Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "gate_proj",
-    "down_proj",
+    "up_proj",
     "q_proj",
     "k_proj",
-    "up_proj",
-    "v_proj"
+    "v_proj",
+    "gate_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 sha256:4d4dc628ac1b3c0c8525d8257c50bdc6692dc39fbfe46aa3d223897625b17756
+oid sha256:925328186fc9046ac2f1ff5af090608055c3959c3c02902c0ca8312103d3fde2
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd1e83b36d104c0a299bb436efa590ff934d5fd0e5baf636fa4246a543fd8785
+oid sha256:4966014013084a2df4b3e14bd9452ef3ed52dd660ce7054d6b0da9e36c166388
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9dbb10dde7908d9e87baf72adbae4b0fde018a81ad2198cc850bfbd29d34430
+oid sha256:6f917b555e13f2e5eceb0a6ff695119008107a9c930c365e9b7e40e83f7fd140
 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": 7.995842162075721e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0010394594810698436,
+  "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": 7.995842162075721e-05,
       "eval_loss": 0.8471629619598389,
-      "eval_runtime": 258.2147,
-      "eval_samples_per_second": 20.394,
-      "eval_steps_per_second": 10.197,
+      "eval_runtime": 258.4487,
+      "eval_samples_per_second": 20.375,
+      "eval_steps_per_second": 10.188,
       "step": 1
+    },
+    {
+      "epoch": 0.000399792108103786,
+      "grad_norm": 1.4865186214447021,
+      "learning_rate": 5e-05,
+      "loss": 0.7428,
+      "step": 5
+    },
+    {
+      "epoch": 0.000799584216207572,
+      "grad_norm": 0.7193690538406372,
+      "learning_rate": 0.0001,
+      "loss": 0.6748,
+      "step": 10
+    },
+    {
+      "epoch": 0.000799584216207572,
+      "eval_loss": 0.6413815021514893,
+      "eval_runtime": 258.9633,
+      "eval_samples_per_second": 20.335,
+      "eval_steps_per_second": 10.167,
+      "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": 61184724172800.0,
+  "total_flos": 893296972922880.0,
   "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 sha256:8f3144a09d675f890561578f20382343b30519c82cc0c7e2cf744abaa647fb01
+oid sha256:8420b6db29c78560a3e0e69c066cadc7c56df15315b1d3d07487e752bb217839
 size 6776