Training in progress, step 2204, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "q_proj",
+    "down_proj",
+    "v_proj",
     "up_proj",
     "o_proj",
-    "down_proj",
-    "gate_proj",
-    "v_proj"
+    "q_proj",
+    "gate_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:d4ebfd33b7abf52b0221e9e6438f57ad9ade398d642264074d5d78d52f2f5585
+oid sha256:4cd256ed2cf42f5e6bc1d967561fc9127cf3d00a74d8f5a7e02bc912e9049cbd
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9619aab8a0a055b531f39ab557331b389a9fa2d2149d494c38f79b5da0e3fcf4
+oid sha256:04f754a5c68f69f9b9c234616ef4b49186fe7b13f01c59b58c7a934af44d58eb
 size 75455810

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ac4b4577a5f40e218c95809a4ca1e01ef0e14557bfe8b9b2264ff12642a30a5
+oid sha256:a5bf72d5bfc771492b725bac038dec0ee052dc91b53de82cb1ff14643a5998ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aceee179503688e049bca3e607cee6f931f429ae5aad6975d08daff2bbd396c8
+oid sha256:a6206caf8c53a2313ff866514fbfe50f942337f5cabab9c55ae18e70725c9d9e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8524434340514221,
+  "epoch": 0.8539933312042428,
   "eval_steps": 500,
-  "global_step": 2200,
+  "global_step": 2204,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -15407,6 +15407,34 @@
       "learning_rate": 5.472263101036212e-07,
       "loss": 1.4325,
       "step": 2200
+    },
+    {
+      "epoch": 0.8528309083396273,
+      "grad_norm": 0.17984230816364288,
+      "learning_rate": 5.444033342223832e-07,
+      "loss": 1.4107,
+      "step": 2201
+    },
+    {
+      "epoch": 0.8532183826278325,
+      "grad_norm": 0.1888173371553421,
+      "learning_rate": 5.41587239338971e-07,
+      "loss": 1.3489,
+      "step": 2202
+    },
+    {
+      "epoch": 0.8536058569160376,
+      "grad_norm": 0.19261683523654938,
+      "learning_rate": 5.38778029802417e-07,
+      "loss": 1.3745,
+      "step": 2203
+    },
+    {
+      "epoch": 0.8539933312042428,
+      "grad_norm": 0.19721238315105438,
+      "learning_rate": 5.359757099511237e-07,
+      "loss": 1.3864,
+      "step": 2204
     }
   ],
   "logging_steps": 1.0,
@@ -15426,7 +15454,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1761117551250289e+18,
+  "total_flos": 2.1800206142446787e+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 sha256:0c4386e79026127651aadb56025eb1882c7820cff5922fb5a0636ad098d66e40
+oid sha256:16fb774fc7374c972ea93aaa72bc1893a3284121b69ae795a08735c78b3f7dc5
 size 5560