Training in progress, step 5, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
+    "up_proj",
     "v_proj",
     "q_proj",
+    "k_proj",
     "gate_proj",
-    "up_proj",
-    "o_proj"
+    "o_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:a34986d516a8123dc79eaa153c61fe787189362d8d2b3bdd79c43a19022fbb41
+oid sha256:9880f9a14e7e1b16646467ab0d161d117f1598c30881f29672a2b60ced9327ee
 size 67662840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5183c8fbde9b90b9c4373d8d4dd017eae4d483dba61449434e7d1c4c1f5248f2
+oid sha256:cb444bf5ba451c33cc607315d448f7fa02a9ff9b3bbe6e66bca96ebcbf0fa021
 size 34607610

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:340f6406b96d7e0f17315436c2bccb605d75c9d254ec958f91a4f659e4ffcdd7
+oid sha256:eca66d4a74945f7af156bf782963ee63f197435058aae7c08031504382213d7e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bedc6307a5e33c9ada0599345089662b71de7faf79562d8c952efe37fda8ce81
+oid sha256:85e9b4e25668eb135b65c8a2efd824713d5ec7e9a404d37d2fd3021c6e5610a3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,162 +1,87 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14705882352941177,
+  "epoch": 0.07352941176470588,
   "eval_steps": 1,
-  "global_step": 10,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.014705882352941176,
-      "grad_norm": 1.309019684791565,
-      "learning_rate": 5e-06,
+      "grad_norm": 1.3115363121032715,
+      "learning_rate": 5.000000000000001e-07,
       "loss": 1.3327,
       "step": 1
     },
     {
       "epoch": 0.014705882352941176,
       "eval_loss": 1.269364356994629,
-      "eval_runtime": 2.5609,
-      "eval_samples_per_second": 39.05,
-      "eval_steps_per_second": 5.857,
+      "eval_runtime": 2.5109,
+      "eval_samples_per_second": 39.826,
+      "eval_steps_per_second": 5.974,
       "step": 1
     },
     {
       "epoch": 0.029411764705882353,
-      "grad_norm": 1.260735034942627,
-      "learning_rate": 1e-05,
+      "grad_norm": 1.260526180267334,
+      "learning_rate": 1.0000000000000002e-06,
       "loss": 1.1887,
       "step": 2
     },
     {
       "epoch": 0.029411764705882353,
-      "eval_loss": 1.270459771156311,
-      "eval_runtime": 2.4757,
-      "eval_samples_per_second": 40.392,
-      "eval_steps_per_second": 6.059,
+      "eval_loss": 1.267616868019104,
+      "eval_runtime": 2.4914,
+      "eval_samples_per_second": 40.138,
+      "eval_steps_per_second": 6.021,
       "step": 2
     },
     {
       "epoch": 0.04411764705882353,
-      "grad_norm": 1.3263417482376099,
-      "learning_rate": 1.5e-05,
-      "loss": 1.5717,
+      "grad_norm": 1.3265948295593262,
+      "learning_rate": 1.5e-06,
+      "loss": 1.5761,
       "step": 3
     },
     {
       "epoch": 0.04411764705882353,
-      "eval_loss": 1.265608310699463,
-      "eval_runtime": 2.4864,
-      "eval_samples_per_second": 40.218,
-      "eval_steps_per_second": 6.033,
+      "eval_loss": 1.267909288406372,
+      "eval_runtime": 2.4844,
+      "eval_samples_per_second": 40.251,
+      "eval_steps_per_second": 6.038,
       "step": 3
     },
     {
       "epoch": 0.058823529411764705,
-      "grad_norm": 1.1789089441299438,
-      "learning_rate": 2e-05,
-      "loss": 1.3113,
+      "grad_norm": 1.2248256206512451,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.3197,
       "step": 4
     },
     {
       "epoch": 0.058823529411764705,
-      "eval_loss": 1.2618610858917236,
-      "eval_runtime": 2.4817,
-      "eval_samples_per_second": 40.295,
-      "eval_steps_per_second": 6.044,
+      "eval_loss": 1.2693428993225098,
+      "eval_runtime": 3.2428,
+      "eval_samples_per_second": 30.838,
+      "eval_steps_per_second": 4.626,
       "step": 4
     },
     {
       "epoch": 0.07352941176470588,
-      "grad_norm": 1.2095729112625122,
-      "learning_rate": 2.5e-05,
-      "loss": 1.3671,
+      "grad_norm": 1.2737431526184082,
+      "learning_rate": 2.5e-06,
+      "loss": 1.3721,
       "step": 5
     },
     {
       "epoch": 0.07352941176470588,
-      "eval_loss": 1.2535583972930908,
-      "eval_runtime": 2.5307,
-      "eval_samples_per_second": 39.515,
-      "eval_steps_per_second": 5.927,
+      "eval_loss": 1.267417311668396,
+      "eval_runtime": 3.3541,
+      "eval_samples_per_second": 29.814,
+      "eval_steps_per_second": 4.472,
       "step": 5
-    },
-    {
-      "epoch": 0.08823529411764706,
-      "grad_norm": 1.2121447324752808,
-      "learning_rate": 3e-05,
-      "loss": 1.4151,
-      "step": 6
-    },
-    {
-      "epoch": 0.08823529411764706,
-      "eval_loss": 1.2435675859451294,
-      "eval_runtime": 2.5551,
-      "eval_samples_per_second": 39.137,
-      "eval_steps_per_second": 5.871,
-      "step": 6
-    },
-    {
-      "epoch": 0.10294117647058823,
-      "grad_norm": 0.8902429938316345,
-      "learning_rate": 3.5e-05,
-      "loss": 1.2607,
-      "step": 7
-    },
-    {
-      "epoch": 0.10294117647058823,
-      "eval_loss": 1.2300522327423096,
-      "eval_runtime": 2.5552,
-      "eval_samples_per_second": 39.136,
-      "eval_steps_per_second": 5.87,
-      "step": 7
-    },
-    {
-      "epoch": 0.11764705882352941,
-      "grad_norm": 1.3416252136230469,
-      "learning_rate": 4e-05,
-      "loss": 1.4189,
-      "step": 8
-    },
-    {
-      "epoch": 0.11764705882352941,
-      "eval_loss": 1.225598931312561,
-      "eval_runtime": 2.529,
-      "eval_samples_per_second": 39.541,
-      "eval_steps_per_second": 5.931,
-      "step": 8
-    },
-    {
-      "epoch": 0.1323529411764706,
-      "grad_norm": 0.9632052779197693,
-      "learning_rate": 4.5e-05,
-      "loss": 1.3843,
-      "step": 9
-    },
-    {
-      "epoch": 0.1323529411764706,
-      "eval_loss": 1.223665475845337,
-      "eval_runtime": 2.5804,
-      "eval_samples_per_second": 38.753,
-      "eval_steps_per_second": 5.813,
-      "step": 9
-    },
-    {
-      "epoch": 0.14705882352941177,
-      "grad_norm": 0.9364734292030334,
-      "learning_rate": 5e-05,
-      "loss": 1.3753,
-      "step": 10
-    },
-    {
-      "epoch": 0.14705882352941177,
-      "eval_loss": 1.2201740741729736,
-      "eval_runtime": 2.4614,
-      "eval_samples_per_second": 40.628,
-      "eval_steps_per_second": 6.094,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -171,12 +96,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 628058829619200.0,
+  "total_flos": 314029414809600.0,
   "train_batch_size": 7,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75498497562a7e64e3f8e51308001a48b87d7bec418686da140d400a6112b73f
+oid sha256:a08ac483867b17b481761ba9b309a0d55e03c0ec5de5cd02764b9f24cd7d6afe
 size 6648