Training in progress, step 25800, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "k_proj",
+    "down_proj",
     "up_proj",
-    "v_proj",
     "q_proj",
     "gate_proj",
-    "down_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 sha256:8c7f93eabe6ac3c54d66eaa201fd02227487a26f7778737a9f254ff462e973e4
+oid sha256:09e7569231f9d48775234e444dc3002609a2aaf23f9fbb03afc31dd08b174acd
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73914a91d2c85155b01b949bf4bca1b47684ea4ff1764db4a597aed9516fd5ab
+oid sha256:1795d0f5907365f50ee8bf592e588c51cf0c1336607a8958053b6df1866c85ef
 size 85736914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f8c4f9076fe893e7a53debd026211a9b9066658d86f31864434230c495759f3
+oid sha256:e1e0be0fbdc67baa64bde42b3f62fb0cbfa6b616dea815616465446e745a61cd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8114cada636c19d5007acc44352f3b0449c4b5ebb7cb27bcb702507137d58166
+oid sha256:afd4eb6473181bbf6da6b1613c063360450d1f8ec75384d51547bd12664e8b3a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0696068625227282,
+  "epoch": 0.07674602790967469,
   "eval_steps": 2000,
-  "global_step": 23400,
+  "global_step": 25800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -826,6 +826,90 @@
       "learning_rate": 1.999045551990737e-05,
       "loss": 1.536,
       "step": 23400
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.7328152656555176,
+      "learning_rate": 1.9990292364225084e-05,
+      "loss": 1.5166,
+      "step": 23600
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.3295519351959229,
+      "learning_rate": 1.9990126996188935e-05,
+      "loss": 1.5488,
+      "step": 23800
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.1913652420043945,
+      "learning_rate": 1.998996023220988e-05,
+      "loss": 1.5219,
+      "step": 24000
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.8065701723098755,
+      "learning_rate": 1.998979207231122e-05,
+      "loss": 1.5181,
+      "step": 24200
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.8158023357391357,
+      "learning_rate": 1.998962336776768e-05,
+      "loss": 1.5176,
+      "step": 24400
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.4990816116333008,
+      "learning_rate": 1.9989452423079802e-05,
+      "loss": 1.4998,
+      "step": 24600
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.655572533607483,
+      "learning_rate": 1.9989280082543273e-05,
+      "loss": 1.5426,
+      "step": 24800
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.9679639339447021,
+      "learning_rate": 1.9989106346182187e-05,
+      "loss": 1.5603,
+      "step": 25000
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 1.2155619859695435,
+      "learning_rate": 1.9988931214020803e-05,
+      "loss": 1.5368,
+      "step": 25200
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.3557419776916504,
+      "learning_rate": 1.9988754686083607e-05,
+      "loss": 1.531,
+      "step": 25400
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.433875322341919,
+      "learning_rate": 1.998857676239526e-05,
+      "loss": 1.5502,
+      "step": 25600
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.2107449769973755,
+      "learning_rate": 1.998839744298062e-05,
+      "loss": 1.5509,
+      "step": 25800
     }
   ],
   "logging_steps": 200,
@@ -833,7 +917,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 4.745472228553851e+17,
+  "total_flos": 5.996940170325443e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null