norm": 1032.5780029296875,
       "learning_rate": 2e-05,
       "loss": 95.6979,
       "step": 1
@@ -18,60 +18,60 @@
     {
       "epoch": 1.4832558950151478e-05,
       "eval_loss": 23.534069061279297,
-      "eval_runtime": 1949.8674,
-      "eval_samples_per_second": 14.558,
-      "eval_steps_per_second": 7.279,
+      "eval_runtime": 1979.9599,
+      "eval_samples_per_second": 14.337,
+      "eval_steps_per_second": 7.169,
       "step": 1
     },
     {
       "epoch": 2.9665117900302956e-05,
-      "grad_norm": 1290.805908203125,
+      "grad_norm": 1325.1285400390625,
       "learning_rate": 4e-05,
       "loss": 96.301,
       "step": 2
     },
     {
       "epoch": 4.449767685045443e-05,
-      "grad_norm": 1336.470458984375,
+      "grad_norm": 1420.2266845703125,
       "learning_rate": 6e-05,
-      "loss": 94.7096,
+      "loss": 95.2096,
       "step": 3
     },
     {
       "epoch": 4.449767685045443e-05,
-      "eval_loss": 23.524295806884766,
-      "eval_runtime": 1952.0732,
-      "eval_samples_per_second": 14.542,
-      "eval_steps_per_second": 7.271,
+      "eval_loss": 23.52667999267578,
+      "eval_runtime": 1953.433,
+      "eval_samples_per_second": 14.532,
+      "eval_steps_per_second": 7.266,
       "step": 3
     },
     {
       "epoch": 5.933023580060591e-05,
-      "grad_norm": 1352.6219482421875,
+      "grad_norm": 1357.5682373046875,
       "learning_rate": 8e-05,
-      "loss": 93.8438,
+      "loss": 93.3733,
       "step": 4
     },
     {
       "epoch": 7.416279475075739e-05,
-      "grad_norm": 1339.363037109375,
+      "grad_norm": 1045.089599609375,
       "learning_rate": 0.0001,
-      "loss": 95.0979,
+      "loss": 94.556,
       "step": 5
     },
     {
       "epoch": 8.899535370090886e-05,
-      "grad_norm": 1209.0018310546875,
+      "grad_norm": 1248.4478759765625,
       "learning_rate": 0.00012,
-      "loss": 94.5627,
+      "loss": 94.1798,
       "step": 6
     },
     {
       "epoch": 8.899535370090886e-05,
-      "eval_loss": 23.490365982055664,
-      "eval_runtime": 1965.3434,
-      "eval_samples_per_second": 14.444,
-      "eval_steps_per_second": 7.222,
+      "eval_loss": 23.505847930908203,
+      "eval_runtime": 2012.6089,
+      "eval_samples_per_second": 14.105,
+      "eval_steps_per_second": 7.053,
       "step": 6
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d86c51d2ca2d99a14e4584b069fa4439ceac2ad5a3d3e4ab990e6fdef6302e
+oid sha256:a5d1a4c4f62778001e2235adc1fcdfcba8e80da1a2496854cc7a72e5b2c2f1ca
 size 6776