Training in progress, step 26600, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "o_proj",
+    "gate_proj",
     "k_proj",
-    "down_proj",
     "up_proj",
     "q_proj",
-    "gate_proj",
-    "o_proj",
-    "v_proj"
+    "down_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 sha256:09e7569231f9d48775234e444dc3002609a2aaf23f9fbb03afc31dd08b174acd
+oid sha256:a66649ed360eedf7f38576a034cb81a9f0d0d85b4e760a08a7af7c644b300130
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1795d0f5907365f50ee8bf592e588c51cf0c1336607a8958053b6df1866c85ef
+oid sha256:0a84728d3e6388a2e313a0b930591e1caa03457e9373fa5a9018a74d4f76a4dd
 size 85736914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1e0be0fbdc67baa64bde42b3f62fb0cbfa6b616dea815616465446e745a61cd
+oid sha256:e52e46a86dee0df6899d8616f9314a071547c40c5f77f9c7869ec679d05b2712
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afd4eb6473181bbf6da6b1613c063360450d1f8ec75384d51547bd12664e8b3a
+oid sha256:034fc0fef9516d254e4e7d37234cc827f307f60cceb9a55e70e7d8869181a03e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07674602790967469,
+  "epoch": 0.31650299882129407,
   "eval_steps": 2000,
-  "global_step": 25800,
+  "global_step": 26600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -910,14 +910,42 @@
       "learning_rate": 1.998839744298062e-05,
       "loss": 1.5509,
       "step": 25800
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.8327608704566956,
+      "learning_rate": 1.9812018045085563e-05,
+      "loss": 1.5483,
+      "step": 26000
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.7521975636482239,
+      "learning_rate": 1.980912147882786e-05,
+      "loss": 1.5296,
+      "step": 26200
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.7781311869621277,
+      "learning_rate": 1.9806202981642514e-05,
+      "loss": 1.5346,
+      "step": 26400
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.7848681211471558,
+      "learning_rate": 1.9803262560054603e-05,
+      "loss": 1.5271,
+      "step": 26600
     }
   ],
   "logging_steps": 200,
-  "max_steps": 1680865,
+  "max_steps": 420215,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 5.996940170325443e+17,
+  "total_flos": 7.664136678128517e+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:e88463ac0cd6182d9b1cd0ac83ec16eba34109ec5568773d1ab337bb23a66942
+oid sha256:c09e4d0caa94d3d4acabbf865ee69cc816a077a03533c04bf2c5e62bf08ec171
 size 4920