Training in progress, step 12, checkpoint

checkpoint-12/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
+    "down_proj",
     "v_proj",
-    "gate_proj",
+    "o_proj",
+    "q_proj",
     "up_proj",
-    "down_proj",
-    "q_proj"
+    "gate_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

checkpoint-12/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e84ec00171ae221c0d3a4d37efa910c8675b6af80c879c17e8c0ff7a8af903cb
+oid sha256:7ec81cd5bfe5e6d62465954b1cb2eec7dbff2facfd005c949df2a1292edc4230
 size 137714904

checkpoint-12/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:317e856d2cc4aca3bd24f66741edd5e25c64b47f7f5d456abe1edc1f1ac822ca
+oid sha256:233d85aa4eff5e16bf450abd9b55bd9b3bc86b1a26dd11a489b534ee3d850910
 size 275817586

checkpoint-12/trainer_state.json

@@ -10,118 +10,118 @@
   "log_history": [
     {
       "epoch": 0.0006200589055960316,
-      "grad_norm": 0.599152684211731,
+      "grad_norm": 0.6006524562835693,
       "learning_rate": 4.000000000000001e-06,
-      "loss": 1.4569,
+      "loss": 1.4363,
       "step": 1
     },
     {
       "epoch": 0.0012401178111920632,
-      "grad_norm": 0.41296300292015076,
+      "grad_norm": 0.4452102482318878,
       "learning_rate": 8.000000000000001e-06,
-      "loss": 1.1609,
+      "loss": 1.1641,
       "step": 2
     },
     {
       "epoch": 0.0018601767167880949,
-      "grad_norm": 0.3926275372505188,
+      "grad_norm": 0.418393075466156,
       "learning_rate": 1.2e-05,
-      "loss": 0.9938,
+      "loss": 1.0005,
       "step": 3
     },
     {
       "epoch": 0.0018601767167880949,
-      "eval_loss": 1.2600003480911255,
-      "eval_runtime": 49.3684,
-      "eval_samples_per_second": 2.026,
-      "eval_steps_per_second": 2.026,
+      "eval_loss": 1.2559138536453247,
+      "eval_runtime": 50.2632,
+      "eval_samples_per_second": 1.99,
+      "eval_steps_per_second": 1.99,
       "step": 3
     },
     {
       "epoch": 0.0024802356223841263,
-      "grad_norm": 0.4559924006462097,
+      "grad_norm": 0.4599858820438385,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 1.1897,
+      "loss": 1.1938,
       "step": 4
     },
     {
       "epoch": 0.0031002945279801583,
-      "grad_norm": 0.40210390090942383,
+      "grad_norm": 0.4313387870788574,
       "learning_rate": 2e-05,
-      "loss": 0.9835,
+      "loss": 0.9897,
       "step": 5
     },
     {
       "epoch": 0.0037203534335761897,
-      "grad_norm": 0.45071661472320557,
+      "grad_norm": 0.4715091586112976,
       "learning_rate": 1.9200000000000003e-05,
-      "loss": 1.112,
+      "loss": 1.1105,
       "step": 6
     },
     {
       "epoch": 0.0037203534335761897,
-      "eval_loss": 1.2538120746612549,
-      "eval_runtime": 49.623,
-      "eval_samples_per_second": 2.015,
-      "eval_steps_per_second": 2.015,
+      "eval_loss": 1.2492942810058594,
+      "eval_runtime": 49.6589,
+      "eval_samples_per_second": 2.014,
+      "eval_steps_per_second": 2.014,
       "step": 6
     },
     {
       "epoch": 0.004340412339172222,
-      "grad_norm": 0.44490283727645874,
+      "grad_norm": 0.4590495824813843,
       "learning_rate": 1.8400000000000003e-05,
-      "loss": 1.0809,
+      "loss": 1.0824,
       "step": 7
     },
     {
       "epoch": 0.004960471244768253,
-      "grad_norm": 0.6036495566368103,
+      "grad_norm": 0.6232957243919373,
       "learning_rate": 1.76e-05,
-      "loss": 1.2205,
+      "loss": 1.2176,
       "step": 8
     },
     {
       "epoch": 0.005580530150364285,
-      "grad_norm": 0.4536096751689911,
+      "grad_norm": 0.4820755422115326,
       "learning_rate": 1.6800000000000002e-05,
-      "loss": 1.0715,
+      "loss": 1.0774,
       "step": 9
     },
     {
       "epoch": 0.005580530150364285,
-      "eval_loss": 1.2402353286743164,
-      "eval_runtime": 49.777,
-      "eval_samples_per_second": 2.009,
-      "eval_steps_per_second": 2.009,
+      "eval_loss": 1.2356064319610596,
+      "eval_runtime": 49.9029,
+      "eval_samples_per_second": 2.004,
+      "eval_steps_per_second": 2.004,
       "step": 9
     },
     {
       "epoch": 0.0062005890559603165,
-      "grad_norm": 0.5870596170425415,
+      "grad_norm": 0.614038348197937,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 1.3001,
+      "loss": 1.2989,
       "step": 10
     },
     {
       "epoch": 0.0068206479615563476,
-      "grad_norm": 0.5543638467788696,
+      "grad_norm": 0.5838705897331238,
       "learning_rate": 1.5200000000000002e-05,
-      "loss": 1.0459,
+      "loss": 1.05,
       "step": 11
     },
     {
       "epoch": 0.0074407068671523795,
-      "grad_norm": 0.6657857894897461,
+      "grad_norm": 0.6922520995140076,
       "learning_rate": 1.4400000000000001e-05,
-      "loss": 1.4109,
+      "loss": 1.3979,
       "step": 12
     },
     {
       "epoch": 0.0074407068671523795,
-      "eval_loss": 1.2233326435089111,
-      "eval_runtime": 49.0096,
-      "eval_samples_per_second": 2.04,
-      "eval_steps_per_second": 2.04,
+      "eval_loss": 1.2183419466018677,
+      "eval_runtime": 50.5422,
+      "eval_samples_per_second": 1.979,
+      "eval_steps_per_second": 1.979,
       "step": 12
     }
   ],
@@ -142,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.498972851610419e+16,
+  "total_flos": 2.535580378532659e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-12/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf98514c81a51106969007e868d7ab8fb036a6bedc2987ddadf4a06b2a43f04f
+oid sha256:522b553cd97c4d175d86850f43dd8230595c851fb1c776adff1402d853af53e9
 size 5752