Training in progress, step 1, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "down_proj",
     "o_proj",
-    "v_proj",
     "q_proj",
-    "gate_proj",
     "k_proj",
-    "down_proj",
-    "up_proj"
+    "v_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:b2c4c96bd6e6537f75a7f4f6816262ee4243201bcb3f6ddd81103ea2388e9b1c
+oid sha256:294871b5ca4ef10d46401f5d93773247d2c92d751d38cbeb679bce63233d3900
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52583850703b49ea25242028855c94a9e288a6d74a72a70a929d600e7afe121
+oid sha256:eef8a3ca1274fe973be3061f0819d18308c37acd9bb40adba64b56b22ea349c8
 size 43122580

last-checkpoint/trainer_state.json

@@ -11,16 +11,16 @@
     {
       "epoch": 0.5333333333333333,
       "eval_loss": 1.501295566558838,
-      "eval_runtime": 0.7275,
-      "eval_samples_per_second": 17.87,
-      "eval_steps_per_second": 2.749,
+      "eval_runtime": 0.7171,
+      "eval_samples_per_second": 18.129,
+      "eval_steps_per_second": 2.789,
       "step": 1
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 2,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 2,
   "save_steps": 1,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -29,7 +29,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de3eb087581c09348a01c3741fa7a48dbbcf5257533832ae2adfacf68e447f
+oid sha256:108dac83a23960babacd1978472db8df5d6985f9fe67aef52c7f31e2eb623ddf
 size 6776