Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "down_proj",
     "v_proj",
     "o_proj",
+    "gate_proj",
     "k_proj",
-    "down_proj",
-    "q_proj",
-    "up_proj"
+    "up_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:f8c4261ea898133ef4cf474c7d5bee79c7a44def40aad99ef7a343e927ab39ac
+oid sha256:60bec59f6e85bb70c3c3a7c37c88486d5705371c3ac8ce922f4d08f01eb55d94
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb26120e9b7ab349d7c516db9b433e5421b52aaf07782d543ce46d6d249990d3
+oid sha256:f87a2d216349dbd7e02a8c090b0278556744108f0f22882105962d505c90ffa4
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be8b1b9e7bfbfa0a07c044af5d4d41c9b69c03fb50ecb3685b8b3b42939557eb
+oid sha256:2cda33dcba506d3b59a241f55c9e7d21dcc373169f79a4faa43c5f8c8beb8326
 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": 0.011315417256011316,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.1471004243281471,
+  "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": 0.011315417256011316,
       "eval_loss": 10.555892944335938,
-      "eval_runtime": 36.5124,
-      "eval_samples_per_second": 16.296,
-      "eval_steps_per_second": 2.054,
+      "eval_runtime": 36.4498,
+      "eval_samples_per_second": 16.324,
+      "eval_steps_per_second": 2.058,
       "step": 1
+    },
+    {
+      "epoch": 0.11315417256011315,
+      "grad_norm": 23.465301513671875,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 5.9727,
+      "step": 10
+    },
+    {
+      "epoch": 0.11315417256011315,
+      "eval_loss": 0.7171273827552795,
+      "eval_runtime": 37.0437,
+      "eval_samples_per_second": 16.062,
+      "eval_steps_per_second": 2.025,
+      "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": 3057746266030080.0,
+  "total_flos": 3.975070145839104e+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 sha256:777da725b76862ec56f945c80f6032a703bf37f0326a9412f4ecd6d6580813c5
+oid sha256:ba8a1724238ff12cb8fb8bee79de6f9627564943d22b18ce834e64099de17534
 size 6776