Training in progress, step 6, checkpoint

checkpoint-6/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-6/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c9cf394e61a28f95d79f35ea65b925b599236f12dbb1e8683bcb24716d4632d
+oid sha256:f993cdbafc496c3db9a53efee330eec953c2ab32271b03619e739a639f34504d
 size 137714904

checkpoint-6/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:552c28b5d08459204936b88d2014c0577441164bbcb48d2f93c8ea566d49e500
+oid sha256:c6f7fd96efbc4e6d32584bc5618e7427198b872936bd6006c48f604630221be9
 size 275817586

checkpoint-6/trainer_state.json

@@ -10,60 +10,60 @@
   "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
     }
   ],
@@ -84,7 +84,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3962531544313856e+16,
+  "total_flos": 1.4145485023690752e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-6/training_args.bin

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