Training in progress, step 2480, checkpoint

last-checkpoint/adapter_config.json

@@ -23,10 +23,10 @@
     "down_proj",
     "q_proj",
     "up_proj",
-    "v_proj",
     "k_proj",
-    "gate_proj",
-    "o_proj"
+    "o_proj",
+    "v_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 sha256:4e296b9bb163171f7d3292e7f975cd8851abb7f06f131d59f3fc27ddc0971e89
+oid sha256:7d2c33d436bbae09929b10f741d360ab726e726a94e1c65395877fddd4f9e454
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2409c85204b25b0c68db7e75cff61155bb985b9ed5e78015f6ae41839de13b08
+oid sha256:5011f00bab7f837ab30278bc7c4e1335b56b3448a40f1f394154b2d06a99d72e
 size 75455810

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:477febd7eab5cb9a16378af748559d02a17dca77e420484aefc4f371d4457c5a
+oid sha256:23b6619ef6832a5ad150938e82c728b260a07dd3b3ae733f6bc9ea6d005dd4b4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c588c84c1abcb13cdaadd37cc81933f6bbcbd611f3b25ba28f6d4d519a813632
+oid sha256:7fc524921ad40def3d582e1dca3b700998a5e2a41bf8de3461800594bda41107
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9593863375960551,
+  "epoch": 0.9609362347488758,
   "eval_steps": 500,
-  "global_step": 2476,
+  "global_step": 2480,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17339,6 +17339,34 @@
       "learning_rate": 4.170111648909736e-08,
       "loss": 1.3903,
       "step": 2476
+    },
+    {
+      "epoch": 0.9597738118842603,
+      "grad_norm": 0.20792566239833832,
+      "learning_rate": 4.090411741682565e-08,
+      "loss": 1.3801,
+      "step": 2477
+    },
+    {
+      "epoch": 0.9601612861724654,
+      "grad_norm": 0.19542264938354492,
+      "learning_rate": 4.0114776921067465e-08,
+      "loss": 1.4094,
+      "step": 2478
+    },
+    {
+      "epoch": 0.9605487604606706,
+      "grad_norm": 0.21897444128990173,
+      "learning_rate": 3.933309622084103e-08,
+      "loss": 1.4193,
+      "step": 2479
+    },
+    {
+      "epoch": 0.9609362347488758,
+      "grad_norm": 0.20047014951705933,
+      "learning_rate": 3.855907652333402e-08,
+      "loss": 1.3831,
+      "step": 2480
     }
   ],
   "logging_steps": 1.0,
@@ -17358,7 +17386,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.448841409909757e+18,
+  "total_flos": 2.452775401006673e+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 sha256:76c56280507313f331f5ebcc5db348eedc6cc0a045fc5f4c2b79d99b9c533ba6
+oid sha256:9396e82ae7c78d167148ae12181b033e8cac56f246093dcb3425d034c307f798
 size 5560