Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -22,8 +22,8 @@
   "target_modules": [
     "dense_h_to_4h",
     "dense_4h_to_h",
-    "dense",
-    "query_key_value"
+    "query_key_value",
+    "dense"
   ],
   "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 sha256:9f923c2edfa5556724b04542b873e39293e33ced2d9281cf7500f0ac53f554ab
+oid sha256:03bfd81f246a73e9d29c3402b9b87e7ada9d9235a0d00b09e8a56d073b3bb735
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0509f6372826a6ba603c4e4ef53c5f3c7047ad225a967da2f8a768c9ea26abe
+oid sha256:1914d8eae14ba4a0a750378fb43ad8cac1be21bdb1e31ef1b935d0e9fc5ebf68
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77bba18256fafda32f39805d8a79bd94ed0adb267c51253610b58903e54ff6d3
+oid sha256:b77036b953e485790a99d4b25b62dadc9eec6d915d87108a7cb9a6f1bb7e3fc5
 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": 3.933368733651936e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0005113379353747517,
+  "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": 3.933368733651936e-05,
       "eval_loss": 11.096795082092285,
-      "eval_runtime": 46.1958,
-      "eval_samples_per_second": 231.731,
-      "eval_steps_per_second": 115.876,
+      "eval_runtime": 46.8316,
+      "eval_samples_per_second": 228.585,
+      "eval_steps_per_second": 114.303,
       "step": 1
+    },
+    {
+      "epoch": 0.00019666843668259682,
+      "grad_norm": 1.5377999544143677,
+      "learning_rate": 5e-05,
+      "loss": 44.3816,
+      "step": 5
+    },
+    {
+      "epoch": 0.00039333687336519363,
+      "grad_norm": 1.4307451248168945,
+      "learning_rate": 0.0001,
+      "loss": 44.3909,
+      "step": 10
+    },
+    {
+      "epoch": 0.00039333687336519363,
+      "eval_loss": 11.09162712097168,
+      "eval_runtime": 45.6691,
+      "eval_samples_per_second": 234.404,
+      "eval_steps_per_second": 117.213,
+      "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": 747110400.0,
+  "total_flos": 9712435200.0,
   "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:de74d6e85fd2fb7d255a6b39da8205526dd7db95feb787acba00cc960c24a33c
+oid sha256:89f23cbd66e7cd4918356d49d4520fd16bf719f0861b4ca9c9d727c00c2ee906
 size 6776