Training in progress, step 2408, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "down_proj",
-    "v_proj",
-    "up_proj",
-    "o_proj",
     "q_proj",
-    "gate_proj"
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "o_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:d5e9f0e5cacd39add29676029c1b56d2faf079ccd31bde8511c1febd454f5a9f
+oid sha256:0d72b4e2e87323c107d49210059f17ed429c454a732752da6c5865e25a205ff0
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:376458bdc1ce44f1b5535f1f0d029f16825f2845553d0946a862dfe22caf77d0
+oid sha256:49ffb8ca622c9fd52fdb5cbea86d262d3918af11162d338978c48cb7a4c35ced
 size 75455810

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ba69556735679742033757906d03bee67367a53da70c19be3cbf4b9c125c815
+oid sha256:f0032afed3d1763dc3a76db5bc3dd838c54e15ccb9ba9d135fc44f226bea6c5d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f1f2f00d6cbbb8c1507d772e16322e2d45dfb1a89defdca62f9b6a650ede70
+oid sha256:fd695d7bacd57e69ba2766eb0aca6257cbed1471361dfa5ddb27276deb1bf1c3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9314881888452812,
+  "epoch": 0.933038085998102,
   "eval_steps": 500,
-  "global_step": 2404,
+  "global_step": 2408,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -16835,6 +16835,34 @@
       "learning_rate": 1.1911842790474637e-07,
       "loss": 1.3321,
       "step": 2404
+    },
+    {
+      "epoch": 0.9318756631334864,
+      "grad_norm": 0.19932667911052704,
+      "learning_rate": 1.1777397912764388e-07,
+      "loss": 1.3773,
+      "step": 2405
+    },
+    {
+      "epoch": 0.9322631374216916,
+      "grad_norm": 0.17850585281848907,
+      "learning_rate": 1.1643707021313455e-07,
+      "loss": 1.3967,
+      "step": 2406
+    },
+    {
+      "epoch": 0.9326506117098968,
+      "grad_norm": 0.18462300300598145,
+      "learning_rate": 1.151077032258724e-07,
+      "loss": 1.3623,
+      "step": 2407
+    },
+    {
+      "epoch": 0.933038085998102,
+      "grad_norm": 0.19249114394187927,
+      "learning_rate": 1.137858802188646e-07,
+      "loss": 1.3932,
+      "step": 2408
     }
   ],
   "logging_steps": 1.0,
@@ -16854,7 +16882,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.378188494151456e+18,
+  "total_flos": 2.382088049023491e+18,
   "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 sha256:16fb774fc7374c972ea93aaa72bc1893a3284121b69ae795a08735c78b3f7dc5
+oid sha256:76c56280507313f331f5ebcc5db348eedc6cc0a045fc5f4c2b79d99b9c533ba6
 size 5560