Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "v_proj",
-    "gate_proj",
-    "up_proj",
     "k_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
     "q_proj",
-    "o_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:db401385cb61050c996b7acac41706466fd57a58f6f12354b0553d2fcdaaaa9a
+oid sha256:e30f4a7951c6d9eb963d54f969a94726192588ec3bc35c8a8561bfc2558712b1
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f9db507a24850fc177a43fb5b0c8ff433b701fd46661a4bd7f1594f7bd3bc4f
+oid sha256:28f666dc35a95aafe80c665e048431d29366ac0f0ded752326327b83bf0b7f7c
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9fa9b21d8753d2caf62524aabbc0f8a063da501b3b2b4731c156465684d50ac
+oid sha256:405836a400b8251bcce9b8fe6f90aa7292a17fe1c9aabea40a7456bde4466310
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00016304569355561895,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0021195940162230466,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.00016304569355561895,
       "eval_loss": 1.0663607120513916,
-      "eval_runtime": 133.1876,
-      "eval_samples_per_second": 19.394,
-      "eval_steps_per_second": 9.701,
+      "eval_runtime": 133.3275,
+      "eval_samples_per_second": 19.373,
+      "eval_steps_per_second": 9.69,
       "step": 1
+    },
+    {
+      "epoch": 0.0008152284677780948,
+      "grad_norm": 0.11302177608013153,
+      "learning_rate": 5e-05,
+      "loss": 1.0815,
+      "step": 5
+    },
+    {
+      "epoch": 0.0016304569355561896,
+      "grad_norm": 0.10407887399196625,
+      "learning_rate": 0.0001,
+      "loss": 0.9289,
+      "step": 10
+    },
+    {
+      "epoch": 0.0016304569355561896,
+      "eval_loss": 1.0647904872894287,
+      "eval_runtime": 136.8984,
+      "eval_samples_per_second": 18.868,
+      "eval_steps_per_second": 9.438,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 44763596193792.0,
+  "total_flos": 601111148888064.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69bf2b09332f291ec714d444c30535a2b372b4d6692884df750a50257ae8a238
+oid sha256:9fea4dc66cca752418e0b20106b8837b2963e03affa86b9e7833722f3413a99b
 size 6776