Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "v_proj",
-    "down_proj",
-    "o_proj",
     "q_proj",
     "gate_proj",
-    "up_proj"
+    "down_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 sha256:5af7b5bc702c1ab35a5640dd809c24209965d0aad3d5f46017c2f92e7826c8c6
+oid sha256:10fac21fd047b4218e18e0bb73dcb770dc86f4f77d73532aa3bb7f5161612b14
 size 2185308208

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e12b2ed32697d36a744a3de88619575b41923b6461f82d017d654c3dee40df6
+oid sha256:be5bf39939d36d878c858d819e79c7ce76ad12155b30d48edaae8729c8095244
 size 168037178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
+oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,78 +1,107 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00020522116856353732,
+  "epoch": 0.000307831752845306,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 3.420352809392289e-05,
-      "grad_norm": 1.608834147453308,
+      "grad_norm": 1.463192105293274,
       "learning_rate": 2e-05,
-      "loss": 2.8211,
+      "loss": 2.8212,
       "step": 1
     },
     {
       "epoch": 3.420352809392289e-05,
-      "eval_loss": 3.4762773513793945,
-      "eval_runtime": 495.8449,
-      "eval_samples_per_second": 12.415,
-      "eval_steps_per_second": 12.415,
+      "eval_loss": 3.4762721061706543,
+      "eval_runtime": 429.3488,
+      "eval_samples_per_second": 14.338,
+      "eval_steps_per_second": 14.338,
       "step": 1
     },
     {
       "epoch": 6.840705618784578e-05,
-      "grad_norm": 1.8106151819229126,
+      "grad_norm": 1.6494814157485962,
       "learning_rate": 4e-05,
-      "loss": 2.7652,
+      "loss": 2.7649,
       "step": 2
     },
     {
       "epoch": 0.00010261058428176866,
-      "grad_norm": 1.0310214757919312,
+      "grad_norm": 0.9364640116691589,
       "learning_rate": 6e-05,
-      "loss": 2.0629,
+      "loss": 2.0631,
       "step": 3
     },
     {
       "epoch": 0.00010261058428176866,
-      "eval_loss": 3.469648838043213,
-      "eval_runtime": 487.5743,
-      "eval_samples_per_second": 12.626,
-      "eval_steps_per_second": 12.626,
+      "eval_loss": 3.470472812652588,
+      "eval_runtime": 428.3099,
+      "eval_samples_per_second": 14.373,
+      "eval_steps_per_second": 14.373,
       "step": 3
     },
     {
       "epoch": 0.00013681411237569156,
-      "grad_norm": 1.9326692819595337,
+      "grad_norm": 1.7779229879379272,
       "learning_rate": 8e-05,
-      "loss": 2.6316,
+      "loss": 2.6329,
       "step": 4
     },
     {
       "epoch": 0.00017101764046961444,
-      "grad_norm": 1.1122183799743652,
+      "grad_norm": 0.9670753479003906,
       "learning_rate": 0.0001,
-      "loss": 2.4229,
+      "loss": 2.4248,
       "step": 5
     },
     {
       "epoch": 0.00020522116856353732,
-      "grad_norm": 1.5624297857284546,
+      "grad_norm": 1.4301257133483887,
       "learning_rate": 0.00012,
-      "loss": 2.8127,
+      "loss": 2.8174,
       "step": 6
     },
     {
       "epoch": 0.00020522116856353732,
-      "eval_loss": 3.4261391162872314,
-      "eval_runtime": 486.5579,
-      "eval_samples_per_second": 12.652,
-      "eval_steps_per_second": 12.652,
+      "eval_loss": 3.4303219318389893,
+      "eval_runtime": 430.5065,
+      "eval_samples_per_second": 14.299,
+      "eval_steps_per_second": 14.299,
       "step": 6
+    },
+    {
+      "epoch": 0.00023942469665746023,
+      "grad_norm": 1.38871431350708,
+      "learning_rate": 0.00014,
+      "loss": 2.7934,
+      "step": 7
+    },
+    {
+      "epoch": 0.00027362822475138313,
+      "grad_norm": 0.8416540026664734,
+      "learning_rate": 0.00016,
+      "loss": 1.7494,
+      "step": 8
+    },
+    {
+      "epoch": 0.000307831752845306,
+      "grad_norm": 1.5558000802993774,
+      "learning_rate": 0.00018,
+      "loss": 2.2349,
+      "step": 9
+    },
+    {
+      "epoch": 0.000307831752845306,
+      "eval_loss": 3.331357955932617,
+      "eval_runtime": 430.206,
+      "eval_samples_per_second": 14.309,
+      "eval_steps_per_second": 14.309,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109739152867328.0,
+  "total_flos": 1664608729300992.0,
   "train_batch_size": 1,
   "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:ed04e29d3037d87c0defa1a0ab640c5cb173a163f6893e09aa7721b26cfe4d70
+oid sha256:4cb41fba4264376a3ccfb8c093be5867221b5fa61290459b0e68d032b827a444
 size 6776