Training in progress, step 74400, checkpoint

last-checkpoint/adapter_config.json

@@ -24,11 +24,11 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
-    "o_proj",
-    "up_proj",
     "down_proj",
+    "up_proj",
+    "v_proj",
     "gate_proj",
+    "o_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575f61e221017f2179441559ba498b0a30f681ccc1e377951330eaee49c39822
+oid sha256:adade87829d537ad6739250c483b6706bdd890e1f0c9de83cdf06f44b32e5090
 size 1342238560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d6c756dbba2ef1c1b74580a28ab2dcc48755bf2857720a1da48a545c30bb169
+oid sha256:bc5615a410c858c99e3cf7362945f36a6e9c191706d0a029ed4b1e854e10c57b
 size 683268498

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362b5dd6eca4f983f206304be27a2b716fdb6e0e11a8b449b3be57f73f075b0d
+oid sha256:dccc9cbc468284f92a4012f3a3803f3d2cbb7abb4eeb9a6c35e73e04a7df0c1b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad2a07100542f920d814c50556d1f596c833109e04c422ef0d43afdfc163dcec
+oid sha256:e73dccec2330458d52f8108cf9299eca128bc179d6d432f80a29c728273abc45
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05146569428960303,
+  "epoch": 0.05174388723170899,
   "eval_steps": 500,
-  "global_step": 74000,
+  "global_step": 74400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2597,6 +2597,20 @@
       "learning_rate": 1.997713838369215e-05,
       "loss": 1.6841,
       "step": 74000
+    },
+    {
+      "epoch": 0.05160479076065601,
+      "grad_norm": 3.7980597019195557,
+      "learning_rate": 1.9977014708158027e-05,
+      "loss": 1.727,
+      "step": 74200
+    },
+    {
+      "epoch": 0.05174388723170899,
+      "grad_norm": 4.492558479309082,
+      "learning_rate": 1.997689069954923e-05,
+      "loss": 1.6307,
+      "step": 74400
     }
   ],
   "logging_steps": 200,
@@ -2616,7 +2630,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.85329379279872e+17,
+  "total_flos": 9.906764066420982e+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:acabefbc48b0af9c7f4952fd51a56e04992b5bb070918bb0e676e541c603140d
+oid sha256:973554a532ca404cb4db7d5fef3755d36407a35ec7c1a90c277a7941be0f4f1e
 size 6840