Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "up_proj",
-    "down_proj",
     "q_proj",
-    "gate_proj",
-    "k_proj",
+    "down_proj",
     "v_proj",
-    "o_proj"
+    "o_proj",
+    "k_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 sha256:1c8d55a623b200c54075f273b1ea0401ed0bb2140699668b11d4a21da19c7343
+oid sha256:4b2e3d005c4cc3e6317d8d600a872a93ae4695ce4c7fb1f7fcee567f1dc3fb0d
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b75242734187513182c96f6369bc10a33f5c389df40dcad1e89c34a692e30e94
+oid sha256:061a2fc28988615d078a1f3c1f58e52edcae160c82552887df8dfb5bfddcb7f9
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c970d7d4eb47bba5dfaacdd67f4d9c20e077afaa1d7d2f1e5a5fe56d2e6143b3
+oid sha256:f8e2bb08cdd2d07cbeeaee167b52eabd308bf6ce2d3aed349bbb796e573eec92
 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": 0.0003450060376056581,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.004485078488873555,
+  "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": 0.0003450060376056581,
       "eval_loss": 1.9688220024108887,
-      "eval_runtime": 81.0818,
-      "eval_samples_per_second": 15.059,
-      "eval_steps_per_second": 7.536,
+      "eval_runtime": 81.235,
+      "eval_samples_per_second": 15.03,
+      "eval_steps_per_second": 7.521,
       "step": 1
+    },
+    {
+      "epoch": 0.0017250301880282904,
+      "grad_norm": 5.527597904205322,
+      "learning_rate": 5e-05,
+      "loss": 1.901,
+      "step": 5
+    },
+    {
+      "epoch": 0.003450060376056581,
+      "grad_norm": 2.9979825019836426,
+      "learning_rate": 0.0001,
+      "loss": 1.374,
+      "step": 10
+    },
+    {
+      "epoch": 0.003450060376056581,
+      "eval_loss": 1.1795198917388916,
+      "eval_runtime": 81.7617,
+      "eval_samples_per_second": 14.934,
+      "eval_steps_per_second": 7.473,
+      "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": 97895558676480.0,
+  "total_flos": 1272642262794240.0,
   "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:a43c4a452a61b0d00a2b590c120ef96b570395bb4d2b936c83af56c6a6c025df
+oid sha256:022b96d103a96518c8fb5bb750a0fedb99fa3a75035963755c9166c2d29906c2
 size 6776