Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "gate_proj",
-    "o_proj",
+    "v_proj",
     "k_proj",
+    "q_proj",
+    "o_proj",
     "down_proj",
-    "up_proj",
-    "q_proj"
+    "up_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:a0ede185d6292b3ddd6d28fcce4306efcfb1ddc18ac68cbb6c4e5edc92de56a5
+oid sha256:d5c13fccd62d40eacb0889fd51bc6c06bde643a036405c51a0402a126192a413
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1c5110e6858a52f7bf12098cc82593810318d34546afdbc45be7a916493f8cb
+oid sha256:1b6aba3003b7ad06d37942b64ce8b62ac49c420a05e5872ac49cfd9379daa68f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
+oid sha256:a5cba764fcb0e7f18b6d06759624dccc13afd567f3245791b3de96f9fcfce3c5
 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": 9.485866059571239e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0012331625877442611,
+  "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": 9.485866059571239e-05,
       "eval_loss": 2.1410107612609863,
-      "eval_runtime": 552.4253,
-      "eval_samples_per_second": 8.035,
-      "eval_steps_per_second": 4.019,
+      "eval_runtime": 553.002,
+      "eval_samples_per_second": 8.027,
+      "eval_steps_per_second": 4.014,
       "step": 1
+    },
+    {
+      "epoch": 0.0004742933029785619,
+      "grad_norm": 0.34695127606391907,
+      "learning_rate": 5e-05,
+      "loss": 2.2003,
+      "step": 5
+    },
+    {
+      "epoch": 0.0009485866059571238,
+      "grad_norm": 0.4375736117362976,
+      "learning_rate": 0.0001,
+      "loss": 2.0296,
+      "step": 10
+    },
+    {
+      "epoch": 0.0009485866059571238,
+      "eval_loss": 2.1128005981445312,
+      "eval_runtime": 555.0801,
+      "eval_samples_per_second": 7.997,
+      "eval_steps_per_second": 3.999,
+      "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": 369912849629184.0,
+  "total_flos": 4808867045179392.0,
   "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:c23c54a173c8407b8318e613d402826762b6af536159de3007cca35dc43ca725
+oid sha256:9a63d79e57c6ec65637ac04fac6725cba78b229d9bd9031d6e67799ab3cd2000
 size 6776