Training in progress, step 2, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "q_proj",
-    "down_proj",
-    "up_proj",
     "gate_proj",
     "k_proj",
     "o_proj",
-    "v_proj"
+    "up_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:ad668f50164d4cd425d685b6dac944daea2cf1596f093f4dcd118bb87eefd798
+oid sha256:284039d0f04024bd7df9d1931805e5c8db4f9a76ce62007c3615c47f3a01d037
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b6de4428d8a1002e9f1a9a352b0e1b686f90a04cf27f85eccd6cc46c9921084
+oid sha256:3a40c39d880cd8741119832272ac9c076eedfd9b1f7f298c1493ba953ca1ebc7
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c581a322ccb115680b65475b1eab69b643b5de15ce2c699864253548d637017f
+oid sha256:2217bddafdf3b6e8eaedd27506a6ce00af88645969bc815dfff9f073da8be14d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21052631578947367,
+  "epoch": 0.42105263157894735,
   "eval_steps": 1,
-  "global_step": 1,
+  "global_step": 2,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,25 @@
     {
       "epoch": 0.21052631578947367,
       "eval_loss": NaN,
-      "eval_runtime": 0.728,
-      "eval_samples_per_second": 2.747,
-      "eval_steps_per_second": 1.374,
+      "eval_runtime": 0.7307,
+      "eval_samples_per_second": 2.737,
+      "eval_steps_per_second": 1.369,
       "step": 1
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "eval_loss": NaN,
+      "eval_runtime": 0.2749,
+      "eval_samples_per_second": 7.277,
+      "eval_steps_per_second": 3.638,
+      "step": 2
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 5,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1,
+  "num_train_epochs": 2,
+  "save_steps": 2,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +37,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 91853319831552.0,
+  "total_flos": 183706639663104.0,
   "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:a7e26fef844b7bcf4ef6c65c9097ec1e63cd6a4db8767ef8312399703ce5f77c
+oid sha256:1da44f3e17a69fd68c01a03d0e0ec777bc3c4203e6c305251470d6d76c9416cf
 size 6776