Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "down_proj",
-    "up_proj",
-    "v_proj",
+    "k_proj",
     "q_proj",
     "gate_proj",
-    "k_proj"
+    "o_proj",
+    "up_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:e48536186cd2081126869cdbff740091491e88e6d9d788f261b2c11b1864655b
+oid sha256:c2ab1365a6b48d3586a50d3d033fa5a7b878b1f35a26e24b796b4fbef198063f
 size 17425352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab4fdd746f4334f759e9f986a6d447331644ac4e6932ab7f0fc60ba189414942
+oid sha256:b6935d7077d7f3b0a0cd886c3bfd0f850d106a9c94e24dbd0cc9c4de8ce75410
 size 10251668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfa25943342783a61b36c4d0bbac9c63f166b2ceef5f747acc8e288833dd451a
+oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,106 +1,41 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006654466810846781,
+  "epoch": 0.001996340043254034,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0006654466810846781,
-      "grad_norm": 0.10578875988721848,
+      "grad_norm": 0.10643411427736282,
       "learning_rate": 2e-05,
       "loss": 1.3965,
       "step": 1
     },
     {
       "epoch": 0.0013308933621693562,
-      "grad_norm": 0.05910216271877289,
+      "grad_norm": 0.05983343347907066,
       "learning_rate": 4e-05,
       "loss": 1.2724,
       "step": 2
     },
     {
       "epoch": 0.001996340043254034,
-      "grad_norm": 0.07091601938009262,
+      "grad_norm": 0.07062945514917374,
       "learning_rate": 6e-05,
-      "loss": 1.5669,
+      "loss": 1.5656,
       "step": 3
     },
     {
       "epoch": 0.001996340043254034,
-      "eval_loss": 1.6910425424575806,
-      "eval_runtime": 29.6531,
-      "eval_samples_per_second": 21.347,
-      "eval_steps_per_second": 10.69,
+      "eval_loss": 1.6909511089324951,
+      "eval_runtime": 31.9291,
+      "eval_samples_per_second": 19.825,
+      "eval_steps_per_second": 9.928,
       "step": 3
-    },
-    {
-      "epoch": 0.0026617867243387125,
-      "grad_norm": 0.0798959955573082,
-      "learning_rate": 8e-05,
-      "loss": 1.6832,
-      "step": 4
-    },
-    {
-      "epoch": 0.0033272334054233904,
-      "grad_norm": 0.05840625986456871,
-      "learning_rate": 0.0001,
-      "loss": 1.0775,
-      "step": 5
-    },
-    {
-      "epoch": 0.003992680086508068,
-      "grad_norm": 0.07022179663181305,
-      "learning_rate": 0.00012,
-      "loss": 1.3999,
-      "step": 6
-    },
-    {
-      "epoch": 0.003992680086508068,
-      "eval_loss": 1.690689206123352,
-      "eval_runtime": 30.2631,
-      "eval_samples_per_second": 20.917,
-      "eval_steps_per_second": 10.475,
-      "step": 6
-    },
-    {
-      "epoch": 0.004658126767592747,
-      "grad_norm": 0.08359124511480331,
-      "learning_rate": 0.00014,
-      "loss": 1.8143,
-      "step": 7
-    },
-    {
-      "epoch": 0.005323573448677425,
-      "grad_norm": 0.07657521963119507,
-      "learning_rate": 0.00016,
-      "loss": 1.4335,
-      "step": 8
-    },
-    {
-      "epoch": 0.005989020129762102,
-      "grad_norm": 0.09371282160282135,
-      "learning_rate": 0.00018,
-      "loss": 1.4803,
-      "step": 9
-    },
-    {
-      "epoch": 0.005989020129762102,
-      "eval_loss": 1.689441204071045,
-      "eval_runtime": 30.1734,
-      "eval_samples_per_second": 20.979,
-      "eval_steps_per_second": 10.506,
-      "step": 9
-    },
-    {
-      "epoch": 0.006654466810846781,
-      "grad_norm": 0.08498664200305939,
-      "learning_rate": 0.0002,
-      "loss": 1.3204,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -115,12 +50,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 117587666534400.0,
+  "total_flos": 39195888844800.0,
   "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 sha256:5664deb7d8c17ccefd0cec2fd17f0389868b22074df42116dfb134fbdc150dbd
+oid sha256:29e7986c96b72644d34332d340f6205512b219be2949c76ac8a292c93eeef9d2
 size 6904