Training in progress, step 116, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
-    "o_proj",
     "down_proj",
+    "q_proj",
+    "gate_proj",
     "up_proj",
-    "v_proj",
-    "k_proj"
+    "k_proj",
+    "o_proj",
+    "v_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 sha256:3a382456c446f34b195fbfd702a439be3a1e58d2a36d956d357f01865a9f79d8
+oid sha256:6afb5fe8354a6bf44657911c90884a5f22d13610a6fdc04cedfb7adbdf5a6136
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f98750a3e57cc2fc9efbb170ea0c2d4e6e07105ecd32dc2e6b33fd619403c2a
-size 74440308
+oid sha256:5d7691b06ed9b50fbc0611aee62af3da692001feabdc448d28cef6fec0dd397f
+size 75455362

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de022fc7aa1925c72ae7474cead510ec1b0250a1879a157882455c4937721e6f
+oid sha256:4b2d3bdbefea3cedf8425e160a4a6e6072c7d80ec0aea4a71c41506faa0303a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db8ff398e296fc80d27c81c792fc561b8565bd13d3296779cf24d36d13c2df0f
+oid sha256:024d9e78a1ac8400cbdd370a836aa056131227ba28580cf644bcc2ef5b956783
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04339712027898149,
+  "epoch": 0.04494701743180225,
   "eval_steps": 500,
-  "global_step": 112,
+  "global_step": 116,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -791,6 +791,34 @@
       "learning_rate": 9.986107292389465e-06,
       "loss": 1.7713,
       "step": 112
+    },
+    {
+      "epoch": 0.04378459456718668,
+      "grad_norm": 0.10954278707504272,
+      "learning_rate": 9.985640566680987e-06,
+      "loss": 1.7273,
+      "step": 113
+    },
+    {
+      "epoch": 0.04417206885539187,
+      "grad_norm": 0.13270458579063416,
+      "learning_rate": 9.98516614140173e-06,
+      "loss": 1.7355,
+      "step": 114
+    },
+    {
+      "epoch": 0.044559543143597065,
+      "grad_norm": 0.12262709438800812,
+      "learning_rate": 9.984684017284372e-06,
+      "loss": 1.6893,
+      "step": 115
+    },
+    {
+      "epoch": 0.04494701743180225,
+      "grad_norm": 0.11373162269592285,
+      "learning_rate": 9.98419419507348e-06,
+      "loss": 1.7803,
+      "step": 116
     }
   ],
   "logging_steps": 1.0,
@@ -810,7 +838,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1051198111020954e+17,
+  "total_flos": 1.1443990140785664e+17,
   "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 sha256:0fdbe8ab53e2bdf789bc2d047a904abd00bae7cba146ca495869a765cce314de
-size 5496
+oid sha256:4076fd30d59e6db9c1314dd4fbfa0803720cb806be59b54c3307e3dfdb52b74a
+size 5560