Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
-    "down_proj",
-    "o_proj",
     "gate_proj",
     "up_proj",
-    "q_proj"
+    "q_proj",
+    "down_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 sha256:11827574e55e5dd228a2ccf38aa2f37a46377e42c34d5f0dee9e33027081bbc6
+oid sha256:8b0114b8aeac0c99d024930ca6eaf93290cf4d1e4f34541ebd3b69f408c0858a
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e43f25a790ab6eb63584d9f473d8511681e213ab6f79f1265cbf2b43c87e5459
+oid sha256:0648583a162ef069a6b67d732ec9bfe2db80d89859d1e0985fe6317802aeb642
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e520812e0d7ea23c1420ef059833cecb9425854403bb5adf2b3a64ae67df43
+oid sha256:5a84ddc90db20c8ebbe7132f591333b49cb59751c1225abbbb520a5d2fc22243
 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": 0.0007792713812585232,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.010130527956360803,
+  "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": 0.0007792713812585232,
       "eval_loss": 3.89182710647583,
-      "eval_runtime": 24.3498,
-      "eval_samples_per_second": 22.218,
-      "eval_steps_per_second": 11.129,
+      "eval_runtime": 24.4368,
+      "eval_samples_per_second": 22.139,
+      "eval_steps_per_second": 11.09,
       "step": 1
+    },
+    {
+      "epoch": 0.0038963569062926166,
+      "grad_norm": 1.0266491174697876,
+      "learning_rate": 5e-05,
+      "loss": 3.8261,
+      "step": 5
+    },
+    {
+      "epoch": 0.007792713812585233,
+      "grad_norm": 1.0125054121017456,
+      "learning_rate": 0.0001,
+      "loss": 3.8075,
+      "step": 10
+    },
+    {
+      "epoch": 0.007792713812585233,
+      "eval_loss": 3.725928783416748,
+      "eval_runtime": 23.352,
+      "eval_samples_per_second": 23.167,
+      "eval_steps_per_second": 11.605,
+      "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": 32429825851392.0,
+  "total_flos": 421587736068096.0,
   "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 sha256:6660a34e873ee1ef4667a9f6a3524c5b9fd1747866405e6222eefe5b6f094e94
+oid sha256:b8c1dc11f85aff01c1f4bd5e9a04ea7f334ec525b7e04bec615ea26854c472d9
 size 6776