Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
-    "o_proj",
-    "down_proj",
     "k_proj",
     "gate_proj",
-    "up_proj"
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "v_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:b5b9f57de327fb0be78f5a41bce5d6661aaa97a9841b5ca57cf4c7fbe8f802bb
+oid sha256:244266c863b656c944c3f3150aa8f0f240a9e56273044c6d88b69e911d2568ef
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0c961f525b415afe039401251a7cabac4b85d655348465ec6760089e06fea91
+oid sha256:423c6ab65d95ee3c13d0c2dabff7cba9f3fa29b9a5accf90dfed28e429ece8d1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a639da18d5756dd329b70270915837be928d52692379b9e5cd01847b059c27
+oid sha256:46b0ecaac8112b4f90b6fe8f4b2b5e503450792b9cccc6a3804245d9e6e81093
 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": 0.0037593984962406013,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.04887218045112782,
+  "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": 0.0037593984962406013,
       "eval_loss": 4.221013069152832,
-      "eval_runtime": 11.893,
-      "eval_samples_per_second": 9.417,
-      "eval_steps_per_second": 4.709,
+      "eval_runtime": 11.9374,
+      "eval_samples_per_second": 9.382,
+      "eval_steps_per_second": 4.691,
       "step": 1
+    },
+    {
+      "epoch": 0.018796992481203006,
+      "grad_norm": 1.9136879444122314,
+      "learning_rate": 5e-05,
+      "loss": 3.9849,
+      "step": 5
+    },
+    {
+      "epoch": 0.03759398496240601,
+      "grad_norm": 2.47013521194458,
+      "learning_rate": 0.0001,
+      "loss": 3.6386,
+      "step": 10
+    },
+    {
+      "epoch": 0.03759398496240601,
+      "eval_loss": 3.3705058097839355,
+      "eval_runtime": 12.098,
+      "eval_samples_per_second": 9.258,
+      "eval_steps_per_second": 4.629,
+      "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": 3745367602495488.0,
   "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 sha256:6b468cf615a61ca927f3b5afd9e22e617b85f0990ad04c19518aaccc4a2afe0c
+oid sha256:4c5cdf8e932d9e101ad32a488eb3add0f35004da017d279824a1bf2168b4448a
 size 6776