Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -22,8 +22,8 @@
   "target_modules": [
     "dense_4h_to_h",
     "query_key_value",
-    "dense",
-    "dense_h_to_4h"
+    "dense_h_to_4h",
+    "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 sha256:00dd93f80437e870aef2fe487b4167a5e56f0f259272468b96b761022ee2f610
+oid sha256:22edbd67e3e2b7b66f2e474fb32d656430e5b327c5bf7fdd8884fe1212bacf57
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a588a8ba4742c5b524c1e42a79fe02ba893d121b87b9f679c63a0527465283ce
+oid sha256:7fcca085063ce42cf32ee3d2818cc6737176e1afda4ec3c26b410c5118ab0d3f
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75b7f5e0e18a033dedfaea1399e69021ad3be8e7147070fe24654db1b00bbbd3
+oid sha256:c7ab0c44cf5e3ac12d8f244d51e872e33c5a3130f6c55a7340eec5273eed4c50
 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": 0.0005645730416372619,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.007339449541284404,
+  "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": 0.0005645730416372619,
       "eval_loss": 2.1830296516418457,
-      "eval_runtime": 48.2865,
-      "eval_samples_per_second": 15.449,
-      "eval_steps_per_second": 7.725,
+      "eval_runtime": 63.2333,
+      "eval_samples_per_second": 11.798,
+      "eval_steps_per_second": 5.899,
       "step": 1
+    },
+    {
+      "epoch": 0.0028228652081863093,
+      "grad_norm": 4.909060001373291,
+      "learning_rate": 5e-05,
+      "loss": 8.6593,
+      "step": 5
+    },
+    {
+      "epoch": 0.0056457304163726185,
+      "grad_norm": 4.655195713043213,
+      "learning_rate": 0.0001,
+      "loss": 9.0873,
+      "step": 10
+    },
+    {
+      "epoch": 0.0056457304163726185,
+      "eval_loss": 2.043684720993042,
+      "eval_runtime": 45.3827,
+      "eval_samples_per_second": 16.438,
+      "eval_steps_per_second": 8.219,
+      "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": 11260447948800.0,
+  "total_flos": 116357962137600.0,
   "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:cab16b2ecd221af141e6d30b935769f0ffdc301427ae9e8da4a3ff78266f8fe6
+oid sha256:8bf3739f62972eda42a33ada6c592c779266f302439265c15850186466ab78e5
 size 6776