Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
+    "gate_proj",
     "o_proj",
+    "up_proj",
     "v_proj",
-    "down_proj",
     "k_proj",
-    "gate_proj"
+    "q_proj",
+    "down_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 sha256:7df5ced5b60e62c81f9e4fb78a9d5e1379c6bdd142e626a309607d5a68cc3843
+oid sha256:e771b270da7293af440a639bb209ca6898df7fae0d30097d348edd3e55716225
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c96eafb6178cfa585238cab4a5d5f73fb2113b862f92a52a4114fa97e540b262
+oid sha256:cf06354dd34eefa63e4f38c5aa24effe149f7cbcab4e42fa79d3bb7751850b1a
 size 45221242

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 8.23011398707872e-05,
-      "grad_norm": 0.7503308057785034,
+      "grad_norm": 0.6557537913322449,
       "learning_rate": 2e-05,
       "loss": 1.5917,
       "step": 1
@@ -18,96 +18,96 @@
     {
       "epoch": 8.23011398707872e-05,
       "eval_loss": 1.959477186203003,
-      "eval_runtime": 133.9988,
-      "eval_samples_per_second": 19.09,
-      "eval_steps_per_second": 19.09,
+      "eval_runtime": 135.3765,
+      "eval_samples_per_second": 18.895,
+      "eval_steps_per_second": 18.895,
       "step": 1
     },
     {
       "epoch": 0.0001646022797415744,
-      "grad_norm": 0.8759475350379944,
+      "grad_norm": 0.7621749639511108,
       "learning_rate": 4e-05,
       "loss": 1.8288,
       "step": 2
     },
     {
       "epoch": 0.00024690341961236165,
-      "grad_norm": 0.6373544931411743,
+      "grad_norm": 0.5589603781700134,
       "learning_rate": 6e-05,
-      "loss": 1.0265,
+      "loss": 1.0263,
       "step": 3
     },
     {
       "epoch": 0.00024690341961236165,
-      "eval_loss": 1.9565452337265015,
-      "eval_runtime": 160.8486,
-      "eval_samples_per_second": 15.903,
-      "eval_steps_per_second": 15.903,
+      "eval_loss": 1.957216739654541,
+      "eval_runtime": 161.0963,
+      "eval_samples_per_second": 15.879,
+      "eval_steps_per_second": 15.879,
       "step": 3
     },
     {
       "epoch": 0.0003292045594831488,
-      "grad_norm": 0.9935461282730103,
+      "grad_norm": 0.858914315700531,
       "learning_rate": 8e-05,
-      "loss": 1.6082,
+      "loss": 1.6087,
       "step": 4
     },
     {
       "epoch": 0.00041150569935393603,
-      "grad_norm": 0.8985377550125122,
+      "grad_norm": 0.7685796618461609,
       "learning_rate": 0.0001,
-      "loss": 1.332,
+      "loss": 1.3328,
       "step": 5
     },
     {
       "epoch": 0.0004938068392247233,
-      "grad_norm": 0.804458498954773,
+      "grad_norm": 0.6958107948303223,
       "learning_rate": 0.00012,
-      "loss": 1.2777,
+      "loss": 1.2796,
       "step": 6
     },
     {
       "epoch": 0.0004938068392247233,
-      "eval_loss": 1.9385048151016235,
-      "eval_runtime": 172.7761,
-      "eval_samples_per_second": 14.805,
-      "eval_steps_per_second": 14.805,
+      "eval_loss": 1.9416530132293701,
+      "eval_runtime": 172.4872,
+      "eval_samples_per_second": 14.83,
+      "eval_steps_per_second": 14.83,
       "step": 6
     },
     {
       "epoch": 0.0005761079790955105,
-      "grad_norm": 0.7060862183570862,
+      "grad_norm": 0.6250211000442505,
       "learning_rate": 0.00014,
-      "loss": 1.3273,
+      "loss": 1.3284,
       "step": 7
     },
     {
       "epoch": 0.0006584091189662976,
-      "grad_norm": 0.9895685911178589,
+      "grad_norm": 0.9062594175338745,
       "learning_rate": 0.00016,
-      "loss": 1.6312,
+      "loss": 1.6334,
       "step": 8
     },
     {
       "epoch": 0.0007407102588370849,
-      "grad_norm": 0.8735620975494385,
+      "grad_norm": 0.7678062319755554,
       "learning_rate": 0.00018,
-      "loss": 1.4144,
+      "loss": 1.4155,
       "step": 9
     },
     {
       "epoch": 0.0007407102588370849,
-      "eval_loss": 1.9004994630813599,
-      "eval_runtime": 171.1439,
-      "eval_samples_per_second": 14.946,
-      "eval_steps_per_second": 14.946,
+      "eval_loss": 1.9064750671386719,
+      "eval_runtime": 170.6778,
+      "eval_samples_per_second": 14.987,
+      "eval_steps_per_second": 14.987,
       "step": 9
     },
     {
       "epoch": 0.0008230113987078721,
-      "grad_norm": 1.6891236305236816,
+      "grad_norm": 1.5290422439575195,
       "learning_rate": 0.0002,
-      "loss": 1.675,
+      "loss": 1.6838,
       "step": 10
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:478a261d562ef7004d0f64e3e27b2ba59d503990d5008804b57fbc37d15611f7
+oid sha256:923ce18a73524fc48b19c36dee905217bafd6d65025d46d8a80d999e0fe09dba
 size 6776