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:c81ba4577f2b90ebf944c08cd92158beaf7c433a56828aeb2d2670b1ac57f2d2
+oid sha256:e2efbc339582e5e7f609dd0db5aa19798900afe8df90e002a1e00dabb9fb3f77
 size 83945296

checkpoint-12/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc3066cc1d1029a905ce53416b23d2545c51cd844adc7f6327bfd833b2a1ae83
+oid sha256:037a71fde6d575f5374cea59eddced44e3a7c8271bdeaa43eaa2583f7c987f53
 size 168149074

checkpoint-12/trainer_state.json

@@ -10,118 +10,118 @@
   "log_history": [
     {
       "epoch": 0.0006200589055960316,
-      "grad_norm": 0.7731499075889587,
+      "grad_norm": 0.7607094645500183,
       "learning_rate": 4.000000000000001e-06,
-      "loss": 1.166,
+      "loss": 1.1893,
       "step": 1
     },
     {
       "epoch": 0.0012401178111920632,
-      "grad_norm": 0.346652090549469,
+      "grad_norm": 0.3518824279308319,
       "learning_rate": 8.000000000000001e-06,
-      "loss": 0.9594,
+      "loss": 0.9752,
       "step": 2
     },
     {
       "epoch": 0.0018601767167880949,
-      "grad_norm": 0.39937612414360046,
+      "grad_norm": 0.4024870693683624,
       "learning_rate": 1.2e-05,
-      "loss": 0.828,
+      "loss": 0.8467,
       "step": 3
     },
     {
       "epoch": 0.0018601767167880949,
-      "eval_loss": 1.0491173267364502,
-      "eval_runtime": 26.0459,
-      "eval_samples_per_second": 3.839,
-      "eval_steps_per_second": 3.839,
+      "eval_loss": 1.0757174491882324,
+      "eval_runtime": 26.414,
+      "eval_samples_per_second": 3.786,
+      "eval_steps_per_second": 3.786,
       "step": 3
     },
     {
       "epoch": 0.0024802356223841263,
-      "grad_norm": 0.3457990288734436,
+      "grad_norm": 0.36653462052345276,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 0.988,
+      "loss": 1.0056,
       "step": 4
     },
     {
       "epoch": 0.0031002945279801583,
-      "grad_norm": 0.513918399810791,
+      "grad_norm": 0.47098514437675476,
       "learning_rate": 2e-05,
-      "loss": 0.8319,
+      "loss": 0.8545,
       "step": 5
     },
     {
       "epoch": 0.0037203534335761897,
-      "grad_norm": 0.47683727741241455,
+      "grad_norm": 0.5030912160873413,
       "learning_rate": 1.9200000000000003e-05,
-      "loss": 0.9366,
+      "loss": 0.9553,
       "step": 6
     },
     {
       "epoch": 0.0037203534335761897,
-      "eval_loss": 1.0431987047195435,
-      "eval_runtime": 26.2352,
-      "eval_samples_per_second": 3.812,
-      "eval_steps_per_second": 3.812,
+      "eval_loss": 1.0662517547607422,
+      "eval_runtime": 26.7124,
+      "eval_samples_per_second": 3.744,
+      "eval_steps_per_second": 3.744,
       "step": 6
     },
     {
       "epoch": 0.004340412339172222,
-      "grad_norm": 0.4349649250507355,
+      "grad_norm": 0.4823940694332123,
       "learning_rate": 1.8400000000000003e-05,
-      "loss": 0.9076,
+      "loss": 0.9266,
       "step": 7
     },
     {
       "epoch": 0.004960471244768253,
-      "grad_norm": 0.5443339943885803,
+      "grad_norm": 0.5647093653678894,
       "learning_rate": 1.76e-05,
-      "loss": 0.9829,
+      "loss": 1.0013,
       "step": 8
     },
     {
       "epoch": 0.005580530150364285,
-      "grad_norm": 0.3990451395511627,
+      "grad_norm": 0.4058099687099457,
       "learning_rate": 1.6800000000000002e-05,
-      "loss": 0.9045,
+      "loss": 0.9206,
       "step": 9
     },
     {
       "epoch": 0.005580530150364285,
-      "eval_loss": 1.0292819738388062,
-      "eval_runtime": 26.3477,
-      "eval_samples_per_second": 3.795,
-      "eval_steps_per_second": 3.795,
+      "eval_loss": 1.0476710796356201,
+      "eval_runtime": 26.7708,
+      "eval_samples_per_second": 3.735,
+      "eval_steps_per_second": 3.735,
       "step": 9
     },
     {
       "epoch": 0.0062005890559603165,
-      "grad_norm": 0.44750896096229553,
+      "grad_norm": 0.44608208537101746,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 1.0768,
+      "loss": 1.0937,
       "step": 10
     },
     {
       "epoch": 0.0068206479615563476,
-      "grad_norm": 0.6865904331207275,
+      "grad_norm": 0.7088199853897095,
       "learning_rate": 1.5200000000000002e-05,
-      "loss": 0.8717,
+      "loss": 0.8915,
       "step": 11
     },
     {
       "epoch": 0.0074407068671523795,
-      "grad_norm": 0.548491895198822,
+      "grad_norm": 0.5858705639839172,
       "learning_rate": 1.4400000000000001e-05,
-      "loss": 1.1758,
+      "loss": 1.186,
       "step": 12
     },
     {
       "epoch": 0.0074407068671523795,
-      "eval_loss": 1.0153621435165405,
-      "eval_runtime": 26.5025,
-      "eval_samples_per_second": 3.773,
-      "eval_steps_per_second": 3.773,
+      "eval_loss": 1.0301631689071655,
+      "eval_runtime": 27.1639,
+      "eval_samples_per_second": 3.681,
+      "eval_steps_per_second": 3.681,
       "step": 12
     }
   ],
@@ -142,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3299793854087168e+16,
+  "total_flos": 1.3496219744698368e+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:cbe2fb31cf4c04f893e5299faa77267af76b8447f922d82c2d6c0200e1fe225f
+oid sha256:527a35da8257b0136b41661334383dc9a90d4f2271ec7e0b37f6fe024a71f4c9
 size 5688