Training in progress, step 120, checkpoint

last-checkpoint/adapter_config.json

@@ -28,18 +28,18 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "down_proj",
     "gate_proj",
-    "k_proj",
-    "o_proj",
     "q_proj",
     "v_proj",
-    "down_proj"
+    "up_proj",
+    "o_proj",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": null,
   "trainable_token_indices": null,
   "use_dora": false,
   "use_qalora": false,
-  "use_rslora": true
+  "use_rslora": false
 }

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42ef19ac7448b71ef2c7f0ad912c2ee3e37fb7f8f2595fa93636a91b62132912
+oid sha256:517e89777cd0acc23adc7844c9140c49862b632bbe55e0d37e4bbc779c613a97
 size 3380768360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceba1a0a25a3089f0fbe4ad7b2ef2a6b51ebe56c5f49c6415186e4df7e28e94b
-size 1757899449
+oid sha256:bf20b7786740e08a40ec488c2846b5a881d156067618ab1e19e46158812a7a62
+size 1855337587

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c800b778fa7e115e4c34de8529902de8b61c9a1b4bab3eb8295d06dafff030e
+oid sha256:181c5f0270cf39930062ddfa3767a2481d0c360f120b11f8e25dbf533a1cdaba
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117f5f7ecb8bf188570856b720dd33d2d7c01cd9b95297de35cf83f3e9fc739e
+oid sha256:cb481d43b196067ad8292b807ce1f5b4d4770f3d66564b6ee5dd045f67b57cbc
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2328767123287672,
+  "epoch": 0.28753993610223644,
   "eval_steps": 500,
-  "global_step": 90,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -141,10 +141,52 @@
       "learning_rate": 2.0223024531515985e-05,
       "loss": 0.1956,
       "step": 90
+    },
+    {
+      "epoch": 0.04792332268370607,
+      "grad_norm": 0.2704693078994751,
+      "learning_rate": 2.4727026880991426e-05,
+      "loss": 0.3087,
+      "step": 95
+    },
+    {
+      "epoch": 0.09584664536741214,
+      "grad_norm": 0.15272189676761627,
+      "learning_rate": 2.4126313231549726e-05,
+      "loss": 0.2705,
+      "step": 100
+    },
+    {
+      "epoch": 0.14376996805111822,
+      "grad_norm": 0.08888361603021622,
+      "learning_rate": 2.3501398240052193e-05,
+      "loss": 0.266,
+      "step": 105
+    },
+    {
+      "epoch": 0.19169329073482427,
+      "grad_norm": 0.06617572158575058,
+      "learning_rate": 2.2853939068715516e-05,
+      "loss": 0.2504,
+      "step": 110
+    },
+    {
+      "epoch": 0.23961661341853036,
+      "grad_norm": 0.07254050672054291,
+      "learning_rate": 2.2185652662868573e-05,
+      "loss": 0.2381,
+      "step": 115
+    },
+    {
+      "epoch": 0.28753993610223644,
+      "grad_norm": 0.06296419352293015,
+      "learning_rate": 2.1498311197922046e-05,
+      "loss": 0.252,
+      "step": 120
     }
   ],
   "logging_steps": 5,
-  "max_steps": 219,
+  "max_steps": 315,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 30,
@@ -160,7 +202,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6231690613367767e+18,
+  "total_flos": 1.8551401685858673e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8855ef24f42f0e1ba1145f6cd4d570d92cdd85350340e9302a34e4eb24aa4b7e
+oid sha256:c47959f4c81dcb5cc476e8d02fd692e443b4d45c58fa790a42d9629281c83403
 size 6353