Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "q_proj",
     "gate_proj",
     "down_proj",
-    "q_proj",
-    "up_proj",
     "v_proj",
-    "o_proj",
+    "up_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef72ada8a62d6b89db86653e1adb40a14128192e634ee75f023e33ae4a31b936
+oid sha256:4fb732255a3ce75c3dd1e214b911eec5979057d027356643b172d2906ea565f4
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b6de4428d8a1002e9f1a9a352b0e1b686f90a04cf27f85eccd6cc46c9921084
+oid sha256:f3af1a16b061b7f5b92de242f0ba33b08816aad4f6e949c0b8772ac9dafb2dcb
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78a5494664cf913ce325a101c6ab36fec200803191880843cac974227751885
+oid sha256:22938c9225d2e3dd524252659f50b07cc77a167d9f1e289023028da15c7f5a2b
 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": 0.002489110143123833,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.03235843186060983,
+  "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": 0.002489110143123833,
       "eval_loss": NaN,
-      "eval_runtime": 12.1581,
+      "eval_runtime": 12.1584,
       "eval_samples_per_second": 13.982,
       "eval_steps_per_second": 6.991,
       "step": 1
+    },
+    {
+      "epoch": 0.012445550715619166,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.024891101431238332,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.024891101431238332,
+      "eval_loss": NaN,
+      "eval_runtime": 11.6723,
+      "eval_samples_per_second": 14.564,
+      "eval_steps_per_second": 7.282,
+      "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": 183706639663104.0,
+  "total_flos": 2388186315620352.0,
   "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 sha256:8eecebcbad5af540941288d604df8967cb3d0c57734d8cb421c77b252f2923f1
+oid sha256:21dc481c3e1a67fe2bb56722cee3657a5bf532514949b50e317f182f6a4f6366
 size 6776