Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
-    "k_proj",
     "down_proj",
+    "o_proj",
     "v_proj",
-    "gate_proj",
-    "o_proj"
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "gate_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 sha256:574f0787ab4d221df79b893e93f2e0e5d021f642dcfd9f806758bb49636fa2eb
+oid sha256:1f857ffdb78bece282e5971eb5b5bdf47381f6f6f16c3e43edf9a05fd017402f
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b6de4428d8a1002e9f1a9a352b0e1b686f90a04cf27f85eccd6cc46c9921084
+oid sha256:05ca6eb77df6de7a2c08d25f9e16f833e29c3197229f1676e81a6dd80455f6ae
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93272c3f908c0ebc557b963c9f021303626d98af63190f5a873faa2bd9b7a38d
+oid sha256:976d18822cf1854cf0fbfda0c18b6fb9200534b977937f6d98ed073355786b2e
 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": 0.004585841215247922,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.05961593579822299,
+  "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": 0.004585841215247922,
       "eval_loss": NaN,
-      "eval_runtime": 52.2275,
-      "eval_samples_per_second": 28.146,
-      "eval_steps_per_second": 3.523,
+      "eval_runtime": 52.288,
+      "eval_samples_per_second": 28.114,
+      "eval_steps_per_second": 3.519,
       "step": 1
+    },
+    {
+      "epoch": 0.04585841215247922,
+      "grad_norm": NaN,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.04585841215247922,
+      "eval_loss": NaN,
+      "eval_runtime": 51.2152,
+      "eval_samples_per_second": 28.702,
+      "eval_steps_per_second": 3.593,
+      "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": 1469653117304832.0,
+  "total_flos": 1.919734384479437e+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 sha256:313551a64b4e8f87847527ca30bd22a62f0ac6d2a1afb739ce7a5a93e81a649e
+oid sha256:dfa98a6ac83565ecfc19c8b530feb5d0b406395690fd6c491af7ac149ba2dec7
 size 6776