Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
     "gate_proj",
-    "down_proj",
-    "q_proj",
+    "o_proj",
+    "k_proj",
     "up_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj",
+    "down_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 sha256:8b5ea6524a0bcd765ca00c3c11df2d86587b0f41257083ab48beead7fb9871bf
+oid sha256:bcdf731eb46c5f1411441fdfe21ac70517df217bce0ead8945f29cddb93d1230
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9da61c0a3eb4f3b84121b312be1a76dd319722fdb7027feb61ad9be1430b1ad
+oid sha256:3a2fa30a103015c94da3fcfda1ad4bf8862d43509ca6f5e1f74bd7436cbef057
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a639da18d5756dd329b70270915837be928d52692379b9e5cd01847b059c27
+oid sha256:a339fc53708bc4269af93f59572a3f89f52f9321c39f58682c8db021fa5f360c
 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": 2.110261144816671e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00027433394882616724,
+  "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": 2.110261144816671e-05,
       "eval_loss": 4.271842956542969,
-      "eval_runtime": 1836.8297,
-      "eval_samples_per_second": 10.863,
-      "eval_steps_per_second": 5.432,
+      "eval_runtime": 1834.5182,
+      "eval_samples_per_second": 10.876,
+      "eval_steps_per_second": 5.438,
       "step": 1
+    },
+    {
+      "epoch": 0.00010551305724083355,
+      "grad_norm": 2.6179606914520264,
+      "learning_rate": 5e-05,
+      "loss": 3.6149,
+      "step": 5
+    },
+    {
+      "epoch": 0.0002110261144816671,
+      "grad_norm": 5.768125534057617,
+      "learning_rate": 0.0001,
+      "loss": 3.2024,
+      "step": 10
+    },
+    {
+      "epoch": 0.0002110261144816671,
+      "eval_loss": 3.907235622406006,
+      "eval_runtime": 1823.8226,
+      "eval_samples_per_second": 10.94,
+      "eval_steps_per_second": 5.47,
+      "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": 231195531018240.0,
+  "total_flos": 3236737434255360.0,
   "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 sha256:00721769bb5f1e77ab9b43df9aea7326be69dd27719749fb858fe3fa9b3a5b39
+oid sha256:dd2ef8803a3fe14e9c7ffec56e6df775316769b3ac64f24d956942dbd4567027
 size 6776