Training in progress, step 500, checkpoint

last-checkpoint/adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_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:cfd0c3537161f726074b3562cba8b72be14baab258e8757819417a16771eb12b
+oid sha256:78c904af18c31f4a69d6180c9472e0f9049631c4b11a30e09a8dd1f1e0caa1cc
 size 3208536

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aff9fefa614693c96ea85ec4a5f10f7815bedc3aaaf828e17e3feaff0f543974
+oid sha256:75111731874c29a7e862615e89e51e6bdbaa9146731dfdcd1bc43cc76b7df2d8
 size 6477306

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99b6bf2633576a5bcc6ae4d6496d485a98cae17c5f851c237cfbdbab048f4d2e
+oid sha256:fd62d48ed83452b5265e86dff33cf1003a0754fe0aa1b42fc21148154d53550e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a47e8e0c728a6419cdac42f9eb7d9aab7d985a7569fc2a2246cdbf3299396f
+oid sha256:3332507fadf5d43ff4ed4bcaa949f82413d6423fde214dab857321ff53f41972
 size 1064

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
-size 17525357
+oid sha256:88ca2827d357547743e78820b54238345b21f6ee516f44ed822ca74a28af9a09
+size 17525455

last-checkpoint/trainer_state.json

@@ -1,30 +1,23 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 2.1551724137931036,
   "eval_steps": 500,
-  "global_step": 1083,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.3850415512465375,
-      "grad_norm": 2.723154067993164,
-      "learning_rate": 2.6915974145891044e-05,
-      "loss": 0.7381,
+      "epoch": 2.1551724137931036,
+      "grad_norm": 17.473838806152344,
+      "learning_rate": 1.4080459770114942e-05,
+      "loss": 0.5917,
       "step": 500
-    },
-    {
-      "epoch": 2.770083102493075,
-      "grad_norm": 26.0142822265625,
-      "learning_rate": 3.831948291782087e-06,
-      "loss": 0.5497,
-      "step": 1000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1083,
+  "max_steps": 696,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
@@ -35,12 +28,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1020832481829888.0,
+  "total_flos": 459596996587008.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:137f34abacf3c97b6ea24393f8753eac25cc9695068d5a8f1e3ad9ea5584ea97
+oid sha256:ef2ee579c2a03fdaa11cdf4d7c2576d4670d8ac82f21b4b99facc08b8a85100e
 size 5432