Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "up_proj",
     "gate_proj",
     "k_proj",
-    "o_proj",
     "down_proj",
+    "up_proj",
+    "o_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1db47812affe541df2a3d7c2541306dda157724af0be60df1743ed010a87a9a3
+oid sha256:5758910b7145382cf731d24e77acc9af7c177f9baf85115fee0a5b35bd55f293
 size 608249904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb1e20bcf1e2805a5b79c1bfaf8bcfd360d496250a16f4717359fac31a45680a
+oid sha256:c6b4e535bdafcd46830b22e0e14825e981fb1504d1bf58c3629f755bffd96349
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2c76845d1a198321567d417f508e36c6488ae79ee6a5814ae3463528c38bff
+oid sha256:cf191b7c52ae0f5950e3f1f1dec5b3d92cc3089d5753f800d4b1b7550aa71db3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:793e67e8ce9008665aa65ff20b6ea7fbcd694d12c7efb6b4719021ac264b7609
 size 1064

last-checkpoint/trainer_state.json

@@ -1,27 +1,35 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.029411764705882353,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.2647058823529412,
+  "eval_steps": 7,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.029411764705882353,
-      "eval_loss": 7.963089466094971,
-      "eval_runtime": 12.1633,
-      "eval_samples_per_second": 18.909,
-      "eval_steps_per_second": 2.384,
+      "eval_loss": 7.964369297027588,
+      "eval_runtime": 12.1692,
+      "eval_samples_per_second": 18.9,
+      "eval_steps_per_second": 2.383,
       "step": 1
+    },
+    {
+      "epoch": 0.20588235294117646,
+      "eval_loss": 0.220572829246521,
+      "eval_runtime": 12.2392,
+      "eval_samples_per_second": 18.792,
+      "eval_steps_per_second": 2.369,
+      "step": 7
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 34,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 9,
   "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": 2804273268129792.0,
+  "total_flos": 2.523845941316813e+16,
   "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:aed2e9d81c3b1222661222f1ad07a725f4f0b4df58dd26334ff1cbe96268e92c
+oid sha256:3451bb7a809ffe40cd34fbe571bc106bdff5fe75a1235f6225c45d93e835aceb
 size 6776