Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
-    "v_proj",
-    "q_proj",
     "up_proj",
     "k_proj",
-    "down_proj"
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "o_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 sha256:33dfad62ab933ab05c4047651b369c40761a2e530a9476afa05ae962e059f604
+oid sha256:176c7527a6ce6c288c20f92449d664afe9beca49597b02009841150f06e64dc7
 size 10624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a1616e456607aba33be092c0677ca49d6d70f91a2588aee3f9f4b4357922f7
+oid sha256:bf87d8387055e5d822044efd1ca9c09deab7ed732bde4826618fd2959e1e2282
 size 26562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99bcf5ac8488b2a4c6dbe42b144f3d1d61b237d080b40d4d50265b37a38585d5
+oid sha256:65822ab801716a0b101ae7c69a8d42fb2cd06f3a4cee11fa6373539c7f78ccb4
 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": 0.0004769285799451532,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0062000715392869915,
+  "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": 0.0004769285799451532,
       "eval_loss": 12.455657958984375,
-      "eval_runtime": 11.9584,
-      "eval_samples_per_second": 73.84,
-      "eval_steps_per_second": 36.962,
+      "eval_runtime": 11.9624,
+      "eval_samples_per_second": 73.814,
+      "eval_steps_per_second": 36.949,
       "step": 1
+    },
+    {
+      "epoch": 0.002384642899725766,
+      "grad_norm": 0.004523464944213629,
+      "learning_rate": 5e-05,
+      "loss": 12.4565,
+      "step": 5
+    },
+    {
+      "epoch": 0.004769285799451532,
+      "grad_norm": 0.006430428940802813,
+      "learning_rate": 0.0001,
+      "loss": 12.4573,
+      "step": 10
+    },
+    {
+      "epoch": 0.004769285799451532,
+      "eval_loss": 12.455652236938477,
+      "eval_runtime": 12.0822,
+      "eval_samples_per_second": 73.083,
+      "eval_steps_per_second": 36.583,
+      "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": 99483648.0,
+  "total_flos": 1417641984.0,
   "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:d161889a154225121e3661a4adc0b6ec1f56264409bf29d83b627f750430deb7
+oid sha256:9eb3a5d7323b93229d56eeaffd9030e233245be17188546dab5540dec4a49215
 size 6776