Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "o_proj",
+    "v_proj",
     "gate_proj",
-    "k_proj",
-    "down_proj",
     "up_proj",
-    "q_proj",
-    "v_proj"
+    "k_proj",
+    "q_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:b4e4f737f9704680066fde4efbb417c090f67fc921876c94d9625687fbf1c88f
+oid sha256:198b12a1d1ae19884236a4b648456028aa9576a24ee46f293a18320c8e3ed955
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d8edacf257812bb04d6480cd0be9f161db1893978ea0f8d5b1c86429f383c61
+oid sha256:39c9b193403ef7aec83cb1ff5285c1155b490d00964607108ad16df90e3fce80
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4eeceb59e7f605ea79bd68088231033e57f479701230fe841b1641bd12bdaa
+oid sha256:0f006ee8d50a5c1463398e3d8175dd1a90f022c3d0c133415f3e98891da383bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000759085302210836,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.009868108928740868,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.000759085302210836,
       "eval_loss": 3.139888286590576,
-      "eval_runtime": 52.9476,
-      "eval_samples_per_second": 167.618,
-      "eval_steps_per_second": 20.964,
+      "eval_runtime": 52.3233,
+      "eval_samples_per_second": 169.618,
+      "eval_steps_per_second": 21.214,
       "step": 1
+    },
+    {
+      "epoch": 0.007590853022108359,
+      "grad_norm": 0.27882295846939087,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 2.8562,
+      "step": 10
+    },
+    {
+      "epoch": 0.007590853022108359,
+      "eval_loss": 3.068080425262451,
+      "eval_runtime": 51.5948,
+      "eval_samples_per_second": 172.013,
+      "eval_steps_per_second": 21.514,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 68585300951040.0,
+  "total_flos": 1001345393885184.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e1d6f2634bc982328beae958bda019e0f35625061d5273b64107f588093336
+oid sha256:42b43219bba8590e2ee61d32d592ed4d2bdd0bd15bf2d605e1f45f652c4947b2
 size 6776