Training in progress, step 10, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
-    "k_proj",
     "up_proj",
     "v_proj",
+    "gate_proj",
     "q_proj",
-    "down_proj"
+    "o_proj",
+    "down_proj",
+    "k_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:b040665ed42c236ed8d9ce989b6b13aabb0d25ad6b8fe91254c0819eea15a83c
+oid sha256:793a799bd11b9689e570d44fdb6936c92fbe798e305f570153d92a14bc1561ba
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebf9a81325339b0a592b504a17db0f79f6d19bb7914ae3da5c76844de200cd13
+oid sha256:82e95a7a22b890c8c088f00cdd33a1e31b6a3bf010dddd8ede668374163230eb
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec01cee6b9922f10cdf184da58551aa02458d825a83b4df852d4f43f89b88f1a
+oid sha256:16d14b92c6dadc4a845a4add95ab9cec7b1ee94ab044c4e4a55b9e68638c17c4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0014769836711249693,
+  "epoch": 0.0016410929679166325,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00016410929679166325,
-      "grad_norm": 1.91439688205719,
+      "grad_norm": 1.9401438236236572,
       "learning_rate": 2e-05,
       "loss": 2.5636,
       "step": 1
@@ -18,90 +18,97 @@
     {
       "epoch": 0.00016410929679166325,
       "eval_loss": 2.553264856338501,
-      "eval_runtime": 392.8391,
-      "eval_samples_per_second": 6.532,
-      "eval_steps_per_second": 3.266,
+      "eval_runtime": 391.9778,
+      "eval_samples_per_second": 6.546,
+      "eval_steps_per_second": 3.273,
       "step": 1
     },
     {
       "epoch": 0.0003282185935833265,
-      "grad_norm": 2.276977777481079,
+      "grad_norm": 2.3240439891815186,
       "learning_rate": 4e-05,
       "loss": 3.1142,
       "step": 2
     },
     {
       "epoch": 0.0004923278903749898,
-      "grad_norm": 1.631351113319397,
+      "grad_norm": 1.5905076265335083,
       "learning_rate": 6e-05,
-      "loss": 2.6682,
+      "loss": 2.6646,
       "step": 3
     },
     {
       "epoch": 0.0004923278903749898,
-      "eval_loss": 2.547764301300049,
-      "eval_runtime": 393.137,
-      "eval_samples_per_second": 6.527,
-      "eval_steps_per_second": 3.263,
+      "eval_loss": 2.5479984283447266,
+      "eval_runtime": 391.7689,
+      "eval_samples_per_second": 6.55,
+      "eval_steps_per_second": 3.275,
       "step": 3
     },
     {
       "epoch": 0.000656437187166653,
-      "grad_norm": 1.2931513786315918,
+      "grad_norm": 1.3060100078582764,
       "learning_rate": 8e-05,
-      "loss": 2.0285,
+      "loss": 2.0314,
       "step": 4
     },
     {
       "epoch": 0.0008205464839583163,
-      "grad_norm": 1.8168163299560547,
+      "grad_norm": 1.8542362451553345,
       "learning_rate": 0.0001,
-      "loss": 2.5827,
+      "loss": 2.5814,
       "step": 5
     },
     {
       "epoch": 0.0009846557807499795,
-      "grad_norm": 1.7620759010314941,
+      "grad_norm": 1.7674589157104492,
       "learning_rate": 0.00012,
-      "loss": 2.4112,
+      "loss": 2.4127,
       "step": 6
     },
     {
       "epoch": 0.0009846557807499795,
-      "eval_loss": 2.480220317840576,
-      "eval_runtime": 392.327,
-      "eval_samples_per_second": 6.54,
-      "eval_steps_per_second": 3.27,
+      "eval_loss": 2.4773998260498047,
+      "eval_runtime": 391.9581,
+      "eval_samples_per_second": 6.547,
+      "eval_steps_per_second": 3.273,
       "step": 6
     },
     {
       "epoch": 0.0011487650775416428,
-      "grad_norm": 1.6749258041381836,
+      "grad_norm": 1.7092241048812866,
       "learning_rate": 0.00014,
-      "loss": 2.7895,
+      "loss": 2.783,
       "step": 7
     },
     {
       "epoch": 0.001312874374333306,
-      "grad_norm": 1.4969555139541626,
+      "grad_norm": 1.5567394495010376,
       "learning_rate": 0.00016,
-      "loss": 2.375,
+      "loss": 2.3939,
       "step": 8
     },
     {
       "epoch": 0.0014769836711249693,
-      "grad_norm": 1.5681908130645752,
+      "grad_norm": 1.5965105295181274,
       "learning_rate": 0.00018,
-      "loss": 2.414,
+      "loss": 2.4161,
       "step": 9
     },
     {
       "epoch": 0.0014769836711249693,
-      "eval_loss": 2.3583710193634033,
-      "eval_runtime": 391.9968,
-      "eval_samples_per_second": 6.546,
-      "eval_steps_per_second": 3.273,
+      "eval_loss": 2.35837721824646,
+      "eval_runtime": 391.9106,
+      "eval_samples_per_second": 6.547,
+      "eval_steps_per_second": 3.274,
       "step": 9
+    },
+    {
+      "epoch": 0.0016410929679166325,
+      "grad_norm": 2.404068946838379,
+      "learning_rate": 0.0002,
+      "loss": 2.4232,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1741900625215488.0,
+  "total_flos": 1935445139128320.0,
   "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:b3f5f24b610d814119114339e648d6ed3a2253ce76c1f667715f1aee5a38c459
+oid sha256:ef68a0fb19eac9987edac8323a4b4c1375436ffcccaab5f22193ad3a6254b248
 size 6776