Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "q_proj",
-    "o_proj",
     "k_proj",
+    "o_proj",
     "up_proj",
-    "v_proj",
-    "gate_proj"
+    "gate_proj",
+    "q_proj",
+    "down_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:b3d7874ab2ff40f6847403c871d48181fc288b6c7c68fa80449faf3f1f6e7902
+oid sha256:4964deef7def8a5d7b1ecb56311ebe6c9de8b8111a26c6a9951903ada54f7288
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00df8126f980290442bf160f1a4cfbfbef3accf6de98e1a9d174b69d12567369
+oid sha256:089e4d33d63493ca83d0c2cee4f0918ab4f366be1b31f125d3f28c7f9fcf4585
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eceafea254f171991eb2372221c5b96dfb1a6aa3abf95c819282b5b3825bae54
+oid sha256:e95342b7972eb34bcf83df59ba126733ad0e109ff06b5e91fa5e6ba3b10a0f05
 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

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005647324579980234,
+  "epoch": 0.0016941973739940702,
   "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": 0.0005647324579980235,
-      "grad_norm": 6.657321453094482,
+      "grad_norm": 6.638052463531494,
       "learning_rate": 2e-05,
       "loss": 3.0027,
       "step": 1
@@ -18,97 +18,32 @@
     {
       "epoch": 0.0005647324579980235,
       "eval_loss": 2.7413086891174316,
-      "eval_runtime": 209.2902,
-      "eval_samples_per_second": 3.564,
+      "eval_runtime": 209.2602,
+      "eval_samples_per_second": 3.565,
       "eval_steps_per_second": 1.782,
       "step": 1
     },
     {
       "epoch": 0.001129464915996047,
-      "grad_norm": 4.548604965209961,
+      "grad_norm": 4.598910331726074,
       "learning_rate": 4e-05,
       "loss": 2.5806,
       "step": 2
     },
     {
       "epoch": 0.0016941973739940702,
-      "grad_norm": 4.600951194763184,
+      "grad_norm": 4.744904041290283,
       "learning_rate": 6e-05,
-      "loss": 3.2098,
+      "loss": 3.2161,
       "step": 3
     },
     {
       "epoch": 0.0016941973739940702,
-      "eval_loss": 2.6281063556671143,
-      "eval_runtime": 212.6516,
-      "eval_samples_per_second": 3.508,
-      "eval_steps_per_second": 1.754,
+      "eval_loss": 2.631173849105835,
+      "eval_runtime": 213.0702,
+      "eval_samples_per_second": 3.501,
+      "eval_steps_per_second": 1.751,
       "step": 3
-    },
-    {
-      "epoch": 0.002258929831992094,
-      "grad_norm": 5.961012840270996,
-      "learning_rate": 8e-05,
-      "loss": 3.546,
-      "step": 4
-    },
-    {
-      "epoch": 0.002823662289990117,
-      "grad_norm": 3.73958158493042,
-      "learning_rate": 0.0001,
-      "loss": 3.039,
-      "step": 5
-    },
-    {
-      "epoch": 0.0033883947479881405,
-      "grad_norm": 3.5475358963012695,
-      "learning_rate": 0.00012,
-      "loss": 2.3823,
-      "step": 6
-    },
-    {
-      "epoch": 0.0033883947479881405,
-      "eval_loss": 2.191272020339966,
-      "eval_runtime": 211.8851,
-      "eval_samples_per_second": 3.521,
-      "eval_steps_per_second": 1.76,
-      "step": 6
-    },
-    {
-      "epoch": 0.003953127205986164,
-      "grad_norm": 2.7113640308380127,
-      "learning_rate": 0.00014,
-      "loss": 2.2146,
-      "step": 7
-    },
-    {
-      "epoch": 0.004517859663984188,
-      "grad_norm": 2.97259521484375,
-      "learning_rate": 0.00016,
-      "loss": 1.9369,
-      "step": 8
-    },
-    {
-      "epoch": 0.005082592121982211,
-      "grad_norm": 3.431048631668091,
-      "learning_rate": 0.00018,
-      "loss": 1.8664,
-      "step": 9
-    },
-    {
-      "epoch": 0.005082592121982211,
-      "eval_loss": 2.243478536605835,
-      "eval_runtime": 211.702,
-      "eval_samples_per_second": 3.524,
-      "eval_steps_per_second": 1.762,
-      "step": 9
-    },
-    {
-      "epoch": 0.005647324579980234,
-      "grad_norm": 4.549256801605225,
-      "learning_rate": 0.0002,
-      "loss": 1.8522,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +58,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.533788723085312e+16,
+  "total_flos": 4601366169255936.0,
   "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 sha256:3720f97f7b893e4cea2d22e77a048a55441b099c0d2a14c49596be63f4aacc01
+oid sha256:c13cd3c6b3c4bed01f267de28e93961b8bde48e003a58f21ccba8e55ca9ad8da
 size 6776